Merge branch 'localstack' of gitea-s2i2s.isti.cnr.it:moreo/QuaPy into localstack
This commit is contained in:
commit
641228bf62
|
|
@ -20,15 +20,16 @@ jobs:
|
|||
env:
|
||||
QUAPY_TESTS_OMIT_LARGE_DATASETS: True
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v4
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip setuptools wheel
|
||||
python -m pip install -e .[bayes,composable,tests]
|
||||
python -m pip install "qunfold @ git+https://github.com/mirkobunse/qunfold@v0.1.4"
|
||||
python -m pip install -e .[bayes,tests]
|
||||
- name: Test with unittest
|
||||
run: python -m unittest
|
||||
|
||||
|
|
@ -38,15 +39,18 @@ jobs:
|
|||
runs-on: ubuntu-latest
|
||||
if: github.ref == 'refs/heads/master'
|
||||
steps:
|
||||
- uses: actions/checkout@v1
|
||||
- name: Build documentation
|
||||
uses: ammaraskar/sphinx-action@master
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
pre-build-command: |
|
||||
apt-get --allow-releaseinfo-change update -y && apt-get install -y git && git --version
|
||||
python -m pip install --upgrade pip setuptools wheel "jax[cpu]"
|
||||
python -m pip install -e .[composable,neural,docs]
|
||||
docs-folder: "docs/"
|
||||
python-version: 3.11
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip setuptools wheel "jax[cpu]"
|
||||
python -m pip install "qunfold @ git+https://github.com/mirkobunse/qunfold@v0.1.4"
|
||||
python -m pip install -e .[neural,docs]
|
||||
- name: Build documentation
|
||||
run: sphinx-build -M html docs/source docs/build
|
||||
- name: Publish documentation
|
||||
run: |
|
||||
git clone ${{ github.server_url }}/${{ github.repository }}.git --branch gh-pages --single-branch __gh-pages/
|
||||
|
|
|
|||
|
|
@ -1,23 +0,0 @@
|
|||
name: Pylint
|
||||
|
||||
on: [push]
|
||||
|
||||
jobs:
|
||||
build:
|
||||
runs-on: ubuntu-latest
|
||||
strategy:
|
||||
matrix:
|
||||
python-version: ["3.8", "3.9", "3.10"]
|
||||
steps:
|
||||
- uses: actions/checkout@v3
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v3
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pylint
|
||||
- name: Analysing the code with pylint
|
||||
run: |
|
||||
pylint $(git ls-files '*.py')
|
||||
|
|
@ -0,0 +1,126 @@
|
|||
import os
|
||||
from time import time
|
||||
import numpy as np
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
import quapy as qp
|
||||
from KDEy.kdey_devel import KDEyMLauto, KDEyMLauto2, KDEyMLred
|
||||
from LocalStack.method import LocalStackingQuantification, LocalStackingQuantification2
|
||||
from quapy.method.aggregative import PACC, EMQ, KDEyML
|
||||
from quapy.model_selection import GridSearchQ
|
||||
from quapy.protocol import UPP
|
||||
from pathlib import Path
|
||||
|
||||
SEED = 1
|
||||
|
||||
|
||||
|
||||
METHODS = [
|
||||
('PACC', PACC(), {}),
|
||||
('EMQ', EMQ(), {}),
|
||||
('KDEy-ML', KDEyML(), {}),
|
||||
]
|
||||
|
||||
TRANSDUCTIVE_METHODS = [
|
||||
('LSQ', LocalStackingQuantification(EMQ()), {}),
|
||||
('LSQ2', LocalStackingQuantification2(EMQ()), {})
|
||||
]
|
||||
|
||||
def show_results(result_path):
|
||||
import pandas as pd
|
||||
df = pd.read_csv(result_path + '.csv', sep='\t')
|
||||
pd.set_option('display.max_columns', None)
|
||||
pd.set_option('display.max_rows', None)
|
||||
pd.set_option('display.width', 1000) # Ajustar el ancho máximo
|
||||
pv = df.pivot_table(index='Dataset', columns="Method", values=["MAE"], margins=True)
|
||||
print(pv)
|
||||
pv = df.pivot_table(index='Dataset', columns="Method", values=["MRAE"], margins=True)
|
||||
print(pv)
|
||||
pv = df.pivot_table(index='Dataset', columns="Method", values=["KLD"], margins=True)
|
||||
print(pv)
|
||||
pv = df.pivot_table(index='Dataset', columns="Method", values=["TR-TIME"], margins=True)
|
||||
print(pv)
|
||||
pv = df.pivot_table(index='Dataset', columns="Method", values=["TE-TIME"], margins=True)
|
||||
print(pv)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
|
||||
qp.environ['SAMPLE_SIZE'] = 500
|
||||
qp.environ['N_JOBS'] = -1
|
||||
n_bags_val = 25
|
||||
n_bags_test = 100
|
||||
result_dir = f'results_quantification/localstack'
|
||||
|
||||
os.makedirs(result_dir, exist_ok=True)
|
||||
|
||||
global_result_path = f'{result_dir}/allmethods'
|
||||
with open(global_result_path + '.csv', 'wt') as csv:
|
||||
csv.write(f'Method\tDataset\tMAE\tMRAE\tKLD\tTR-TIME\tTE-TIME\n')
|
||||
|
||||
for method_name, quantifier, param_grid in METHODS + TRANSDUCTIVE_METHODS:
|
||||
|
||||
print('Init method', method_name)
|
||||
|
||||
with open(global_result_path + '.csv', 'at') as csv:
|
||||
for dataset in qp.datasets.UCI_MULTICLASS_DATASETS:
|
||||
print('init', dataset)
|
||||
|
||||
# run_experiment(global_result_path, method_name, quantifier, param_grid, dataset)
|
||||
local_result_path = os.path.join(Path(global_result_path).parent, method_name + '_' + dataset + '.dataframe')
|
||||
|
||||
if os.path.exists(local_result_path):
|
||||
print(f'result file {local_result_path} already exist; skipping')
|
||||
report = qp.util.load_report(local_result_path)
|
||||
|
||||
else:
|
||||
with qp.util.temp_seed(SEED):
|
||||
|
||||
data = qp.datasets.fetch_UCIMulticlassDataset(dataset, verbose=True)
|
||||
train, test = data.train_test
|
||||
|
||||
transductive_names = [name for (name, *_) in TRANSDUCTIVE_METHODS]
|
||||
|
||||
if method_name not in transductive_names:
|
||||
if len(param_grid) == 0:
|
||||
t_init = time()
|
||||
quantifier.fit(train)
|
||||
train_time = time() - t_init
|
||||
else:
|
||||
# model selection (train)
|
||||
train, val = train.split_stratified(random_state=SEED)
|
||||
protocol = UPP(val, repeats=n_bags_val)
|
||||
modsel = GridSearchQ(
|
||||
quantifier, param_grid, protocol, refit=True, n_jobs=-1, verbose=1, error='mae'
|
||||
)
|
||||
t_init = time()
|
||||
try:
|
||||
modsel.fit(train)
|
||||
print(f'best params {modsel.best_params_}')
|
||||
print(f'best score {modsel.best_score_}')
|
||||
quantifier = modsel.best_model()
|
||||
except:
|
||||
print('something went wrong... trying to fit the default model')
|
||||
quantifier.fit(train)
|
||||
train_time = time() - t_init
|
||||
else:
|
||||
# transductive
|
||||
t_init = time()
|
||||
quantifier.fit(train) # <-- nothing actually (proyects the X into posteriors only)
|
||||
train_time = time() - t_init
|
||||
|
||||
# test
|
||||
t_init = time()
|
||||
protocol = UPP(test, repeats=n_bags_test)
|
||||
report = qp.evaluation.evaluation_report(
|
||||
quantifier, protocol, error_metrics=['mae', 'mrae', 'kld'], verbose=True
|
||||
)
|
||||
test_time = time() - t_init
|
||||
report['tr_time'] = train_time
|
||||
report['te_time'] = test_time
|
||||
report.to_csv(local_result_path)
|
||||
|
||||
means = report.mean(numeric_only=True)
|
||||
csv.write(f'{method_name}\t{dataset}\t{means["mae"]:.5f}\t{means["mrae"]:.5f}\t{means["kld"]:.5f}\t{means["tr_time"]:.3f}\t{means["te_time"]:.3f}\n')
|
||||
csv.flush()
|
||||
|
||||
show_results(global_result_path)
|
||||
|
|
@ -0,0 +1,112 @@
|
|||
import numpy as np
|
||||
import quapy as qp
|
||||
from sklearn.multioutput import MultiOutputRegressor
|
||||
from sklearn.svm import SVR
|
||||
|
||||
from data import LabelledCollection
|
||||
from quapy.method.base import BaseQuantifier
|
||||
from quapy.method.aggregative import AggregativeSoftQuantifier
|
||||
|
||||
|
||||
class LocalStackingQuantification(BaseQuantifier):
|
||||
|
||||
def __init__(self, surrogate_quantifier, n_samples_gen=200, n_samples_sel=50, comparison_measure='ae', random_state=None):
|
||||
assert isinstance(surrogate_quantifier, AggregativeSoftQuantifier), \
|
||||
f'the surrogate quantifier must be of type {AggregativeSoftQuantifier.__class__.__name__}'
|
||||
self.surrogate_quantifier = surrogate_quantifier
|
||||
self.n_samples_gen = n_samples_gen
|
||||
self.n_samples_sel = n_samples_sel
|
||||
self.comparison_measure = qp.error.from_name(comparison_measure)
|
||||
self.random_state = random_state
|
||||
|
||||
def fit(self, data: LabelledCollection):
|
||||
train, val = data.split_stratified()
|
||||
self.surrogate_quantifier.fit(train)
|
||||
self.val_data = val
|
||||
return self
|
||||
|
||||
def normalize(self, out_simplex:np.ndarray):
|
||||
in_simplex = out_simplex/out_simplex.sum()
|
||||
return in_simplex
|
||||
|
||||
def quantify(self, instances: np.ndarray):
|
||||
assert hasattr(self, 'val_data'), 'quantify called before fit'
|
||||
pred_prevs = self.surrogate_quantifier.quantify(instances)
|
||||
test_size = instances.shape[0]
|
||||
|
||||
samples = []
|
||||
samples_pred_prevs = []
|
||||
samples_distance = []
|
||||
for i in range(self.n_samples_gen):
|
||||
sample_i = self.val_data.sampling(test_size, *pred_prevs, random_state=self.random_state)
|
||||
pred_prev_sample_i = self.surrogate_quantifier.quantify(sample_i.X)
|
||||
err_dist = self.comparison_measure(pred_prevs, pred_prev_sample_i)
|
||||
|
||||
samples.append(sample_i)
|
||||
samples_pred_prevs.append(pred_prev_sample_i)
|
||||
samples_distance.append(err_dist)
|
||||
|
||||
ord_distances = np.argsort(samples_distance)
|
||||
samples_sel = np.asarray(samples)[ord_distances][:self.n_samples_sel]
|
||||
samples_pred_prevs_sel = np.asarray(samples_pred_prevs)[ord_distances][:self.n_samples_sel]
|
||||
|
||||
reg = MultiOutputRegressor(SVR())
|
||||
reg_X = samples_pred_prevs_sel
|
||||
reg_y = [s.prevalence() for s in samples_sel]
|
||||
reg.fit(reg_X, reg_y)
|
||||
|
||||
corrected_prev = reg.predict([pred_prevs])[0]
|
||||
|
||||
corrected_prev = self.normalize(corrected_prev)
|
||||
return corrected_prev
|
||||
|
||||
|
||||
|
||||
class LocalStackingQuantification2(BaseQuantifier):
|
||||
|
||||
"""
|
||||
Este en vez de seleccionar samples de training para los que la prevalencia predicha se parece a la prevalencia
|
||||
predica en test, saca directamente samples de training con la prevalencia predicha en test
|
||||
"""
|
||||
|
||||
def __init__(self, surrogate_quantifier, n_samples_gen=200, n_samples_sel=50, comparison_measure='ae', random_state=None):
|
||||
assert isinstance(surrogate_quantifier, AggregativeSoftQuantifier), \
|
||||
f'the surrogate quantifier must be of type {AggregativeSoftQuantifier.__class__.__name__}'
|
||||
self.surrogate_quantifier = surrogate_quantifier
|
||||
self.n_samples_gen = n_samples_gen
|
||||
self.n_samples_sel = n_samples_sel
|
||||
self.comparison_measure = qp.error.from_name(comparison_measure)
|
||||
self.random_state = random_state
|
||||
|
||||
def fit(self, data: LabelledCollection):
|
||||
train, val = data.split_stratified()
|
||||
self.surrogate_quantifier.fit(train)
|
||||
self.val_data = val
|
||||
return self
|
||||
|
||||
def normalize(self, out_simplex:np.ndarray):
|
||||
in_simplex = out_simplex/out_simplex.sum()
|
||||
return in_simplex
|
||||
|
||||
def quantify(self, instances: np.ndarray):
|
||||
assert hasattr(self, 'val_data'), 'quantify called before fit'
|
||||
pred_prevs = self.surrogate_quantifier.quantify(instances)
|
||||
test_size = instances.shape[0]
|
||||
|
||||
samples = []
|
||||
samples_pred_prevs = []
|
||||
for i in range(self.n_samples_gen):
|
||||
sample_i = self.val_data.sampling(test_size, *pred_prevs, random_state=self.random_state)
|
||||
pred_prev_sample_i = self.surrogate_quantifier.quantify(sample_i.X)
|
||||
samples.append(sample_i)
|
||||
samples_pred_prevs.append(pred_prev_sample_i)
|
||||
|
||||
reg = MultiOutputRegressor(SVR())
|
||||
reg_X = samples_pred_prevs
|
||||
reg_y = [s.prevalence() for s in samples]
|
||||
reg.fit(reg_X, reg_y)
|
||||
|
||||
corrected_prev = reg.predict([pred_prevs])[0]
|
||||
|
||||
corrected_prev = self.normalize(corrected_prev)
|
||||
return corrected_prev
|
||||
|
|
@ -11,9 +11,14 @@ import sys
|
|||
from os.path import join
|
||||
quapy_path = join(pathlib.Path(__file__).parents[2].resolve().as_posix(), 'quapy')
|
||||
wiki_path = join(pathlib.Path(__file__).parents[0].resolve().as_posix(), 'wiki')
|
||||
source_path = pathlib.Path(__file__).parents[2].resolve().as_posix()
|
||||
print(f'quapy path={quapy_path}')
|
||||
print(f'quapy source path={source_path}')
|
||||
sys.path.insert(0, quapy_path)
|
||||
sys.path.insert(0, wiki_path)
|
||||
sys.path.insert(0, source_path)
|
||||
|
||||
print(sys.path)
|
||||
|
||||
|
||||
project = 'QuaPy: A Python-based open-source framework for quantification'
|
||||
|
|
|
|||
|
|
@ -447,7 +447,7 @@ The [](quapy.method.composable) module allows the composition of quantification
|
|||
```sh
|
||||
pip install --upgrade pip setuptools wheel
|
||||
pip install "jax[cpu]"
|
||||
pip install quapy[composable]
|
||||
pip install "qunfold @ git+https://github.com/mirkobunse/qunfold@v0.1.4"
|
||||
```
|
||||
|
||||
### Basics
|
||||
|
|
|
|||
|
|
@ -2,6 +2,13 @@
|
|||
This example illustrates the composition of quantification methods from
|
||||
arbitrary loss functions and feature transformations. It will extend the basic
|
||||
example on the usage of quapy with this composition.
|
||||
|
||||
This example requires the installation of qunfold, the back-end of QuaPy's
|
||||
composition module:
|
||||
|
||||
pip install --upgrade pip setuptools wheel
|
||||
pip install "jax[cpu]"
|
||||
pip install "qunfold @ git+https://github.com/mirkobunse/qunfold@v0.1.4"
|
||||
"""
|
||||
|
||||
import numpy as np
|
||||
|
|
|
|||
|
|
@ -1,45 +1,57 @@
|
|||
"""This module allows the composition of quantification methods from loss functions and feature transformations. This functionality is realized through an integration of the qunfold package: https://github.com/mirkobunse/qunfold."""
|
||||
|
||||
import qunfold
|
||||
from qunfold.quapy import QuaPyWrapper
|
||||
from qunfold.sklearn import CVClassifier
|
||||
from qunfold import (
|
||||
LeastSquaresLoss, # losses
|
||||
BlobelLoss,
|
||||
EnergyLoss,
|
||||
HellingerSurrogateLoss,
|
||||
CombinedLoss,
|
||||
TikhonovRegularization,
|
||||
TikhonovRegularized,
|
||||
ClassTransformer, # transformers
|
||||
HistogramTransformer,
|
||||
DistanceTransformer,
|
||||
KernelTransformer,
|
||||
EnergyKernelTransformer,
|
||||
LaplacianKernelTransformer,
|
||||
GaussianKernelTransformer,
|
||||
GaussianRFFKernelTransformer,
|
||||
)
|
||||
_import_error_message = """qunfold, the back-end of quapy.method.composable, is not properly installed.
|
||||
|
||||
__all__ = [ # control public members, e.g., for auto-documentation in sphinx; omit QuaPyWrapper
|
||||
"ComposableQuantifier",
|
||||
"CVClassifier",
|
||||
"LeastSquaresLoss",
|
||||
"BlobelLoss",
|
||||
"EnergyLoss",
|
||||
"HellingerSurrogateLoss",
|
||||
"CombinedLoss",
|
||||
"TikhonovRegularization",
|
||||
"TikhonovRegularized",
|
||||
"ClassTransformer",
|
||||
"HistogramTransformer",
|
||||
"DistanceTransformer",
|
||||
"KernelTransformer",
|
||||
"EnergyKernelTransformer",
|
||||
"LaplacianKernelTransformer",
|
||||
"GaussianKernelTransformer",
|
||||
"GaussianRFFKernelTransformer",
|
||||
]
|
||||
To fix this error, call:
|
||||
|
||||
pip install --upgrade pip setuptools wheel
|
||||
pip install "jax[cpu]"
|
||||
pip install "qunfold @ git+https://github.com/mirkobunse/qunfold@v0.1.4"
|
||||
"""
|
||||
|
||||
try:
|
||||
import qunfold
|
||||
from qunfold.quapy import QuaPyWrapper
|
||||
from qunfold.sklearn import CVClassifier
|
||||
from qunfold import (
|
||||
LeastSquaresLoss, # losses
|
||||
BlobelLoss,
|
||||
EnergyLoss,
|
||||
HellingerSurrogateLoss,
|
||||
CombinedLoss,
|
||||
TikhonovRegularization,
|
||||
TikhonovRegularized,
|
||||
ClassTransformer, # transformers
|
||||
HistogramTransformer,
|
||||
DistanceTransformer,
|
||||
KernelTransformer,
|
||||
EnergyKernelTransformer,
|
||||
LaplacianKernelTransformer,
|
||||
GaussianKernelTransformer,
|
||||
GaussianRFFKernelTransformer,
|
||||
)
|
||||
|
||||
__all__ = [ # control public members, e.g., for auto-documentation in sphinx; omit QuaPyWrapper
|
||||
"ComposableQuantifier",
|
||||
"CVClassifier",
|
||||
"LeastSquaresLoss",
|
||||
"BlobelLoss",
|
||||
"EnergyLoss",
|
||||
"HellingerSurrogateLoss",
|
||||
"CombinedLoss",
|
||||
"TikhonovRegularization",
|
||||
"TikhonovRegularized",
|
||||
"ClassTransformer",
|
||||
"HistogramTransformer",
|
||||
"DistanceTransformer",
|
||||
"KernelTransformer",
|
||||
"EnergyKernelTransformer",
|
||||
"LaplacianKernelTransformer",
|
||||
"GaussianKernelTransformer",
|
||||
"GaussianRFFKernelTransformer",
|
||||
]
|
||||
except ImportError as e:
|
||||
raise ImportError(_import_error_message) from e
|
||||
|
||||
def ComposableQuantifier(loss, transformer, **kwargs):
|
||||
"""A generic quantification / unfolding method that solves a linear system of equations.
|
||||
|
|
|
|||
Loading…
Reference in New Issue