From 952cf5e76706ad7d186cf75778000e25d74ff161 Mon Sep 17 00:00:00 2001 From: Alejandro Moreo Date: Fri, 10 Feb 2023 19:02:17 +0100 Subject: [PATCH] fixing bugs in one-vs-all --- docs/build/html/genindex.html | 26 ++-- docs/build/html/objects.inv | Bin 2873 -> 2859 bytes docs/build/html/quapy.classification.html | 2 +- docs/build/html/quapy.data.html | 33 +++- docs/build/html/quapy.html | 26 ++-- docs/build/html/quapy.method.html | 141 ++++++------------ docs/build/html/searchindex.js | 2 +- examples/custom_quantifier.py | 8 +- examples/lequa2022_experiments.py | 26 +++- .../{one_vs_all_example.py => one_vs_all.py} | 7 +- quapy/CHANGE_LOG.txt | 2 - quapy/method/aggregative.py | 2 +- quapy/method/base.py | 11 +- quapy/model_selection.py | 3 +- quapy/protocol.py | 136 +++++++++++++++-- quapy/tests/test_protocols.py | 57 ++++++- 16 files changed, 308 insertions(+), 174 deletions(-) rename examples/{one_vs_all_example.py => one_vs_all.py} (90%) diff --git a/docs/build/html/genindex.html b/docs/build/html/genindex.html index 7e5281f..fc438e0 100644 --- a/docs/build/html/genindex.html +++ b/docs/build/html/genindex.html @@ -113,7 +113,7 @@
  • (quapy.method.aggregative.HDy method)
    • -
  • (quapy.method.aggregative.OneVsAll method) +
  • (quapy.method.aggregative.OneVsAllAggregative method)
  • (quapy.method.aggregative.PACC method)
    • @@ -177,8 +177,6 @@
  • CC (class in quapy.method.aggregative)
  • check_prevalence_vector() (in module quapy.functional) -
    • -
  • classes (quapy.method.base.OneVsAllGeneric property)
  • classes_ (quapy.classification.calibration.RecalibratedProbabilisticClassifierBase property) @@ -187,7 +185,7 @@
  • (quapy.method.aggregative.AggregativeQuantifier property)
    • -
  • (quapy.method.aggregative.OneVsAll property) +
  • (quapy.method.base.OneVsAllGeneric property)
  • (quapy.method.neural.QuaNetTrainer property)
    • @@ -203,7 +201,7 @@
  • (quapy.method.aggregative.ELM method)
    • -
  • (quapy.method.aggregative.OneVsAll method) +
  • (quapy.method.aggregative.OneVsAllAggregative method)
  • (quapy.method.aggregative.PACC method)
    • @@ -358,8 +356,6 @@
  • (quapy.method.aggregative.EMQ method)
  • (quapy.method.aggregative.HDy method) -
    • -
  • (quapy.method.aggregative.OneVsAll method)
  • (quapy.method.aggregative.PACC method)
    • @@ -426,10 +422,6 @@
  • (quapy.classification.neural.NeuralClassifierTrainer method)
  • (quapy.classification.neural.TextClassifierNet method) -
    • -
  • (quapy.method.aggregative.OneVsAll method) -
    • -
  • (quapy.method.base.OneVsAllGeneric method)
  • (quapy.method.meta.Ensemble method)
    • @@ -443,6 +435,8 @@
  • get_probability_distribution() (in module quapy.method.meta)
  • get_quapy_home() (in module quapy.util) +
    • +
  • getOneVsAll() (in module quapy.method.base)
  • getPteCondEstim() (quapy.method.aggregative.ACC class method) @@ -539,6 +533,8 @@
  • MedianSweep (in module quapy.method.aggregative)
  • MedianSweep2 (in module quapy.method.aggregative) +
    • +
  • mix() (quapy.data.base.LabelledCollection class method)
  • mkld() (in module quapy.error)
    • @@ -641,10 +637,12 @@ @@ -604,7 +605,7 @@ in the grid multiplied by repeat

    -class quapy.protocol.AbstractStochasticSeededProtocol(random_state=None)
    +class quapy.protocol.AbstractStochasticSeededProtocol(random_state=0)

    Bases: AbstractProtocol

    An AbstractStochasticSeededProtocol is a protocol that generates, via any random procedure (e.g., via random sampling), sequences of quapy.data.base.LabelledCollection samples. @@ -616,8 +617,8 @@ needed for extracting the samples, and

    Parameters:
    -

    random_state – the seed for allowing to replicate any sequence of samples. Default is None, meaning that -the sequence will be different every time the protocol is called.

    +

    random_state – the seed for allowing to replicate any sequence of samples. Default is 0, meaning that +the sequence will be consistent every time the protocol is called.

    @@ -659,7 +660,7 @@ the sequence will be different every time the protocol is called.

    -class quapy.protocol.DomainMixer(domainA: LabelledCollection, domainB: LabelledCollection, sample_size, repeats=1, prevalence=None, mixture_points=11, random_state=None, return_type='sample_prev')
    +class quapy.protocol.DomainMixer(domainA: LabelledCollection, domainB: LabelledCollection, sample_size, repeats=1, prevalence=None, mixture_points=11, random_state=0, return_type='sample_prev')

    Bases: AbstractStochasticSeededProtocol

    Generates mixtures of two domains (A and B) at controlled rates, but preserving the original class prevalence.

    @@ -675,7 +676,8 @@ will be taken from the domain A (default).

  • mixture_points – an integer indicating the number of points to take from a linear scale (e.g., 21 will generate the mixture points [1, 0.95, 0.9, …, 0]), or the array of mixture values itself. the specific points

    • -

  • random_state –

    • +

  • random_state – allows replicating samples across runs (default 0, meaning that the sequence of samples +will be the same every time the protocol is called)

    • @@ -719,7 +721,7 @@ the specific points

    -class quapy.protocol.NPP(data: LabelledCollection, sample_size=None, repeats=100, random_state=None, return_type='sample_prev')
    +class quapy.protocol.NPP(data: LabelledCollection, sample_size=None, repeats=100, random_state=0, return_type='sample_prev')

    Bases: AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol

    A generator of samples that implements the natural prevalence protocol (NPP). The NPP consists of drawing samples uniformly at random, therefore approximately preserving the natural prevalence of the collection.

    @@ -730,7 +732,8 @@ samples uniformly at random, therefore approximately preserving the natural prev

  • sample_size – integer, the number of instances in each sample; if None (default) then it is taken from qp.environ[“SAMPLE_SIZE”]. If this is not set, a ValueError exception is raised.

  • repeats – the number of samples to generate. Default is 100.

    • -

  • random_state – allows replicating samples across runs (default None)

    • +

  • random_state – allows replicating samples across runs (default 0, meaning that the sequence of samples +will be the same every time the protocol is called)

  • return_type – set to “sample_prev” (default) to get the pairs of (sample, prevalence) at each iteration, or to “labelled_collection” to get instead instances of LabelledCollection

    • @@ -802,7 +805,7 @@ to “labelled_collection” to get instead instances of LabelledCollection

    <
    -class quapy.protocol.USimplexPP(data: LabelledCollection, sample_size=None, repeats=100, random_state=None, return_type='sample_prev')
    +class quapy.protocol.USimplexPP(data: LabelledCollection, sample_size=None, repeats=100, random_state=0, return_type='sample_prev')

    Bases: AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol

    A variant of APP that, instead of using a grid of equidistant prevalence values, relies on the Kraemer algorithm for sampling unit (k-1)-simplex uniformly at random, with @@ -817,7 +820,8 @@ combinations of the grid values of APP makes this endeavour intractable.

  • sample_size – integer, the number of instances in each sample; if None (default) then it is taken from qp.environ[“SAMPLE_SIZE”]. If this is not set, a ValueError exception is raised.

  • repeats – the number of samples to generate. Default is 100.

    • -

  • random_state – allows replicating samples across runs (default None)

    • +

  • random_state – allows replicating samples across runs (default 0, meaning that the sequence of samples +will be the same every time the protocol is called)

  • return_type – set to “sample_prev” (default) to get the pairs of (sample, prevalence) at each iteration, or to “labelled_collection” to get instead instances of LabelledCollection

    • diff --git a/docs/build/html/quapy.method.html b/docs/build/html/quapy.method.html index a3ba728..19a1e0b 100644 --- a/docs/build/html/quapy.method.html +++ b/docs/build/html/quapy.method.html @@ -781,9 +781,9 @@ validation data, or as an integer, indicating that the misclassification rates s
    -
    -class quapy.method.aggregative.OneVsAll(binary_quantifier, n_jobs=None)
    -

    Bases: AggregativeQuantifier

    +
    +class quapy.method.aggregative.OneVsAllAggregative(binary_quantifier, n_jobs=None, parallel_backend='loky')
    +

    Bases: OneVsAllGeneric, AggregativeQuantifier

    Allows any binary quantifier to perform quantification on single-label datasets. The method maintains one binary quantifier for each class, and then l1-normalizes the outputs so that the class prevelences sum up to 1. @@ -795,12 +795,15 @@ This variant was used, along with the -

    -aggregate(classif_predictions)
    +
    +aggregate(classif_predictions)

    Implements the aggregation of label predictions.

    Parameters:
    @@ -812,21 +815,9 @@ one-vs-all manner

    -
    -
    -property classes_
    -

    Class labels, in the same order in which class prevalence values are to be computed. -This default implementation actually returns the class labels of the learner.

    -
    -
    Returns:
    -

    array-like

    -
    -
    -
    -
    -
    -classify(instances)
    +
    +classify(instances)

    If the base quantifier is not probabilistic, returns a matrix of shape (n,m,) with n the number of instances and m the number of classes. The entry (i,j) is a binary value indicating whether instance i `belongs to class `j. The binary classifications are independent of each other, meaning that an instance @@ -845,63 +836,6 @@ probabilities are independent of each other, meaning that, in general, they do n

    -
    -
    -fit(data: LabelledCollection, fit_classifier=True)
    -

    Trains the aggregative quantifier

    -
    -
    Parameters:
    -
      -

    • data – a quapy.data.base.LabelledCollection consisting of the training data

      • -

    • fit_classifier – whether or not to train the learner (default is True). Set to False if the -learner has been trained outside the quantifier.

      • -
    -
    -
    Returns:
    -

    self

    -
    -
    -
    - -
    -
    -get_params(deep=True)
    -

    Get parameters for this estimator.

    -
    -
    Parameters:
    -

    deep (bool, default=True) – If True, will return the parameters for this estimator and -contained subobjects that are estimators.

    -
    -
    Returns:
    -

    params – Parameter names mapped to their values.

    -
    -
    Return type:
    -

    dict

    -
    -
    -
    - -
    -
    -set_params(**parameters)
    -

    Set the parameters of this estimator.

    -

    The method works on simple estimators as well as on nested objects -(such as Pipeline). The latter have -parameters of the form <component>__<parameter> so that it’s -possible to update each component of a nested object.

    -
    -
    Parameters:
    -

    **params (dict) – Estimator parameters.

    -
    -
    Returns:
    -

    self – Estimator instance.

    -
    -
    Return type:
    -

    estimator instance

    -
    -
    -
    -
    @@ -1362,38 +1296,57 @@ validation data, or as an integer, indicating that the misclassification rates s
    -
    -class quapy.method.base.OneVsAllGeneric(binary_quantifier, n_jobs=None)
    +
    +class quapy.method.base.OneVsAll

    Bases: object

    +
    + +
    +
    +class quapy.method.base.OneVsAllGeneric(binary_quantifier, n_jobs=None, parallel_backend='loky')
    +

    Bases: OneVsAll, BaseQuantifier

    Allows any binary quantifier to perform quantification on single-label datasets. The method maintains one binary quantifier for each class, and then l1-normalizes the outputs so that the class prevelence values sum up to 1.

    -
    -property classes
    +
    +property classes_
    -fit(data: LabelledCollection, **kwargs)
    -
    - -
    -
    -get_params(deep=True)
    -
    +fit(data: LabelledCollection, fit_classifier=True) +

    Trains a quantifier.

    +
    +
    Parameters:
    +

    data – a quapy.data.base.LabelledCollection consisting of the training data

    +
    +
    Returns:
    +

    self

    +
    +
    +
    -quantify(X, *args)
    -
    - -
    -
    -set_params(**parameters)
    -
    +quantify(instances) +

    Generate class prevalence estimates for the sample’s instances

    +
    +
    Parameters:
    +

    instances – array-like

    +
    +
    Returns:
    +

    np.ndarray of shape (n_classes,) with class prevalence estimates.

    +
    +
    +
    +
    +
    +quapy.method.base.getOneVsAll(binary_quantifier, n_jobs=None, parallel_backend='loky')
    +
    +

    quapy.method.meta

    diff --git a/docs/build/html/searchindex.js b/docs/build/html/searchindex.js index 1f4419a..99c18d6 100644 --- a/docs/build/html/searchindex.js +++ b/docs/build/html/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["Datasets", "Evaluation", "Installation", "Methods", "Model-Selection", "Plotting", "index", "modules", "quapy", "quapy.classification", "quapy.data", "quapy.method"], "filenames": ["Datasets.md", "Evaluation.md", "Installation.rst", "Methods.md", "Model-Selection.md", "Plotting.md", "index.rst", "modules.rst", "quapy.rst", "quapy.classification.rst", "quapy.data.rst", "quapy.method.rst"], "titles": ["Datasets", "Evaluation", "Installation", "Quantification Methods", "Model Selection", "Plotting", "Welcome to QuaPy\u2019s documentation!", "quapy", "quapy package", "quapy.classification package", "quapy.data package", "quapy.method package"], "terms": {"quapi": [0, 1, 2, 3, 4, 5], "make": [0, 1, 3, 8, 11], "avail": [0, 1, 2, 3, 5, 6, 9, 11], "sever": 0, "have": [0, 1, 2, 3, 4, 5, 8, 10, 11], "been": [0, 3, 4, 5, 8, 9, 10, 11], "us": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "quantif": [0, 1, 6, 8, 9, 10, 11], "literatur": [0, 1, 4, 6], "well": [0, 3, 4, 5, 11], "an": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "interfac": [0, 1, 11], "allow": [0, 1, 2, 3, 5, 8, 9, 10, 11], "anyon": 0, "import": [0, 1, 3, 4, 5, 6, 10, 11], "A": [0, 3, 8, 9, 10, 11], "object": [0, 8, 9, 10, 11], "i": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "roughli": 0, "pair": [0, 8], "labelledcollect": [0, 3, 4, 8, 10, 11], "one": [0, 1, 3, 4, 5, 8, 10, 11], "plai": 0, "role": 0, "train": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "set": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "anoth": [0, 1, 3, 5], "test": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "class": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "consist": [0, 4, 5, 8, 9, 10, 11], "iter": [0, 8, 11], "instanc": [0, 3, 4, 5, 6, 8, 9, 10, 11], "label": [0, 3, 4, 5, 6, 8, 9, 10, 11], "thi": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "handl": 0, "most": [0, 3, 5, 6, 8, 10, 11], "sampl": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "function": [0, 1, 3, 4, 5, 6, 7, 9, 10, 11], "take": [0, 3, 5, 8, 10, 11], "look": [0, 1, 3, 5, 11], "follow": [0, 1, 3, 4, 5, 6, 8, 11], "code": [0, 3, 4, 5, 9], "qp": [0, 1, 3, 4, 5, 6, 8, 10, 11], "f": [0, 1, 3, 4, 5, 6, 10], "1st": 0, "posit": [0, 3, 5, 8, 10, 11], "document": [0, 1, 3, 5, 9, 10, 11], "2nd": 0, "onli": [0, 3, 5, 8, 9, 10, 11], "neg": [0, 5, 8, 11], "neutral": 0, "3rd": 0, "2": [0, 1, 3, 5, 8, 10, 11], "0": [0, 1, 3, 4, 5, 8, 9, 10, 11], "1": [0, 1, 3, 4, 5, 8, 9, 10, 11], "print": [0, 1, 3, 4, 6, 9, 10], "strprev": [0, 1, 8], "preval": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "prec": [0, 8], "output": [0, 1, 3, 4, 9, 10, 11], "show": [0, 1, 3, 4, 5, 8, 9, 10, 11], "digit": 0, "precis": [0, 1, 8], "17": 0, "50": [0, 5, 8, 11], "33": [0, 5, 8], "One": [0, 1, 3, 11], "can": [0, 1, 2, 3, 4, 5, 8, 10, 11], "easili": [0, 2, 5, 9], "produc": [0, 1, 5, 8], "new": [0, 3, 8, 9, 10], "desir": [0, 1, 10], "sample_s": [0, 1, 3, 4, 5, 8, 11], "10": [0, 1, 4, 5, 8, 9, 11], "prev": [0, 1, 8, 10], "4": [0, 1, 3, 4, 5, 10, 11], "5": [0, 1, 3, 4, 5, 8, 9, 10, 11], "which": [0, 1, 3, 4, 5, 8, 9, 10, 11], "40": [0, 3, 4, 11], "made": [0, 2, 8, 10, 11], "across": [0, 1, 4, 5, 6, 8, 11], "differ": [0, 1, 3, 4, 5, 6, 8, 10, 11], "run": [0, 1, 2, 3, 4, 5, 8, 10, 11], "e": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "g": [0, 1, 3, 4, 6, 8, 10, 11], "method": [0, 1, 4, 5, 6, 8], "same": [0, 3, 5, 8, 10, 11], "exact": [0, 10], "retain": [0, 3, 9, 11], "index": [0, 3, 6, 8, 9, 10, 11], "gener": [0, 1, 3, 4, 5, 8, 9, 10, 11], "sampling_index": [0, 10], "sampling_from_index": [0, 10], "also": [0, 1, 2, 3, 5, 6, 8, 9], "implement": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "artifici": [0, 1, 3, 4, 5, 6, 8], "protocol": [0, 3, 4, 5, 6, 7, 10, 11], "via": [0, 2, 3, 8, 9, 11], "python": [0, 6], "": [0, 1, 3, 4, 5, 8, 9, 10, 11], "seri": [0, 10], "equidist": [0, 8], "rang": [0, 5, 8, 11], "entir": [0, 3, 4, 5, 8], "spectrum": [0, 1, 4, 5, 8], "simplex": [0, 8], "space": [0, 4, 8, 9], "artificial_sampling_gener": 0, "100": [0, 1, 3, 4, 5, 8, 9, 10, 11], "n_preval": [0, 8], "each": [0, 1, 3, 4, 5, 8, 9, 10, 11], "valid": [0, 1, 3, 4, 5, 8, 9, 10, 11], "combin": [0, 1, 4, 8, 11], "origin": [0, 3, 8, 10], "from": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "split": [0, 3, 4, 5, 8, 9, 10, 11], "point": [0, 1, 3, 8, 10], "25": [0, 5, 8, 9, 11], "75": [0, 5, 8], "00": [0, 1, 4], "see": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "evalu": [0, 3, 4, 5, 6, 7, 9, 10, 11], "wiki": [0, 3], "further": [0, 1, 3, 9, 10, 11], "detail": [0, 1, 3, 6, 9, 10, 11], "how": [0, 1, 3, 4, 5, 8, 10, 11], "properli": 0, "three": [0, 5], "about": [0, 5, 8, 10], "kindl": [0, 1, 3, 5, 10, 11], "devic": [0, 3, 5, 9, 11], "harri": 0, "potter": 0, "known": [0, 3, 4, 8, 11], "imdb": [0, 5, 10], "movi": 0, "fetch": [0, 6], "unifi": [0, 11], "For": [0, 1, 5, 6, 8, 10], "exampl": [0, 1, 3, 4, 5, 8, 9, 10, 11], "fetch_review": [0, 1, 3, 4, 5, 10, 11], "These": [0, 9], "esuli": [0, 2, 3, 9, 10, 11], "moreo": [0, 3, 4, 10, 11], "sebastiani": [0, 3, 4, 10, 11], "2018": [0, 3, 10], "octob": [0, 3], "recurr": [0, 3, 10], "neural": [0, 8, 10], "network": [0, 8, 9, 10, 11], "In": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "proceed": [0, 3, 10], "27th": [0, 3, 10], "acm": [0, 3, 10, 11], "intern": [0, 3, 9, 10], "confer": [0, 3, 9, 10], "inform": [0, 1, 3, 4, 8, 9, 10, 11], "knowledg": [0, 3, 10], "manag": [0, 3, 10], "pp": [0, 3, 9], "1775": [0, 3], "1778": [0, 3], "The": [0, 1, 2, 4, 5, 6, 8, 9, 10, 11], "list": [0, 5, 8, 9, 10, 11], "id": [0, 3, 10], "reviews_sentiment_dataset": [0, 10], "some": [0, 1, 3, 5, 8, 10, 11], "statist": [0, 1, 8, 11], "fhe": 0, "ar": [0, 1, 3, 4, 5, 8, 9, 10, 11], "summar": 0, "below": [0, 2, 3, 5, 8, 10], "size": [0, 1, 3, 8, 9, 10, 11], "type": [0, 3, 8, 10, 11], "hp": [0, 3, 4, 10], "9533": 0, "18399": 0, "018": 0, "982": 0, "065": 0, "935": 0, "text": [0, 3, 8, 9, 10, 11], "3821": [0, 10], "21591": [0, 10], "081": [0, 10], "919": [0, 10], "063": [0, 10], "937": [0, 10], "25000": 0, "500": [0, 1, 4, 5, 11], "11": [0, 1, 6, 8], "analysi": [0, 3, 6, 10], "access": [0, 3, 10, 11], "were": 0, "tf": [0, 10], "idf": 0, "format": [0, 5, 10, 11], "present": [0, 3, 10], "two": [0, 1, 3, 4, 5, 8, 10, 11], "val": [0, 9, 10], "model": [0, 1, 5, 6, 8, 9, 11], "select": [0, 3, 6, 8, 10, 11], "purpos": [0, 11], "exemplifi": 0, "load": [0, 3, 8, 10, 11], "fetch_twitt": [0, 3, 6, 10], "gasp": [0, 10], "for_model_select": [0, 10], "true": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "gao": [0, 3, 10, 11], "w": [0, 3, 10], "2015": [0, 2, 3, 9, 11], "august": 0, "tweet": [0, 3, 10], "classif": [0, 1, 3, 6, 8, 10, 11], "ieee": 0, "advanc": [0, 6], "social": [0, 3, 10], "mine": [0, 3], "asonam": 0, "97": 0, "104": 0, "semeval13": [0, 10], "semeval14": [0, 10], "semeval15": [0, 10], "share": [0, 10], "semev": 0, "mean": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "would": [0, 1, 3, 5, 6, 10, 11], "get": [0, 1, 5, 8, 9, 10, 11], "when": [0, 1, 3, 4, 5, 8, 9, 10], "request": [0, 8, 10, 11], "ani": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "them": [0, 3, 11], "consult": [0, 1], "twitter_sentiment_datasets_test": [0, 10], "9": [0, 1, 3, 5, 8], "replac": [0, 3, 10], "twitter_sentiment_datasets_train": [0, 10], "found": [0, 3, 4, 8, 9, 10], "featur": [0, 10], "3": [0, 1, 3, 5, 6, 8, 9, 10, 11], "8788": 0, "3765": 0, "694582": 0, "421": 0, "496": 0, "082": [0, 1], "407": 0, "507": 0, "086": 0, "spars": [0, 10], "hcr": [0, 3, 10], "1594": 0, "798": 0, "222046": 0, "546": 0, "211": 0, "243": 0, "640": 0, "167": 0, "193": 0, "omd": [0, 10], "1839": 0, "787": 0, "199151": 0, "463": 0, "271": 0, "266": 0, "437": 0, "283": [0, 1], "280": 0, "sander": [0, 10], "2155": 0, "923": 0, "229399": 0, "161": 0, "691": 0, "148": 0, "164": [0, 3], "688": 0, "11338": 0, "3813": 0, "1215742": 0, "159": 0, "470": 0, "372": 0, "158": 0, "430": 0, "412": 0, "1853": 0, "109": 0, "361": 0, "530": 0, "2390": 0, "153": 0, "413": 0, "434": 0, "semeval16": [0, 6, 10], "8000": 0, "2000": 0, "889504": 0, "157": 0, "351": 0, "492": 0, "163": [0, 1], "341": 0, "497": 0, "sst": [0, 10], "2971": 0, "1271": 0, "376132": 0, "261": 0, "452": 0, "288": 0, "207": 0, "481": 0, "312": 0, "wa": [0, 3, 5, 8, 10, 11], "2184": 0, "936": 0, "248563": 0, "305": 0, "414": 0, "281": 0, "282": 0, "446": 0, "272": 0, "wb": [0, 10], "4259": 0, "1823": 0, "404333": 0, "270": 0, "392": 0, "337": 0, "274": 0, "335": 0, "32": [0, 6], "repositori": [0, 10], "p\u00e9rez": [0, 3, 10, 11], "g\u00e1llego": [0, 3, 10, 11], "p": [0, 3, 8, 9, 10, 11], "quevedo": [0, 3, 10], "j": [0, 3, 10, 11], "r": [0, 3, 8, 10], "del": [0, 3, 10], "coz": [0, 3, 10], "2017": [0, 3, 10, 11], "ensembl": [0, 6, 10, 11], "problem": [0, 3, 5, 8, 10, 11], "characteriz": [0, 3, 10], "chang": [0, 1, 3, 10], "distribut": [0, 3, 5, 8, 10, 11], "case": [0, 1, 3, 4, 5, 8, 9, 10, 11], "studi": [0, 3, 10], "fusion": [0, 3, 10], "34": [0, 3, 10, 11], "87": [0, 3, 10], "doe": [0, 2, 3, 8, 11], "exactli": 0, "coincid": [0, 6], "et": [0, 2, 9, 10, 11], "al": [0, 2, 9, 10, 11], "sinc": [0, 1, 3, 5, 10, 11], "we": [0, 1, 3, 4, 5, 6, 10], "unabl": 0, "find": [0, 4, 11], "diabet": 0, "phonem": 0, "call": [0, 1, 5, 8, 10, 11], "fetch_ucidataset": [0, 3, 10], "yeast": [0, 10], "verbos": [0, 1, 4, 8, 9, 10, 11], "return": [0, 1, 3, 4, 5, 8, 9, 10, 11], "randomli": [0, 10], "drawn": [0, 1, 4, 8, 10], "stratifi": [0, 3, 9, 10, 11], "manner": [0, 9, 11], "whole": [0, 1, 3, 4, 8, 9], "collect": [0, 8, 9, 10], "70": 0, "30": [0, 1, 3, 11], "respect": [0, 1, 5, 8, 11], "option": [0, 1, 3, 5, 10, 11], "indic": [0, 1, 3, 4, 5, 8, 9, 10, 11], "descript": [0, 10], "should": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "standard": [0, 1, 5, 8, 9, 10, 11], "paper": [0, 3, 9, 11], "submit": 0, "kfcv": [0, 9, 10, 11], "order": [0, 2, 3, 5, 8, 10, 11], "accommod": 0, "practic": [0, 4], "could": [0, 1, 3, 4, 5, 6], "first": [0, 1, 2, 3, 5, 8, 10, 11], "instanti": [0, 1, 3, 4, 8, 9, 11], "creat": [0, 6, 8, 11], "time": [0, 1, 3, 8, 10], "fetch_ucilabelledcollect": [0, 10], "nfold": [0, 8, 10], "nrepeat": [0, 10], "abov": [0, 3, 5, 8], "conduct": [0, 8], "2x5fcv": 0, "all": [0, 1, 2, 3, 5, 8, 9, 11], "come": [0, 8, 10, 11], "numer": [0, 1, 3, 6, 10, 11], "form": [0, 8, 10, 11], "dens": [0, 11], "matric": [0, 5, 10], "acut": 0, "120": 0, "6": [0, 1, 3, 5, 10], "508": 0, "b": [0, 8, 10, 11], "583": 0, "417": 0, "balanc": [0, 4, 11], "625": 0, "539": 0, "461": 0, "922": 0, "078": 0, "breast": 0, "cancer": 0, "683": 0, "350": 0, "650": 0, "cmc": 0, "1473": 0, "573": 0, "427": 0, "774": 0, "226": 0, "653": 0, "347": 0, "ctg": 0, "2126": 0, "22": [0, 3, 9, 10], "222": [0, 9], "778": 0, "861": 0, "139": 0, "917": 0, "083": 0, "german": 0, "1000": [0, 4, 11], "24": [0, 9], "300": [0, 1, 9], "700": 0, "haberman": [0, 3], "306": 0, "735": 0, "265": 0, "ionospher": 0, "641": 0, "359": 0, "iri": 0, "150": 0, "667": 0, "333": 0, "mammograph": 0, "830": 0, "514": 0, "486": 0, "pageblock": 0, "5473": 0, "979": 0, "021": 0, "semeion": 0, "1593": 0, "256": [0, 9], "901": 0, "099": 0, "sonar": 0, "208": 0, "60": 0, "534": 0, "466": 0, "spambas": 0, "4601": 0, "57": 0, "606": 0, "394": 0, "spectf": 0, "267": 0, "44": 0, "794": 0, "206": 0, "tictacto": 0, "958": 0, "transfus": 0, "748": 0, "762": 0, "238": 0, "wdbc": 0, "569": 0, "627": 0, "373": 0, "wine": 0, "178": 0, "13": [0, 9], "669": 0, "331": 0, "601": 0, "399": 0, "730": 0, "q": [0, 2, 3, 8, 9, 11], "red": 0, "1599": 0, "465": 0, "535": 0, "white": 0, "4898": 0, "665": 0, "1484": 0, "8": [0, 1, 5, 10, 11], "711": 0, "289": 0, "download": [0, 2, 3, 8, 10], "automat": [0, 1], "thei": [0, 3, 11], "store": [0, 9, 10, 11], "quapy_data": [0, 8], "folder": [0, 10, 11], "faster": [0, 10], "reus": [0, 3, 8, 10], "howev": [0, 4, 5], "requir": [0, 1, 3, 6, 9], "special": [0, 5, 10], "action": 0, "moment": [0, 3], "fulli": [0, 8], "autom": [0, 3, 6], "cardiotocographi": 0, "excel": 0, "file": [0, 5, 8, 9, 10, 11], "user": [0, 1, 5], "instal": [0, 3, 6, 9, 11], "xlrd": [0, 2], "modul": [0, 1, 3, 5, 6, 7], "open": [0, 6, 10], "page": [0, 2, 6], "block": [0, 8], "need": [0, 3, 8, 10, 11], "unix": 0, "compress": 0, "extens": [0, 2, 5], "z": [0, 10], "directli": [0, 1, 3], "doabl": 0, "packag": [0, 2, 3, 6, 7], "like": [0, 1, 3, 5, 8, 9, 10, 11], "gzip": 0, "zip": [0, 5], "uncompress": 0, "o": [0, 8], "depend": [0, 1, 4, 5, 8, 11], "softwar": 0, "manual": 0, "do": [0, 1, 3, 4, 8, 9, 10, 11], "invok": [0, 1, 3, 8, 10], "provid": [0, 3, 5, 6, 10, 11], "loader": [0, 10], "simpl": [0, 3, 5, 11], "deal": 0, "t": [0, 1, 3, 8, 9, 11], "pre": [0, 3], "n": [0, 1, 8, 9, 11], "second": [0, 1, 3, 5, 8, 10], "represent": [0, 3, 8, 9, 11], "col": [0, 10], "int": [0, 5, 8, 10, 11], "float": [0, 3, 8, 9, 10, 11], "charg": [0, 10], "classmethod": [0, 8, 10, 11], "def": [0, 1, 3, 5, 8], "cl": 0, "path": [0, 3, 5, 8, 9, 10, 11], "str": [0, 8, 10, 11], "loader_func": [0, 10], "callabl": [0, 8, 10, 11], "defin": [0, 3, 8, 9, 10, 11], "argument": [0, 1, 3, 5, 8, 10, 11], "initi": [0, 9, 11], "particular": [0, 1, 3, 11], "receiv": [0, 3, 5], "addition": 0, "number": [0, 1, 3, 5, 8, 9, 10, 11], "specifi": [0, 1, 3, 5, 8, 9, 10], "otherwis": [0, 3, 8, 10], "infer": [0, 10], "least": [0, 10], "pass": [0, 1, 5, 8, 9, 11], "along": [0, 3, 8, 11], "train_path": [0, 10], "my_data": 0, "dat": [0, 9], "test_path": [0, 10], "my_custom_load": 0, "rb": 0, "fin": 0, "preprocess": [0, 1, 3, 8, 11], "includ": [0, 1, 3, 5, 6, 10, 11], "text2tfidf": [0, 1, 3, 10], "tfidf": [0, 4, 5, 10], "vector": [0, 8, 9, 10, 11], "reduce_column": [0, 10], "reduc": [0, 10], "column": [0, 10], "base": [0, 3, 6, 8, 9], "term": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "frequenc": [0, 10, 11], "transform": [0, 9, 10, 11], "valu": [0, 1, 3, 8, 9, 10, 11], "score": [0, 1, 4, 8, 9, 10], "subtract": [0, 8, 10], "normal": [0, 1, 3, 8, 10, 11], "deviat": [0, 1, 5, 8, 10], "so": [0, 1, 3, 5, 8, 9, 10, 11], "zero": [0, 8], "unit": [0, 8], "varianc": [0, 5], "textual": [0, 6, 10], "token": [0, 9, 10], "appeal": 1, "tool": [1, 6], "scenario": [1, 3, 4, 5, 6], "dataset": [1, 3, 4, 5, 6, 8, 9, 11], "shift": [1, 4, 6, 8, 9, 11], "particularli": 1, "prior": [1, 3, 4, 5, 6, 8, 11], "probabl": [1, 3, 4, 5, 6, 8, 9, 11], "That": [1, 4], "interest": [1, 5, 6, 8], "estim": [1, 3, 5, 6, 8, 9, 10, 11], "aris": 1, "under": 1, "belief": 1, "those": [1, 3, 4, 5, 8, 9, 11], "might": [1, 8, 10], "ones": [1, 3, 5, 8, 10, 11], "observ": [1, 11], "dure": [1, 5, 11], "other": [1, 3, 5, 6, 8, 10, 11], "word": [1, 3, 6, 9, 10, 11], "simpli": [1, 2, 3, 4, 5, 6, 8, 11], "predictor": 1, "assum": [1, 6, 11], "unlik": [1, 4, 8], "machin": [1, 4, 6, 9], "learn": [1, 2, 3, 4, 6, 8, 9, 10, 11], "govern": 1, "iid": [1, 5, 6], "assumpt": [1, 5, 6], "brief": [1, 10], "dedic": [1, 10], "explain": [1, 5], "here": [1, 11], "mae": [1, 4, 6, 8, 9, 11], "absolut": [1, 3, 5, 6, 8, 11], "mrae": [1, 6, 8, 9, 11], "rel": [1, 3, 8, 10, 11], "mse": [1, 3, 6, 8, 11], "squar": [1, 3, 8], "mkld": [1, 8, 11], "kullback": [1, 3, 8, 11], "leibler": [1, 3, 8, 11], "diverg": [1, 3, 8, 11], "mnkld": [1, 8, 11], "ae": [1, 2, 5, 8, 11], "rae": [1, 2, 8, 11], "se": [1, 8], "kld": [1, 2, 8, 9, 11], "nkld": [1, 2, 6, 8, 9, 11], "individu": [1, 3], "without": [1, 3, 8, 10], "averag": [1, 3, 8, 10, 11], "acc": [1, 3, 5, 6, 8, 11], "accuraci": [1, 5, 8, 11], "f1e": [1, 8], "f1": [1, 8, 9], "true_prev": [1, 5, 8], "prevs_hat": [1, 8], "ndarrai": [1, 3, 8, 10, 11], "contain": [1, 2, 3, 5, 8, 9, 10, 11], "smooth": [1, 8], "stabil": [1, 11], "third": [1, 5], "ep": [1, 8], "none": [1, 4, 8, 9, 10, 11], "paramet": [1, 3, 4, 8, 9, 10, 11], "epsilon": [1, 8, 11], "tradition": 1, "2t": [1, 8], "past": 1, "either": [1, 3, 8, 11], "environ": [1, 3, 4, 5, 8, 11], "variabl": [1, 3, 5, 8, 10], "onc": [1, 3, 5, 8, 10], "ommit": 1, "thereaft": 1, "recommend": [1, 5, 11], "np": [1, 3, 4, 5, 8, 10, 11], "asarrai": 1, "let": [1, 3, 11], "estim_prev": [1, 5, 8], "ae_": 1, "3f": [1, 6], "200": [1, 9], "600": 1, "914": 1, "final": [1, 3, 5, 11], "possibl": [1, 3, 8, 11], "string": [1, 8, 10, 11], "error_funct": 1, "from_nam": [1, 8], "accord": [1, 3, 4, 8, 9, 10, 11], "fix": [1, 4], "cover": [1, 4, 8, 9], "full": [1, 8], "contrast": 1, "natur": [1, 8], "despit": 1, "introduc": 1, "approxim": [1, 5, 8, 9], "preserv": [1, 5, 8], "procol": 1, "equal": [1, 8, 11], "distant": [1, 8], "interv": [1, 5, 8], "n_prevpoint": [1, 4, 5, 8], "determin": [1, 4, 5, 8], "constrain": [1, 5, 8, 10], "obtain": [1, 4, 8, 9, 11], "66": [1, 11], "given": [1, 3, 4, 8, 9, 10, 11], "num_prevalence_combin": [1, 8], "21": [1, 3, 5, 8], "n_class": [1, 3, 8, 9, 10, 11], "n_repeat": [1, 8], "1771": 1, "note": [1, 3, 4, 5, 8, 10], "last": [1, 3, 5, 8, 9, 10], "typic": [1, 4, 5, 8, 9, 10, 11], "singl": [1, 3, 6, 11], "higher": [1, 5], "comput": [1, 3, 5, 8, 11], "perform": [1, 3, 4, 5, 6, 8, 9, 11], "signific": 1, "instead": [1, 3, 4, 8, 10, 11], "work": [1, 3, 4, 5, 8, 10, 11], "wai": [1, 11], "around": [1, 10], "maximum": [1, 8, 9, 11], "budg": 1, "close": [1, 10], "than": [1, 4, 5, 8, 9, 10], "budget": [1, 4], "achiev": [1, 3, 4, 5], "get_nprevpoints_approxim": [1, 8], "5000": [1, 5], "4960": 1, "cost": 1, "sometim": 1, "cumbersom": 1, "control": [1, 4, 8], "overal": 1, "experi": [1, 2, 3, 4, 5, 8], "rather": [1, 4], "By": [1, 3, 8], "avoid": [1, 8], "lead": [1, 10], "closer": 1, "surpass": 1, "script": [1, 2, 3, 6, 11], "pacc": [1, 3, 5, 8, 11], "reli": [1, 3, 8, 11], "logist": [1, 3, 9, 11], "regressor": [1, 3], "classifi": [1, 4, 5, 6, 8, 9, 11], "variou": [1, 5], "metric": [1, 3, 4, 6, 8, 11], "sklearn": [1, 3, 4, 5, 6, 9, 10, 11], "linear_model": [1, 3, 4, 6, 9], "logisticregress": [1, 3, 4, 6, 9, 11], "data": [1, 3, 4, 5, 6, 8, 9, 11], "min_df": [1, 3, 4, 5, 10, 11], "inplac": [1, 3, 10, 11], "lr": [1, 3, 9, 11], "aggreg": [1, 4, 5, 6, 8], "fit": [1, 3, 4, 5, 6, 8, 9, 10, 11], "df": 1, "artificial_sampling_report": 1, "mani": [1, 3, 4, 5, 6, 8, 10, 11], "extract": [1, 8, 10], "categori": [1, 8], "n_repetit": [1, 4, 5], "n_job": [1, 3, 4, 8, 9, 10, 11], "parallel": [1, 3, 8, 9, 10, 11], "worker": [1, 8, 9, 10, 11], "cpu": [1, 9, 11], "random_se": [1, 8], "42": 1, "random": [1, 3, 4, 5, 8, 10], "seed": [1, 4, 8], "replic": [1, 4, 8], "error_metr": [1, 4, 8], "line": [1, 3, 8], "result": [1, 2, 3, 4, 5, 6, 11], "report": 1, "panda": [1, 2], "datafram": 1, "displai": [1, 5, 8, 9], "just": [1, 3], "clearer": 1, "shown": [1, 5, 8], "convert": [1, 3, 8, 9, 10, 11], "repres": [1, 3, 5, 8, 10, 11], "decim": 1, "default": [1, 3, 8, 9, 10, 11], "pd": 1, "set_opt": 1, "expand_frame_repr": 1, "fals": [1, 3, 5, 8, 9, 10, 11], "map": [1, 9, 11], "000": 1, "000e": 1, "091": 1, "909": 1, "009": 1, "048": 1, "426e": 1, "04": 1, "837": 1, "037": 1, "114": 1, "633e": 1, "03": 1, "7": [1, 5, 8, 9, 11], "717": 1, "017": 1, "041": 1, "383e": 1, "366": 1, "634": 1, "034": 1, "070": 1, "412e": 1, "459": 1, "541": 1, "387e": 1, "565": 1, "435": 1, "035": 1, "073": 1, "535e": 1, "654": 1, "346": 1, "046": 1, "108": 1, "701e": 1, "725": 1, "275": 1, "075": 1, "235": 1, "515e": 1, "02": 1, "858": 1, "142": 1, "042": 1, "229": 1, "740e": 1, "945": 1, "055": 1, "27": [1, 3, 9], "357": 1, "219e": 1, "578": 1, "dtype": [1, 10], "float64": 1, "artificial_sampling_ev": [1, 4], "artificial_sampling_predict": [1, 5], "arrai": [1, 3, 5, 8, 9, 10, 11], "pip": 2, "older": 2, "version": [2, 8, 9, 11], "scikit": [2, 3, 4, 8, 9, 10, 11], "numpi": [2, 4, 8, 9], "scipi": [2, 10], "pytorch": [2, 11], "quanet": [2, 6, 9, 11], "svmperf": [2, 3, 8, 11], "patch": [2, 3, 9, 11], "joblib": 2, "tqdm": 2, "matplotlib": [2, 8], "involv": [2, 5, 8], "you": [2, 3], "appli": [2, 3, 4, 5, 8, 9, 10, 11], "ext": 2, "compil": [2, 3], "sourc": [2, 3, 6, 9], "prepare_svmperf": [2, 3], "sh": [2, 3], "job": 2, "directori": [2, 8, 9, 10, 11], "svm_perf_quantif": [2, 3], "optim": [2, 3, 4, 8, 9, 11], "measur": [2, 3, 4, 5, 6, 8, 11], "propos": [2, 3, 11], "barranquero": [2, 3, 9, 11], "extend": [2, 3, 8, 11], "former": [2, 11], "categor": [3, 10], "belong": [3, 11], "non": [3, 11], "group": 3, "though": [3, 8], "plan": 3, "add": [3, 4, 8, 10], "more": [3, 5, 11], "futur": 3, "character": [3, 6], "fact": [3, 5], "product": [3, 10], "quantifi": [3, 4, 5, 6, 8, 10, 11], "shoud": 3, "basequantifi": [3, 8, 11], "abstract": [3, 8, 9, 10, 11], "abstractmethod": 3, "self": [3, 8, 9, 10, 11], "set_param": [3, 8, 9, 11], "get_param": [3, 8, 9, 11], "deep": [3, 8, 11], "familiar": 3, "structur": [3, 11], "inspir": 3, "reason": [3, 5, 6], "why": 3, "ha": [3, 4, 5, 8, 9, 10, 11], "adopt": [3, 4, 10], "respond": 3, "predict": [3, 4, 5, 8, 9, 11], "input": [3, 5, 8, 9, 11], "element": [3, 10, 11], "while": [3, 5, 9, 10, 11], "selector": 3, "process": [3, 4, 8], "hyperparamet": [3, 8, 11], "search": [3, 4, 6, 8, 11], "part": [3, 10], "aggregativequantifi": [3, 11], "must": [3, 10, 11], "fit_learn": 3, "classif_predict": [3, 11], "mention": 3, "befor": [3, 8, 9, 10, 11], "inde": [3, 4], "alreadi": [3, 8, 11], "preclassifi": 3, "maintain": [3, 11], "through": [3, 8], "properti": [3, 8, 9, 10, 11], "learner": [3, 4, 9, 11], "extern": 3, "probabilist": [3, 9, 11], "inherit": 3, "aggregativeprobabilisticquantifi": [3, 11], "posterior": [3, 8, 9, 11], "crisp": [3, 8, 11], "decis": [3, 8, 9, 11], "hard": [3, 9], "classif_posterior": [3, 11], "posterior_prob": [3, 11], "advantag": [3, 11], "procedur": [3, 6, 8], "veri": [3, 5], "effici": 3, "everi": [3, 8, 11], "leverag": 3, "speed": [3, 11], "up": [3, 4, 8, 9, 11], "over": [3, 4, 8], "customarili": [3, 4], "done": 3, "four": 3, "cc": [3, 5, 11], "simplest": 3, "deliv": [3, 11], "adjust": [3, 6, 8, 11], "pcc": [3, 4, 5, 11], "soft": 3, "serv": [3, 8, 10], "complet": [3, 5, 11], "equip": [3, 5], "svm": [3, 5, 6, 9, 10, 11], "linearsvc": [3, 5, 10], "pickl": [3, 8, 10, 11], "alia": [3, 8, 10, 11], "classifyandcount": [3, 11], "estim_preval": [3, 6, 11], "rate": [3, 8, 9, 11], "binari": [3, 5, 6, 8, 9, 10, 11], "init": 3, "addit": 3, "val_split": [3, 4, 9, 11], "integ": [3, 8, 9, 10, 11], "k": [3, 6, 8, 9, 10, 11], "fold": [3, 8, 10, 11], "cross": [3, 8, 9, 10, 11], "specif": [3, 4, 8], "held": [3, 4, 8, 9, 11], "out": [3, 4, 5, 8, 9, 10, 11], "postpon": 3, "constructor": 3, "prevail": 3, "overrid": 3, "illustr": [3, 4, 5], "seem": 3, "calibr": [3, 8], "calibratedclassifiercv": 3, "base_estim": 3, "cv": [3, 4], "predict_proba": [3, 9, 11], "As": [3, 4], "calibratedclassifi": 3, "except": [3, 8, 11], "rais": [3, 8, 11], "lastli": 3, "everyth": 3, "said": 3, "aboud": 3, "sld": [3, 11], "expectationmaximizationquantifi": [3, 11], "describ": [3, 8, 11], "saeren": [3, 11], "m": [3, 8, 11], "latinn": [3, 11], "decaesteck": [3, 11], "c": [3, 4, 8, 9, 10, 11], "2002": 3, "priori": 3, "14": 3, "41": 3, "attempt": [3, 11], "although": [3, 4, 5, 11], "improv": [3, 8, 9, 11], "rank": [3, 9], "almost": 3, "alwai": [3, 4, 5, 11], "among": 3, "effect": 3, "carri": [3, 10, 11], "gonz\u00e1lez": 3, "castro": 3, "v": [3, 8, 9, 11], "alaiz": 3, "rodr\u0131": 3, "guez": 3, "alegr": 3, "2013": 3, "scienc": 3, "218": 3, "146": 3, "It": [3, 4, 5, 8], "allia": 3, "hellingerdistancei": [3, 11], "mixtur": [3, 8, 11], "previou": 3, "overridden": [3, 11], "proport": [3, 4, 9, 10, 11], "taken": [3, 8, 9, 10], "itself": [3, 8, 11], "accept": 3, "elm": [3, 11], "famili": [3, 11], "target": [3, 5, 6, 8, 9, 11], "orient": [3, 6, 8, 11], "joachim": [3, 9, 11], "svmq": [3, 11], "d\u00edez": 3, "reliabl": 3, "pattern": 3, "recognit": 3, "48": 3, "591": 3, "604": 3, "svmkld": [3, 11], "multivari": [3, 9], "transact": 3, "discoveri": 3, "articl": [3, 4], "svmnkld": [3, 11], "svmae": [3, 11], "error": [3, 4, 6, 7, 9, 11], "svmrae": [3, 11], "what": 3, "nowadai": 3, "consid": [3, 5, 8, 9, 10, 11], "behav": [3, 5], "If": [3, 5, 8, 10, 11], "want": [3, 4], "custom": [3, 6, 10], "modifi": [3, 8], "assign": [3, 10], "Then": 3, "re": [3, 4, 9, 10], "thing": 3, "your": 3, "svmperf_hom": 3, "valid_loss": [3, 9, 11], "mycustomloss": 3, "28": [3, 10], "current": [3, 8, 9, 10, 11], "support": [3, 6, 9, 10, 11], "oper": 3, "trivial": 3, "strategi": [3, 4], "2016": [3, 10, 11], "sentiment": [3, 6, 10], "19": [3, 10], "onevsal": [3, 11], "know": 3, "where": [3, 5, 8, 9, 10, 11], "top": [3, 8, 11], "thu": [3, 4, 5, 8, 9, 11], "nor": 3, "castano": [3, 10], "2019": [3, 10, 11], "dynam": [3, 9, 10, 11], "task": [3, 4, 10], "45": [3, 5, 10], "15": [3, 8, 10], "polici": [3, 11], "processor": 3, "av": [3, 11], "ptr": [3, 11], "member": [3, 11], "d": [3, 11], "static": [3, 11], "red_siz": [3, 11], "pleas": 3, "check": [3, 4, 8], "offer": [3, 6], "torch": [3, 9, 11], "embed": [3, 9, 11], "lstm": [3, 9, 11], "cnn": [3, 11], "its": [3, 4, 8, 9, 11], "layer": [3, 9, 11], "neuralclassifiertrain": [3, 9, 11], "cnnnet": [3, 9, 11], "vocabulary_s": [3, 9, 10, 11], "cuda": [3, 9, 11], "supervis": [4, 6], "strongli": [4, 5], "good": [4, 5], "choic": [4, 11], "hyper": [4, 8, 9], "wherebi": 4, "chosen": [4, 8], "pick": 4, "best": [4, 8, 9, 11], "being": [4, 8, 11], "criteria": 4, "solv": [4, 11], "assess": 4, "own": 4, "right": [4, 8, 10], "impos": [4, 8], "aim": [4, 5], "appropri": 4, "configur": [4, 8], "design": 4, "long": [4, 9], "regard": 4, "next": [4, 8, 9, 10], "section": 4, "argu": 4, "alejandro": 4, "fabrizio": 4, "count": [4, 5, 6, 8, 10, 11], "arxiv": 4, "preprint": 4, "2011": 4, "02552": 4, "2020": [4, 9], "varieti": 4, "exhibit": [4, 5], "degre": 4, "model_select": [4, 7, 11], "gridsearchq": [4, 8, 11], "grid": [4, 8, 11], "explor": [4, 8], "portion": 4, "param_grid": [4, 8, 11], "logspac": [4, 11], "class_weight": [4, 11], "eval_budget": 4, "refit": [4, 8], "retrain": [4, 9], "goe": 4, "end": [4, 8, 11], "best_params_": 4, "best_model_": 4, "101": 4, "5f": 4, "system": [4, 11], "start": 4, "hyperparam": 4, "0001": [4, 11], "got": [4, 11], "24987": 4, "48135": 4, "001": [4, 9, 11], "24866": 4, "100000": 4, "43676": 4, "finish": 4, "param": [4, 8, 9, 11], "19982": 4, "develop": [4, 6], "1010": 4, "5005": 4, "54it": 4, "20342": 4, "altern": 4, "computation": 4, "costli": 4, "try": 4, "theoret": 4, "suboptim": 4, "opt": 4, "gridsearchcv": [4, 11], "10000": 4, "5379": 4, "55it": 4, "41734": 4, "wors": [4, 5, 8], "larg": 4, "between": [4, 5, 6, 8, 9, 11], "modal": 4, "turn": 4, "better": 4, "nonetheless": 4, "happen": [4, 5], "basic": [5, 11], "help": 5, "analys": [5, 6], "outcom": 5, "main": 5, "method_nam": [5, 8, 11], "name": [5, 8, 9, 10, 11], "shape": [5, 8, 9, 10, 11], "correspond": [5, 10], "matrix": [5, 8, 11], "appear": 5, "occur": [5, 10], "merg": 5, "emq": [5, 11], "55": 5, "showcas": 5, "wide": 5, "variant": [5, 6, 8, 11], "linear": [5, 8, 11], "review": [5, 6, 10], "step": [5, 8], "05": [5, 8, 11], "gen_data": 5, "base_classifi": 5, "yield": [5, 8, 10, 11], "tr_prev": [5, 8, 11], "append": 5, "__class__": 5, "__name__": 5, "insight": 5, "view": 5, "y": [5, 8, 9, 10, 11], "axi": [5, 8], "against": 5, "x": [5, 8, 9, 10, 11], "unfortun": 5, "limit": [5, 8, 11], "binary_diagon": [5, 8], "train_prev": [5, 8], "savepath": [5, 8], "bin_diag": 5, "png": 5, "save": [5, 8], "pdf": [5, 11], "cyan": 5, "dot": [5, 8], "color": [5, 8], "band": [5, 8], "hidden": [5, 9, 11], "show_std": [5, 8], "unadjust": 5, "bias": 5, "toward": [5, 10], "seen": [5, 8, 11], "evinc": 5, "box": [5, 8], "binary_bias_glob": [5, 8], "bin_bia": 5, "unbias": 5, "center": 5, "tend": 5, "overestim": 5, "high": [5, 8], "lower": [5, 11], "again": 5, "accordingli": 5, "20": [5, 8, 11], "90": [5, 8], "rewrit": 5, "method_data": 5, "training_preval": 5, "linspac": 5, "training_s": 5, "suffic": 5, "latex": 5, "syntax": 5, "_": [5, 8, 10], "now": 5, "clearli": 5, "binary_bias_bin": [5, 8], "broken": [5, 8], "down": [5, 8, 10], "bin": [5, 8, 11], "To": [5, 10], "nbin": [5, 8, 11], "isometr": [5, 8], "subinterv": 5, "interestingli": 5, "enough": 5, "seemingli": 5, "tendenc": 5, "low": [5, 8, 9], "underestim": 5, "beyond": 5, "67": [5, 8], "curios": 5, "pretti": 5, "discuss": 5, "analyz": 5, "compar": [5, 8], "both": 5, "irrespect": [5, 11], "harder": 5, "interpret": [5, 6, 11], "error_by_drift": [5, 8], "error_nam": [5, 8], "n_bin": [5, 8, 11], "err_drift": 5, "whenev": [5, 8], "clear": 5, "lowest": 5, "difficult": 5, "rememb": 5, "solid": 5, "comparison": 5, "detriment": 5, "visual": [5, 6], "hide": 5, "framework": [6, 11], "written": 6, "root": 6, "concept": 6, "baselin": 6, "integr": 6, "commonli": 6, "facilit": 6, "twitter": [6, 10], "true_preval": 6, "hold": [6, 8, 11], "endeavour": [6, 8], "popular": 6, "expect": [6, 11], "maxim": [6, 11], "hdy": [6, 11], "versatil": 6, "etc": 6, "uci": [6, 10], "nativ": 6, "loss": [6, 9, 11], "perf": [6, 9, 11], "ad": 6, "meta": [6, 8], "plot": [6, 7], "diagon": [6, 8], "bia": [6, 8, 9, 11], "drift": 6, "api": 6, "subpackag": 7, "submodul": 7, "util": [7, 9], "content": 7, "bctscalibr": 9, "nbvscalibr": 9, "recalibratedprobabilisticclassifi": 9, "recalibratedprobabilisticclassifierbas": 9, "classes_": [9, 10, 11], "fit_cv": 9, "fit_tr_val": 9, "tscalibr": 9, "vscalibr": 9, "lowranklogisticregress": 9, "document_embed": 9, "lstmnet": 9, "reset_net_param": 9, "textclassifiernet": 9, "dimens": [8, 9, 10, 11], "forward": [9, 11], "xavier_uniform": 9, "torchdataset": 9, "asdataload": 9, "decision_funct": 9, "splitstratifi": 10, "stat": 10, "train_test": 10, "xp": 10, "xy": 10, "split_random": 10, "split_stratifi": 10, "uniform_sampl": 10, "uniform_sampling_index": 10, "fetch_lequa2022": 10, "warn": 10, "indextransform": 10, "add_word": 10, "fit_transform": 10, "reader": 8, "binar": [8, 10], "from_csv": 10, "from_spars": 10, "from_text": 10, "reindex_label": 10, "getptecondestim": 11, "solve_adjust": 11, "adjustedclassifyandcount": 11, "distributionmatch": 11, "dy": 11, "em": 11, "max_it": 11, "explicitlossminimis": 11, "max": 11, "ms2": 11, "mediansweep": 11, "mediansweep2": 11, "probabilisticadjustedclassifyandcount": 11, "probabilisticclassifyandcount": 11, "smm": 11, "t50": 11, "thresholdoptim": 11, "cross_generate_predict": 11, "cross_generate_predictions_depr": 11, "binaryquantifi": 11, "onevsallgener": 11, "eacc": 11, "ecc": 11, "eemq": 11, "ehdi": 11, "epacc": 11, "valid_polici": 11, "ensemblefactori": 11, "get_probability_distribut": 11, "quanetmodul": 11, "quanettrain": 11, "clean_checkpoint": 11, "clean_checkpoint_dir": 11, "mae_loss": 11, "non_aggreg": 8, "maximumlikelihoodprevalenceestim": 11, "absolute_error": 8, "hat": 8, "frac": 8, "mathcal": 8, "sum_": 8, "acc_error": 8, "y_true": 8, "y_pred": 8, "tp": 8, "tn": 8, "fp": 8, "fn": 8, "stand": [8, 11], "f1_error": 8, "macro": 8, "f_1": 8, "harmon": 8, "recal": 8, "2tp": 8, "independ": [8, 11], "err_nam": 8, "p_hat": 8, "d_": 8, "kl": 8, "log": [8, 10], "factor": 8, "beforehand": 8, "n_sampl": [8, 9], "mean_absolute_error": 8, "mean_relative_absolute_error": 8, "relative_absolute_error": 8, "underlin": 8, "displaystyl": 8, "abstractprotocol": 8, "union": [8, 11], "aggr_speedup": 8, "auto": 8, "evaluation_report": 8, "app": [8, 11], "repeat": 8, "smooth_limits_epsilon": 8, "random_st": [8, 10], "return_typ": 8, "sample_prev": 8, "abstractstochasticseededprotocol": 8, "onlabelledcollectionprotocol": 8, "95": 8, "copi": [8, 10], "quantiti": 8, "labelled_collect": 8, "prevalence_grid": 8, "exhaust": 8, "sum": [8, 11], "implicit": 8, "return_constrained_dim": 8, "rest": [8, 9, 10, 11], "quit": 8, "obvious": 8, "determinist": 8, "anywher": 8, "multipli": 8, "necessari": 8, "samples_paramet": 8, "total": 8, "parent": 8, "sequenc": 8, "enforc": 8, "collat": 8, "arg": [8, 10, 11], "domainmix": 8, "domaina": 8, "domainb": 8, "mixture_point": 8, "domain": 8, "scale": [8, 9, 11], "npp": 8, "draw": 8, "uniformli": 8, "therefor": 8, "get_col": 8, "get_labelled_collect": 8, "on_preclassified_inst": 8, "pre_classif": 8, "in_plac": 8, "usimplexpp": 8, "kraemer": 8, "algorithm": [8, 11], "sens": 8, "guarante": [8, 10], "prefer": 8, "intract": 8, "hellingerdist": 8, "hellingh": 8, "distanc": [8, 11], "hd": [8, 11], "discret": [8, 11], "sqrt": 8, "p_i": 8, "q_i": 8, "real": [8, 9, 10, 11], "topsoedist": 8, "1e": [8, 9, 11], "topso": [8, 11], "adjusted_quantif": 8, "prevalence_estim": 8, "tpr": [8, 11], "fpr": [8, 11], "clip": 8, "exce": 8, "check_prevalence_vector": 8, "raise_except": 8, "toleranz": 8, "08": 8, "combinations_budget": 8, "largest": 8, "dimension": [8, 9, 10, 11], "repetit": 8, "less": [8, 10], "normalize_preval": 8, "l1": [8, 11], "calcul": 8, "binom": 8, "mass": 8, "alloc": [8, 9], "solut": 8, "star": 8, "bar": 8, "prevalence_from_label": 8, "n_instanc": [8, 9, 11], "correctli": 8, "even": 8, "len": 8, "prevalence_from_prob": 8, "bool": [8, 9, 11], "argmax": 8, "prevalence_linspac": 8, "01": [8, 9, 11], "separ": [8, 10], "99": 8, "uniform_prevalence_sampl": 8, "adapt": [8, 9], "post": 8, "http": [8, 10, 11], "stackexchang": 8, "com": 8, "question": 8, "3227": 8, "uniform": [8, 10], "uniform_simplex_sampl": 8, "dict": [8, 10, 11], "timeout": 8, "dictionari": [8, 9, 10, 11], "kei": [8, 10], "quantification_error": 8, "whether": [8, 9, 10, 11], "ignor": [8, 10, 11], "gen": 8, "establish": 8, "timer": 8, "longer": 8, "timeouterror": 8, "bound": [8, 11], "stdout": 8, "best_model": 8, "after": [8, 11], "minim": [8, 11], "routin": [8, 10, 11], "unus": [8, 9], "contanin": 8, "cross_val_predict": 8, "akin": [8, 11], "issu": 8, "reproduc": [8, 10], "pos_class": [8, 10], "titl": 8, "colormap": 8, "listedcolormap": 8, "vertical_xtick": 8, "legend": 8, "local": 8, "sign": 8, "minu": 8, "classs": 8, "compon": [8, 9, 11], "cm": 8, "tab10": 8, "secondari": 8, "global": 8, "method_ord": 8, "henc": [8, 10], "conveni": 8, "multiclass": [8, 10, 11], "inconveni": 8, "leyend": 8, "hightlight": 8, "associ": [8, 10], "brokenbar_supremacy_by_drift": 8, "isomer": 8, "x_error": 8, "y_error": 8, "ttest_alpha": 8, "005": 8, "tail_density_threshold": 8, "region": 8, "chart": 8, "condit": [8, 11], "ii": 8, "significantli": 8, "side": 8, "confid": 8, "percentil": 8, "divid": 8, "amount": 8, "similar": [8, 11], "threshold": [8, 11], "densiti": 8, "tail": 8, "discard": 8, "outlier": 8, "show_dens": 8, "show_legend": 8, "logscal": 8, "vline": 8, "especi": 8, "mai": 8, "cumberson": 8, "gain": 8, "understand": 8, "fare": 8, "regim": 8, "highlight": 8, "vertic": 8, "earlystop": 8, "patienc": [8, 9, 11], "lower_is_bett": 8, "earli": [8, 9, 11], "stop": [8, 9, 11], "epoch": [8, 9, 11], "best_epoch": 8, "best_scor": 8, "consecut": [8, 9, 11], "monitor": 8, "obtaind": 8, "far": [8, 9, 10], "flag": 8, "keep": 8, "track": 8, "boolean": [8, 10, 11], "create_if_not_exist": 8, "makedir": 8, "exist_ok": 8, "join": 8, "dir": 8, "subdir": 8, "anotherdir": 8, "create_parent_dir": 8, "exist": 8, "txt": 8, "download_fil": 8, "url": 8, "archive_filenam": 8, "destin": 8, "filenam": 8, "download_file_if_not_exist": 8, "dowload": 8, "get_quapy_hom": 8, "home": [8, 10], "perman": 8, "map_parallel": 8, "func": 8, "slice": 8, "item": 8, "wrapper": [8, 9, 10, 11], "multiprocess": 8, "delai": 8, "args_i": 8, "silent": [8, 11], "child": 8, "ensur": 8, "pickled_resourc": 8, "pickle_path": 8, "generation_func": 8, "fast": [8, 10], "resourc": 8, "some_arrai": 8, "mock": [8, 9], "rand": 8, "my_arrai": 8, "pkl": 8, "save_text_fil": 8, "disk": 8, "miss": 8, "temp_se": 8, "context": 8, "tempor": 8, "outer": 8, "state": 8, "within": [8, 11], "get_njob": [], "correct": [9, 11], "temperatur": [9, 11], "bct": [9, 11], "abstent": 9, "alexandari": [9, 11], "afterward": [9, 11], "No": [9, 11], "nbv": [9, 11], "baseestim": [9, 11], "calibratorfactori": 9, "n_compon": 9, "kwarg": [9, 10, 11], "decomposit": 9, "truncatedsvd": 9, "princip": 9, "regress": 9, "n_featur": 9, "length": [9, 10], "eventu": [9, 10], "unalt": 9, "emb": 9, "embedding_s": 9, "hidden_s": 9, "repr_siz": 9, "kernel_height": 9, "stride": 9, "pad": [9, 10], "drop_p": 9, "convolut": 9, "vocabulari": [9, 10], "kernel": 9, "drop": 9, "dropout": [9, 11], "batch": 9, "dataload": 9, "tensor": 9, "n_dimens": 9, "lstm_class_nlay": 9, "short": 9, "memori": 9, "net": 9, "weight_decai": 9, "batch_siz": 9, "64": [9, 11], "batch_size_test": 9, "512": [9, 11], "padding_length": 9, "checkpointpath": 9, "checkpoint": [9, 11], "classifier_net": 9, "weight": [9, 10], "decai": 9, "wait": 9, "enabl": 9, "gpu": [9, 11], "vocab_s": 9, "reiniti": 9, "trainer": 9, "disjoint": 9, "embed_s": 9, "nn": 9, "pad_length": 9, "xavier": 9, "shuffl": [9, 10], "longest": 9, "shorter": 9, "svmperf_bas": [9, 11], "classifiermixin": 9, "thorsten": 9, "refer": [9, 10], "svm_perf_learn": 9, "svm_perf_classifi": 9, "trade": 9, "off": 9, "margin": 9, "std": 9, "qacc": 9, "qf1": 9, "qgm": 9, "12": 9, "26": 9, "23": 9, "train_siz": 10, "conform": 10, "round": 10, "loader_kwarg": 10, "read": 10, "tupl": [10, 11], "tr": 10, "te": 10, "csr": 10, "csr_matrix": 10, "4403": 10, "my_collect": 10, "codefram": 10, "larger": [10, 11], "actual": [10, 11], "empti": 10, "met": 10, "whose": [10, 11], "train_prop": 10, "left": [8, 10], "stratif": 10, "greater": 10, "dataset_nam": 10, "data_hom": 10, "test_split": 10, "predefin": 10, "uci_dataset": 10, "dump": 10, "leav": 10, "quay_data": 10, "ml": 10, "5fcvx2": 10, "x2": 10, "offici": 10, "lequa": 10, "competit": 10, "t1a": 10, "t1b": 10, "t2a": 10, "t2b": 10, "raw": 10, "merchandis": 10, "sperduti": 10, "2022": 10, "overview": 10, "clef": 10, "lequa2022_experi": 10, "py": 10, "guid": 10, "val_gen": 10, "test_gen": 10, "samplesfromdir": 10, "minimun": 10, "kept": 10, "subsequ": 10, "mining6": 10, "devel": 10, "style": 10, "countvector": 10, "keyword": [10, 11], "nogap": 10, "regardless": 10, "codifi": 10, "unknown": 10, "surfac": 10, "assert": 10, "gap": 10, "preced": 10, "decid": 10, "uniqu": 10, "rare": 10, "unk": 10, "minimum": [10, 11], "occurr": 10, "org": [10, 11], "stabl": 10, "feature_extract": 10, "html": 10, "subtyp": 10, "spmatrix": 10, "remov": [10, 11], "infrequ": 10, "aka": [10, 11], "sublinear_tf": 10, "scall": 10, "counter": 10, "tfidfvector": 10, "whcih": 10, "had": 10, "encod": 10, "utf": 10, "csv": 10, "feat1": 10, "feat2": 10, "featn": 10, "covari": 10, "express": 10, "row": 10, "class2int": 10, "collet": 10, "fomart": 10, "progress": 10, "sentenc": 10, "classnam": 10, "u1": 10, "misclassif": 11, "n_classes_": [], "fit_classifi": 11, "bypass": 11, "y_": 11, "ptecondestim": 11, "prevs_estim": 11, "ax": 11, "entri": 11, "y_i": 11, "y_j": 11, "_posterior_probabilities_": 11, "attribut": 11, "subclass": 11, "give": 11, "outsid": 11, "unless": 11, "noth": 11, "els": 11, "cdf": 11, "match": 11, "helling": 11, "sought": 11, "channel": 11, "proper": 11, "ch": 11, "di": 11, "dij": 11, "fraction": 11, "th": 11, "tol": 11, "ternari": 11, "dl": 11, "doi": 11, "1145": 11, "3219819": 11, "3220059": 11, "histogram": 11, "toler": 11, "explicit": 11, "exact_train_prev": 11, "recalib": 11, "updat": 11, "likelihood": [9, 11], "mutual": 11, "recurs": 11, "until": 11, "converg": 11, "suggest": 11, "recalibr": 11, "reach": 11, "loop": 11, "cumul": 11, "unlabel": 11, "latter": 11, "forman": 11, "2006": 11, "2008": 11, "goal": 11, "bring": 11, "denomin": 11, "median": 11, "sweep": 11, "binary_quantifi": 11, "prevel": 11, "emploi": 11, "resp": 11, "subobject": 11, "nest": 11, "pipelin": 11, "__": 11, "simplif": 11, "2021": 11, "equival": 11, "cosest": 11, "heurist": 11, "choos": 11, "ground": 11, "complement": 11, "param_mod_sel": 11, "param_model_sel": 11, "min_po": 11, "max_sample_s": 11, "closest": 11, "preliminari": 11, "recomput": 11, "compat": 11, "l": 11, "base_quantifier_class": 11, "factori": 11, "common": 11, "doc_embedding_s": 11, "stats_siz": 11, "lstm_hidden_s": 11, "lstm_nlayer": 11, "ff_layer": 11, "1024": 11, "bidirect": 11, "qdrop_p": 11, "order_bi": 11, "cell": 11, "connect": 11, "ff": 11, "sort": 11, "doc_embed": 11, "doc_posterior": 11, "recip": 11, "care": 11, "regist": 11, "hook": 11, "n_epoch": 11, "tr_iter_per_poch": 11, "va_iter_per_poch": 11, "checkpointdir": 11, "checkpointnam": 11, "phase": 11, "anyth": 11, "truth": 11, "mlpe": 11, "lazi": 11, "put": 11, "assumpion": 11, "beat": [9, 11], "estimant": 11, "kundaj": 9, "shrikumar": 9, "novemb": 9, "232": 9, "pmlr": 9, "outpu": 9, "partit": 9, "ight": [], "valueerror": 8}, "objects": {"": [[8, 0, 0, "-", "quapy"]], "quapy": [[9, 0, 0, "-", "classification"], [10, 0, 0, "-", "data"], [8, 0, 0, "-", "error"], [8, 0, 0, "-", "evaluation"], [8, 0, 0, "-", "functional"], [11, 0, 0, "-", "method"], [8, 0, 0, "-", "model_selection"], [8, 0, 0, "-", "plot"], [8, 0, 0, "-", "protocol"], [8, 0, 0, "-", "util"]], "quapy.classification": [[9, 0, 0, "-", "calibration"], [9, 0, 0, "-", "methods"], [9, 0, 0, "-", "neural"], [9, 0, 0, "-", "svmperf"]], "quapy.classification.calibration": [[9, 1, 1, "", "BCTSCalibration"], [9, 1, 1, "", "NBVSCalibration"], [9, 1, 1, "", "RecalibratedProbabilisticClassifier"], [9, 1, 1, "", "RecalibratedProbabilisticClassifierBase"], [9, 1, 1, "", "TSCalibration"], [9, 1, 1, "", "VSCalibration"]], "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase": [[9, 2, 1, "", "classes_"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "fit_cv"], [9, 3, 1, "", "fit_tr_val"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"]], "quapy.classification.methods": [[9, 1, 1, "", "LowRankLogisticRegression"]], "quapy.classification.methods.LowRankLogisticRegression": [[9, 3, 1, "", "fit"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"], [9, 3, 1, "", "set_params"], [9, 3, 1, "", "transform"]], "quapy.classification.neural": [[9, 1, 1, "", "CNNnet"], [9, 1, 1, "", "LSTMnet"], [9, 1, 1, "", "NeuralClassifierTrainer"], [9, 1, 1, "", "TextClassifierNet"], [9, 1, 1, "", "TorchDataset"]], "quapy.classification.neural.CNNnet": [[9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "get_params"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"]], "quapy.classification.neural.LSTMnet": [[9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "get_params"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"]], "quapy.classification.neural.NeuralClassifierTrainer": [[9, 2, 1, "", "device"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"], [9, 3, 1, "", "reset_net_params"], [9, 3, 1, "", "set_params"], [9, 3, 1, "", "transform"]], "quapy.classification.neural.TextClassifierNet": [[9, 3, 1, "", "dimensions"], [9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "forward"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict_proba"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"], [9, 3, 1, "", "xavier_uniform"]], "quapy.classification.neural.TorchDataset": [[9, 3, 1, "", "asDataloader"]], "quapy.classification.svmperf": [[9, 1, 1, "", "SVMperf"]], "quapy.classification.svmperf.SVMperf": [[9, 3, 1, "", "decision_function"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "set_params"], [9, 4, 1, "", "valid_losses"]], "quapy.data": [[10, 0, 0, "-", "base"], [10, 0, 0, "-", "datasets"], [10, 0, 0, "-", "preprocessing"], [10, 0, 0, "-", "reader"]], "quapy.data.base": [[10, 1, 1, "", "Dataset"], [10, 1, 1, "", "LabelledCollection"]], "quapy.data.base.Dataset": [[10, 3, 1, "", "SplitStratified"], [10, 2, 1, "", "binary"], [10, 2, 1, "", "classes_"], [10, 3, 1, "", "kFCV"], [10, 3, 1, "", "load"], [10, 2, 1, "", "n_classes"], [10, 3, 1, "", "stats"], [10, 2, 1, "", "train_test"], [10, 2, 1, "", "vocabulary_size"]], "quapy.data.base.LabelledCollection": [[10, 2, 1, "", "X"], [10, 2, 1, "", "Xp"], [10, 2, 1, "", "Xy"], [10, 2, 1, "", "binary"], [10, 3, 1, "", "counts"], [10, 3, 1, "", "kFCV"], [10, 3, 1, "", "load"], [10, 2, 1, "", "n_classes"], [10, 2, 1, "", "p"], [10, 3, 1, "", "prevalence"], [10, 3, 1, "", "sampling"], [10, 3, 1, "", "sampling_from_index"], [10, 3, 1, "", "sampling_index"], [10, 3, 1, "", "split_random"], [10, 3, 1, "", "split_stratified"], [10, 3, 1, "", "stats"], [10, 3, 1, "", "uniform_sampling"], [10, 3, 1, "", "uniform_sampling_index"], [10, 2, 1, "", "y"]], "quapy.data.datasets": [[10, 5, 1, "", "fetch_UCIDataset"], [10, 5, 1, "", "fetch_UCILabelledCollection"], [10, 5, 1, "", "fetch_lequa2022"], [10, 5, 1, "", "fetch_reviews"], [10, 5, 1, "", "fetch_twitter"], [10, 5, 1, "", "warn"]], "quapy.data.preprocessing": [[10, 1, 1, "", "IndexTransformer"], [10, 5, 1, "", "index"], [10, 5, 1, "", "reduce_columns"], [10, 5, 1, "", "standardize"], [10, 5, 1, "", "text2tfidf"]], "quapy.data.preprocessing.IndexTransformer": [[10, 3, 1, "", "add_word"], [10, 3, 1, "", "fit"], [10, 3, 1, "", "fit_transform"], [10, 3, 1, "", "transform"], [10, 3, 1, "", "vocabulary_size"]], "quapy.data.reader": [[10, 5, 1, "", "binarize"], [10, 5, 1, "", "from_csv"], [10, 5, 1, "", "from_sparse"], [10, 5, 1, "", "from_text"], [10, 5, 1, "", "reindex_labels"]], "quapy.error": [[8, 5, 1, "", "absolute_error"], [8, 5, 1, "", "acc_error"], [8, 5, 1, "", "acce"], [8, 5, 1, "", "ae"], [8, 5, 1, "", "f1_error"], [8, 5, 1, "", "f1e"], [8, 5, 1, "", "from_name"], [8, 5, 1, "", "kld"], [8, 5, 1, "", "mae"], [8, 5, 1, "", "mean_absolute_error"], [8, 5, 1, "", "mean_relative_absolute_error"], [8, 5, 1, "", "mkld"], [8, 5, 1, "", "mnkld"], [8, 5, 1, "", "mrae"], [8, 5, 1, "", "mse"], [8, 5, 1, "", "nkld"], [8, 5, 1, "", "rae"], [8, 5, 1, "", "relative_absolute_error"], [8, 5, 1, "", "se"], [8, 5, 1, "", "smooth"]], "quapy.evaluation": [[8, 5, 1, "", "evaluate"], [8, 5, 1, "", "evaluation_report"], [8, 5, 1, "", "prediction"]], "quapy.functional": [[8, 5, 1, "", "HellingerDistance"], [8, 5, 1, "", "TopsoeDistance"], [8, 5, 1, "", "adjusted_quantification"], [8, 5, 1, "", "check_prevalence_vector"], [8, 5, 1, "", "get_nprevpoints_approximation"], [8, 5, 1, "", "normalize_prevalence"], [8, 5, 1, "", "num_prevalence_combinations"], [8, 5, 1, "", "prevalence_from_labels"], [8, 5, 1, "", "prevalence_from_probabilities"], [8, 5, 1, "", "prevalence_linspace"], [8, 5, 1, "", "strprev"], [8, 5, 1, "", "uniform_prevalence_sampling"], [8, 5, 1, "", "uniform_simplex_sampling"]], "quapy.method": [[11, 0, 0, "-", "aggregative"], [11, 0, 0, "-", "base"], [11, 0, 0, "-", "meta"], [11, 0, 0, "-", "neural"], [11, 0, 0, "-", "non_aggregative"]], "quapy.method.aggregative": [[11, 1, 1, "", "ACC"], [11, 4, 1, "", "AdjustedClassifyAndCount"], [11, 1, 1, "", "AggregativeProbabilisticQuantifier"], [11, 1, 1, "", "AggregativeQuantifier"], [11, 1, 1, "", "CC"], [11, 4, 1, "", "ClassifyAndCount"], [11, 1, 1, "", "DistributionMatching"], [11, 1, 1, "", "DyS"], [11, 1, 1, "", "ELM"], [11, 1, 1, "", "EMQ"], [11, 4, 1, "", "ExpectationMaximizationQuantifier"], [11, 4, 1, "", "ExplicitLossMinimisation"], [11, 1, 1, "", "HDy"], [11, 4, 1, "", "HellingerDistanceY"], [11, 1, 1, "", "MAX"], [11, 1, 1, "", "MS"], [11, 1, 1, "", "MS2"], [11, 4, 1, "", "MedianSweep"], [11, 4, 1, "", "MedianSweep2"], [11, 1, 1, "", "OneVsAll"], [11, 1, 1, "", "PACC"], [11, 1, 1, "", "PCC"], [11, 4, 1, "", "ProbabilisticAdjustedClassifyAndCount"], [11, 4, 1, "", "ProbabilisticClassifyAndCount"], [11, 4, 1, "", "SLD"], [11, 1, 1, "", "SMM"], [11, 1, 1, "", "SVMAE"], [11, 1, 1, "", "SVMKLD"], [11, 1, 1, "", "SVMNKLD"], [11, 1, 1, "", "SVMQ"], [11, 1, 1, "", "SVMRAE"], [11, 1, 1, "", "T50"], [11, 1, 1, "", "ThresholdOptimization"], [11, 1, 1, "", "X"], [11, 5, 1, "", "cross_generate_predictions"], [11, 5, 1, "", "cross_generate_predictions_depr"]], "quapy.method.aggregative.ACC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "getPteCondEstim"], [11, 3, 1, "", "solve_adjustment"]], "quapy.method.aggregative.AggregativeProbabilisticQuantifier": [[11, 3, 1, "", "classify"]], "quapy.method.aggregative.AggregativeQuantifier": [[11, 3, 1, "", "aggregate"], [11, 2, 1, "", "classes_"], [11, 2, 1, "", "classifier"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.method.aggregative.CC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.DistributionMatching": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.DyS": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.ELM": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.EMQ": [[11, 3, 1, "", "EM"], [11, 4, 1, "", "EPSILON"], [11, 4, 1, "", "MAX_ITER"], [11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "predict_proba"]], "quapy.method.aggregative.HDy": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.OneVsAll": [[11, 3, 1, "", "aggregate"], [11, 2, 1, "", "classes_"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 3, 1, "", "set_params"]], "quapy.method.aggregative.PACC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "getPteCondEstim"]], "quapy.method.aggregative.PCC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.SMM": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.ThresholdOptimization": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.base": [[11, 1, 1, "", "BaseQuantifier"], [11, 1, 1, "", "BinaryQuantifier"], [11, 1, 1, "", "OneVsAllGeneric"]], "quapy.method.base.BaseQuantifier": [[11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.method.base.OneVsAllGeneric": [[11, 2, 1, "", "classes"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 3, 1, "", "quantify"], [11, 3, 1, "", "set_params"]], "quapy.method.meta": [[11, 5, 1, "", "EACC"], [11, 5, 1, "", "ECC"], [11, 5, 1, "", "EEMQ"], [11, 5, 1, "", "EHDy"], [11, 5, 1, "", "EPACC"], [11, 1, 1, "", "Ensemble"], [11, 5, 1, "", "ensembleFactory"], [11, 5, 1, "", "get_probability_distribution"]], "quapy.method.meta.Ensemble": [[11, 4, 1, "", "VALID_POLICIES"], [11, 2, 1, "", "aggregative"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 2, 1, "", "probabilistic"], [11, 3, 1, "", "quantify"], [11, 3, 1, "", "set_params"]], "quapy.method.neural": [[11, 1, 1, "", "QuaNetModule"], [11, 1, 1, "", "QuaNetTrainer"], [11, 5, 1, "", "mae_loss"]], "quapy.method.neural.QuaNetModule": [[11, 2, 1, "", "device"], [11, 3, 1, "", "forward"], [11, 4, 1, "", "training"]], "quapy.method.neural.QuaNetTrainer": [[11, 2, 1, "", "classes_"], [11, 3, 1, "", "clean_checkpoint"], [11, 3, 1, "", "clean_checkpoint_dir"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 3, 1, "", "quantify"], [11, 3, 1, "", "set_params"]], "quapy.method.non_aggregative": [[11, 1, 1, "", "MaximumLikelihoodPrevalenceEstimation"]], "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation": [[11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.model_selection": [[8, 1, 1, "", "GridSearchQ"], [8, 5, 1, "", "cross_val_predict"]], "quapy.model_selection.GridSearchQ": [[8, 3, 1, "", "best_model"], [8, 3, 1, "", "fit"], [8, 3, 1, "", "get_params"], [8, 3, 1, "", "quantify"], [8, 3, 1, "", "set_params"]], "quapy.plot": [[8, 5, 1, "", "binary_bias_bins"], [8, 5, 1, "", "binary_bias_global"], [8, 5, 1, "", "binary_diagonal"], [8, 5, 1, "", "brokenbar_supremacy_by_drift"], [8, 5, 1, "", "error_by_drift"]], "quapy.protocol": [[8, 1, 1, "", "APP"], [8, 1, 1, "", "AbstractProtocol"], [8, 1, 1, "", "AbstractStochasticSeededProtocol"], [8, 1, 1, "", "DomainMixer"], [8, 1, 1, "", "NPP"], [8, 1, 1, "", "OnLabelledCollectionProtocol"], [8, 1, 1, "", "USimplexPP"]], "quapy.protocol.APP": [[8, 3, 1, "", "prevalence_grid"], [8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.AbstractProtocol": [[8, 3, 1, "", "total"]], "quapy.protocol.AbstractStochasticSeededProtocol": [[8, 3, 1, "", "collator"], [8, 2, 1, "", "random_state"], [8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"]], "quapy.protocol.DomainMixer": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.NPP": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.OnLabelledCollectionProtocol": [[8, 4, 1, "", "RETURN_TYPES"], [8, 3, 1, "", "get_collator"], [8, 3, 1, "", "get_labelled_collection"], [8, 3, 1, "", "on_preclassified_instances"]], "quapy.protocol.USimplexPP": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.util": [[8, 1, 1, "", "EarlyStop"], [8, 5, 1, "", "create_if_not_exist"], [8, 5, 1, "", "create_parent_dir"], [8, 5, 1, "", "download_file"], [8, 5, 1, "", "download_file_if_not_exists"], [8, 5, 1, "", "get_quapy_home"], [8, 5, 1, "", "map_parallel"], [8, 5, 1, "", "parallel"], [8, 5, 1, "", "pickled_resource"], [8, 5, 1, "", "save_text_file"], [8, 5, 1, "", "temp_seed"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:property", "3": "py:method", "4": "py:attribute", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "property", "Python property"], "3": ["py", "method", "Python method"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "function", "Python function"]}, "titleterms": {"dataset": [0, 10], "review": 0, "twitter": 0, "sentiment": 0, "uci": 0, "machin": 0, "learn": 0, "issu": 0, "ad": 0, "custom": 0, "data": [0, 10], "process": 0, "evalu": [1, 8], "error": [1, 5, 8], "measur": 1, "protocol": [1, 8], "instal": 2, "requir": 2, "svm": 2, "perf": 2, "quantif": [2, 3, 4, 5], "orient": [2, 4], "loss": [2, 3, 4], "method": [3, 9, 11], "aggreg": [3, 11], "The": 3, "classifi": 3, "count": 3, "variant": 3, "expect": 3, "maxim": 3, "emq": 3, "helling": 3, "distanc": 3, "y": 3, "hdy": 3, "explicit": 3, "minim": 3, "meta": [3, 11], "model": [3, 4], "ensembl": 3, "quanet": 3, "neural": [3, 9, 11], "network": 3, "select": 4, "target": 4, "classif": [4, 9], "plot": [5, 8], "diagon": 5, "bia": 5, "drift": 5, "welcom": 6, "quapi": [6, 7, 8, 9, 10, 11], "": 6, "document": 6, "introduct": 6, "A": 6, "quick": 6, "exampl": 6, "featur": 6, "content": [6, 8, 9, 10, 11], "indic": 6, "tabl": 6, "packag": [8, 9, 10, 11], "subpackag": 8, "submodul": [8, 9, 10, 11], "function": 8, "model_select": 8, "util": 8, "modul": [8, 9, 10, 11], "calibr": 9, "svmperf": 9, "base": [10, 11], "preprocess": 10, "reader": 10, "non_aggreg": 11}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Datasets": [[0, "datasets"]], "Reviews Datasets": [[0, "reviews-datasets"]], "Twitter Sentiment Datasets": [[0, "twitter-sentiment-datasets"]], "UCI Machine Learning": [[0, "uci-machine-learning"]], "Issues:": [[0, "issues"]], "Adding Custom Datasets": [[0, "adding-custom-datasets"]], "Data Processing": [[0, "data-processing"]], "Evaluation": [[1, "evaluation"]], "Error Measures": [[1, "error-measures"]], "Evaluation Protocols": [[1, "evaluation-protocols"]], "Installation": [[2, "installation"]], "Requirements": [[2, "requirements"]], "SVM-perf with quantification-oriented losses": [[2, "svm-perf-with-quantification-oriented-losses"]], "Quantification Methods": [[3, "quantification-methods"]], "Aggregative Methods": [[3, "aggregative-methods"]], "The Classify & Count variants": [[3, "the-classify-count-variants"]], "Expectation Maximization (EMQ)": [[3, "expectation-maximization-emq"]], "Hellinger Distance y (HDy)": [[3, "hellinger-distance-y-hdy"]], "Explicit Loss Minimization": [[3, "explicit-loss-minimization"]], "Meta Models": [[3, "meta-models"]], "Ensembles": [[3, "ensembles"]], "The QuaNet neural network": [[3, "the-quanet-neural-network"]], "Model Selection": [[4, "model-selection"]], "Targeting a Quantification-oriented loss": [[4, "targeting-a-quantification-oriented-loss"]], "Targeting a Classification-oriented loss": [[4, "targeting-a-classification-oriented-loss"]], "Plotting": [[5, "plotting"]], "Diagonal Plot": [[5, "diagonal-plot"]], "Quantification bias": [[5, "quantification-bias"]], "Error by Drift": [[5, "error-by-drift"]], "Welcome to QuaPy\u2019s documentation!": [[6, "welcome-to-quapy-s-documentation"]], "Introduction": [[6, "introduction"]], "A quick example:": [[6, "a-quick-example"]], "Features": [[6, "features"]], "Contents:": [[6, null]], "Indices and tables": [[6, "indices-and-tables"]], "quapy": [[7, "quapy"]], "Submodules": [[9, "submodules"], [8, "submodules"], [10, "submodules"], [11, "submodules"]], "Module contents": [[9, "module-quapy.classification"], [8, "module-quapy"], [10, "module-quapy.data"], [11, "module-quapy.method"]], "quapy.classification package": [[9, "quapy-classification-package"]], "quapy.classification.calibration": [[9, "quapy-classification-calibration"]], "quapy.classification.methods": [[9, "module-quapy.classification.methods"]], "quapy.classification.neural": [[9, "module-quapy.classification.neural"]], "quapy.classification.svmperf": [[9, "module-quapy.classification.svmperf"]], "quapy package": [[8, "quapy-package"]], "quapy.error": [[8, "module-quapy.error"]], "quapy.evaluation": [[8, "module-quapy.evaluation"]], "quapy.protocol": [[8, "quapy-protocol"]], "quapy.functional": [[8, "module-quapy.functional"]], "quapy.model_selection": [[8, "module-quapy.model_selection"]], "quapy.plot": [[8, "module-quapy.plot"]], "quapy.util": [[8, "module-quapy.util"]], "Subpackages": [[8, "subpackages"]], "quapy.data package": [[10, "quapy-data-package"]], "quapy.data.base": [[10, "module-quapy.data.base"]], "quapy.data.datasets": [[10, "module-quapy.data.datasets"]], "quapy.data.preprocessing": [[10, "module-quapy.data.preprocessing"]], "quapy.data.reader": [[10, "module-quapy.data.reader"]], "quapy.method package": [[11, "quapy-method-package"]], "quapy.method.aggregative": [[11, "module-quapy.method.aggregative"]], "quapy.method.base": [[11, "module-quapy.method.base"]], "quapy.method.meta": [[11, "module-quapy.method.meta"]], "quapy.method.neural": [[11, "module-quapy.method.neural"]], "quapy.method.non_aggregative": [[11, "module-quapy.method.non_aggregative"]]}, "indexentries": {"app (class in quapy.protocol)": [[8, "quapy.protocol.APP"]], "abstractprotocol (class in quapy.protocol)": [[8, "quapy.protocol.AbstractProtocol"]], "abstractstochasticseededprotocol (class in quapy.protocol)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol"]], "domainmixer (class in quapy.protocol)": [[8, "quapy.protocol.DomainMixer"]], "earlystop (class in quapy.util)": [[8, "quapy.util.EarlyStop"]], "gridsearchq (class in quapy.model_selection)": [[8, "quapy.model_selection.GridSearchQ"]], "hellingerdistance() (in module quapy.functional)": [[8, "quapy.functional.HellingerDistance"]], "npp (class in quapy.protocol)": [[8, "quapy.protocol.NPP"]], "onlabelledcollectionprotocol (class in quapy.protocol)": [[8, "quapy.protocol.OnLabelledCollectionProtocol"]], "return_types (quapy.protocol.onlabelledcollectionprotocol attribute)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.RETURN_TYPES"]], "topsoedistance() (in module quapy.functional)": [[8, "quapy.functional.TopsoeDistance"]], "usimplexpp (class in quapy.protocol)": [[8, "quapy.protocol.USimplexPP"]], "absolute_error() (in module quapy.error)": [[8, "quapy.error.absolute_error"]], "acc_error() (in module quapy.error)": [[8, "quapy.error.acc_error"]], "acce() (in module quapy.error)": [[8, "quapy.error.acce"]], "adjusted_quantification() (in module quapy.functional)": [[8, "quapy.functional.adjusted_quantification"]], "ae() (in module quapy.error)": [[8, "quapy.error.ae"]], "best_model() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.best_model"]], "binary_bias_bins() (in module quapy.plot)": [[8, "quapy.plot.binary_bias_bins"]], "binary_bias_global() (in module quapy.plot)": [[8, "quapy.plot.binary_bias_global"]], "binary_diagonal() (in module quapy.plot)": [[8, "quapy.plot.binary_diagonal"]], "brokenbar_supremacy_by_drift() (in module quapy.plot)": [[8, "quapy.plot.brokenbar_supremacy_by_drift"]], "check_prevalence_vector() (in module quapy.functional)": [[8, "quapy.functional.check_prevalence_vector"]], "collator() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.collator"]], "create_if_not_exist() (in module quapy.util)": [[8, "quapy.util.create_if_not_exist"]], "create_parent_dir() (in module quapy.util)": [[8, "quapy.util.create_parent_dir"]], "cross_val_predict() (in module quapy.model_selection)": [[8, "quapy.model_selection.cross_val_predict"]], "download_file() (in module quapy.util)": [[8, "quapy.util.download_file"]], "download_file_if_not_exists() (in module quapy.util)": [[8, "quapy.util.download_file_if_not_exists"]], "error_by_drift() (in module quapy.plot)": [[8, "quapy.plot.error_by_drift"]], "evaluate() (in module quapy.evaluation)": [[8, "quapy.evaluation.evaluate"]], "evaluation_report() (in module quapy.evaluation)": [[8, "quapy.evaluation.evaluation_report"]], "f1_error() (in module quapy.error)": [[8, "quapy.error.f1_error"]], "f1e() (in module quapy.error)": [[8, "quapy.error.f1e"]], "fit() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.fit"]], "from_name() (in module quapy.error)": [[8, "quapy.error.from_name"]], "get_collator() (quapy.protocol.onlabelledcollectionprotocol class method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.get_collator"]], "get_labelled_collection() (quapy.protocol.onlabelledcollectionprotocol method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection"]], "get_nprevpoints_approximation() (in module quapy.functional)": [[8, "quapy.functional.get_nprevpoints_approximation"]], "get_params() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.get_params"]], "get_quapy_home() (in module quapy.util)": [[8, "quapy.util.get_quapy_home"]], "kld() (in module quapy.error)": [[8, "quapy.error.kld"]], "mae() (in module quapy.error)": [[8, "quapy.error.mae"]], "map_parallel() (in module quapy.util)": [[8, "quapy.util.map_parallel"]], "mean_absolute_error() (in module quapy.error)": [[8, "quapy.error.mean_absolute_error"]], "mean_relative_absolute_error() (in module quapy.error)": [[8, "quapy.error.mean_relative_absolute_error"]], "mkld() (in module quapy.error)": [[8, "quapy.error.mkld"]], "mnkld() (in module quapy.error)": [[8, "quapy.error.mnkld"]], "module": [[8, "module-quapy"], [8, "module-quapy.error"], [8, "module-quapy.evaluation"], [8, "module-quapy.functional"], [8, "module-quapy.model_selection"], [8, "module-quapy.plot"], [8, "module-quapy.protocol"], [8, "module-quapy.util"], [10, "module-quapy.data"], [10, "module-quapy.data.base"], [10, "module-quapy.data.datasets"], [10, "module-quapy.data.preprocessing"], [10, "module-quapy.data.reader"], [11, "module-quapy.method"], [11, "module-quapy.method.aggregative"], [11, "module-quapy.method.base"], [11, "module-quapy.method.meta"], [11, "module-quapy.method.neural"], [11, "module-quapy.method.non_aggregative"]], "mrae() (in module quapy.error)": [[8, "quapy.error.mrae"]], "mse() (in module quapy.error)": [[8, "quapy.error.mse"]], "nkld() (in module quapy.error)": [[8, "quapy.error.nkld"]], "normalize_prevalence() (in module quapy.functional)": [[8, "quapy.functional.normalize_prevalence"]], "num_prevalence_combinations() (in module quapy.functional)": [[8, "quapy.functional.num_prevalence_combinations"]], "on_preclassified_instances() (quapy.protocol.onlabelledcollectionprotocol method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.on_preclassified_instances"]], "parallel() (in module quapy.util)": [[8, "quapy.util.parallel"]], "pickled_resource() (in module quapy.util)": [[8, "quapy.util.pickled_resource"]], "prediction() (in module quapy.evaluation)": [[8, "quapy.evaluation.prediction"]], "prevalence_from_labels() (in module quapy.functional)": [[8, "quapy.functional.prevalence_from_labels"]], "prevalence_from_probabilities() (in module quapy.functional)": [[8, "quapy.functional.prevalence_from_probabilities"]], "prevalence_grid() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.prevalence_grid"]], "prevalence_linspace() (in module quapy.functional)": [[8, "quapy.functional.prevalence_linspace"]], "quantify() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.quantify"]], "quapy": [[8, "module-quapy"]], "quapy.error": [[8, "module-quapy.error"]], "quapy.evaluation": [[8, "module-quapy.evaluation"]], "quapy.functional": [[8, "module-quapy.functional"]], "quapy.model_selection": [[8, "module-quapy.model_selection"]], "quapy.plot": [[8, "module-quapy.plot"]], "quapy.protocol": [[8, "module-quapy.protocol"]], "quapy.util": [[8, "module-quapy.util"]], "rae() (in module quapy.error)": [[8, "quapy.error.rae"]], "random_state (quapy.protocol.abstractstochasticseededprotocol property)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.random_state"]], "relative_absolute_error() (in module quapy.error)": [[8, "quapy.error.relative_absolute_error"]], "sample() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.sample"]], "sample() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.sample"]], "sample() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.sample"]], "sample() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.sample"]], "sample() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.sample"]], "samples_parameters() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.samples_parameters"]], "samples_parameters() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.samples_parameters"]], "samples_parameters() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.samples_parameters"]], "samples_parameters() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.samples_parameters"]], "samples_parameters() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.samples_parameters"]], "save_text_file() (in module quapy.util)": [[8, "quapy.util.save_text_file"]], "se() (in module quapy.error)": [[8, "quapy.error.se"]], "set_params() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.set_params"]], "smooth() (in module quapy.error)": [[8, "quapy.error.smooth"]], "strprev() (in module quapy.functional)": [[8, "quapy.functional.strprev"]], "temp_seed() (in module quapy.util)": [[8, "quapy.util.temp_seed"]], "total() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.total"]], "total() (quapy.protocol.abstractprotocol method)": [[8, "quapy.protocol.AbstractProtocol.total"]], "total() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.total"]], "total() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.total"]], "total() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.total"]], "uniform_prevalence_sampling() (in module quapy.functional)": [[8, "quapy.functional.uniform_prevalence_sampling"]], "uniform_simplex_sampling() (in module quapy.functional)": [[8, "quapy.functional.uniform_simplex_sampling"]], "dataset (class in quapy.data.base)": [[10, "quapy.data.base.Dataset"]], "indextransformer (class in quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.IndexTransformer"]], "labelledcollection (class in quapy.data.base)": [[10, "quapy.data.base.LabelledCollection"]], "splitstratified() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.SplitStratified"]], "x (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.X"]], "xp (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.Xp"]], "xy (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.Xy"]], "add_word() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.add_word"]], "binarize() (in module quapy.data.reader)": [[10, "quapy.data.reader.binarize"]], "binary (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.binary"]], "binary (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.binary"]], "classes_ (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.classes_"]], "counts() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.counts"]], "fetch_ucidataset() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_UCIDataset"]], "fetch_ucilabelledcollection() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_UCILabelledCollection"]], "fetch_lequa2022() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_lequa2022"]], "fetch_reviews() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_reviews"]], "fetch_twitter() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_twitter"]], "fit() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.fit"]], "fit_transform() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.fit_transform"]], "from_csv() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_csv"]], "from_sparse() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_sparse"]], "from_text() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_text"]], "index() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.index"]], "kfcv() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.kFCV"]], "kfcv() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.kFCV"]], "load() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.load"]], "load() (quapy.data.base.labelledcollection class method)": [[10, "quapy.data.base.LabelledCollection.load"]], "n_classes (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.n_classes"]], "n_classes (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.n_classes"]], "p (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.p"]], "prevalence() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.prevalence"]], "quapy.data": [[10, "module-quapy.data"]], "quapy.data.base": [[10, "module-quapy.data.base"]], "quapy.data.datasets": [[10, "module-quapy.data.datasets"]], "quapy.data.preprocessing": [[10, "module-quapy.data.preprocessing"]], "quapy.data.reader": [[10, "module-quapy.data.reader"]], "reduce_columns() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.reduce_columns"]], "reindex_labels() (in module quapy.data.reader)": [[10, "quapy.data.reader.reindex_labels"]], "sampling() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling"]], "sampling_from_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling_from_index"]], "sampling_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling_index"]], "split_random() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.split_random"]], "split_stratified() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.split_stratified"]], "standardize() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.standardize"]], "stats() (quapy.data.base.dataset method)": [[10, "quapy.data.base.Dataset.stats"]], "stats() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.stats"]], "text2tfidf() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.text2tfidf"]], "train_test (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.train_test"]], "transform() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.transform"]], "uniform_sampling() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.uniform_sampling"]], "uniform_sampling_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.uniform_sampling_index"]], "vocabulary_size (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.vocabulary_size"]], "vocabulary_size() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.vocabulary_size"]], "warn() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.warn"]], "y (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.y"]], "acc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ACC"]], "adjustedclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.AdjustedClassifyAndCount"]], "aggregativeprobabilisticquantifier (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.AggregativeProbabilisticQuantifier"]], "aggregativequantifier (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.AggregativeQuantifier"]], "basequantifier (class in quapy.method.base)": [[11, "quapy.method.base.BaseQuantifier"]], "binaryquantifier (class in quapy.method.base)": [[11, "quapy.method.base.BinaryQuantifier"]], "cc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.CC"]], "classifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ClassifyAndCount"]], "distributionmatching (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.DistributionMatching"]], "dys (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.DyS"]], "eacc() (in module quapy.method.meta)": [[11, "quapy.method.meta.EACC"]], "ecc() (in module quapy.method.meta)": [[11, "quapy.method.meta.ECC"]], "eemq() (in module quapy.method.meta)": [[11, "quapy.method.meta.EEMQ"]], "ehdy() (in module quapy.method.meta)": [[11, "quapy.method.meta.EHDy"]], "elm (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ELM"]], "em() (quapy.method.aggregative.emq class method)": [[11, "quapy.method.aggregative.EMQ.EM"]], "emq (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.EMQ"]], "epacc() (in module quapy.method.meta)": [[11, "quapy.method.meta.EPACC"]], "epsilon (quapy.method.aggregative.emq attribute)": [[11, "quapy.method.aggregative.EMQ.EPSILON"]], "ensemble (class in quapy.method.meta)": [[11, "quapy.method.meta.Ensemble"]], "expectationmaximizationquantifier (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ExpectationMaximizationQuantifier"]], "explicitlossminimisation (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ExplicitLossMinimisation"]], "hdy (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.HDy"]], "hellingerdistancey (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.HellingerDistanceY"]], "max (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MAX"]], "max_iter (quapy.method.aggregative.emq attribute)": [[11, "quapy.method.aggregative.EMQ.MAX_ITER"]], "ms (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MS"]], "ms2 (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MS2"]], "maximumlikelihoodprevalenceestimation (class in quapy.method.non_aggregative)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation"]], "mediansweep (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.MedianSweep"]], "mediansweep2 (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.MedianSweep2"]], "onevsall (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.OneVsAll"]], "onevsallgeneric (class in quapy.method.base)": [[11, "quapy.method.base.OneVsAllGeneric"]], "pacc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.PACC"]], "pcc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.PCC"]], "probabilisticadjustedclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ProbabilisticAdjustedClassifyAndCount"]], "probabilisticclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ProbabilisticClassifyAndCount"]], "quanetmodule (class in quapy.method.neural)": [[11, "quapy.method.neural.QuaNetModule"]], "quanettrainer (class in quapy.method.neural)": [[11, "quapy.method.neural.QuaNetTrainer"]], "sld (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.SLD"]], "smm (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SMM"]], "svmae (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMAE"]], "svmkld (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMKLD"]], "svmnkld (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMNKLD"]], "svmq (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMQ"]], "svmrae (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMRAE"]], "t50 (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.T50"]], "thresholdoptimization (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ThresholdOptimization"]], "valid_policies (quapy.method.meta.ensemble attribute)": [[11, "quapy.method.meta.Ensemble.VALID_POLICIES"]], "x (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.X"]], "aggregate() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.aggregate"]], "aggregate() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.aggregate"]], "aggregate() (quapy.method.aggregative.cc method)": [[11, "quapy.method.aggregative.CC.aggregate"]], "aggregate() (quapy.method.aggregative.distributionmatching method)": [[11, "quapy.method.aggregative.DistributionMatching.aggregate"]], "aggregate() (quapy.method.aggregative.dys method)": [[11, "quapy.method.aggregative.DyS.aggregate"]], "aggregate() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.aggregate"]], "aggregate() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.aggregate"]], "aggregate() (quapy.method.aggregative.hdy method)": [[11, "quapy.method.aggregative.HDy.aggregate"]], "aggregate() (quapy.method.aggregative.onevsall method)": [[11, "quapy.method.aggregative.OneVsAll.aggregate"]], "aggregate() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.aggregate"]], "aggregate() (quapy.method.aggregative.pcc method)": [[11, "quapy.method.aggregative.PCC.aggregate"]], "aggregate() (quapy.method.aggregative.smm method)": [[11, "quapy.method.aggregative.SMM.aggregate"]], "aggregate() (quapy.method.aggregative.thresholdoptimization method)": [[11, "quapy.method.aggregative.ThresholdOptimization.aggregate"]], "aggregative (quapy.method.meta.ensemble property)": [[11, "quapy.method.meta.Ensemble.aggregative"]], "classes (quapy.method.base.onevsallgeneric property)": [[11, "quapy.method.base.OneVsAllGeneric.classes"]], "classes_ (quapy.method.aggregative.aggregativequantifier property)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classes_"]], "classes_ (quapy.method.aggregative.onevsall property)": [[11, "quapy.method.aggregative.OneVsAll.classes_"]], "classes_ (quapy.method.neural.quanettrainer property)": [[11, "quapy.method.neural.QuaNetTrainer.classes_"]], "classifier (quapy.method.aggregative.aggregativequantifier property)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classifier"]], "classify() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.classify"]], "classify() (quapy.method.aggregative.aggregativeprobabilisticquantifier method)": [[11, "quapy.method.aggregative.AggregativeProbabilisticQuantifier.classify"]], "classify() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classify"]], "classify() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.classify"]], "classify() (quapy.method.aggregative.onevsall method)": [[11, "quapy.method.aggregative.OneVsAll.classify"]], "classify() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.classify"]], "clean_checkpoint() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.clean_checkpoint"]], "clean_checkpoint_dir() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.clean_checkpoint_dir"]], "cross_generate_predictions() (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.cross_generate_predictions"]], "cross_generate_predictions_depr() (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.cross_generate_predictions_depr"]], "device (quapy.method.neural.quanetmodule property)": [[11, "quapy.method.neural.QuaNetModule.device"]], "ensemblefactory() (in module quapy.method.meta)": [[11, "quapy.method.meta.ensembleFactory"]], "fit() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.fit"]], "fit() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.fit"]], "fit() (quapy.method.aggregative.cc method)": [[11, "quapy.method.aggregative.CC.fit"]], "fit() (quapy.method.aggregative.distributionmatching method)": [[11, "quapy.method.aggregative.DistributionMatching.fit"]], "fit() (quapy.method.aggregative.dys method)": [[11, "quapy.method.aggregative.DyS.fit"]], "fit() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.fit"]], "fit() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.fit"]], "fit() (quapy.method.aggregative.hdy method)": [[11, "quapy.method.aggregative.HDy.fit"]], "fit() (quapy.method.aggregative.onevsall method)": [[11, "quapy.method.aggregative.OneVsAll.fit"]], "fit() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.fit"]], "fit() (quapy.method.aggregative.pcc method)": [[11, "quapy.method.aggregative.PCC.fit"]], "fit() (quapy.method.aggregative.smm method)": [[11, "quapy.method.aggregative.SMM.fit"]], "fit() (quapy.method.aggregative.thresholdoptimization method)": [[11, "quapy.method.aggregative.ThresholdOptimization.fit"]], "fit() (quapy.method.base.basequantifier method)": [[11, "quapy.method.base.BaseQuantifier.fit"]], "fit() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.fit"]], "fit() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.fit"]], "fit() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.fit"]], "fit() (quapy.method.non_aggregative.maximumlikelihoodprevalenceestimation method)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.fit"]], "forward() (quapy.method.neural.quanetmodule method)": [[11, "quapy.method.neural.QuaNetModule.forward"]], "getptecondestim() (quapy.method.aggregative.acc class method)": [[11, "quapy.method.aggregative.ACC.getPteCondEstim"]], "getptecondestim() (quapy.method.aggregative.pacc class method)": [[11, "quapy.method.aggregative.PACC.getPteCondEstim"]], "get_params() (quapy.method.aggregative.onevsall method)": [[11, "quapy.method.aggregative.OneVsAll.get_params"]], "get_params() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.get_params"]], "get_params() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.get_params"]], "get_params() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.get_params"]], "get_probability_distribution() (in module quapy.method.meta)": [[11, "quapy.method.meta.get_probability_distribution"]], "mae_loss() (in module quapy.method.neural)": [[11, "quapy.method.neural.mae_loss"]], "predict_proba() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.predict_proba"]], "probabilistic (quapy.method.meta.ensemble property)": [[11, "quapy.method.meta.Ensemble.probabilistic"]], "quantify() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.quantify"]], "quantify() (quapy.method.base.basequantifier method)": [[11, "quapy.method.base.BaseQuantifier.quantify"]], "quantify() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.quantify"]], "quantify() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.quantify"]], "quantify() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.quantify"]], "quantify() (quapy.method.non_aggregative.maximumlikelihoodprevalenceestimation method)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.quantify"]], "quapy.method": [[11, "module-quapy.method"]], "quapy.method.aggregative": [[11, "module-quapy.method.aggregative"]], "quapy.method.base": [[11, "module-quapy.method.base"]], "quapy.method.meta": [[11, "module-quapy.method.meta"]], "quapy.method.neural": [[11, "module-quapy.method.neural"]], "quapy.method.non_aggregative": [[11, "module-quapy.method.non_aggregative"]], "set_params() (quapy.method.aggregative.onevsall method)": [[11, "quapy.method.aggregative.OneVsAll.set_params"]], "set_params() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.set_params"]], "set_params() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.set_params"]], "set_params() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.set_params"]], "solve_adjustment() (quapy.method.aggregative.acc class method)": [[11, "quapy.method.aggregative.ACC.solve_adjustment"]], "training (quapy.method.neural.quanetmodule attribute)": [[11, "quapy.method.neural.QuaNetModule.training"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["Datasets", "Evaluation", "Installation", "Methods", "Model-Selection", "Plotting", "index", "modules", "quapy", "quapy.classification", "quapy.data", "quapy.method"], "filenames": ["Datasets.md", "Evaluation.md", "Installation.rst", "Methods.md", "Model-Selection.md", "Plotting.md", "index.rst", "modules.rst", "quapy.rst", "quapy.classification.rst", "quapy.data.rst", "quapy.method.rst"], "titles": ["Datasets", "Evaluation", "Installation", "Quantification Methods", "Model Selection", "Plotting", "Welcome to QuaPy\u2019s documentation!", "quapy", "quapy package", "quapy.classification package", "quapy.data package", "quapy.method package"], "terms": {"quapi": [0, 1, 2, 3, 4, 5], "make": [0, 1, 3, 8, 11], "avail": [0, 1, 2, 3, 5, 6, 9, 11], "sever": [0, 10], "have": [0, 1, 2, 3, 4, 5, 8, 10, 11], "been": [0, 3, 4, 5, 8, 9, 10, 11], "us": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "quantif": [0, 1, 6, 8, 9, 10, 11], "literatur": [0, 1, 4, 6], "well": [0, 3, 4, 5, 11], "an": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "interfac": [0, 1, 11], "allow": [0, 1, 2, 3, 5, 8, 9, 10, 11], "anyon": 0, "import": [0, 1, 3, 4, 5, 6, 10, 11], "A": [0, 3, 8, 9, 10, 11], "object": [0, 8, 9, 10, 11], "i": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "roughli": 0, "pair": [0, 8], "labelledcollect": [0, 3, 4, 8, 10, 11], "one": [0, 1, 3, 4, 5, 8, 10, 11], "plai": 0, "role": 0, "train": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "set": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "anoth": [0, 1, 3, 5, 10], "test": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "class": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "consist": [0, 4, 5, 8, 9, 10, 11], "iter": [0, 8, 11], "instanc": [0, 3, 4, 5, 6, 8, 9, 10, 11], "label": [0, 3, 4, 5, 6, 8, 9, 10, 11], "thi": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "handl": 0, "most": [0, 3, 5, 6, 8, 10, 11], "sampl": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "function": [0, 1, 3, 4, 5, 6, 7, 9, 10, 11], "take": [0, 3, 5, 8, 10, 11], "look": [0, 1, 3, 5, 11], "follow": [0, 1, 3, 4, 5, 6, 8, 11], "code": [0, 3, 4, 5, 9], "qp": [0, 1, 3, 4, 5, 6, 8, 10, 11], "f": [0, 1, 3, 4, 5, 6, 10], "1st": 0, "posit": [0, 3, 5, 8, 10, 11], "document": [0, 1, 3, 5, 9, 10, 11], "2nd": 0, "onli": [0, 3, 5, 8, 9, 10, 11], "neg": [0, 5, 8, 11], "neutral": 0, "3rd": 0, "2": [0, 1, 3, 5, 8, 10, 11], "0": [0, 1, 3, 4, 5, 8, 9, 10, 11], "1": [0, 1, 3, 4, 5, 8, 9, 10, 11], "print": [0, 1, 3, 4, 6, 9, 10], "strprev": [0, 1, 8], "preval": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "prec": [0, 8], "output": [0, 1, 3, 4, 9, 10, 11], "show": [0, 1, 3, 4, 5, 8, 9, 10, 11], "digit": 0, "precis": [0, 1, 8], "17": 0, "50": [0, 5, 8, 11], "33": [0, 5, 8], "One": [0, 1, 3, 11], "can": [0, 1, 2, 3, 4, 5, 8, 10, 11], "easili": [0, 2, 5, 9], "produc": [0, 1, 5, 8], "new": [0, 3, 8, 9, 10], "desir": [0, 1, 10], "sample_s": [0, 1, 3, 4, 5, 8, 11], "10": [0, 1, 4, 5, 8, 9, 11], "prev": [0, 1, 8, 10], "4": [0, 1, 3, 4, 5, 10, 11], "5": [0, 1, 3, 4, 5, 8, 9, 10, 11], "which": [0, 1, 3, 4, 5, 8, 9, 10, 11], "40": [0, 3, 4, 11], "made": [0, 2, 8, 10, 11], "across": [0, 1, 4, 5, 6, 8, 11], "differ": [0, 1, 3, 4, 5, 6, 8, 10, 11], "run": [0, 1, 2, 3, 4, 5, 8, 10, 11], "e": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "g": [0, 1, 3, 4, 6, 8, 10, 11], "method": [0, 1, 4, 5, 6, 8], "same": [0, 3, 5, 8, 10, 11], "exact": [0, 10], "retain": [0, 3, 9, 11], "index": [0, 3, 6, 8, 9, 10, 11], "gener": [0, 1, 3, 4, 5, 8, 9, 10, 11], "sampling_index": [0, 10], "sampling_from_index": [0, 10], "also": [0, 1, 2, 3, 5, 6, 8, 9], "implement": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "artifici": [0, 1, 3, 4, 5, 6, 8], "protocol": [0, 3, 4, 5, 6, 7, 10, 11], "via": [0, 2, 3, 8, 9, 11], "python": [0, 6], "": [0, 1, 3, 4, 5, 8, 9, 10, 11], "seri": [0, 10], "equidist": [0, 8], "rang": [0, 5, 8, 11], "entir": [0, 3, 4, 5, 8], "spectrum": [0, 1, 4, 5, 8], "simplex": [0, 8], "space": [0, 4, 8, 9], "artificial_sampling_gener": 0, "100": [0, 1, 3, 4, 5, 8, 9, 10, 11], "n_preval": [0, 8], "each": [0, 1, 3, 4, 5, 8, 9, 10, 11], "valid": [0, 1, 3, 4, 5, 8, 9, 10, 11], "combin": [0, 1, 4, 8, 11], "origin": [0, 3, 8, 10], "from": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "split": [0, 3, 4, 5, 8, 9, 10, 11], "point": [0, 1, 3, 8, 10], "25": [0, 5, 8, 9, 11], "75": [0, 5, 8], "00": [0, 1, 4], "see": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "evalu": [0, 3, 4, 5, 6, 7, 9, 10, 11], "wiki": [0, 3], "further": [0, 1, 3, 9, 10, 11], "detail": [0, 1, 3, 6, 9, 10, 11], "how": [0, 1, 3, 4, 5, 8, 10, 11], "properli": 0, "three": [0, 5], "about": [0, 5, 8, 10], "kindl": [0, 1, 3, 5, 10, 11], "devic": [0, 3, 5, 9, 11], "harri": 0, "potter": 0, "known": [0, 3, 4, 8, 11], "imdb": [0, 5, 10], "movi": 0, "fetch": [0, 6], "unifi": [0, 11], "For": [0, 1, 5, 6, 8, 10], "exampl": [0, 1, 3, 4, 5, 8, 9, 10, 11], "fetch_review": [0, 1, 3, 4, 5, 10, 11], "These": [0, 9], "esuli": [0, 2, 3, 9, 10, 11], "moreo": [0, 3, 4, 10, 11], "sebastiani": [0, 3, 4, 10, 11], "2018": [0, 3, 10], "octob": [0, 3], "recurr": [0, 3, 10], "neural": [0, 8, 10], "network": [0, 8, 9, 10, 11], "In": [0, 1, 2, 3, 4, 5, 6, 8, 9, 10, 11], "proceed": [0, 3, 10], "27th": [0, 3, 10], "acm": [0, 3, 10, 11], "intern": [0, 3, 9, 10], "confer": [0, 3, 9, 10], "inform": [0, 1, 3, 4, 8, 9, 10, 11], "knowledg": [0, 3, 10], "manag": [0, 3, 10], "pp": [0, 3, 9], "1775": [0, 3], "1778": [0, 3], "The": [0, 1, 2, 4, 5, 6, 8, 9, 10, 11], "list": [0, 5, 8, 9, 10, 11], "id": [0, 3, 10], "reviews_sentiment_dataset": [0, 10], "some": [0, 1, 3, 5, 8, 10, 11], "statist": [0, 1, 8, 11], "fhe": 0, "ar": [0, 1, 3, 4, 5, 8, 9, 10, 11], "summar": 0, "below": [0, 2, 3, 5, 8, 10], "size": [0, 1, 3, 8, 9, 10, 11], "type": [0, 3, 8, 10, 11], "hp": [0, 3, 4, 10], "9533": 0, "18399": 0, "018": 0, "982": 0, "065": 0, "935": 0, "text": [0, 3, 8, 9, 10, 11], "3821": [0, 10], "21591": [0, 10], "081": [0, 10], "919": [0, 10], "063": [0, 10], "937": [0, 10], "25000": 0, "500": [0, 1, 4, 5, 11], "11": [0, 1, 6, 8], "analysi": [0, 3, 6, 10], "access": [0, 3, 10, 11], "were": 0, "tf": [0, 10], "idf": 0, "format": [0, 5, 10, 11], "present": [0, 3, 10], "two": [0, 1, 3, 4, 5, 8, 10, 11], "val": [0, 9, 10], "model": [0, 1, 5, 6, 8, 9, 11], "select": [0, 3, 6, 8, 10, 11], "purpos": [0, 11], "exemplifi": 0, "load": [0, 3, 8, 10, 11], "fetch_twitt": [0, 3, 6, 10], "gasp": [0, 10], "for_model_select": [0, 10], "true": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "gao": [0, 3, 10, 11], "w": [0, 3, 10], "2015": [0, 2, 3, 9, 11], "august": 0, "tweet": [0, 3, 10], "classif": [0, 1, 3, 6, 8, 10, 11], "ieee": 0, "advanc": [0, 6], "social": [0, 3, 10], "mine": [0, 3], "asonam": 0, "97": 0, "104": 0, "semeval13": [0, 10], "semeval14": [0, 10], "semeval15": [0, 10], "share": [0, 10], "semev": 0, "mean": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "would": [0, 1, 3, 5, 6, 10, 11], "get": [0, 1, 5, 8, 9, 10, 11], "when": [0, 1, 3, 4, 5, 8, 9, 10], "request": [0, 8, 10, 11], "ani": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "them": [0, 3, 10, 11], "consult": [0, 1], "twitter_sentiment_datasets_test": [0, 10], "9": [0, 1, 3, 5, 8], "replac": [0, 3, 10], "twitter_sentiment_datasets_train": [0, 10], "found": [0, 3, 4, 8, 9, 10], "featur": [0, 10], "3": [0, 1, 3, 5, 6, 8, 9, 10, 11], "8788": 0, "3765": 0, "694582": 0, "421": 0, "496": 0, "082": [0, 1], "407": 0, "507": 0, "086": 0, "spars": [0, 10], "hcr": [0, 3, 10], "1594": 0, "798": 0, "222046": 0, "546": 0, "211": 0, "243": 0, "640": 0, "167": 0, "193": 0, "omd": [0, 10], "1839": 0, "787": 0, "199151": 0, "463": 0, "271": 0, "266": 0, "437": 0, "283": [0, 1], "280": 0, "sander": [0, 10], "2155": 0, "923": 0, "229399": 0, "161": 0, "691": 0, "148": 0, "164": [0, 3], "688": 0, "11338": 0, "3813": 0, "1215742": 0, "159": 0, "470": 0, "372": 0, "158": 0, "430": 0, "412": 0, "1853": 0, "109": 0, "361": 0, "530": 0, "2390": 0, "153": 0, "413": 0, "434": 0, "semeval16": [0, 6, 10], "8000": 0, "2000": 0, "889504": 0, "157": 0, "351": 0, "492": 0, "163": [0, 1], "341": 0, "497": 0, "sst": [0, 10], "2971": 0, "1271": 0, "376132": 0, "261": 0, "452": 0, "288": 0, "207": 0, "481": 0, "312": 0, "wa": [0, 3, 5, 8, 10, 11], "2184": 0, "936": 0, "248563": 0, "305": 0, "414": 0, "281": 0, "282": 0, "446": 0, "272": 0, "wb": [0, 10], "4259": 0, "1823": 0, "404333": 0, "270": 0, "392": 0, "337": 0, "274": 0, "335": 0, "32": [0, 6], "repositori": [0, 10], "p\u00e9rez": [0, 3, 10, 11], "g\u00e1llego": [0, 3, 10, 11], "p": [0, 3, 8, 9, 10, 11], "quevedo": [0, 3, 10], "j": [0, 3, 10, 11], "r": [0, 3, 8, 10], "del": [0, 3, 10], "coz": [0, 3, 10], "2017": [0, 3, 10, 11], "ensembl": [0, 6, 10, 11], "problem": [0, 3, 5, 8, 10, 11], "characteriz": [0, 3, 10], "chang": [0, 1, 3, 10], "distribut": [0, 3, 5, 8, 10, 11], "case": [0, 1, 3, 4, 5, 8, 9, 10, 11], "studi": [0, 3, 10], "fusion": [0, 3, 10], "34": [0, 3, 10, 11], "87": [0, 3, 10], "doe": [0, 2, 3, 8, 11], "exactli": 0, "coincid": [0, 6], "et": [0, 2, 9, 10, 11], "al": [0, 2, 9, 10, 11], "sinc": [0, 1, 3, 5, 10, 11], "we": [0, 1, 3, 4, 5, 6, 10], "unabl": 0, "find": [0, 4, 11], "diabet": 0, "phonem": 0, "call": [0, 1, 5, 8, 10, 11], "fetch_ucidataset": [0, 3, 10], "yeast": [0, 10], "verbos": [0, 1, 4, 8, 9, 10, 11], "return": [0, 1, 3, 4, 5, 8, 9, 10, 11], "randomli": [0, 10], "drawn": [0, 1, 4, 8, 10], "stratifi": [0, 3, 9, 10, 11], "manner": [0, 9, 11], "whole": [0, 1, 3, 4, 8, 9], "collect": [0, 8, 9, 10], "70": 0, "30": [0, 1, 3, 11], "respect": [0, 1, 5, 8, 11], "option": [0, 1, 3, 5, 10, 11], "indic": [0, 1, 3, 4, 5, 8, 9, 10, 11], "descript": [0, 10], "should": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "standard": [0, 1, 5, 8, 9, 10, 11], "paper": [0, 3, 9, 11], "submit": 0, "kfcv": [0, 9, 10, 11], "order": [0, 2, 3, 5, 8, 10, 11], "accommod": 0, "practic": [0, 4], "could": [0, 1, 3, 4, 5, 6], "first": [0, 1, 2, 3, 5, 8, 10, 11], "instanti": [0, 1, 3, 4, 8, 9, 11], "creat": [0, 6, 8, 11], "time": [0, 1, 3, 8, 10, 11], "fetch_ucilabelledcollect": [0, 10], "nfold": [0, 8, 10], "nrepeat": [0, 10], "abov": [0, 3, 5, 8], "conduct": [0, 8], "2x5fcv": 0, "all": [0, 1, 2, 3, 5, 8, 9, 11], "come": [0, 8, 10, 11], "numer": [0, 1, 3, 6, 10, 11], "form": [0, 8, 10, 11], "dens": [0, 11], "matric": [0, 5, 10], "acut": 0, "120": 0, "6": [0, 1, 3, 5, 10], "508": 0, "b": [0, 8, 10, 11], "583": 0, "417": 0, "balanc": [0, 4, 11], "625": 0, "539": 0, "461": 0, "922": 0, "078": 0, "breast": 0, "cancer": 0, "683": 0, "350": 0, "650": 0, "cmc": 0, "1473": 0, "573": 0, "427": 0, "774": 0, "226": 0, "653": 0, "347": 0, "ctg": 0, "2126": 0, "22": [0, 3, 9, 10], "222": [0, 9], "778": 0, "861": 0, "139": 0, "917": 0, "083": 0, "german": 0, "1000": [0, 4, 11], "24": [0, 9], "300": [0, 1, 9], "700": 0, "haberman": [0, 3], "306": 0, "735": 0, "265": 0, "ionospher": 0, "641": 0, "359": 0, "iri": 0, "150": 0, "667": 0, "333": 0, "mammograph": 0, "830": 0, "514": 0, "486": 0, "pageblock": 0, "5473": 0, "979": 0, "021": 0, "semeion": 0, "1593": 0, "256": [0, 9], "901": 0, "099": 0, "sonar": 0, "208": 0, "60": 0, "534": 0, "466": 0, "spambas": 0, "4601": 0, "57": 0, "606": 0, "394": 0, "spectf": 0, "267": 0, "44": 0, "794": 0, "206": 0, "tictacto": 0, "958": 0, "transfus": 0, "748": 0, "762": 0, "238": 0, "wdbc": 0, "569": 0, "627": 0, "373": 0, "wine": 0, "178": 0, "13": [0, 9], "669": 0, "331": 0, "601": 0, "399": 0, "730": 0, "q": [0, 2, 3, 8, 9, 11], "red": 0, "1599": 0, "465": 0, "535": 0, "white": 0, "4898": 0, "665": 0, "1484": 0, "8": [0, 1, 5, 10, 11], "711": 0, "289": 0, "download": [0, 2, 3, 8, 10], "automat": [0, 1], "thei": [0, 3, 11], "store": [0, 9, 10, 11], "quapy_data": [0, 8], "folder": [0, 10, 11], "faster": [0, 10], "reus": [0, 3, 8, 10], "howev": [0, 4, 5], "requir": [0, 1, 3, 6, 9], "special": [0, 5, 10], "action": 0, "moment": [0, 3], "fulli": [0, 8], "autom": [0, 3, 6], "cardiotocographi": 0, "excel": 0, "file": [0, 5, 8, 9, 10, 11], "user": [0, 1, 5], "instal": [0, 3, 6, 9, 11], "xlrd": [0, 2], "modul": [0, 1, 3, 5, 6, 7], "open": [0, 6, 10], "page": [0, 2, 6], "block": [0, 8], "need": [0, 3, 8, 10, 11], "unix": 0, "compress": 0, "extens": [0, 2, 5], "z": [0, 10], "directli": [0, 1, 3], "doabl": 0, "packag": [0, 2, 3, 6, 7], "like": [0, 1, 3, 5, 8, 9, 10, 11], "gzip": 0, "zip": [0, 5], "uncompress": 0, "o": [0, 8], "depend": [0, 1, 4, 5, 8, 11], "softwar": 0, "manual": 0, "do": [0, 1, 3, 4, 8, 9, 10, 11], "invok": [0, 1, 3, 8, 10], "provid": [0, 3, 5, 6, 10, 11], "loader": [0, 10], "simpl": [0, 3, 5, 11], "deal": 0, "t": [0, 1, 3, 8, 9, 11], "pre": [0, 3], "n": [0, 1, 8, 9, 11], "second": [0, 1, 3, 5, 8, 10], "represent": [0, 3, 8, 9, 11], "col": [0, 10], "int": [0, 5, 8, 10, 11], "float": [0, 3, 8, 9, 10, 11], "charg": [0, 10], "classmethod": [0, 8, 10, 11], "def": [0, 1, 3, 5, 8], "cl": 0, "path": [0, 3, 5, 8, 9, 10, 11], "str": [0, 8, 10, 11], "loader_func": [0, 10], "callabl": [0, 8, 10, 11], "defin": [0, 3, 8, 9, 10, 11], "argument": [0, 1, 3, 5, 8, 10, 11], "initi": [0, 9, 11], "particular": [0, 1, 3, 11], "receiv": [0, 3, 5], "addition": 0, "number": [0, 1, 3, 5, 8, 9, 10, 11], "specifi": [0, 1, 3, 5, 8, 9, 10], "otherwis": [0, 3, 8, 10], "infer": [0, 10], "least": [0, 10], "pass": [0, 1, 5, 8, 9, 11], "along": [0, 3, 8, 11], "train_path": [0, 10], "my_data": 0, "dat": [0, 9], "test_path": [0, 10], "my_custom_load": 0, "rb": 0, "fin": 0, "preprocess": [0, 1, 3, 8, 11], "includ": [0, 1, 3, 5, 6, 10, 11], "text2tfidf": [0, 1, 3, 10], "tfidf": [0, 4, 5, 10], "vector": [0, 8, 9, 10, 11], "reduce_column": [0, 10], "reduc": [0, 10], "column": [0, 10], "base": [0, 3, 6, 8, 9], "term": [0, 1, 3, 4, 5, 6, 8, 9, 10, 11], "frequenc": [0, 10, 11], "transform": [0, 9, 10, 11], "valu": [0, 1, 3, 8, 9, 10, 11], "score": [0, 1, 4, 8, 9, 10], "subtract": [0, 8, 10], "normal": [0, 1, 3, 8, 10, 11], "deviat": [0, 1, 5, 8, 10], "so": [0, 1, 3, 5, 8, 9, 10, 11], "zero": [0, 8], "unit": [0, 8], "varianc": [0, 5], "textual": [0, 6, 10], "token": [0, 9, 10], "appeal": 1, "tool": [1, 6], "scenario": [1, 3, 4, 5, 6], "dataset": [1, 3, 4, 5, 6, 8, 9, 11], "shift": [1, 4, 6, 8, 9, 11], "particularli": 1, "prior": [1, 3, 4, 5, 6, 8, 11], "probabl": [1, 3, 4, 5, 6, 8, 9, 11], "That": [1, 4], "interest": [1, 5, 6, 8], "estim": [1, 3, 5, 6, 8, 9, 10, 11], "aris": 1, "under": 1, "belief": 1, "those": [1, 3, 4, 5, 8, 9, 11], "might": [1, 8, 10], "ones": [1, 3, 5, 8, 10, 11], "observ": [1, 11], "dure": [1, 5, 11], "other": [1, 3, 5, 6, 8, 10, 11], "word": [1, 3, 6, 9, 10, 11], "simpli": [1, 2, 3, 4, 5, 6, 8, 11], "predictor": 1, "assum": [1, 6, 11], "unlik": [1, 4, 8], "machin": [1, 4, 6, 9], "learn": [1, 2, 3, 4, 6, 8, 9, 10, 11], "govern": 1, "iid": [1, 5, 6], "assumpt": [1, 5, 6], "brief": [1, 10], "dedic": [1, 10], "explain": [1, 5], "here": [1, 11], "mae": [1, 4, 6, 8, 9, 11], "absolut": [1, 3, 5, 6, 8, 11], "mrae": [1, 6, 8, 9, 11], "rel": [1, 3, 8, 10, 11], "mse": [1, 3, 6, 8, 11], "squar": [1, 3, 8], "mkld": [1, 8, 11], "kullback": [1, 3, 8, 11], "leibler": [1, 3, 8, 11], "diverg": [1, 3, 8, 11], "mnkld": [1, 8, 11], "ae": [1, 2, 5, 8, 11], "rae": [1, 2, 8, 11], "se": [1, 8], "kld": [1, 2, 8, 9, 11], "nkld": [1, 2, 6, 8, 9, 11], "individu": [1, 3], "without": [1, 3, 8, 10], "averag": [1, 3, 8, 10, 11], "acc": [1, 3, 5, 6, 8, 11], "accuraci": [1, 5, 8, 11], "f1e": [1, 8], "f1": [1, 8, 9], "true_prev": [1, 5, 8], "prevs_hat": [1, 8], "ndarrai": [1, 3, 8, 10, 11], "contain": [1, 2, 3, 5, 8, 9, 10, 11], "smooth": [1, 8], "stabil": [1, 11], "third": [1, 5], "ep": [1, 8], "none": [1, 4, 8, 9, 10, 11], "paramet": [1, 3, 4, 8, 9, 10, 11], "epsilon": [1, 8, 11], "tradition": 1, "2t": [1, 8], "past": 1, "either": [1, 3, 8, 11], "environ": [1, 3, 4, 5, 8, 11], "variabl": [1, 3, 5, 8, 10], "onc": [1, 3, 5, 8, 10], "ommit": 1, "thereaft": 1, "recommend": [1, 5, 11], "np": [1, 3, 4, 5, 8, 10, 11], "asarrai": 1, "let": [1, 3, 11], "estim_prev": [1, 5, 8], "ae_": 1, "3f": [1, 6], "200": [1, 9], "600": 1, "914": 1, "final": [1, 3, 5, 11], "possibl": [1, 3, 8, 11], "string": [1, 8, 10, 11], "error_funct": 1, "from_nam": [1, 8], "accord": [1, 3, 4, 8, 9, 10, 11], "fix": [1, 4], "cover": [1, 4, 8, 9], "full": [1, 8], "contrast": 1, "natur": [1, 8], "despit": 1, "introduc": 1, "approxim": [1, 5, 8, 9], "preserv": [1, 5, 8], "procol": 1, "equal": [1, 8, 11], "distant": [1, 8], "interv": [1, 5, 8], "n_prevpoint": [1, 4, 5, 8], "determin": [1, 4, 5, 8], "constrain": [1, 5, 8, 10], "obtain": [1, 4, 8, 9, 11], "66": [1, 11], "given": [1, 3, 4, 8, 9, 10, 11], "num_prevalence_combin": [1, 8], "21": [1, 3, 5, 8], "n_class": [1, 3, 8, 9, 10, 11], "n_repeat": [1, 8], "1771": 1, "note": [1, 3, 4, 5, 8, 10], "last": [1, 3, 5, 8, 9, 10], "typic": [1, 4, 5, 8, 9, 10, 11], "singl": [1, 3, 6, 11], "higher": [1, 5], "comput": [1, 3, 5, 8, 11], "perform": [1, 3, 4, 5, 6, 8, 9, 11], "signific": 1, "instead": [1, 3, 4, 8, 10, 11], "work": [1, 3, 4, 5, 8, 10, 11], "wai": [1, 11], "around": [1, 10], "maximum": [1, 8, 9, 11], "budg": 1, "close": [1, 10], "than": [1, 4, 5, 8, 9, 10], "budget": [1, 4], "achiev": [1, 3, 4, 5], "get_nprevpoints_approxim": [1, 8], "5000": [1, 5], "4960": 1, "cost": 1, "sometim": 1, "cumbersom": 1, "control": [1, 4, 8], "overal": 1, "experi": [1, 2, 3, 4, 5, 8], "rather": [1, 4], "By": [1, 3, 8], "avoid": [1, 8], "lead": [1, 10], "closer": 1, "surpass": 1, "script": [1, 2, 3, 6, 11], "pacc": [1, 3, 5, 8, 11], "reli": [1, 3, 8, 11], "logist": [1, 3, 9, 11], "regressor": [1, 3], "classifi": [1, 4, 5, 6, 8, 9, 11], "variou": [1, 5], "metric": [1, 3, 4, 6, 8, 11], "sklearn": [1, 3, 4, 5, 6, 9, 10, 11], "linear_model": [1, 3, 4, 6, 9], "logisticregress": [1, 3, 4, 6, 9, 11], "data": [1, 3, 4, 5, 6, 8, 9, 11], "min_df": [1, 3, 4, 5, 10, 11], "inplac": [1, 3, 10, 11], "lr": [1, 3, 9, 11], "aggreg": [1, 4, 5, 6, 8], "fit": [1, 3, 4, 5, 6, 8, 9, 10, 11], "df": 1, "artificial_sampling_report": 1, "mani": [1, 3, 4, 5, 6, 8, 11], "extract": [1, 8, 10], "categori": [1, 8], "n_repetit": [1, 4, 5], "n_job": [1, 3, 4, 8, 9, 10, 11], "parallel": [1, 3, 8, 9, 10, 11], "worker": [1, 8, 9, 10, 11], "cpu": [1, 9, 11], "random_se": [1, 8], "42": 1, "random": [1, 3, 4, 5, 8, 10], "seed": [1, 4, 8, 10], "replic": [1, 4, 8], "error_metr": [1, 4, 8], "line": [1, 3, 8], "result": [1, 2, 3, 4, 5, 6, 11], "report": 1, "panda": [1, 2], "datafram": 1, "displai": [1, 5, 8, 9], "just": [1, 3], "clearer": 1, "shown": [1, 5, 8], "convert": [1, 3, 8, 9, 10, 11], "repres": [1, 3, 5, 8, 10, 11], "decim": 1, "default": [1, 3, 8, 9, 10, 11], "pd": 1, "set_opt": 1, "expand_frame_repr": 1, "fals": [1, 3, 5, 8, 9, 10, 11], "map": [1, 9, 11], "000": 1, "000e": 1, "091": 1, "909": 1, "009": 1, "048": 1, "426e": 1, "04": 1, "837": 1, "037": 1, "114": 1, "633e": 1, "03": 1, "7": [1, 5, 8, 9, 11], "717": 1, "017": 1, "041": 1, "383e": 1, "366": 1, "634": 1, "034": 1, "070": 1, "412e": 1, "459": 1, "541": 1, "387e": 1, "565": 1, "435": 1, "035": 1, "073": 1, "535e": 1, "654": 1, "346": 1, "046": 1, "108": 1, "701e": 1, "725": 1, "275": 1, "075": 1, "235": 1, "515e": 1, "02": 1, "858": 1, "142": 1, "042": 1, "229": 1, "740e": 1, "945": 1, "055": 1, "27": [1, 3, 9], "357": 1, "219e": 1, "578": 1, "dtype": [1, 10], "float64": 1, "artificial_sampling_ev": [1, 4], "artificial_sampling_predict": [1, 5], "arrai": [1, 3, 5, 8, 9, 10, 11], "pip": 2, "older": 2, "version": [2, 8, 9, 11], "scikit": [2, 3, 4, 8, 9, 10, 11], "numpi": [2, 4, 8, 9], "scipi": [2, 10], "pytorch": [2, 11], "quanet": [2, 6, 9, 11], "svmperf": [2, 3, 8, 11], "patch": [2, 3, 9, 11], "joblib": [2, 11], "tqdm": 2, "matplotlib": [2, 8], "involv": [2, 5, 8], "you": [2, 3], "appli": [2, 3, 4, 5, 8, 9, 10, 11], "ext": 2, "compil": [2, 3], "sourc": [2, 3, 6, 9], "prepare_svmperf": [2, 3], "sh": [2, 3], "job": 2, "directori": [2, 8, 9, 10, 11], "svm_perf_quantif": [2, 3], "optim": [2, 3, 4, 8, 9, 11], "measur": [2, 3, 4, 5, 6, 8, 11], "propos": [2, 3, 11], "barranquero": [2, 3, 9, 11], "extend": [2, 3, 8, 11], "former": [2, 11], "categor": [3, 10], "belong": [3, 11], "non": [3, 11], "group": 3, "though": [3, 8], "plan": 3, "add": [3, 4, 8, 10], "more": [3, 5, 11], "futur": 3, "character": [3, 6], "fact": [3, 5], "product": [3, 10], "quantifi": [3, 4, 5, 6, 8, 10, 11], "shoud": 3, "basequantifi": [3, 8, 11], "abstract": [3, 8, 9, 10, 11], "abstractmethod": 3, "self": [3, 8, 9, 10, 11], "set_param": [3, 8, 9, 11], "get_param": [3, 8, 9, 11], "deep": [3, 8, 11], "familiar": 3, "structur": [3, 11], "inspir": 3, "reason": [3, 5, 6], "why": 3, "ha": [3, 4, 5, 8, 9, 10, 11], "adopt": [3, 4, 10], "respond": 3, "predict": [3, 4, 5, 8, 9, 11], "input": [3, 5, 8, 9, 11], "element": [3, 10, 11], "while": [3, 5, 9, 10, 11], "selector": 3, "process": [3, 4, 8], "hyperparamet": [3, 8, 11], "search": [3, 4, 6, 8, 11], "part": [3, 10], "aggregativequantifi": [3, 11], "must": [3, 10, 11], "fit_learn": 3, "classif_predict": [3, 11], "mention": 3, "befor": [3, 8, 9, 10, 11], "inde": [3, 4], "alreadi": [3, 8, 11], "preclassifi": 3, "maintain": [3, 11], "through": [3, 8], "properti": [3, 8, 9, 10, 11], "learner": [3, 4, 9, 11], "extern": 3, "probabilist": [3, 9, 11], "inherit": 3, "aggregativeprobabilisticquantifi": [3, 11], "posterior": [3, 8, 9, 11], "crisp": [3, 8, 11], "decis": [3, 8, 9, 11], "hard": [3, 9], "classif_posterior": [3, 11], "posterior_prob": [3, 11], "advantag": [3, 11], "procedur": [3, 6, 8], "veri": [3, 5], "effici": 3, "everi": [3, 8, 11], "leverag": 3, "speed": [3, 11], "up": [3, 4, 8, 9, 11], "over": [3, 4, 8], "customarili": [3, 4], "done": 3, "four": 3, "cc": [3, 5, 11], "simplest": 3, "deliv": [3, 11], "adjust": [3, 6, 8, 11], "pcc": [3, 4, 5, 11], "soft": 3, "serv": [3, 8, 10], "complet": [3, 5, 11], "equip": [3, 5], "svm": [3, 5, 6, 9, 10, 11], "linearsvc": [3, 5, 10], "pickl": [3, 8, 10, 11], "alia": [3, 8, 10, 11], "classifyandcount": [3, 11], "estim_preval": [3, 6, 11], "rate": [3, 8, 9, 11], "binari": [3, 5, 6, 8, 9, 10, 11], "init": 3, "addit": 3, "val_split": [3, 4, 9, 11], "integ": [3, 8, 9, 10, 11], "k": [3, 6, 8, 9, 10, 11], "fold": [3, 8, 10, 11], "cross": [3, 8, 9, 10, 11], "specif": [3, 4, 8], "held": [3, 4, 8, 9, 11], "out": [3, 4, 5, 8, 9, 10, 11], "postpon": 3, "constructor": 3, "prevail": 3, "overrid": 3, "illustr": [3, 4, 5], "seem": 3, "calibr": [3, 8], "calibratedclassifiercv": 3, "base_estim": 3, "cv": [3, 4], "predict_proba": [3, 9, 11], "As": [3, 4], "calibratedclassifi": 3, "except": [3, 8, 11], "rais": [3, 8, 11], "lastli": 3, "everyth": 3, "said": 3, "aboud": 3, "sld": [3, 11], "expectationmaximizationquantifi": [3, 11], "describ": [3, 8, 11], "saeren": [3, 11], "m": [3, 8, 11], "latinn": [3, 11], "decaesteck": [3, 11], "c": [3, 4, 8, 9, 10, 11], "2002": 3, "priori": 3, "14": 3, "41": 3, "attempt": [3, 11], "although": [3, 4, 5, 11], "improv": [3, 8, 9, 11], "rank": [3, 9], "almost": 3, "alwai": [3, 4, 5, 11], "among": 3, "effect": 3, "carri": [3, 10, 11], "gonz\u00e1lez": 3, "castro": 3, "v": [3, 8, 9, 11], "alaiz": 3, "rodr\u0131": 3, "guez": 3, "alegr": 3, "2013": 3, "scienc": 3, "218": 3, "146": 3, "It": [3, 4, 5, 8], "allia": 3, "hellingerdistancei": [3, 11], "mixtur": [3, 8, 11], "previou": 3, "overridden": [3, 11], "proport": [3, 4, 9, 10, 11], "taken": [3, 8, 9, 10], "itself": [3, 8, 11], "accept": 3, "elm": [3, 11], "famili": [3, 11], "target": [3, 5, 6, 8, 9, 11], "orient": [3, 6, 8, 11], "joachim": [3, 9, 11], "svmq": [3, 11], "d\u00edez": 3, "reliabl": 3, "pattern": 3, "recognit": 3, "48": 3, "591": 3, "604": 3, "svmkld": [3, 11], "multivari": [3, 9], "transact": 3, "discoveri": 3, "articl": [3, 4], "svmnkld": [3, 11], "svmae": [3, 11], "error": [3, 4, 6, 7, 9, 11], "svmrae": [3, 11], "what": 3, "nowadai": 3, "consid": [3, 5, 8, 9, 10, 11], "behav": [3, 5], "If": [3, 5, 8, 10, 11], "want": [3, 4], "custom": [3, 6, 10], "modifi": [3, 8], "assign": [3, 10], "Then": 3, "re": [3, 4, 9, 10], "thing": 3, "your": 3, "svmperf_hom": 3, "valid_loss": [3, 9, 11], "mycustomloss": 3, "28": [3, 10], "current": [3, 8, 9, 10, 11], "support": [3, 6, 9, 10, 11], "oper": 3, "trivial": 3, "strategi": [3, 4], "2016": [3, 10, 11], "sentiment": [3, 6, 10], "19": [3, 10], "onevsal": [3, 11], "know": 3, "where": [3, 5, 8, 9, 10, 11], "top": [3, 8, 11], "thu": [3, 4, 5, 8, 9, 11], "nor": 3, "castano": [3, 10], "2019": [3, 10, 11], "dynam": [3, 9, 10, 11], "task": [3, 4, 10], "45": [3, 5, 10], "15": [3, 8, 10], "polici": [3, 11], "processor": 3, "av": [3, 11], "ptr": [3, 11], "member": [3, 11], "d": [3, 11], "static": [3, 11], "red_siz": [3, 11], "pleas": 3, "check": [3, 4, 8], "offer": [3, 6], "torch": [3, 9, 11], "embed": [3, 9, 11], "lstm": [3, 9, 11], "cnn": [3, 11], "its": [3, 4, 8, 9, 11], "layer": [3, 9, 11], "neuralclassifiertrain": [3, 9, 11], "cnnnet": [3, 9, 11], "vocabulary_s": [3, 9, 10, 11], "cuda": [3, 9, 11], "supervis": [4, 6], "strongli": [4, 5], "good": [4, 5], "choic": [4, 11], "hyper": [4, 8, 9], "wherebi": 4, "chosen": [4, 8], "pick": 4, "best": [4, 8, 9, 11], "being": [4, 8, 11], "criteria": 4, "solv": [4, 11], "assess": 4, "own": 4, "right": [4, 8, 10], "impos": [4, 8], "aim": [4, 5], "appropri": 4, "configur": [4, 8], "design": 4, "long": [4, 9], "regard": 4, "next": [4, 8, 9, 10], "section": 4, "argu": 4, "alejandro": 4, "fabrizio": 4, "count": [4, 5, 6, 8, 10, 11], "arxiv": 4, "preprint": 4, "2011": 4, "02552": 4, "2020": [4, 9], "varieti": 4, "exhibit": [4, 5], "degre": 4, "model_select": [4, 7, 11], "gridsearchq": [4, 8, 11], "grid": [4, 8, 11], "explor": [4, 8], "portion": 4, "param_grid": [4, 8, 11], "logspac": [4, 11], "class_weight": [4, 11], "eval_budget": 4, "refit": [4, 8], "retrain": [4, 9], "goe": 4, "end": [4, 8, 11], "best_params_": 4, "best_model_": 4, "101": 4, "5f": 4, "system": [4, 11], "start": 4, "hyperparam": 4, "0001": [4, 11], "got": [4, 11], "24987": 4, "48135": 4, "001": [4, 9, 11], "24866": 4, "100000": 4, "43676": 4, "finish": 4, "param": [4, 8, 9, 11], "19982": 4, "develop": [4, 6], "1010": 4, "5005": 4, "54it": 4, "20342": 4, "altern": 4, "computation": 4, "costli": 4, "try": 4, "theoret": 4, "suboptim": 4, "opt": 4, "gridsearchcv": [4, 11], "10000": 4, "5379": 4, "55it": 4, "41734": 4, "wors": [4, 5, 8], "larg": 4, "between": [4, 5, 6, 8, 9, 11], "modal": 4, "turn": 4, "better": 4, "nonetheless": 4, "happen": [4, 5], "basic": [5, 11], "help": [5, 11], "analys": [5, 6], "outcom": 5, "main": 5, "method_nam": [5, 8, 11], "name": [5, 8, 9, 10, 11], "shape": [5, 8, 9, 10, 11], "correspond": [5, 10], "matrix": [5, 8, 11], "appear": 5, "occur": [5, 10], "merg": 5, "emq": [5, 11], "55": 5, "showcas": 5, "wide": 5, "variant": [5, 6, 8, 11], "linear": [5, 8, 11], "review": [5, 6, 10], "step": [5, 8], "05": [5, 8, 11], "gen_data": 5, "base_classifi": 5, "yield": [5, 8, 10, 11], "tr_prev": [5, 8, 11], "append": 5, "__class__": 5, "__name__": 5, "insight": 5, "view": 5, "y": [5, 8, 9, 10, 11], "axi": [5, 8], "against": 5, "x": [5, 8, 9, 10, 11], "unfortun": 5, "limit": [5, 8, 11], "binary_diagon": [5, 8], "train_prev": [5, 8], "savepath": [5, 8], "bin_diag": 5, "png": 5, "save": [5, 8], "pdf": [5, 11], "cyan": 5, "dot": [5, 8], "color": [5, 8], "band": [5, 8], "hidden": [5, 9, 11], "show_std": [5, 8], "unadjust": 5, "bias": 5, "toward": [5, 10], "seen": [5, 8, 11], "evinc": 5, "box": [5, 8], "binary_bias_glob": [5, 8], "bin_bia": 5, "unbias": 5, "center": 5, "tend": 5, "overestim": 5, "high": [5, 8], "lower": [5, 11], "again": 5, "accordingli": 5, "20": [5, 8, 11], "90": [5, 8], "rewrit": 5, "method_data": 5, "training_preval": 5, "linspac": 5, "training_s": 5, "suffic": 5, "latex": 5, "syntax": 5, "_": [5, 8, 10], "now": 5, "clearli": 5, "binary_bias_bin": [5, 8], "broken": [5, 8], "down": [5, 8, 10], "bin": [5, 8, 11], "To": [5, 10], "nbin": [5, 8, 11], "isometr": [5, 8], "subinterv": 5, "interestingli": 5, "enough": 5, "seemingli": 5, "tendenc": 5, "low": [5, 8, 9], "underestim": 5, "beyond": 5, "67": [5, 8], "curios": 5, "pretti": 5, "discuss": 5, "analyz": 5, "compar": [5, 8], "both": [5, 10], "irrespect": [5, 11], "harder": 5, "interpret": [5, 6, 11], "error_by_drift": [5, 8], "error_nam": [5, 8], "n_bin": [5, 8, 11], "err_drift": 5, "whenev": [5, 8], "clear": 5, "lowest": 5, "difficult": 5, "rememb": 5, "solid": 5, "comparison": 5, "detriment": 5, "visual": [5, 6], "hide": 5, "framework": [6, 11], "written": 6, "root": 6, "concept": 6, "baselin": 6, "integr": 6, "commonli": 6, "facilit": 6, "twitter": [6, 10], "true_preval": 6, "hold": [6, 8, 11], "endeavour": [6, 8], "popular": 6, "expect": [6, 11], "maxim": [6, 11], "hdy": [6, 11], "versatil": 6, "etc": 6, "uci": [6, 10], "nativ": 6, "loss": [6, 9, 11], "perf": [6, 9, 11], "ad": 6, "meta": [6, 8], "plot": [6, 7], "diagon": [6, 8], "bia": [6, 8, 9, 11], "drift": 6, "api": 6, "subpackag": 7, "submodul": 7, "util": [7, 9, 10], "content": 7, "bctscalibr": 9, "nbvscalibr": 9, "recalibratedprobabilisticclassifi": 9, "recalibratedprobabilisticclassifierbas": 9, "classes_": [9, 10, 11], "fit_cv": 9, "fit_tr_val": 9, "tscalibr": 9, "vscalibr": 9, "lowranklogisticregress": 9, "document_embed": 9, "lstmnet": 9, "reset_net_param": 9, "textclassifiernet": 9, "dimens": [8, 9, 10, 11], "forward": [9, 11], "xavier_uniform": 9, "torchdataset": 9, "asdataload": 9, "decision_funct": 9, "splitstratifi": 10, "stat": 10, "train_test": 10, "xp": 10, "xy": 10, "split_random": 10, "split_stratifi": 10, "uniform_sampl": 10, "uniform_sampling_index": 10, "fetch_lequa2022": 10, "warn": 10, "indextransform": 10, "add_word": 10, "fit_transform": 10, "reader": 8, "binar": [8, 10], "from_csv": 10, "from_spars": 10, "from_text": 10, "reindex_label": 10, "getptecondestim": 11, "solve_adjust": 11, "adjustedclassifyandcount": 11, "distributionmatch": 11, "dy": 11, "em": 11, "max_it": 11, "explicitlossminimis": 11, "max": 11, "ms2": 11, "mediansweep": 11, "mediansweep2": 11, "probabilisticadjustedclassifyandcount": 11, "probabilisticclassifyandcount": 11, "smm": 11, "t50": 11, "thresholdoptim": 11, "cross_generate_predict": 11, "cross_generate_predictions_depr": 11, "binaryquantifi": 11, "onevsallgener": 11, "eacc": 11, "ecc": 11, "eemq": 11, "ehdi": 11, "epacc": 11, "valid_polici": 11, "ensemblefactori": 11, "get_probability_distribut": 11, "quanetmodul": 11, "quanettrain": 11, "clean_checkpoint": 11, "clean_checkpoint_dir": 11, "mae_loss": 11, "non_aggreg": 8, "maximumlikelihoodprevalenceestim": 11, "absolute_error": 8, "hat": 8, "frac": 8, "mathcal": 8, "sum_": 8, "acc_error": 8, "y_true": 8, "y_pred": 8, "tp": 8, "tn": 8, "fp": 8, "fn": 8, "stand": [8, 11], "f1_error": 8, "macro": 8, "f_1": 8, "harmon": 8, "recal": 8, "2tp": 8, "independ": [8, 11], "err_nam": 8, "p_hat": 8, "d_": 8, "kl": 8, "log": [8, 10], "factor": 8, "beforehand": 8, "n_sampl": [8, 9], "mean_absolute_error": 8, "mean_relative_absolute_error": 8, "relative_absolute_error": 8, "underlin": 8, "displaystyl": 8, "abstractprotocol": 8, "union": [8, 10, 11], "aggr_speedup": 8, "auto": 8, "evaluation_report": 8, "app": [8, 11], "repeat": 8, "smooth_limits_epsilon": 8, "random_st": [8, 10], "return_typ": 8, "sample_prev": 8, "abstractstochasticseededprotocol": 8, "onlabelledcollectionprotocol": 8, "95": 8, "copi": [8, 10], "quantiti": 8, "labelled_collect": 8, "prevalence_grid": 8, "exhaust": 8, "sum": [8, 11], "implicit": 8, "return_constrained_dim": 8, "rest": [8, 9, 10, 11], "quit": 8, "obvious": 8, "determinist": 8, "anywher": 8, "multipli": 8, "necessari": 8, "samples_paramet": 8, "total": 8, "parent": 8, "sequenc": 8, "enforc": 8, "collat": 8, "arg": [8, 10], "domainmix": 8, "domaina": 8, "domainb": 8, "mixture_point": 8, "domain": 8, "scale": [8, 9, 11], "npp": 8, "draw": 8, "uniformli": 8, "therefor": 8, "get_col": 8, "get_labelled_collect": 8, "on_preclassified_inst": 8, "pre_classif": 8, "in_plac": 8, "usimplexpp": 8, "kraemer": 8, "algorithm": [8, 11], "sens": 8, "guarante": [8, 10], "prefer": 8, "intract": 8, "hellingerdist": 8, "hellingh": 8, "distanc": [8, 11], "hd": [8, 11], "discret": [8, 11], "sqrt": 8, "p_i": 8, "q_i": 8, "real": [8, 9, 10, 11], "topsoedist": 8, "1e": [8, 9, 11], "topso": [8, 11], "adjusted_quantif": 8, "prevalence_estim": 8, "tpr": [8, 11], "fpr": [8, 11], "clip": 8, "exce": 8, "check_prevalence_vector": 8, "raise_except": 8, "toleranz": 8, "08": 8, "combinations_budget": 8, "largest": 8, "dimension": [8, 9, 10, 11], "repetit": 8, "less": [8, 10], "normalize_preval": 8, "l1": [8, 11], "calcul": 8, "binom": 8, "mass": 8, "alloc": [8, 9], "solut": 8, "star": 8, "bar": 8, "prevalence_from_label": 8, "n_instanc": [8, 9, 11], "correctli": 8, "even": 8, "len": 8, "prevalence_from_prob": 8, "bool": [8, 9, 11], "argmax": 8, "prevalence_linspac": 8, "01": [8, 9, 11], "separ": [8, 10], "99": 8, "uniform_prevalence_sampl": 8, "adapt": [8, 9], "post": 8, "http": [8, 10, 11], "stackexchang": 8, "com": 8, "question": 8, "3227": 8, "uniform": [8, 10], "uniform_simplex_sampl": 8, "dict": [8, 10, 11], "timeout": 8, "dictionari": [8, 9, 10, 11], "kei": [8, 10], "quantification_error": 8, "whether": [8, 9, 10, 11], "ignor": [8, 10, 11], "gen": 8, "establish": 8, "timer": 8, "longer": [8, 11], "timeouterror": 8, "bound": [8, 11], "stdout": 8, "best_model": 8, "after": [8, 11], "minim": [8, 11], "routin": [8, 10, 11], "unus": [8, 9], "contanin": 8, "cross_val_predict": 8, "akin": [8, 11], "issu": 8, "reproduc": [8, 10], "pos_class": [8, 10], "titl": 8, "colormap": 8, "listedcolormap": 8, "vertical_xtick": 8, "legend": 8, "local": 8, "sign": 8, "minu": 8, "classs": 8, "compon": [8, 9, 11], "cm": 8, "tab10": 8, "secondari": 8, "global": 8, "method_ord": 8, "henc": [8, 10], "conveni": 8, "multiclass": [8, 10, 11], "inconveni": 8, "leyend": 8, "hightlight": 8, "associ": 8, "brokenbar_supremacy_by_drift": 8, "isomer": 8, "x_error": 8, "y_error": 8, "ttest_alpha": 8, "005": 8, "tail_density_threshold": 8, "region": 8, "chart": 8, "condit": [8, 11], "ii": 8, "significantli": 8, "side": 8, "confid": 8, "percentil": 8, "divid": 8, "amount": 8, "similar": [8, 11], "threshold": [8, 11], "densiti": 8, "tail": 8, "discard": 8, "outlier": 8, "show_dens": 8, "show_legend": 8, "logscal": 8, "vline": 8, "especi": 8, "mai": 8, "cumberson": 8, "gain": 8, "understand": 8, "fare": 8, "regim": 8, "highlight": 8, "vertic": 8, "earlystop": 8, "patienc": [8, 9, 11], "lower_is_bett": 8, "earli": [8, 9, 11], "stop": [8, 9, 11], "epoch": [8, 9, 11], "best_epoch": 8, "best_scor": 8, "consecut": [8, 9, 11], "monitor": 8, "obtaind": 8, "far": [8, 9, 10], "flag": 8, "keep": 8, "track": 8, "boolean": [8, 10, 11], "create_if_not_exist": 8, "makedir": 8, "exist_ok": 8, "join": 8, "dir": [8, 11], "subdir": 8, "anotherdir": 8, "create_parent_dir": 8, "exist": 8, "txt": 8, "download_fil": 8, "url": 8, "archive_filenam": 8, "destin": 8, "filenam": 8, "download_file_if_not_exist": 8, "dowload": 8, "get_quapy_hom": 8, "home": [8, 10], "perman": 8, "map_parallel": 8, "func": 8, "slice": 8, "item": 8, "wrapper": [8, 9, 10, 11], "multiprocess": [8, 11], "delai": 8, "args_i": 8, "silent": [8, 11], "child": 8, "ensur": 8, "pickled_resourc": 8, "pickle_path": 8, "generation_func": 8, "fast": [8, 10], "resourc": 8, "some_arrai": 8, "mock": [8, 9], "rand": 8, "my_arrai": 8, "pkl": 8, "save_text_fil": 8, "disk": 8, "miss": 8, "temp_se": 8, "context": 8, "tempor": 8, "outer": 8, "state": 8, "within": [8, 11], "get_njob": [], "correct": [9, 11], "temperatur": [9, 11], "bct": [9, 11], "abstent": 9, "alexandari": [9, 11], "afterward": [9, 11], "No": [9, 11], "nbv": [9, 11], "baseestim": [9, 11], "calibratorfactori": 9, "n_compon": 9, "kwarg": [9, 10, 11], "decomposit": 9, "truncatedsvd": 9, "princip": 9, "regress": 9, "n_featur": 9, "length": [9, 10], "eventu": [9, 10], "unalt": 9, "emb": 9, "embedding_s": 9, "hidden_s": 9, "repr_siz": 9, "kernel_height": 9, "stride": 9, "pad": [9, 10], "drop_p": 9, "convolut": 9, "vocabulari": [9, 10], "kernel": 9, "drop": 9, "dropout": [9, 11], "batch": 9, "dataload": 9, "tensor": 9, "n_dimens": 9, "lstm_class_nlay": 9, "short": 9, "memori": 9, "net": 9, "weight_decai": 9, "batch_siz": 9, "64": [9, 11], "batch_size_test": 9, "512": [9, 11], "padding_length": 9, "checkpointpath": 9, "checkpoint": [9, 11], "classifier_net": 9, "weight": [9, 10], "decai": 9, "wait": 9, "enabl": 9, "gpu": [9, 11], "vocab_s": 9, "reiniti": 9, "trainer": 9, "disjoint": 9, "embed_s": 9, "nn": 9, "pad_length": 9, "xavier": 9, "shuffl": [9, 10], "longest": 9, "shorter": 9, "svmperf_bas": [9, 11], "classifiermixin": 9, "thorsten": 9, "refer": [9, 10], "svm_perf_learn": 9, "svm_perf_classifi": 9, "trade": 9, "off": 9, "margin": 9, "std": 9, "qacc": 9, "qf1": 9, "qgm": 9, "12": 9, "26": 9, "23": 9, "train_siz": 10, "conform": 10, "round": 10, "loader_kwarg": 10, "read": 10, "tupl": [10, 11], "tr": 10, "te": 10, "csr": 10, "csr_matrix": 10, "4403": 10, "my_collect": 10, "codefram": 10, "larger": [10, 11], "actual": [10, 11], "empti": 10, "met": 10, "whose": [10, 11], "train_prop": 10, "left": [8, 10], "stratif": 10, "greater": 10, "dataset_nam": 10, "data_hom": 10, "test_split": 10, "predefin": 10, "uci_dataset": 10, "dump": 10, "leav": 10, "quay_data": 10, "ml": 10, "5fcvx2": 10, "x2": 10, "offici": 10, "lequa": 10, "competit": 10, "t1a": 10, "t1b": 10, "t2a": 10, "t2b": 10, "raw": 10, "merchandis": 10, "sperduti": 10, "2022": 10, "overview": 10, "clef": 10, "lequa2022_experi": 10, "py": 10, "guid": 10, "val_gen": 10, "test_gen": 10, "samplesfromdir": 10, "minimun": 10, "kept": 10, "subsequ": 10, "mining6": 10, "devel": 10, "style": 10, "countvector": 10, "keyword": [10, 11], "nogap": 10, "regardless": 10, "codifi": 10, "unknown": 10, "surfac": 10, "assert": 10, "gap": 10, "preced": 10, "decid": 10, "uniqu": 10, "rare": 10, "unk": 10, "minimum": [10, 11], "occurr": 10, "org": [10, 11], "stabl": 10, "feature_extract": 10, "html": 10, "subtyp": 10, "spmatrix": 10, "remov": [10, 11], "infrequ": 10, "aka": [10, 11], "sublinear_tf": 10, "scall": 10, "counter": 10, "tfidfvector": 10, "whcih": 10, "had": 10, "encod": 10, "utf": 10, "csv": 10, "feat1": 10, "feat2": 10, "featn": 10, "covari": 10, "express": 10, "row": 10, "class2int": 10, "collet": 10, "fomart": 10, "progress": 10, "sentenc": 10, "classnam": 10, "u1": 10, "misclassif": 11, "n_classes_": [], "fit_classifi": 11, "bypass": 11, "y_": 11, "ptecondestim": 11, "prevs_estim": 11, "ax": 11, "entri": 11, "y_i": 11, "y_j": 11, "_posterior_probabilities_": 11, "attribut": 11, "subclass": 11, "give": 11, "outsid": 11, "unless": 11, "noth": 11, "els": 11, "cdf": 11, "match": 11, "helling": 11, "sought": 11, "channel": 11, "proper": 11, "ch": 11, "di": 11, "dij": 11, "fraction": 11, "th": 11, "tol": 11, "ternari": 11, "dl": 11, "doi": 11, "1145": 11, "3219819": 11, "3220059": 11, "histogram": 11, "toler": 11, "explicit": 11, "exact_train_prev": 11, "recalib": 11, "updat": 11, "likelihood": [9, 11], "mutual": 11, "recurs": 11, "until": 11, "converg": 11, "suggest": 11, "recalibr": 11, "reach": 11, "loop": 11, "cumul": 11, "unlabel": 11, "latter": 11, "forman": 11, "2006": 11, "2008": 11, "goal": 11, "bring": 11, "denomin": 11, "median": 11, "sweep": 11, "binary_quantifi": 11, "prevel": 11, "emploi": 11, "resp": 11, "subobject": 11, "nest": 11, "pipelin": 11, "__": 11, "simplif": 11, "2021": 11, "equival": 11, "cosest": 11, "heurist": 11, "choos": 11, "ground": 11, "complement": 11, "param_mod_sel": 11, "param_model_sel": 11, "min_po": 11, "max_sample_s": 11, "closest": 11, "preliminari": 11, "recomput": 11, "compat": 11, "l": 11, "base_quantifier_class": 11, "factori": 11, "common": 11, "doc_embedding_s": 11, "stats_siz": 11, "lstm_hidden_s": 11, "lstm_nlayer": 11, "ff_layer": 11, "1024": 11, "bidirect": 11, "qdrop_p": 11, "order_bi": 11, "cell": 11, "connect": 11, "ff": 11, "sort": 11, "doc_embed": 11, "doc_posterior": 11, "recip": 11, "care": 11, "regist": 11, "hook": 11, "n_epoch": 11, "tr_iter_per_poch": 11, "va_iter_per_poch": 11, "checkpointdir": 11, "checkpointnam": 11, "phase": 11, "anyth": 11, "truth": 11, "mlpe": 11, "lazi": 11, "put": 11, "assumpion": 11, "beat": [9, 11], "estimant": 11, "kundaj": 9, "shrikumar": 9, "novemb": 9, "232": 9, "pmlr": 9, "outpu": [], "partit": 9, "ight": [], "valueerror": 8, "attach": 10, "mix": 10, "onevsallaggreg": 11, "parallel_backend": 11, "loki": 11, "backend": 11, "cannot": 11, "temp": 11, "getonevsal": 11}, "objects": {"": [[8, 0, 0, "-", "quapy"]], "quapy": [[9, 0, 0, "-", "classification"], [10, 0, 0, "-", "data"], [8, 0, 0, "-", "error"], [8, 0, 0, "-", "evaluation"], [8, 0, 0, "-", "functional"], [11, 0, 0, "-", "method"], [8, 0, 0, "-", "model_selection"], [8, 0, 0, "-", "plot"], [8, 0, 0, "-", "protocol"], [8, 0, 0, "-", "util"]], "quapy.classification": [[9, 0, 0, "-", "calibration"], [9, 0, 0, "-", "methods"], [9, 0, 0, "-", "neural"], [9, 0, 0, "-", "svmperf"]], "quapy.classification.calibration": [[9, 1, 1, "", "BCTSCalibration"], [9, 1, 1, "", "NBVSCalibration"], [9, 1, 1, "", "RecalibratedProbabilisticClassifier"], [9, 1, 1, "", "RecalibratedProbabilisticClassifierBase"], [9, 1, 1, "", "TSCalibration"], [9, 1, 1, "", "VSCalibration"]], "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase": [[9, 2, 1, "", "classes_"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "fit_cv"], [9, 3, 1, "", "fit_tr_val"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"]], "quapy.classification.methods": [[9, 1, 1, "", "LowRankLogisticRegression"]], "quapy.classification.methods.LowRankLogisticRegression": [[9, 3, 1, "", "fit"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"], [9, 3, 1, "", "set_params"], [9, 3, 1, "", "transform"]], "quapy.classification.neural": [[9, 1, 1, "", "CNNnet"], [9, 1, 1, "", "LSTMnet"], [9, 1, 1, "", "NeuralClassifierTrainer"], [9, 1, 1, "", "TextClassifierNet"], [9, 1, 1, "", "TorchDataset"]], "quapy.classification.neural.CNNnet": [[9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "get_params"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"]], "quapy.classification.neural.LSTMnet": [[9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "get_params"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"]], "quapy.classification.neural.NeuralClassifierTrainer": [[9, 2, 1, "", "device"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "predict_proba"], [9, 3, 1, "", "reset_net_params"], [9, 3, 1, "", "set_params"], [9, 3, 1, "", "transform"]], "quapy.classification.neural.TextClassifierNet": [[9, 3, 1, "", "dimensions"], [9, 3, 1, "", "document_embedding"], [9, 3, 1, "", "forward"], [9, 3, 1, "", "get_params"], [9, 3, 1, "", "predict_proba"], [9, 4, 1, "", "training"], [9, 2, 1, "", "vocabulary_size"], [9, 3, 1, "", "xavier_uniform"]], "quapy.classification.neural.TorchDataset": [[9, 3, 1, "", "asDataloader"]], "quapy.classification.svmperf": [[9, 1, 1, "", "SVMperf"]], "quapy.classification.svmperf.SVMperf": [[9, 3, 1, "", "decision_function"], [9, 3, 1, "", "fit"], [9, 3, 1, "", "predict"], [9, 3, 1, "", "set_params"], [9, 4, 1, "", "valid_losses"]], "quapy.data": [[10, 0, 0, "-", "base"], [10, 0, 0, "-", "datasets"], [10, 0, 0, "-", "preprocessing"], [10, 0, 0, "-", "reader"]], "quapy.data.base": [[10, 1, 1, "", "Dataset"], [10, 1, 1, "", "LabelledCollection"]], "quapy.data.base.Dataset": [[10, 3, 1, "", "SplitStratified"], [10, 2, 1, "", "binary"], [10, 2, 1, "", "classes_"], [10, 3, 1, "", "kFCV"], [10, 3, 1, "", "load"], [10, 2, 1, "", "n_classes"], [10, 3, 1, "", "stats"], [10, 2, 1, "", "train_test"], [10, 2, 1, "", "vocabulary_size"]], "quapy.data.base.LabelledCollection": [[10, 2, 1, "", "X"], [10, 2, 1, "", "Xp"], [10, 2, 1, "", "Xy"], [10, 2, 1, "", "binary"], [10, 3, 1, "", "counts"], [10, 3, 1, "", "kFCV"], [10, 3, 1, "", "load"], [10, 3, 1, "", "mix"], [10, 2, 1, "", "n_classes"], [10, 2, 1, "", "p"], [10, 3, 1, "", "prevalence"], [10, 3, 1, "", "sampling"], [10, 3, 1, "", "sampling_from_index"], [10, 3, 1, "", "sampling_index"], [10, 3, 1, "", "split_random"], [10, 3, 1, "", "split_stratified"], [10, 3, 1, "", "stats"], [10, 3, 1, "", "uniform_sampling"], [10, 3, 1, "", "uniform_sampling_index"], [10, 2, 1, "", "y"]], "quapy.data.datasets": [[10, 5, 1, "", "fetch_UCIDataset"], [10, 5, 1, "", "fetch_UCILabelledCollection"], [10, 5, 1, "", "fetch_lequa2022"], [10, 5, 1, "", "fetch_reviews"], [10, 5, 1, "", "fetch_twitter"], [10, 5, 1, "", "warn"]], "quapy.data.preprocessing": [[10, 1, 1, "", "IndexTransformer"], [10, 5, 1, "", "index"], [10, 5, 1, "", "reduce_columns"], [10, 5, 1, "", "standardize"], [10, 5, 1, "", "text2tfidf"]], "quapy.data.preprocessing.IndexTransformer": [[10, 3, 1, "", "add_word"], [10, 3, 1, "", "fit"], [10, 3, 1, "", "fit_transform"], [10, 3, 1, "", "transform"], [10, 3, 1, "", "vocabulary_size"]], "quapy.data.reader": [[10, 5, 1, "", "binarize"], [10, 5, 1, "", "from_csv"], [10, 5, 1, "", "from_sparse"], [10, 5, 1, "", "from_text"], [10, 5, 1, "", "reindex_labels"]], "quapy.error": [[8, 5, 1, "", "absolute_error"], [8, 5, 1, "", "acc_error"], [8, 5, 1, "", "acce"], [8, 5, 1, "", "ae"], [8, 5, 1, "", "f1_error"], [8, 5, 1, "", "f1e"], [8, 5, 1, "", "from_name"], [8, 5, 1, "", "kld"], [8, 5, 1, "", "mae"], [8, 5, 1, "", "mean_absolute_error"], [8, 5, 1, "", "mean_relative_absolute_error"], [8, 5, 1, "", "mkld"], [8, 5, 1, "", "mnkld"], [8, 5, 1, "", "mrae"], [8, 5, 1, "", "mse"], [8, 5, 1, "", "nkld"], [8, 5, 1, "", "rae"], [8, 5, 1, "", "relative_absolute_error"], [8, 5, 1, "", "se"], [8, 5, 1, "", "smooth"]], "quapy.evaluation": [[8, 5, 1, "", "evaluate"], [8, 5, 1, "", "evaluation_report"], [8, 5, 1, "", "prediction"]], "quapy.functional": [[8, 5, 1, "", "HellingerDistance"], [8, 5, 1, "", "TopsoeDistance"], [8, 5, 1, "", "adjusted_quantification"], [8, 5, 1, "", "check_prevalence_vector"], [8, 5, 1, "", "get_nprevpoints_approximation"], [8, 5, 1, "", "normalize_prevalence"], [8, 5, 1, "", "num_prevalence_combinations"], [8, 5, 1, "", "prevalence_from_labels"], [8, 5, 1, "", "prevalence_from_probabilities"], [8, 5, 1, "", "prevalence_linspace"], [8, 5, 1, "", "strprev"], [8, 5, 1, "", "uniform_prevalence_sampling"], [8, 5, 1, "", "uniform_simplex_sampling"]], "quapy.method": [[11, 0, 0, "-", "aggregative"], [11, 0, 0, "-", "base"], [11, 0, 0, "-", "meta"], [11, 0, 0, "-", "neural"], [11, 0, 0, "-", "non_aggregative"]], "quapy.method.aggregative": [[11, 1, 1, "", "ACC"], [11, 4, 1, "", "AdjustedClassifyAndCount"], [11, 1, 1, "", "AggregativeProbabilisticQuantifier"], [11, 1, 1, "", "AggregativeQuantifier"], [11, 1, 1, "", "CC"], [11, 4, 1, "", "ClassifyAndCount"], [11, 1, 1, "", "DistributionMatching"], [11, 1, 1, "", "DyS"], [11, 1, 1, "", "ELM"], [11, 1, 1, "", "EMQ"], [11, 4, 1, "", "ExpectationMaximizationQuantifier"], [11, 4, 1, "", "ExplicitLossMinimisation"], [11, 1, 1, "", "HDy"], [11, 4, 1, "", "HellingerDistanceY"], [11, 1, 1, "", "MAX"], [11, 1, 1, "", "MS"], [11, 1, 1, "", "MS2"], [11, 4, 1, "", "MedianSweep"], [11, 4, 1, "", "MedianSweep2"], [11, 1, 1, "", "OneVsAllAggregative"], [11, 1, 1, "", "PACC"], [11, 1, 1, "", "PCC"], [11, 4, 1, "", "ProbabilisticAdjustedClassifyAndCount"], [11, 4, 1, "", "ProbabilisticClassifyAndCount"], [11, 4, 1, "", "SLD"], [11, 1, 1, "", "SMM"], [11, 1, 1, "", "SVMAE"], [11, 1, 1, "", "SVMKLD"], [11, 1, 1, "", "SVMNKLD"], [11, 1, 1, "", "SVMQ"], [11, 1, 1, "", "SVMRAE"], [11, 1, 1, "", "T50"], [11, 1, 1, "", "ThresholdOptimization"], [11, 1, 1, "", "X"], [11, 5, 1, "", "cross_generate_predictions"], [11, 5, 1, "", "cross_generate_predictions_depr"]], "quapy.method.aggregative.ACC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "getPteCondEstim"], [11, 3, 1, "", "solve_adjustment"]], "quapy.method.aggregative.AggregativeProbabilisticQuantifier": [[11, 3, 1, "", "classify"]], "quapy.method.aggregative.AggregativeQuantifier": [[11, 3, 1, "", "aggregate"], [11, 2, 1, "", "classes_"], [11, 2, 1, "", "classifier"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.method.aggregative.CC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.DistributionMatching": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.DyS": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.ELM": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.EMQ": [[11, 3, 1, "", "EM"], [11, 4, 1, "", "EPSILON"], [11, 4, 1, "", "MAX_ITER"], [11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "predict_proba"]], "quapy.method.aggregative.HDy": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.OneVsAllAggregative": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"]], "quapy.method.aggregative.PACC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "classify"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "getPteCondEstim"]], "quapy.method.aggregative.PCC": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.SMM": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.aggregative.ThresholdOptimization": [[11, 3, 1, "", "aggregate"], [11, 3, 1, "", "fit"]], "quapy.method.base": [[11, 1, 1, "", "BaseQuantifier"], [11, 1, 1, "", "BinaryQuantifier"], [11, 1, 1, "", "OneVsAll"], [11, 1, 1, "", "OneVsAllGeneric"], [11, 5, 1, "", "getOneVsAll"]], "quapy.method.base.BaseQuantifier": [[11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.method.base.OneVsAllGeneric": [[11, 2, 1, "", "classes_"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.method.meta": [[11, 5, 1, "", "EACC"], [11, 5, 1, "", "ECC"], [11, 5, 1, "", "EEMQ"], [11, 5, 1, "", "EHDy"], [11, 5, 1, "", "EPACC"], [11, 1, 1, "", "Ensemble"], [11, 5, 1, "", "ensembleFactory"], [11, 5, 1, "", "get_probability_distribution"]], "quapy.method.meta.Ensemble": [[11, 4, 1, "", "VALID_POLICIES"], [11, 2, 1, "", "aggregative"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 2, 1, "", "probabilistic"], [11, 3, 1, "", "quantify"], [11, 3, 1, "", "set_params"]], "quapy.method.neural": [[11, 1, 1, "", "QuaNetModule"], [11, 1, 1, "", "QuaNetTrainer"], [11, 5, 1, "", "mae_loss"]], "quapy.method.neural.QuaNetModule": [[11, 2, 1, "", "device"], [11, 3, 1, "", "forward"], [11, 4, 1, "", "training"]], "quapy.method.neural.QuaNetTrainer": [[11, 2, 1, "", "classes_"], [11, 3, 1, "", "clean_checkpoint"], [11, 3, 1, "", "clean_checkpoint_dir"], [11, 3, 1, "", "fit"], [11, 3, 1, "", "get_params"], [11, 3, 1, "", "quantify"], [11, 3, 1, "", "set_params"]], "quapy.method.non_aggregative": [[11, 1, 1, "", "MaximumLikelihoodPrevalenceEstimation"]], "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation": [[11, 3, 1, "", "fit"], [11, 3, 1, "", "quantify"]], "quapy.model_selection": [[8, 1, 1, "", "GridSearchQ"], [8, 5, 1, "", "cross_val_predict"]], "quapy.model_selection.GridSearchQ": [[8, 3, 1, "", "best_model"], [8, 3, 1, "", "fit"], [8, 3, 1, "", "get_params"], [8, 3, 1, "", "quantify"], [8, 3, 1, "", "set_params"]], "quapy.plot": [[8, 5, 1, "", "binary_bias_bins"], [8, 5, 1, "", "binary_bias_global"], [8, 5, 1, "", "binary_diagonal"], [8, 5, 1, "", "brokenbar_supremacy_by_drift"], [8, 5, 1, "", "error_by_drift"]], "quapy.protocol": [[8, 1, 1, "", "APP"], [8, 1, 1, "", "AbstractProtocol"], [8, 1, 1, "", "AbstractStochasticSeededProtocol"], [8, 1, 1, "", "DomainMixer"], [8, 1, 1, "", "NPP"], [8, 1, 1, "", "OnLabelledCollectionProtocol"], [8, 1, 1, "", "USimplexPP"]], "quapy.protocol.APP": [[8, 3, 1, "", "prevalence_grid"], [8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.AbstractProtocol": [[8, 3, 1, "", "total"]], "quapy.protocol.AbstractStochasticSeededProtocol": [[8, 3, 1, "", "collator"], [8, 2, 1, "", "random_state"], [8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"]], "quapy.protocol.DomainMixer": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.NPP": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.protocol.OnLabelledCollectionProtocol": [[8, 4, 1, "", "RETURN_TYPES"], [8, 3, 1, "", "get_collator"], [8, 3, 1, "", "get_labelled_collection"], [8, 3, 1, "", "on_preclassified_instances"]], "quapy.protocol.USimplexPP": [[8, 3, 1, "", "sample"], [8, 3, 1, "", "samples_parameters"], [8, 3, 1, "", "total"]], "quapy.util": [[8, 1, 1, "", "EarlyStop"], [8, 5, 1, "", "create_if_not_exist"], [8, 5, 1, "", "create_parent_dir"], [8, 5, 1, "", "download_file"], [8, 5, 1, "", "download_file_if_not_exists"], [8, 5, 1, "", "get_quapy_home"], [8, 5, 1, "", "map_parallel"], [8, 5, 1, "", "parallel"], [8, 5, 1, "", "pickled_resource"], [8, 5, 1, "", "save_text_file"], [8, 5, 1, "", "temp_seed"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:property", "3": "py:method", "4": "py:attribute", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "property", "Python property"], "3": ["py", "method", "Python method"], "4": ["py", "attribute", "Python attribute"], "5": ["py", "function", "Python function"]}, "titleterms": {"dataset": [0, 10], "review": 0, "twitter": 0, "sentiment": 0, "uci": 0, "machin": 0, "learn": 0, "issu": 0, "ad": 0, "custom": 0, "data": [0, 10], "process": 0, "evalu": [1, 8], "error": [1, 5, 8], "measur": 1, "protocol": [1, 8], "instal": 2, "requir": 2, "svm": 2, "perf": 2, "quantif": [2, 3, 4, 5], "orient": [2, 4], "loss": [2, 3, 4], "method": [3, 9, 11], "aggreg": [3, 11], "The": 3, "classifi": 3, "count": 3, "variant": 3, "expect": 3, "maxim": 3, "emq": 3, "helling": 3, "distanc": 3, "y": 3, "hdy": 3, "explicit": 3, "minim": 3, "meta": [3, 11], "model": [3, 4], "ensembl": 3, "quanet": 3, "neural": [3, 9, 11], "network": 3, "select": 4, "target": 4, "classif": [4, 9], "plot": [5, 8], "diagon": 5, "bia": 5, "drift": 5, "welcom": 6, "quapi": [6, 7, 8, 9, 10, 11], "": 6, "document": 6, "introduct": 6, "A": 6, "quick": 6, "exampl": 6, "featur": 6, "content": [6, 8, 9, 10, 11], "indic": 6, "tabl": 6, "packag": [8, 9, 10, 11], "subpackag": 8, "submodul": [8, 9, 10, 11], "function": 8, "model_select": 8, "util": 8, "modul": [8, 9, 10, 11], "calibr": 9, "svmperf": 9, "base": [10, 11], "preprocess": 10, "reader": 10, "non_aggreg": 11}, "envversion": {"sphinx.domains.c": 2, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 8, "sphinx.domains.index": 1, "sphinx.domains.javascript": 2, "sphinx.domains.math": 2, "sphinx.domains.python": 3, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx": 57}, "alltitles": {"Datasets": [[0, "datasets"]], "Reviews Datasets": [[0, "reviews-datasets"]], "Twitter Sentiment Datasets": [[0, "twitter-sentiment-datasets"]], "UCI Machine Learning": [[0, "uci-machine-learning"]], "Issues:": [[0, "issues"]], "Adding Custom Datasets": [[0, "adding-custom-datasets"]], "Data Processing": [[0, "data-processing"]], "Evaluation": [[1, "evaluation"]], "Error Measures": [[1, "error-measures"]], "Evaluation Protocols": [[1, "evaluation-protocols"]], "Installation": [[2, "installation"]], "Requirements": [[2, "requirements"]], "SVM-perf with quantification-oriented losses": [[2, "svm-perf-with-quantification-oriented-losses"]], "Quantification Methods": [[3, "quantification-methods"]], "Aggregative Methods": [[3, "aggregative-methods"]], "The Classify & Count variants": [[3, "the-classify-count-variants"]], "Expectation Maximization (EMQ)": [[3, "expectation-maximization-emq"]], "Hellinger Distance y (HDy)": [[3, "hellinger-distance-y-hdy"]], "Explicit Loss Minimization": [[3, "explicit-loss-minimization"]], "Meta Models": [[3, "meta-models"]], "Ensembles": [[3, "ensembles"]], "The QuaNet neural network": [[3, "the-quanet-neural-network"]], "Model Selection": [[4, "model-selection"]], "Targeting a Quantification-oriented loss": [[4, "targeting-a-quantification-oriented-loss"]], "Targeting a Classification-oriented loss": [[4, "targeting-a-classification-oriented-loss"]], "Plotting": [[5, "plotting"]], "Diagonal Plot": [[5, "diagonal-plot"]], "Quantification bias": [[5, "quantification-bias"]], "Error by Drift": [[5, "error-by-drift"]], "Welcome to QuaPy\u2019s documentation!": [[6, "welcome-to-quapy-s-documentation"]], "Introduction": [[6, "introduction"]], "A quick example:": [[6, "a-quick-example"]], "Features": [[6, "features"]], "Contents:": [[6, null]], "Indices and tables": [[6, "indices-and-tables"]], "quapy": [[7, "quapy"]], "quapy package": [[8, "quapy-package"]], "Submodules": [[8, "submodules"], [9, "submodules"], [10, "submodules"], [11, "submodules"]], "quapy.error": [[8, "module-quapy.error"]], "quapy.evaluation": [[8, "module-quapy.evaluation"]], "quapy.protocol": [[8, "quapy-protocol"]], "quapy.functional": [[8, "module-quapy.functional"]], "quapy.model_selection": [[8, "module-quapy.model_selection"]], "quapy.plot": [[8, "module-quapy.plot"]], "quapy.util": [[8, "module-quapy.util"]], "Subpackages": [[8, "subpackages"]], "Module contents": [[8, "module-quapy"], [9, "module-quapy.classification"], [10, "module-quapy.data"], [11, "module-quapy.method"]], "quapy.classification package": [[9, "quapy-classification-package"]], "quapy.classification.calibration": [[9, "quapy-classification-calibration"]], "quapy.classification.methods": [[9, "module-quapy.classification.methods"]], "quapy.classification.neural": [[9, "module-quapy.classification.neural"]], "quapy.classification.svmperf": [[9, "module-quapy.classification.svmperf"]], "quapy.data package": [[10, "quapy-data-package"]], "quapy.data.base": [[10, "module-quapy.data.base"]], "quapy.data.datasets": [[10, "module-quapy.data.datasets"]], "quapy.data.preprocessing": [[10, "module-quapy.data.preprocessing"]], "quapy.data.reader": [[10, "module-quapy.data.reader"]], "quapy.method package": [[11, "quapy-method-package"]], "quapy.method.aggregative": [[11, "module-quapy.method.aggregative"]], "quapy.method.base": [[11, "module-quapy.method.base"]], "quapy.method.meta": [[11, "module-quapy.method.meta"]], "quapy.method.neural": [[11, "module-quapy.method.neural"]], "quapy.method.non_aggregative": [[11, "module-quapy.method.non_aggregative"]]}, "indexentries": {"app (class in quapy.protocol)": [[8, "quapy.protocol.APP"]], "abstractprotocol (class in quapy.protocol)": [[8, "quapy.protocol.AbstractProtocol"]], "abstractstochasticseededprotocol (class in quapy.protocol)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol"]], "domainmixer (class in quapy.protocol)": [[8, "quapy.protocol.DomainMixer"]], "earlystop (class in quapy.util)": [[8, "quapy.util.EarlyStop"]], "gridsearchq (class in quapy.model_selection)": [[8, "quapy.model_selection.GridSearchQ"]], "hellingerdistance() (in module quapy.functional)": [[8, "quapy.functional.HellingerDistance"]], "npp (class in quapy.protocol)": [[8, "quapy.protocol.NPP"]], "onlabelledcollectionprotocol (class in quapy.protocol)": [[8, "quapy.protocol.OnLabelledCollectionProtocol"]], "return_types (quapy.protocol.onlabelledcollectionprotocol attribute)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.RETURN_TYPES"]], "topsoedistance() (in module quapy.functional)": [[8, "quapy.functional.TopsoeDistance"]], "usimplexpp (class in quapy.protocol)": [[8, "quapy.protocol.USimplexPP"]], "absolute_error() (in module quapy.error)": [[8, "quapy.error.absolute_error"]], "acc_error() (in module quapy.error)": [[8, "quapy.error.acc_error"]], "acce() (in module quapy.error)": [[8, "quapy.error.acce"]], "adjusted_quantification() (in module quapy.functional)": [[8, "quapy.functional.adjusted_quantification"]], "ae() (in module quapy.error)": [[8, "quapy.error.ae"]], "best_model() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.best_model"]], "binary_bias_bins() (in module quapy.plot)": [[8, "quapy.plot.binary_bias_bins"]], "binary_bias_global() (in module quapy.plot)": [[8, "quapy.plot.binary_bias_global"]], "binary_diagonal() (in module quapy.plot)": [[8, "quapy.plot.binary_diagonal"]], "brokenbar_supremacy_by_drift() (in module quapy.plot)": [[8, "quapy.plot.brokenbar_supremacy_by_drift"]], "check_prevalence_vector() (in module quapy.functional)": [[8, "quapy.functional.check_prevalence_vector"]], "collator() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.collator"]], "create_if_not_exist() (in module quapy.util)": [[8, "quapy.util.create_if_not_exist"]], "create_parent_dir() (in module quapy.util)": [[8, "quapy.util.create_parent_dir"]], "cross_val_predict() (in module quapy.model_selection)": [[8, "quapy.model_selection.cross_val_predict"]], "download_file() (in module quapy.util)": [[8, "quapy.util.download_file"]], "download_file_if_not_exists() (in module quapy.util)": [[8, "quapy.util.download_file_if_not_exists"]], "error_by_drift() (in module quapy.plot)": [[8, "quapy.plot.error_by_drift"]], "evaluate() (in module quapy.evaluation)": [[8, "quapy.evaluation.evaluate"]], "evaluation_report() (in module quapy.evaluation)": [[8, "quapy.evaluation.evaluation_report"]], "f1_error() (in module quapy.error)": [[8, "quapy.error.f1_error"]], "f1e() (in module quapy.error)": [[8, "quapy.error.f1e"]], "fit() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.fit"]], "from_name() (in module quapy.error)": [[8, "quapy.error.from_name"]], "get_collator() (quapy.protocol.onlabelledcollectionprotocol class method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.get_collator"]], "get_labelled_collection() (quapy.protocol.onlabelledcollectionprotocol method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.get_labelled_collection"]], "get_nprevpoints_approximation() (in module quapy.functional)": [[8, "quapy.functional.get_nprevpoints_approximation"]], "get_params() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.get_params"]], "get_quapy_home() (in module quapy.util)": [[8, "quapy.util.get_quapy_home"]], "kld() (in module quapy.error)": [[8, "quapy.error.kld"]], "mae() (in module quapy.error)": [[8, "quapy.error.mae"]], "map_parallel() (in module quapy.util)": [[8, "quapy.util.map_parallel"]], "mean_absolute_error() (in module quapy.error)": [[8, "quapy.error.mean_absolute_error"]], "mean_relative_absolute_error() (in module quapy.error)": [[8, "quapy.error.mean_relative_absolute_error"]], "mkld() (in module quapy.error)": [[8, "quapy.error.mkld"]], "mnkld() (in module quapy.error)": [[8, "quapy.error.mnkld"]], "module": [[8, "module-quapy"], [8, "module-quapy.error"], [8, "module-quapy.evaluation"], [8, "module-quapy.functional"], [8, "module-quapy.model_selection"], [8, "module-quapy.plot"], [8, "module-quapy.protocol"], [8, "module-quapy.util"], [9, "module-quapy.classification"], [9, "module-quapy.classification.calibration"], [9, "module-quapy.classification.methods"], [9, "module-quapy.classification.neural"], [9, "module-quapy.classification.svmperf"], [10, "module-quapy.data"], [10, "module-quapy.data.base"], [10, "module-quapy.data.datasets"], [10, "module-quapy.data.preprocessing"], [10, "module-quapy.data.reader"], [11, "module-quapy.method"], [11, "module-quapy.method.aggregative"], [11, "module-quapy.method.base"], [11, "module-quapy.method.meta"], [11, "module-quapy.method.neural"], [11, "module-quapy.method.non_aggregative"]], "mrae() (in module quapy.error)": [[8, "quapy.error.mrae"]], "mse() (in module quapy.error)": [[8, "quapy.error.mse"]], "nkld() (in module quapy.error)": [[8, "quapy.error.nkld"]], "normalize_prevalence() (in module quapy.functional)": [[8, "quapy.functional.normalize_prevalence"]], "num_prevalence_combinations() (in module quapy.functional)": [[8, "quapy.functional.num_prevalence_combinations"]], "on_preclassified_instances() (quapy.protocol.onlabelledcollectionprotocol method)": [[8, "quapy.protocol.OnLabelledCollectionProtocol.on_preclassified_instances"]], "parallel() (in module quapy.util)": [[8, "quapy.util.parallel"]], "pickled_resource() (in module quapy.util)": [[8, "quapy.util.pickled_resource"]], "prediction() (in module quapy.evaluation)": [[8, "quapy.evaluation.prediction"]], "prevalence_from_labels() (in module quapy.functional)": [[8, "quapy.functional.prevalence_from_labels"]], "prevalence_from_probabilities() (in module quapy.functional)": [[8, "quapy.functional.prevalence_from_probabilities"]], "prevalence_grid() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.prevalence_grid"]], "prevalence_linspace() (in module quapy.functional)": [[8, "quapy.functional.prevalence_linspace"]], "quantify() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.quantify"]], "quapy": [[8, "module-quapy"]], "quapy.error": [[8, "module-quapy.error"]], "quapy.evaluation": [[8, "module-quapy.evaluation"]], "quapy.functional": [[8, "module-quapy.functional"]], "quapy.model_selection": [[8, "module-quapy.model_selection"]], "quapy.plot": [[8, "module-quapy.plot"]], "quapy.protocol": [[8, "module-quapy.protocol"]], "quapy.util": [[8, "module-quapy.util"]], "rae() (in module quapy.error)": [[8, "quapy.error.rae"]], "random_state (quapy.protocol.abstractstochasticseededprotocol property)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.random_state"]], "relative_absolute_error() (in module quapy.error)": [[8, "quapy.error.relative_absolute_error"]], "sample() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.sample"]], "sample() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.sample"]], "sample() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.sample"]], "sample() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.sample"]], "sample() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.sample"]], "samples_parameters() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.samples_parameters"]], "samples_parameters() (quapy.protocol.abstractstochasticseededprotocol method)": [[8, "quapy.protocol.AbstractStochasticSeededProtocol.samples_parameters"]], "samples_parameters() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.samples_parameters"]], "samples_parameters() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.samples_parameters"]], "samples_parameters() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.samples_parameters"]], "save_text_file() (in module quapy.util)": [[8, "quapy.util.save_text_file"]], "se() (in module quapy.error)": [[8, "quapy.error.se"]], "set_params() (quapy.model_selection.gridsearchq method)": [[8, "quapy.model_selection.GridSearchQ.set_params"]], "smooth() (in module quapy.error)": [[8, "quapy.error.smooth"]], "strprev() (in module quapy.functional)": [[8, "quapy.functional.strprev"]], "temp_seed() (in module quapy.util)": [[8, "quapy.util.temp_seed"]], "total() (quapy.protocol.app method)": [[8, "quapy.protocol.APP.total"]], "total() (quapy.protocol.abstractprotocol method)": [[8, "quapy.protocol.AbstractProtocol.total"]], "total() (quapy.protocol.domainmixer method)": [[8, "quapy.protocol.DomainMixer.total"]], "total() (quapy.protocol.npp method)": [[8, "quapy.protocol.NPP.total"]], "total() (quapy.protocol.usimplexpp method)": [[8, "quapy.protocol.USimplexPP.total"]], "uniform_prevalence_sampling() (in module quapy.functional)": [[8, "quapy.functional.uniform_prevalence_sampling"]], "uniform_simplex_sampling() (in module quapy.functional)": [[8, "quapy.functional.uniform_simplex_sampling"]], "bctscalibration (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.BCTSCalibration"]], "cnnnet (class in quapy.classification.neural)": [[9, "quapy.classification.neural.CNNnet"]], "lstmnet (class in quapy.classification.neural)": [[9, "quapy.classification.neural.LSTMnet"]], "lowranklogisticregression (class in quapy.classification.methods)": [[9, "quapy.classification.methods.LowRankLogisticRegression"]], "nbvscalibration (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.NBVSCalibration"]], "neuralclassifiertrainer (class in quapy.classification.neural)": [[9, "quapy.classification.neural.NeuralClassifierTrainer"]], "recalibratedprobabilisticclassifier (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifier"]], "recalibratedprobabilisticclassifierbase (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase"]], "svmperf (class in quapy.classification.svmperf)": [[9, "quapy.classification.svmperf.SVMperf"]], "tscalibration (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.TSCalibration"]], "textclassifiernet (class in quapy.classification.neural)": [[9, "quapy.classification.neural.TextClassifierNet"]], "torchdataset (class in quapy.classification.neural)": [[9, "quapy.classification.neural.TorchDataset"]], "vscalibration (class in quapy.classification.calibration)": [[9, "quapy.classification.calibration.VSCalibration"]], "asdataloader() (quapy.classification.neural.torchdataset method)": [[9, "quapy.classification.neural.TorchDataset.asDataloader"]], "classes_ (quapy.classification.calibration.recalibratedprobabilisticclassifierbase property)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.classes_"]], "decision_function() (quapy.classification.svmperf.svmperf method)": [[9, "quapy.classification.svmperf.SVMperf.decision_function"]], "device (quapy.classification.neural.neuralclassifiertrainer property)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.device"]], "dimensions() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.dimensions"]], "document_embedding() (quapy.classification.neural.cnnnet method)": [[9, "quapy.classification.neural.CNNnet.document_embedding"]], "document_embedding() (quapy.classification.neural.lstmnet method)": [[9, "quapy.classification.neural.LSTMnet.document_embedding"]], "document_embedding() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.document_embedding"]], "fit() (quapy.classification.calibration.recalibratedprobabilisticclassifierbase method)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit"]], "fit() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.fit"]], "fit() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.fit"]], "fit() (quapy.classification.svmperf.svmperf method)": [[9, "quapy.classification.svmperf.SVMperf.fit"]], "fit_cv() (quapy.classification.calibration.recalibratedprobabilisticclassifierbase method)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_cv"]], "fit_tr_val() (quapy.classification.calibration.recalibratedprobabilisticclassifierbase method)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.fit_tr_val"]], "forward() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.forward"]], "get_params() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.get_params"]], "get_params() (quapy.classification.neural.cnnnet method)": [[9, "quapy.classification.neural.CNNnet.get_params"]], "get_params() (quapy.classification.neural.lstmnet method)": [[9, "quapy.classification.neural.LSTMnet.get_params"]], "get_params() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.get_params"]], "get_params() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.get_params"]], "predict() (quapy.classification.calibration.recalibratedprobabilisticclassifierbase method)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict"]], "predict() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.predict"]], "predict() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.predict"]], "predict() (quapy.classification.svmperf.svmperf method)": [[9, "quapy.classification.svmperf.SVMperf.predict"]], "predict_proba() (quapy.classification.calibration.recalibratedprobabilisticclassifierbase method)": [[9, "quapy.classification.calibration.RecalibratedProbabilisticClassifierBase.predict_proba"]], "predict_proba() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.predict_proba"]], "predict_proba() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.predict_proba"]], "predict_proba() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.predict_proba"]], "quapy.classification": [[9, "module-quapy.classification"]], "quapy.classification.calibration": [[9, "module-quapy.classification.calibration"]], "quapy.classification.methods": [[9, "module-quapy.classification.methods"]], "quapy.classification.neural": [[9, "module-quapy.classification.neural"]], "quapy.classification.svmperf": [[9, "module-quapy.classification.svmperf"]], "reset_net_params() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.reset_net_params"]], "set_params() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.set_params"]], "set_params() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.set_params"]], "set_params() (quapy.classification.svmperf.svmperf method)": [[9, "quapy.classification.svmperf.SVMperf.set_params"]], "training (quapy.classification.neural.cnnnet attribute)": [[9, "quapy.classification.neural.CNNnet.training"]], "training (quapy.classification.neural.lstmnet attribute)": [[9, "quapy.classification.neural.LSTMnet.training"]], "training (quapy.classification.neural.textclassifiernet attribute)": [[9, "quapy.classification.neural.TextClassifierNet.training"]], "transform() (quapy.classification.methods.lowranklogisticregression method)": [[9, "quapy.classification.methods.LowRankLogisticRegression.transform"]], "transform() (quapy.classification.neural.neuralclassifiertrainer method)": [[9, "quapy.classification.neural.NeuralClassifierTrainer.transform"]], "valid_losses (quapy.classification.svmperf.svmperf attribute)": [[9, "quapy.classification.svmperf.SVMperf.valid_losses"]], "vocabulary_size (quapy.classification.neural.cnnnet property)": [[9, "quapy.classification.neural.CNNnet.vocabulary_size"]], "vocabulary_size (quapy.classification.neural.lstmnet property)": [[9, "quapy.classification.neural.LSTMnet.vocabulary_size"]], "vocabulary_size (quapy.classification.neural.textclassifiernet property)": [[9, "quapy.classification.neural.TextClassifierNet.vocabulary_size"]], "xavier_uniform() (quapy.classification.neural.textclassifiernet method)": [[9, "quapy.classification.neural.TextClassifierNet.xavier_uniform"]], "dataset (class in quapy.data.base)": [[10, "quapy.data.base.Dataset"]], "indextransformer (class in quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.IndexTransformer"]], "labelledcollection (class in quapy.data.base)": [[10, "quapy.data.base.LabelledCollection"]], "splitstratified() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.SplitStratified"]], "x (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.X"]], "xp (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.Xp"]], "xy (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.Xy"]], "add_word() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.add_word"]], "binarize() (in module quapy.data.reader)": [[10, "quapy.data.reader.binarize"]], "binary (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.binary"]], "binary (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.binary"]], "classes_ (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.classes_"]], "counts() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.counts"]], "fetch_ucidataset() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_UCIDataset"]], "fetch_ucilabelledcollection() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_UCILabelledCollection"]], "fetch_lequa2022() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_lequa2022"]], "fetch_reviews() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_reviews"]], "fetch_twitter() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.fetch_twitter"]], "fit() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.fit"]], "fit_transform() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.fit_transform"]], "from_csv() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_csv"]], "from_sparse() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_sparse"]], "from_text() (in module quapy.data.reader)": [[10, "quapy.data.reader.from_text"]], "index() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.index"]], "kfcv() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.kFCV"]], "kfcv() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.kFCV"]], "load() (quapy.data.base.dataset class method)": [[10, "quapy.data.base.Dataset.load"]], "load() (quapy.data.base.labelledcollection class method)": [[10, "quapy.data.base.LabelledCollection.load"]], "mix() (quapy.data.base.labelledcollection class method)": [[10, "quapy.data.base.LabelledCollection.mix"]], "n_classes (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.n_classes"]], "n_classes (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.n_classes"]], "p (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.p"]], "prevalence() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.prevalence"]], "quapy.data": [[10, "module-quapy.data"]], "quapy.data.base": [[10, "module-quapy.data.base"]], "quapy.data.datasets": [[10, "module-quapy.data.datasets"]], "quapy.data.preprocessing": [[10, "module-quapy.data.preprocessing"]], "quapy.data.reader": [[10, "module-quapy.data.reader"]], "reduce_columns() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.reduce_columns"]], "reindex_labels() (in module quapy.data.reader)": [[10, "quapy.data.reader.reindex_labels"]], "sampling() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling"]], "sampling_from_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling_from_index"]], "sampling_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.sampling_index"]], "split_random() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.split_random"]], "split_stratified() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.split_stratified"]], "standardize() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.standardize"]], "stats() (quapy.data.base.dataset method)": [[10, "quapy.data.base.Dataset.stats"]], "stats() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.stats"]], "text2tfidf() (in module quapy.data.preprocessing)": [[10, "quapy.data.preprocessing.text2tfidf"]], "train_test (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.train_test"]], "transform() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.transform"]], "uniform_sampling() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.uniform_sampling"]], "uniform_sampling_index() (quapy.data.base.labelledcollection method)": [[10, "quapy.data.base.LabelledCollection.uniform_sampling_index"]], "vocabulary_size (quapy.data.base.dataset property)": [[10, "quapy.data.base.Dataset.vocabulary_size"]], "vocabulary_size() (quapy.data.preprocessing.indextransformer method)": [[10, "quapy.data.preprocessing.IndexTransformer.vocabulary_size"]], "warn() (in module quapy.data.datasets)": [[10, "quapy.data.datasets.warn"]], "y (quapy.data.base.labelledcollection property)": [[10, "quapy.data.base.LabelledCollection.y"]], "acc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ACC"]], "adjustedclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.AdjustedClassifyAndCount"]], "aggregativeprobabilisticquantifier (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.AggregativeProbabilisticQuantifier"]], "aggregativequantifier (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.AggregativeQuantifier"]], "basequantifier (class in quapy.method.base)": [[11, "quapy.method.base.BaseQuantifier"]], "binaryquantifier (class in quapy.method.base)": [[11, "quapy.method.base.BinaryQuantifier"]], "cc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.CC"]], "classifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ClassifyAndCount"]], "distributionmatching (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.DistributionMatching"]], "dys (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.DyS"]], "eacc() (in module quapy.method.meta)": [[11, "quapy.method.meta.EACC"]], "ecc() (in module quapy.method.meta)": [[11, "quapy.method.meta.ECC"]], "eemq() (in module quapy.method.meta)": [[11, "quapy.method.meta.EEMQ"]], "ehdy() (in module quapy.method.meta)": [[11, "quapy.method.meta.EHDy"]], "elm (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ELM"]], "em() (quapy.method.aggregative.emq class method)": [[11, "quapy.method.aggregative.EMQ.EM"]], "emq (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.EMQ"]], "epacc() (in module quapy.method.meta)": [[11, "quapy.method.meta.EPACC"]], "epsilon (quapy.method.aggregative.emq attribute)": [[11, "quapy.method.aggregative.EMQ.EPSILON"]], "ensemble (class in quapy.method.meta)": [[11, "quapy.method.meta.Ensemble"]], "expectationmaximizationquantifier (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ExpectationMaximizationQuantifier"]], "explicitlossminimisation (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ExplicitLossMinimisation"]], "hdy (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.HDy"]], "hellingerdistancey (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.HellingerDistanceY"]], "max (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MAX"]], "max_iter (quapy.method.aggregative.emq attribute)": [[11, "quapy.method.aggregative.EMQ.MAX_ITER"]], "ms (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MS"]], "ms2 (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.MS2"]], "maximumlikelihoodprevalenceestimation (class in quapy.method.non_aggregative)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation"]], "mediansweep (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.MedianSweep"]], "mediansweep2 (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.MedianSweep2"]], "onevsall (class in quapy.method.base)": [[11, "quapy.method.base.OneVsAll"]], "onevsallaggregative (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.OneVsAllAggregative"]], "onevsallgeneric (class in quapy.method.base)": [[11, "quapy.method.base.OneVsAllGeneric"]], "pacc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.PACC"]], "pcc (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.PCC"]], "probabilisticadjustedclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ProbabilisticAdjustedClassifyAndCount"]], "probabilisticclassifyandcount (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.ProbabilisticClassifyAndCount"]], "quanetmodule (class in quapy.method.neural)": [[11, "quapy.method.neural.QuaNetModule"]], "quanettrainer (class in quapy.method.neural)": [[11, "quapy.method.neural.QuaNetTrainer"]], "sld (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.SLD"]], "smm (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SMM"]], "svmae (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMAE"]], "svmkld (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMKLD"]], "svmnkld (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMNKLD"]], "svmq (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMQ"]], "svmrae (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.SVMRAE"]], "t50 (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.T50"]], "thresholdoptimization (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.ThresholdOptimization"]], "valid_policies (quapy.method.meta.ensemble attribute)": [[11, "quapy.method.meta.Ensemble.VALID_POLICIES"]], "x (class in quapy.method.aggregative)": [[11, "quapy.method.aggregative.X"]], "aggregate() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.aggregate"]], "aggregate() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.aggregate"]], "aggregate() (quapy.method.aggregative.cc method)": [[11, "quapy.method.aggregative.CC.aggregate"]], "aggregate() (quapy.method.aggregative.distributionmatching method)": [[11, "quapy.method.aggregative.DistributionMatching.aggregate"]], "aggregate() (quapy.method.aggregative.dys method)": [[11, "quapy.method.aggregative.DyS.aggregate"]], "aggregate() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.aggregate"]], "aggregate() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.aggregate"]], "aggregate() (quapy.method.aggregative.hdy method)": [[11, "quapy.method.aggregative.HDy.aggregate"]], "aggregate() (quapy.method.aggregative.onevsallaggregative method)": [[11, "quapy.method.aggregative.OneVsAllAggregative.aggregate"]], "aggregate() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.aggregate"]], "aggregate() (quapy.method.aggregative.pcc method)": [[11, "quapy.method.aggregative.PCC.aggregate"]], "aggregate() (quapy.method.aggregative.smm method)": [[11, "quapy.method.aggregative.SMM.aggregate"]], "aggregate() (quapy.method.aggregative.thresholdoptimization method)": [[11, "quapy.method.aggregative.ThresholdOptimization.aggregate"]], "aggregative (quapy.method.meta.ensemble property)": [[11, "quapy.method.meta.Ensemble.aggregative"]], "classes_ (quapy.method.aggregative.aggregativequantifier property)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classes_"]], "classes_ (quapy.method.base.onevsallgeneric property)": [[11, "quapy.method.base.OneVsAllGeneric.classes_"]], "classes_ (quapy.method.neural.quanettrainer property)": [[11, "quapy.method.neural.QuaNetTrainer.classes_"]], "classifier (quapy.method.aggregative.aggregativequantifier property)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classifier"]], "classify() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.classify"]], "classify() (quapy.method.aggregative.aggregativeprobabilisticquantifier method)": [[11, "quapy.method.aggregative.AggregativeProbabilisticQuantifier.classify"]], "classify() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.classify"]], "classify() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.classify"]], "classify() (quapy.method.aggregative.onevsallaggregative method)": [[11, "quapy.method.aggregative.OneVsAllAggregative.classify"]], "classify() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.classify"]], "clean_checkpoint() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.clean_checkpoint"]], "clean_checkpoint_dir() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.clean_checkpoint_dir"]], "cross_generate_predictions() (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.cross_generate_predictions"]], "cross_generate_predictions_depr() (in module quapy.method.aggregative)": [[11, "quapy.method.aggregative.cross_generate_predictions_depr"]], "device (quapy.method.neural.quanetmodule property)": [[11, "quapy.method.neural.QuaNetModule.device"]], "ensemblefactory() (in module quapy.method.meta)": [[11, "quapy.method.meta.ensembleFactory"]], "fit() (quapy.method.aggregative.acc method)": [[11, "quapy.method.aggregative.ACC.fit"]], "fit() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.fit"]], "fit() (quapy.method.aggregative.cc method)": [[11, "quapy.method.aggregative.CC.fit"]], "fit() (quapy.method.aggregative.distributionmatching method)": [[11, "quapy.method.aggregative.DistributionMatching.fit"]], "fit() (quapy.method.aggregative.dys method)": [[11, "quapy.method.aggregative.DyS.fit"]], "fit() (quapy.method.aggregative.elm method)": [[11, "quapy.method.aggregative.ELM.fit"]], "fit() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.fit"]], "fit() (quapy.method.aggregative.hdy method)": [[11, "quapy.method.aggregative.HDy.fit"]], "fit() (quapy.method.aggregative.pacc method)": [[11, "quapy.method.aggregative.PACC.fit"]], "fit() (quapy.method.aggregative.pcc method)": [[11, "quapy.method.aggregative.PCC.fit"]], "fit() (quapy.method.aggregative.smm method)": [[11, "quapy.method.aggregative.SMM.fit"]], "fit() (quapy.method.aggregative.thresholdoptimization method)": [[11, "quapy.method.aggregative.ThresholdOptimization.fit"]], "fit() (quapy.method.base.basequantifier method)": [[11, "quapy.method.base.BaseQuantifier.fit"]], "fit() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.fit"]], "fit() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.fit"]], "fit() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.fit"]], "fit() (quapy.method.non_aggregative.maximumlikelihoodprevalenceestimation method)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.fit"]], "forward() (quapy.method.neural.quanetmodule method)": [[11, "quapy.method.neural.QuaNetModule.forward"]], "getonevsall() (in module quapy.method.base)": [[11, "quapy.method.base.getOneVsAll"]], "getptecondestim() (quapy.method.aggregative.acc class method)": [[11, "quapy.method.aggregative.ACC.getPteCondEstim"]], "getptecondestim() (quapy.method.aggregative.pacc class method)": [[11, "quapy.method.aggregative.PACC.getPteCondEstim"]], "get_params() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.get_params"]], "get_params() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.get_params"]], "get_probability_distribution() (in module quapy.method.meta)": [[11, "quapy.method.meta.get_probability_distribution"]], "mae_loss() (in module quapy.method.neural)": [[11, "quapy.method.neural.mae_loss"]], "predict_proba() (quapy.method.aggregative.emq method)": [[11, "quapy.method.aggregative.EMQ.predict_proba"]], "probabilistic (quapy.method.meta.ensemble property)": [[11, "quapy.method.meta.Ensemble.probabilistic"]], "quantify() (quapy.method.aggregative.aggregativequantifier method)": [[11, "quapy.method.aggregative.AggregativeQuantifier.quantify"]], "quantify() (quapy.method.base.basequantifier method)": [[11, "quapy.method.base.BaseQuantifier.quantify"]], "quantify() (quapy.method.base.onevsallgeneric method)": [[11, "quapy.method.base.OneVsAllGeneric.quantify"]], "quantify() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.quantify"]], "quantify() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.quantify"]], "quantify() (quapy.method.non_aggregative.maximumlikelihoodprevalenceestimation method)": [[11, "quapy.method.non_aggregative.MaximumLikelihoodPrevalenceEstimation.quantify"]], "quapy.method": [[11, "module-quapy.method"]], "quapy.method.aggregative": [[11, "module-quapy.method.aggregative"]], "quapy.method.base": [[11, "module-quapy.method.base"]], "quapy.method.meta": [[11, "module-quapy.method.meta"]], "quapy.method.neural": [[11, "module-quapy.method.neural"]], "quapy.method.non_aggregative": [[11, "module-quapy.method.non_aggregative"]], "set_params() (quapy.method.meta.ensemble method)": [[11, "quapy.method.meta.Ensemble.set_params"]], "set_params() (quapy.method.neural.quanettrainer method)": [[11, "quapy.method.neural.QuaNetTrainer.set_params"]], "solve_adjustment() (quapy.method.aggregative.acc class method)": [[11, "quapy.method.aggregative.ACC.solve_adjustment"]], "training (quapy.method.neural.quanetmodule attribute)": [[11, "quapy.method.neural.QuaNetModule.training"]]}}) \ No newline at end of file diff --git a/examples/custom_quantifier.py b/examples/custom_quantifier.py index a025b87..705c371 100644 --- a/examples/custom_quantifier.py +++ b/examples/custom_quantifier.py @@ -11,7 +11,7 @@ from sklearn.linear_model import LogisticRegression # Define a custom quantifier: for this example, we will consider a new quantification algorithm that uses a # logistic regressor for generating posterior probabilities, and then applies a custom threshold value to the # posteriors. Since the quantifier internally uses a classifier, it is an aggregative quantifier; and since it -# relies on posterior probabilities, then it is a probabilistic aggregative quantifier. Note also it has an +# relies on posterior probabilities, it is a probabilistic-aggregative quantifier. Note also it has an # internal hyperparameter (let say, alpha) which is the decision threshold. Let's also assume the quantifier # is binary, for simplicity. @@ -47,13 +47,13 @@ if __name__ == '__main__': # load the IMDb dataset train, test = qp.datasets.fetch_reviews('imdb', tfidf=True, min_df=5).train_test - train, val = train.split_stratified(train_prop=0.75) # model selection # let us assume we want to explore our hyperparameter alpha along with one hyperparameter of the classifier + train, val = train.split_stratified(train_prop=0.75) param_grid = { - 'alpha': np.linspace(0,1,11), # quantifier-dependent hyperparameter - 'classifier__C': np.logspace(-2,2,5) # classifier-dependent hyperparameter + 'alpha': np.linspace(0, 1, 11), # quantifier-dependent hyperparameter + 'classifier__C': np.logspace(-2, 2, 5) # classifier-dependent hyperparameter } quantifier = GridSearchQ(quantifier, param_grid, protocol=APP(val), n_jobs=-1, verbose=True).fit(train) diff --git a/examples/lequa2022_experiments.py b/examples/lequa2022_experiments.py index 41bc495..6b6225d 100644 --- a/examples/lequa2022_experiments.py +++ b/examples/lequa2022_experiments.py @@ -9,19 +9,37 @@ from method.aggregative import EMQ from model_selection import GridSearchQ import pandas as pd +""" +This example shows hoy to use the LeQua datasets (new in v0.1.7). For more information about the datasets, and the +LeQua competition itself, check: +https://lequa2022.github.io/index (the site of the competition) +https://ceur-ws.org/Vol-3180/paper-146.pdf (the overview paper) +""" +# there are 4 tasks (T1A, T1B, T2A, T2B) task = 'T1A' +# set the sample size in the environment. The sample size is task-dendendent and can be consulted by doing: qp.environ['SAMPLE_SIZE'] = LEQUA2022_SAMPLE_SIZE[task] +qp.environ['N_JOBS'] = -1 + +# the fetch method returns a training set (an instance of LabelledCollection) and two generators: one for the +# validation set and another for the test sets. These generators are both instances of classes that extend +# AbstractProtocol (i.e., classes that implement sampling generation procedures) and, in particular, are instances +# of SamplesFromDir, a protocol that simply iterates over pre-generated samples (those provided for the competition) +# stored in a directory. training, val_generator, test_generator = fetch_lequa2022(task=task) # define the quantifier -learner = CalibratedClassifierCV(LogisticRegression()) -quantifier = EMQ(classifier=learner) +quantifier = EMQ(classifier=LogisticRegression()) # model selection -param_grid = {'C': np.logspace(-3, 3, 7), 'class_weight': ['balanced', None]} -model_selection = GridSearchQ(quantifier, param_grid, protocol=val_generator, n_jobs=-1, refit=False, verbose=True) +param_grid = { + 'classifier__C': np.logspace(-3, 3, 7), # classifier-dependent: inverse of regularization strength + 'classifier__class_weight': ['balanced', None], # classifier-dependent: weights of each class + 'recalib': ['bcts', 'platt', None] # quantifier-dependent: recalibration method (new in v0.1.7) +} +model_selection = GridSearchQ(quantifier, param_grid, protocol=val_generator, error='mrae', refit=False, verbose=True) quantifier = model_selection.fit(training) # evaluation diff --git a/examples/one_vs_all_example.py b/examples/one_vs_all.py similarity index 90% rename from examples/one_vs_all_example.py rename to examples/one_vs_all.py index 7488199..9e40551 100644 --- a/examples/one_vs_all_example.py +++ b/examples/one_vs_all.py @@ -12,6 +12,7 @@ and positive. We will use a one-vs-all approach using a binary quantifier for de """ qp.environ['SAMPLE_SIZE'] = 100 +qp.environ['N_JOBS'] = -1 """ Any binary quantifier can be turned into a single-label quantifier by means of getOneVsAll function. @@ -21,7 +22,7 @@ an instance of AggregativeQuantifier. Although OneVsAllGeneric works in all case some additional advantages (namely, all the advantages that AggregativeQuantifiers enjoy, i.e., faster predictions during evaluation). """ -quantifier = getOneVsAll(MS2(LogisticRegression()), parallel_backend="loky") +quantifier = getOneVsAll(MS2(LogisticRegression())) print(f'the quantifier is an instance of {quantifier.__class__.__name__}') # load a ternary dataset @@ -38,8 +39,8 @@ param_grid = { 'binary_quantifier__classifier__class_weight': ['balanced', None] # classifier-dependent hyperparameter } print('starting model selection') -gs = GridSearchQ(quantifier, param_grid, protocol=USimplexPP(val), n_jobs=-1, verbose=True, refit=False) -quantifier = gs.fit(train_modsel).best_model() +model_selection = GridSearchQ(quantifier, param_grid, protocol=USimplexPP(val), verbose=True, refit=False) +quantifier = model_selection.fit(train_modsel).best_model() print('training on the whole training set') train, test = qp.datasets.fetch_twitter('hcr', for_model_selection=False, pickle=True).train_test diff --git a/quapy/CHANGE_LOG.txt b/quapy/CHANGE_LOG.txt index 4b14d14..d531ce6 100644 --- a/quapy/CHANGE_LOG.txt +++ b/quapy/CHANGE_LOG.txt @@ -84,7 +84,5 @@ Change Log 0.1.7 Things to fix: -------------- - update unit tests -- update Wikis... - improve plots -- documentation of protocols is incomplete diff --git a/quapy/method/aggregative.py b/quapy/method/aggregative.py index e07f665..1f2b8ba 100644 --- a/quapy/method/aggregative.py +++ b/quapy/method/aggregative.py @@ -1262,7 +1262,7 @@ class OneVsAllAggregative(OneVsAllGeneric, AggregativeQuantifier): is removed and no longer available at predict time. """ - def __init__(self, binary_quantifier, n_jobs=None, parallel_backend='loky'): + def __init__(self, binary_quantifier, n_jobs=None, parallel_backend='multiprocessing'): assert isinstance(binary_quantifier, BaseQuantifier), \ f'{self.binary_quantifier} does not seem to be a Quantifier' assert isinstance(binary_quantifier, AggregativeQuantifier), \ diff --git a/quapy/method/base.py b/quapy/method/base.py index 1803085..1aa64e2 100644 --- a/quapy/method/base.py +++ b/quapy/method/base.py @@ -54,13 +54,13 @@ class OneVsAll: pass -def getOneVsAll(binary_quantifier, n_jobs=None, parallel_backend='loky'): +def getOneVsAll(binary_quantifier, n_jobs=None): assert isinstance(binary_quantifier, BaseQuantifier), \ f'{binary_quantifier} does not seem to be a Quantifier' if isinstance(binary_quantifier, qp.method.aggregative.AggregativeQuantifier): - return qp.method.aggregative.OneVsAllAggregative(binary_quantifier, n_jobs, parallel_backend) + return qp.method.aggregative.OneVsAllAggregative(binary_quantifier, n_jobs) else: - return OneVsAllGeneric(binary_quantifier, n_jobs, parallel_backend) + return OneVsAllGeneric(binary_quantifier, n_jobs) class OneVsAllGeneric(OneVsAll,BaseQuantifier): @@ -69,7 +69,7 @@ class OneVsAllGeneric(OneVsAll,BaseQuantifier): quantifier for each class, and then l1-normalizes the outputs so that the class prevelence values sum up to 1. """ - def __init__(self, binary_quantifier, n_jobs=None, parallel_backend='loky'): + def __init__(self, binary_quantifier, n_jobs=None): assert isinstance(binary_quantifier, BaseQuantifier), \ f'{binary_quantifier} does not seem to be a Quantifier' if isinstance(binary_quantifier, qp.method.aggregative.AggregativeQuantifier): @@ -77,7 +77,6 @@ class OneVsAllGeneric(OneVsAll,BaseQuantifier): f'you might prefer instantiating {qp.method.aggregative.OneVsAllAggregative.__name__}') self.binary_quantifier = binary_quantifier self.n_jobs = qp._get_njobs(n_jobs) - self.parallel_backend = parallel_backend def fit(self, data: LabelledCollection, fit_classifier=True): assert not data.binary, f'{self.__class__.__name__} expect non-binary data' @@ -89,7 +88,7 @@ class OneVsAllGeneric(OneVsAll,BaseQuantifier): def _parallel(self, func, *args, **kwargs): return np.asarray( - Parallel(n_jobs=self.n_jobs, backend=self.parallel_backend)( + Parallel(n_jobs=self.n_jobs, backend='threading')( delayed(func)(c, *args, **kwargs) for c in self.classes_ ) ) diff --git a/quapy/model_selection.py b/quapy/model_selection.py index b8b9282..84c9707 100644 --- a/quapy/model_selection.py +++ b/quapy/model_selection.py @@ -86,7 +86,8 @@ class GridSearchQ(BaseQuantifier): tinit = time() - hyper = [dict({k: values[i] for i, k in enumerate(params_keys)}) for values in itertools.product(*params_values)] + hyper = [dict({k: val[i] for i, k in enumerate(params_keys)}) for val in itertools.product(*params_values)] + self._sout(f'starting model selection with {self.n_jobs =}') #pass a seed to parallel so it is set in clild processes scores = qp.util.parallel( self._delayed_eval, diff --git a/quapy/protocol.py b/quapy/protocol.py index 1dec78b..70f4a48 100644 --- a/quapy/protocol.py +++ b/quapy/protocol.py @@ -45,13 +45,13 @@ class AbstractStochasticSeededProtocol(AbstractProtocol): needed for extracting the samples, and :meth:`sample` that, given some parameters as input, deterministically generates a sample. - :param random_state: the seed for allowing to replicate any sequence of samples. Default is None, meaning that - the sequence will be different every time the protocol is called. + :param random_state: the seed for allowing to replicate any sequence of samples. Default is 0, meaning that + the sequence will be consistent every time the protocol is called. """ _random_state = -1 # means "not set" - def __init__(self, random_state=None): + def __init__(self, random_state=0): self.random_state = random_state @property @@ -82,6 +82,13 @@ class AbstractStochasticSeededProtocol(AbstractProtocol): ... def __call__(self): + """ + Yields one sample at a time. The type of object returned depends on the `collator` function. The + default behaviour returns tuples of the form `(sample, prevalence)`. + + :return: a tuple `(sample, prevalence)` if return_type='sample_prev', or an instance of + :class:`qp.data.LabelledCollection` if return_type='labelled_collection' + """ with ExitStack() as stack: if self.random_state == -1: raise ValueError('The random seed has never been initialized. ' @@ -96,13 +103,33 @@ class AbstractStochasticSeededProtocol(AbstractProtocol): class OnLabelledCollectionProtocol: + """ + Protocols that generate samples from a :class:`qp.data.LabelledCollection` object. + """ RETURN_TYPES = ['sample_prev', 'labelled_collection'] def get_labelled_collection(self): + """ + Returns the labelled collection on which this protocol acts. + + :return: an object of type :class:`qp.data.LabelledCollection` + """ return self.data def on_preclassified_instances(self, pre_classifications, in_place=False): + """ + Returns a copy of this protocol that acts on a modified version of the original + :class:`qp.data.LabelledCollection` in which the original instances have been replaced + with the outputs of a classifier for each instance. (This is convenient for speeding-up + the evaluation procedures for many samples, by pre-classifying the instances in advance.) + + :param pre_classifications: the predictions issued by a classifier, typically an array-like + with shape `(n_instances,)` when the classifier is a hard one, or with shape + `(n_instances, n_classes)` when the classifier is a probabilistic one. + :param in_place: whether or not to apply the modification in-place or in a new copy (default). + :return: a copy of this protocol + """ assert len(pre_classifications) == len(self.data), \ f'error: the pre-classified data has different shape ' \ f'(expected {len(self.data)}, found {len(pre_classifications)})' @@ -115,6 +142,15 @@ class OnLabelledCollectionProtocol: @classmethod def get_collator(cls, return_type='sample_prev'): + """ + Returns a collator function, i.e., a function that prepares the yielded data + + :param return_type: either 'sample_prev' (default) if the collator is requested to yield tuples of + `(sample, prevalence)`, or 'labelled_collection' when it is requested to yield instances of + :class:`qp.data.LabelledCollection` + :return: the collator function (a callable function that takes as input an instance of + :class:`qp.data.LabelledCollection`) + """ assert return_type in cls.RETURN_TYPES, \ f'unknown return type passed as argument; valid ones are {cls.RETURN_TYPES}' if return_type=='sample_prev': @@ -139,13 +175,14 @@ class APP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): grid (default is 21) :param repeats: number of copies for each valid prevalence vector (default is 10) :param smooth_limits_epsilon: the quantity to add and subtract to the limits 0 and 1 - :param random_state: allows replicating samples across runs (default None) + :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples + will be the same every time the protocol is called) :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or to "labelled_collection" to get instead instances of LabelledCollection """ def __init__(self, data:LabelledCollection, sample_size=None, n_prevalences=21, repeats=10, - smooth_limits_epsilon=0, random_state=None, return_type='sample_prev'): + smooth_limits_epsilon=0, random_state=0, return_type='sample_prev'): super(APP, self).__init__(random_state) self.data = data self.sample_size = qp._get_sample_size(sample_size) @@ -179,6 +216,11 @@ class APP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): return prevs def samples_parameters(self): + """ + Return all the necessary parameters to replicate the samples as according to the APP protocol. + + :return: a list of indexes that realize the APP sampling + """ indexes = [] for prevs in self.prevalence_grid(): index = self.data.sampling_index(self.sample_size, *prevs) @@ -186,9 +228,20 @@ class APP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): return indexes def sample(self, index): + """ + Realizes the sample given the index of the instances. + + :param index: indexes of the instances to select + :return: an instance of :class:`qp.data.LabelledCollection` + """ return self.data.sampling_from_index(index) def total(self): + """ + Returns the number of samples that will be generated + + :return: int + """ return F.num_prevalence_combinations(self.n_prevalences, self.data.n_classes, self.repeats) @@ -201,12 +254,14 @@ class NPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised. :param repeats: the number of samples to generate. Default is 100. - :param random_state: allows replicating samples across runs (default None) + :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples + will be the same every time the protocol is called) :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or to "labelled_collection" to get instead instances of LabelledCollection """ - def __init__(self, data:LabelledCollection, sample_size=None, repeats=100, random_state=None, return_type='sample_prev'): + def __init__(self, data:LabelledCollection, sample_size=None, repeats=100, random_state=0, + return_type='sample_prev'): super(NPP, self).__init__(random_state) self.data = data self.sample_size = qp._get_sample_size(sample_size) @@ -215,6 +270,11 @@ class NPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): self.collator = OnLabelledCollectionProtocol.get_collator(return_type) def samples_parameters(self): + """ + Return all the necessary parameters to replicate the samples as according to the NPP protocol. + + :return: a list of indexes that realize the NPP sampling + """ indexes = [] for _ in range(self.repeats): index = self.data.uniform_sampling_index(self.sample_size) @@ -222,9 +282,20 @@ class NPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol): return indexes def sample(self, index): + """ + Realizes the sample given the index of the instances. + + :param index: indexes of the instances to select + :return: an instance of :class:`qp.data.LabelledCollection` + """ return self.data.sampling_from_index(index) def total(self): + """ + Returns the number of samples that will be generated (equals to "repeats") + + :return: int + """ return self.repeats @@ -241,12 +312,13 @@ class USimplexPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol) :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised. :param repeats: the number of samples to generate. Default is 100. - :param random_state: allows replicating samples across runs (default None) + :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples + will be the same every time the protocol is called) :param return_type: set to "sample_prev" (default) to get the pairs of (sample, prevalence) at each iteration, or to "labelled_collection" to get instead instances of LabelledCollection """ - def __init__(self, data: LabelledCollection, sample_size=None, repeats=100, random_state=None, + def __init__(self, data: LabelledCollection, sample_size=None, repeats=100, random_state=0, return_type='sample_prev'): super(USimplexPP, self).__init__(random_state) self.data = data @@ -256,6 +328,11 @@ class USimplexPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol) self.collator = OnLabelledCollectionProtocol.get_collator(return_type) def samples_parameters(self): + """ + Return all the necessary parameters to replicate the samples as according to the USimplexPP protocol. + + :return: a list of indexes that realize the USimplexPP sampling + """ indexes = [] for prevs in F.uniform_simplex_sampling(n_classes=self.data.n_classes, size=self.repeats): index = self.data.sampling_index(self.sample_size, *prevs) @@ -263,9 +340,20 @@ class USimplexPP(AbstractStochasticSeededProtocol, OnLabelledCollectionProtocol) return indexes def sample(self, index): + """ + Realizes the sample given the index of the instances. + + :param index: indexes of the instances to select + :return: an instance of :class:`qp.data.LabelledCollection` + """ return self.data.sampling_from_index(index) def total(self): + """ + Returns the number of samples that will be generated (equals to "repeats") + + :return: int + """ return self.repeats @@ -273,17 +361,19 @@ class DomainMixer(AbstractStochasticSeededProtocol): """ Generates mixtures of two domains (A and B) at controlled rates, but preserving the original class prevalence. - :param domainA: - :param domainB: - :param sample_size: - :param repeats: + :param domainA: one domain, an object of :class:`qp.data.LabelledCollection` + :param domainB: another domain, an object of :class:`qp.data.LabelledCollection` + :param sample_size: integer, the number of instances in each sample; if None (default) then it is taken from + qp.environ["SAMPLE_SIZE"]. If this is not set, a ValueError exception is raised. + :param repeats: int, number of samples to draw for every mixture rate :param prevalence: the prevalence to preserv along the mixtures. If specified, should be an array containing one prevalence value (positive float) for each class and summing up to one. If not specified, the prevalence will be taken from the domain A (default). :param mixture_points: an integer indicating the number of points to take from a linear scale (e.g., 21 will generate the mixture points [1, 0.95, 0.9, ..., 0]), or the array of mixture values itself. the specific points - :param random_state: + :param random_state: allows replicating samples across runs (default 0, meaning that the sequence of samples + will be the same every time the protocol is called) """ def __init__( @@ -294,7 +384,7 @@ class DomainMixer(AbstractStochasticSeededProtocol): repeats=1, prevalence=None, mixture_points=11, - random_state=None, + random_state=0, return_type='sample_prev'): super(DomainMixer, self).__init__(random_state) self.A = domainA @@ -319,6 +409,11 @@ class DomainMixer(AbstractStochasticSeededProtocol): self.collator = OnLabelledCollectionProtocol.get_collator(return_type) def samples_parameters(self): + """ + Return all the necessary parameters to replicate the samples as according to the this protocol. + + :return: a list of zipped indexes (from A and B) that realize the sampling + """ indexesA, indexesB = [], [] for propA in self.mixture_points: for _ in range(self.repeats): @@ -331,12 +426,23 @@ class DomainMixer(AbstractStochasticSeededProtocol): return list(zip(indexesA, indexesB)) def sample(self, indexes): + """ + Realizes the sample given a pair of indexes of the instances from A and B. + + :param indexes: indexes of the instances to select from A and B + :return: an instance of :class:`qp.data.LabelledCollection` + """ indexesA, indexesB = indexes sampleA = self.A.sampling_from_index(indexesA) sampleB = self.B.sampling_from_index(indexesB) return sampleA+sampleB def total(self): + """ + Returns the number of samples that will be generated (equals to "repeats * mixture_points") + + :return: int + """ return self.repeats * len(self.mixture_points) diff --git a/quapy/tests/test_protocols.py b/quapy/tests/test_protocols.py index e5d446e..c7e4b15 100644 --- a/quapy/tests/test_protocols.py +++ b/quapy/tests/test_protocols.py @@ -28,13 +28,27 @@ class TestProtocols(unittest.TestCase): self.assertEqual(samples1, samples2) - def test_app_not_replicate(self): - data = mock_labelled_collection() - p = APP(data, sample_size=5, n_prevalences=11) + p = APP(data, sample_size=5, n_prevalences=11) # <- random_state is by default set to 0 samples1 = samples_to_str(p) samples2 = samples_to_str(p) + self.assertEqual(samples1, samples2) + + def test_app_not_replicate(self): + data = mock_labelled_collection() + p = APP(data, sample_size=5, n_prevalences=11, random_state=None) + + samples1 = samples_to_str(p) + samples2 = samples_to_str(p) + + self.assertNotEqual(samples1, samples2) + + p = APP(data, sample_size=5, n_prevalences=11, random_state=42) + samples1 = samples_to_str(p) + p = APP(data, sample_size=5, n_prevalences=11, random_state=0) + samples2 = samples_to_str(p) + self.assertNotEqual(samples1, samples2) def test_app_number(self): @@ -64,13 +78,26 @@ class TestProtocols(unittest.TestCase): self.assertEqual(samples1, samples2) - def test_npp_not_replicate(self): - data = mock_labelled_collection() - p = NPP(data, sample_size=5, repeats=5) + p = NPP(data, sample_size=5, repeats=5) # <- random_state is by default set to 0 samples1 = samples_to_str(p) samples2 = samples_to_str(p) + self.assertEqual(samples1, samples2) + + def test_npp_not_replicate(self): + data = mock_labelled_collection() + p = NPP(data, sample_size=5, repeats=5, random_state=None) + + samples1 = samples_to_str(p) + samples2 = samples_to_str(p) + + self.assertNotEqual(samples1, samples2) + + p = NPP(data, sample_size=5, repeats=5, random_state=42) + samples1 = samples_to_str(p) + p = NPP(data, sample_size=5, repeats=5, random_state=0) + samples2 = samples_to_str(p) self.assertNotEqual(samples1, samples2) def test_kraemer_replicate(self): @@ -82,9 +109,16 @@ class TestProtocols(unittest.TestCase): self.assertEqual(samples1, samples2) + p = USimplexPP(data, sample_size=5, repeats=10) # <- random_state is by default set to 0 + + samples1 = samples_to_str(p) + samples2 = samples_to_str(p) + + self.assertEqual(samples1, samples2) + def test_kraemer_not_replicate(self): data = mock_labelled_collection() - p = USimplexPP(data, sample_size=5, repeats=10) + p = USimplexPP(data, sample_size=5, repeats=10, random_state=None) samples1 = samples_to_str(p) samples2 = samples_to_str(p) @@ -101,10 +135,17 @@ class TestProtocols(unittest.TestCase): self.assertEqual(samples1, samples2) + p = DomainMixer(dataA, dataB, sample_size=10, mixture_points=11) # <- random_state is by default set to 0 + + samples1 = samples_to_str(p) + samples2 = samples_to_str(p) + + self.assertEqual(samples1, samples2) + def test_covariate_shift_not_replicate(self): dataA = mock_labelled_collection('domA') dataB = mock_labelled_collection('domB') - p = DomainMixer(dataA, dataB, sample_size=10, mixture_points=11) + p = DomainMixer(dataA, dataB, sample_size=10, mixture_points=11, random_state=None) samples1 = samples_to_str(p) samples2 = samples_to_str(p)