moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #2 from HLT-ISTI/packaging 

pip package
This commit is contained in:
Andrea Esuli 2021-05-10 13:37:48 +02:00 committed by GitHub
parent c280c03fdb 79fbbd9d80
commit 37defb9291
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 204 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
TODO.txt
View File

@ -2,7 +2,6 @@ Packaging:
==========================================
Documentation with sphinx
Document methods with paper references
allow for "pip install"
unit-tests
New features:

2
quapy/__init__.py
View File

@ -10,7 +10,7 @@ from . import model_selection
from . import classification
from quapy.method.base import isprobabilistic, isaggregative
__version__ = '0.1'
__version__ = '0.1.4'
environ = {
'SAMPLE_SIZE': None,

61
quapy/method/meta.py
View File

@ -1,28 +1,32 @@
from copy import deepcopy
from typing import Union
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import f1_score, make_scorer, accuracy_score
from sklearn.model_selection import GridSearchCV, cross_val_predict
from tqdm import tqdm
import numpy as np
from joblib import Parallel, delayed
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import GridSearchCV, cross_val_predict
import quapy as qp
from quapy.data import LabelledCollection
from quapy import functional as F
from quapy.data import LabelledCollection
from quapy.evaluation import evaluate
from quapy.model_selection import GridSearchQ
from . import neural
from .base import BaseQuantifier
from quapy.method.aggregative import CC, ACC, PCC, PACC, HDy, EMQ
QuaNet = neural.QuaNetTrainer
try:
from . import neural
except ModuleNotFoundError:
neural = None
from .base import BaseQuantifier
from quapy.method.aggregative import CC, ACC, PACC, HDy, EMQ
if neural:
QuaNet = neural.QuaNetTrainer
else:
QuaNet = "QuaNet is not available due to missing torch package"
class Ensemble(BaseQuantifier):
VALID_POLICIES = {'ave', 'ptr', 'ds'} | qp.error.QUANTIFICATION_ERROR_NAMES
"""
@ -65,9 +69,9 @@ class Ensemble(BaseQuantifier):
if self.verbose:
print('[Ensemble]' + msg)
def fit(self, data: qp.data.LabelledCollection, val_split: Union[qp.data.LabelledCollection, float]=None):
def fit(self, data: qp.data.LabelledCollection, val_split: Union[qp.data.LabelledCollection, float] = None):
self.sout('Fit')
if self.policy=='ds' and not data.binary:
if self.policy == 'ds' and not data.binary:
raise ValueError(f'ds policy is only defined for binary quantification, but this dataset is not binary')
if val_split is None:
val_split = self.val_split
@ -132,7 +136,7 @@ class Ensemble(BaseQuantifier):
tests = [m[3] for m in self.ensemble]
scores = []
for i, model in enumerate(self.ensemble):
scores.append(evaluate(model[0], tests[:i] + tests[i+1:], error, self.n_jobs))
scores.append(evaluate(model[0], tests[:i] + tests[i + 1:], error, self.n_jobs))
order = np.argsort(scores)
self.ensemble = _select_k(self.ensemble, order, k=self.red_size)
@ -168,7 +172,7 @@ class Ensemble(BaseQuantifier):
lr_base = LogisticRegression(class_weight='balanced', max_iter=1000)
optim = GridSearchCV(
lr_base, param_grid={'C': np.logspace(-4,4,9)}, cv=5, n_jobs=self.n_jobs, refit=True
lr_base, param_grid={'C': np.logspace(-4, 4, 9)}, cv=5, n_jobs=self.n_jobs, refit=True
).fit(X, y)
posteriors = cross_val_predict(
@ -204,8 +208,8 @@ class Ensemble(BaseQuantifier):
def get_probability_distribution(posterior_probabilities, bins=8):
assert posterior_probabilities.shape[1]==2, 'the posterior probabilities do not seem to be for a binary problem'
posterior_probabilities = posterior_probabilities[:,1] # take the positive posteriors only
assert posterior_probabilities.shape[1] == 2, 'the posterior probabilities do not seem to be for a binary problem'
posterior_probabilities = posterior_probabilities[:, 1] # take the positive posteriors only
distribution, _ = np.histogram(posterior_probabilities, bins=bins, range=(0, 1), density=True)
return distribution
@ -223,7 +227,7 @@ def _delayed_new_instance(args):
if val_split is not None:
if isinstance(val_split, float):
assert 0 < val_split < 1, 'val_split should be in (0,1)'
data, val_split = data.split_stratified(train_prop=1-val_split)
data, val_split = data.split_stratified(train_prop=1 - val_split)
sample_index = data.sampling_index(sample_size, *prev)
sample = data.sampling_from_index(sample_index)
@ -255,7 +259,7 @@ def _draw_simplex(ndim, min_val, max_trials=100):
:return: a sample from the ndim-dimensional simplex that is uniform in S(ndim)-R where S(ndim) is the simplex
and R is the simplex subset containing dimensions lower than min_val
"""
if min_val >= 1/ndim:
if min_val >= 1 / ndim:
raise ValueError(f'no sample can be draw from the {ndim}-dimensional simplex so that '
f'all its values are >={min_val} (try with a larger value for min_pos)')
trials = 0
@ -300,14 +304,15 @@ def _check_error(error):
f'the name of an error function in {qp.error.ERROR_NAMES}')
def ensembleFactory(learner, base_quantifier_class, param_grid=None, optim=None, param_model_sel:dict=None, **kwargs):
if optim is not None:
if param_grid is None:
raise ValueError(f'param_grid is None but optim was requested.')
if param_model_sel is None:
raise ValueError(f'param_model_sel is None but optim was requested.')
error = _check_error(optim)
return _instantiate_ensemble(learner, base_quantifier_class, param_grid, error, param_model_sel, **kwargs)
def ensembleFactory(learner, base_quantifier_class, param_grid=None, optim=None, param_model_sel: dict = None,
**kwargs):
if optim is not None:
if param_grid is None:
raise ValueError(f'param_grid is None but optim was requested.')
if param_model_sel is None:
raise ValueError(f'param_model_sel is None but optim was requested.')
error = _check_error(optim)
return _instantiate_ensemble(learner, base_quantifier_class, param_grid, error, param_model_sel, **kwargs)
def ECC(learner, param_grid=None, optim=None, param_mod_sel=None, **kwargs):
@ -327,4 +332,4 @@ def EHDy(learner, param_grid=None, optim=None, param_mod_sel=None, **kwargs):
def EEMQ(learner, param_grid=None, optim=None, param_mod_sel=None, **kwargs):
return ensembleFactory(learner, EMQ, param_grid, optim, param_mod_sel, **kwargs)
return ensembleFactory(learner, EMQ, param_grid, optim, param_mod_sel, **kwargs)

6
quapy/tests/test_methods.py
View File

@ -100,6 +100,12 @@ def test_ensemble_method(base_method, learner, dataset: Dataset, policy):
def test_quanet_method():
try:
import quapy.classification.neural
except ModuleNotFoundError:
print('skipping QuaNet test due to missing torch package')
return
dataset = qp.datasets.fetch_reviews('kindle', pickle=True)
dataset = Dataset(dataset.training.sampling(100, *dataset.training.prevalence()),
dataset.test.sampling(100, *dataset.test.prevalence()))

164
setup.py Normal file
View File

@ -0,0 +1,164 @@
from setuptools import setup, find_packages
import pathlib
here = pathlib.Path(__file__).parent.resolve()
long_description = (here / 'README.md').read_text(encoding='utf-8')
def get_version(rel_path):
init_content = (here / rel_path).read_text(encoding='utf-8')
for line in init_content.split('\n'):
if line.startswith('__version__'):
delim = '"' if '"' in line else "'"
return line.split(delim)[1]
else:
raise RuntimeError("Unable to find version string.")
# Arguments marked as "Required" below must be included for upload to PyPI.
# Fields marked as "Optional" may be commented out.
setup(
# This is the name of your project. The first time you publish this
# package, this name will be registered for you. It will determine how
# users can install this project, e.g.:
#
# $ pip install sampleproject
#
# And where it will live on PyPI: https://pypi.org/project/sampleproject/
#
# There are some restrictions on what makes a valid project name
# specification here:
# https://packaging.python.org/specifications/core-metadata/#name
name='QuaPy', # Required
# Versions should comply with PEP 440:
# https://www.python.org/dev/peps/pep-0440/
#
# For a discussion on single-sourcing the version across setup.py and the
# project code, see
# https://packaging.python.org/en/latest/single_source_version.html
version=get_version("quapy/__init__.py"), # Required
# This is a one-line description or tagline of what your project does. This
# corresponds to the "Summary" metadata field:
# https://packaging.python.org/specifications/core-metadata/#summary
description='QuaPy: a framework for Quantification in Python', # Optional
# This is an optional longer description of your project that represents
# the body of text which users will see when they visit PyPI.
#
# Often, this is the same as your README, so you can just read it in from
# that file directly (as we have already done above)
#
# This field corresponds to the "Description" metadata field:
# https://packaging.python.org/specifications/core-metadata/#description-optional
long_description=long_description, # Optional
# Denotes that our long_description is in Markdown; valid values are
# text/plain, text/x-rst, and text/markdown
#
# Optional if long_description is written in reStructuredText (rst) but
# required for plain-text or Markdown; if unspecified, "applications should
# attempt to render [the long_description] as text/x-rst; charset=UTF-8 and
# fall back to text/plain if it is not valid rst" (see link below)
#
# This field corresponds to the "Description-Content-Type" metadata field:
# https://packaging.python.org/specifications/core-metadata/#description-content-type-optional
long_description_content_type='text/markdown', # Optional (see note above)
# This should be a valid link to your project's main homepage.
#
# This field corresponds to the "Home-Page" metadata field:
# https://packaging.python.org/specifications/core-metadata/#home-page-optional
url='https://github.com/HLT-ISTI/QuaPy', # Optional
maintainer='Alejandro Moreo',
maintainer_email='alejandro.moreo@isti.cnr.it',
classifiers=[
'Development Status :: 4 - Beta',
'Intended Audience :: Developers',
'Intended Audience :: Science/Research',
'Programming Language :: Python',
'Topic :: Software Development',
'Topic :: Scientific/Engineering',
'License :: OSI Approved :: BSD License',
'Programming Language :: Python :: 3',
'Programming Language :: Python :: 3.6',
'Programming Language :: Python :: 3.7',
'Programming Language :: Python :: 3.8',
'Programming Language :: Python :: 3.9',
'Programming Language :: Python :: 3 :: Only',
],
keywords='machine learning, quantification, classification, prevalence estimation, priors estimate',
# When your source code is in a subdirectory under the project root, e.g.
# `src/`, it is necessary to specify the `package_dir` argument.
#package_dir={'': 'src'}, # Optional
# You can just specify package directories manually here if your project is
# simple. Or you can use find_packages().
#
# Alternatively, if you just want to distribute a single Python file, use
# the `py_modules` argument instead as follows, which will expect a file
# called `my_module.py` to exist:
#
# py_modules=["my_module"],
#
packages=find_packages(include=['quapy', 'quapy.*']), # Required
python_requires='>=3.6, <4',
install_requires=['scikit-learn', 'pandas', 'tqdm', 'matplotlib'],
# List additional groups of dependencies here (e.g. development
# dependencies). Users will be able to install these using the "extras"
# syntax, for example:
#
# $ pip install sampleproject[dev]
#
# Similar to `install_requires` above, these must be valid existing
# projects.
# extras_require={ # Optional
# 'dev': ['check-manifest'],
# 'test': ['coverage'],
# },
# If there are data files included in your packages that need to be
# installed, specify them here.
# package_data={ # Optional
# 'sample': ['package_data.dat'],
# },
# Although 'package_data' is the preferred approach, in some case you may
# need to place data files outside of your packages. See:
# http://docs.python.org/distutils/setupscript.html#installing-additional-files
#
# In this case, 'data_file' will be installed into '<sys.prefix>/my_data'
# data_files=[('my_data', ['data/data_file'])], # Optional
# To provide executable scripts, use entry points in preference to the
# "scripts" keyword. Entry points provide cross-platform support and allow
# `pip` to create the appropriate form of executable for the target
# platform.
#
# For example, the following would provide a command called `sample` which
# executes the function `main` from this package when invoked:
# entry_points={ # Optional
# 'console_scripts': [
# 'sample=sample:main',
# ],
# },
project_urls={ # Optional
'Contributors': 'https://github.com/HLT-ISTI/QuaPy/graphs/contributors',
'Bug Reports': 'https://github.com/HLT-ISTI/QuaPy/issues',
'Documentation': 'https://github.com/HLT-ISTI/QuaPy/wiki',
'Source': 'https://github.com/HLT-ISTI/QuaPy/',
},
)