experimental method ave-pool, not working due to the fact that onevsall is aggregative and ave-pool is not

NewMethods/methods.py

@@ -1,7 +1,15 @@
-from typing import Union
+import numpy as np
+from sklearn.decomposition import PCA
+from sklearn.preprocessing import StandardScaler
+
 import quapy as qp
+from typing import Union
+
+from quapy.data import LabelledCollection
+from quapy.method.base import BaseQuantifier, BinaryQuantifier
 from quapy.method.aggregative import PACC, EMQ, HDy
 import quapy.functional as F
+from tqdm import tqdm
 
 
 class PACCSLD(PACC):
@@ -35,3 +43,83 @@ class HDySLD(HDy):
     def aggregate(self, classif_posteriors):
         priors, posteriors = EMQ.EM(self.train_prevalence, classif_posteriors, epsilon=1e-4)
         return super(HDySLD, self).aggregate(posteriors)
+
+
+
+class AveragePoolQuantification(BinaryQuantifier):
+    def __init__(self, learner, sample_size, trials, n_components=-1, zscore=False):
+        self.learner = learner
+        self.sample_size = sample_size
+        self.trials = trials
+
+        self.do_zscore = zscore
+        self.zscore = StandardScaler() if self.do_zscore else None
+
+        self.do_pca = n_components>0
+        self.pca = PCA(n_components) if self.do_pca else None
+
+    def fit(self, data: LabelledCollection):
+        training, validation = data.split_stratified(train_prop=0.7)
+
+        X, y = [], []
+
+        nprevpoints = F.get_nprevpoints_approximation(self.trials, data.n_classes)
+        for sample in tqdm(
+                training.artificial_sampling_generator(self.sample_size, n_prevalences=nprevpoints, repeats=1),
+                desc='generating averages'
+        ):
+            X.append(sample.instances.mean(axis=0))
+            y.append(sample.prevalence()[1])
+        while len(X) < self.trials:
+            sample = training.sampling(self.sample_size, F.uniform_simplex_sampling(data.n_classes))
+            X.append(sample.instances.mean(axis=0))
+            y.append(sample.prevalence())
+        X = np.asarray(np.vstack(X))
+        y = np.asarray(y)
+
+        if self.do_pca:
+            X = self.pca.fit_transform(X)
+            print(X.shape)
+
+        if self.do_zscore:
+            X = self.zscore.fit_transform(X)
+
+        print('training regressor...')
+        self.regressor = self.learner.fit(X, y)
+
+        # correction at 0:
+        print('getting corrections...')
+        X0 = np.asarray(np.vstack([validation.sampling(self.sample_size, 0., shuffle=False).instances.mean(axis=0) for _ in range(100)]))
+        X1 = np.asarray(np.vstack([validation.sampling(self.sample_size, 1., shuffle=False).instances.mean(axis=0) for _ in range(100)]))
+
+        if self.do_pca:
+            X0 = self.pca.transform(X0)
+            X1 = self.pca.transform(X1)
+
+        if self.do_zscore:
+            X0 = self.zscore.transform(X0)
+            X1 = self.zscore.transform(X1)
+
+        self.correction_0 = self.regressor.predict(X0).mean()
+        self.correction_1 = self.regressor.predict(X1).mean()
+
+        print('correction-0', self.correction_0)
+        print('correction-1', self.correction_1)
+        print('done')
+
+    def quantify(self, instances):
+        ave = np.asarray(instances.mean(axis=0))
+
+        if self.do_pca:
+            ave = self.pca.transform(ave)
+        if self.do_zscore:
+            ave = self.zscore.transform(ave)
+        phat = self.regressor.predict(ave).item()
+        phat = np.clip((phat-self.correction_0)/(self.correction_1-self.correction_0), 0, 1)
+        return np.asarray([1-phat, phat])
+
+    def set_params(self, **parameters):
+        self.learner.set_params(**parameters)
+
+    def get_params(self, deep=True):
+        return self.learner.get_params(deep=deep)

TweetSentQuant/gen_tables.py

@@ -32,6 +32,7 @@ nice = {
     'quanet': 'QuaNet',
     'hdy': 'HDy',
     'dys': 'DyS',
+    'epaccmaeptr': 'E(PACC)$_\mathrm{Ptr}$',
     'svmperf':'',
     'sanders': 'Sanders',
     'semeval13': 'SemEval13',
@@ -116,7 +117,7 @@ if __name__ == '__main__':
     datasets = qp.datasets.TWITTER_SENTIMENT_DATASETS_TEST
     evaluation_measures = [qp.error.ae, qp.error.rae]
     gao_seb_methods = ['cc', 'acc', 'pcc', 'pacc', 'sld', 'svmq', 'svmkld', 'svmnkld']
-    new_methods = ['hdy']
+    new_methods = ['hdy', 'quanet', 'epaccptr']
 
     gao_seb_ranks, gao_seb_results = get_ranks_from_Gao_Sebastiani()
 

quapy/method/aggregative.py

@@ -547,8 +547,6 @@ class OneVsAll(AggregativeQuantifier):
         else:
             predictions = self.classify(X)
         return self.aggregate(predictions)
-        #prevalences = self.__parallel(self._delayed_binary_quantify, X)
-        #return F.normalize_prevalence(prevalences)
 
     def __parallel(self, func, *args, **kwargs):
         return np.asarray(

test.py

@@ -1,10 +1,12 @@
 from sklearn.linear_model import LogisticRegression
 from sklearn.model_selection import GridSearchCV
-from sklearn.svm import LinearSVC
+from sklearn.svm import LinearSVC, LinearSVR
 import quapy as qp
 import quapy.functional as F
 import sys
 import numpy as np
+
+from NewMethods.methods import AveragePoolQuantification
 from classification.methods import PCALR
 from classification.neural import NeuralClassifierTrainer, CNNnet
 from quapy.model_selection import GridSearchQ
@@ -29,7 +31,7 @@ if binary:
 
 else:
     dataset = qp.datasets.fetch_twitter('hcr', for_model_selection=False, min_df=10, pickle=True)
-    dataset.training = dataset.training.sampling(sample_size, 0.2, 0.5, 0.3)
+    #dataset.training = dataset.training.sampling(sample_size, 0.2, 0.5, 0.3)
 
 print(f'dataset loaded: #training={len(dataset.training)} #test={len(dataset.test)}')
 
@@ -51,14 +53,17 @@ print(f'dataset loaded: #training={len(dataset.training)} #test={len(dataset.tes
 #model = qp.method.meta.QuaNet(learner, sample_size, device='cpu')
 
 #learner = GridSearchCV(LogisticRegression(max_iter=1000), param_grid=param_grid, n_jobs=-1, verbose=1)
-learner = LogisticRegression(max_iter=1000)
+#learner = LogisticRegression(max_iter=1000)
 # model = qp.method.aggregative.ClassifyAndCount(learner)
 
 
-model = qp.method.meta.EPACC(learner, size=10, red_size=5,
-                             param_grid={'C':[1,10,100]},
-                             optim='mae', param_mod_sel={'sample_size':100, 'n_prevpoints':21, 'n_repetitions':5},
-                             policy='ptr', n_jobs=1)
+#model = qp.method.meta.EPACC(learner, size=10, red_size=5,
+#                             param_grid={'C':[1,10,100]},
+#                             optim='mae', param_mod_sel={'sample_size':100, 'n_prevpoints':21, 'n_repetitions':5},
+#                             policy='ptr', n_jobs=1)
+regressor = LinearSVR(max_iter=10000)
+param_grid = {'C': np.logspace(-1,3,5)}
+model = AveragePoolQuantification(regressor, sample_size, trials=5000, n_components=500, zscore=False)
 
 #model = qp.method.meta.EHDy(learner, param_grid=param_grid, optim='mae',
 #                           sample_size=sample_size, eval_budget=max_evaluations//10, n_jobs=-1)
@@ -75,7 +80,7 @@ if qp.isbinary(model) and not qp.isbinary(dataset):
 print(f'fitting model {model.__class__.__name__}')
 #train, val = dataset.training.split_stratified(0.6)
 #model.fit(train, val_split=val)
-model.fit(dataset.training, val_split=dataset.test)
+model.fit(dataset.training)
 
 
 
@@ -112,7 +117,7 @@ for error in qp.error.QUANTIFICATION_ERROR:
     score = error(true_prev, estim_prev)
     print(f'{error.__name__}={score:.5f}')
 
-sys.exit(0)
+#sys.exit(0)
 # Model selection and Evaluation according to the artificial sampling protocol
 # ----------------------------------------------------------------------------
 
@@ -123,7 +128,7 @@ model_selection = GridSearchQ(model,
                               error='mae',
                               refit=True,
                               verbose=True,
-                              timeout=4)
+                              timeout=60*60)
 
 model = model_selection.fit(dataset.training, val_split=0.3)
 #model = model_selection.fit(train, validation=val)