print "Y_train total:", len(y[train_index]) print "Y_train positive:", np.sum(y[train_index]) print "Ratio of positive in train instances", np.sum(y[train_index])/float(len(y[train_index])) clf_ori = TransparentLogisticRegression() clf_ss = TransparentLogisticRegression() clf_ig = TransparentLogisticRegression() X_ss = scale(X) scale_ = decision_tree_scale() X_ig = scale_.fit_transform(X, y) clf_ori.fit(X, y) clf_ss.fit(X_ss, y) clf_ig.fit(X_ig, y) print clf_ori.coef_ print clf_ss.coef_ print clf_ig.coef_ bias_ori = clf_ori.intercept_ bias_ss = clf_ss.intercept_ bias_ig = clf_ig.intercept_ print bias_ori, bias_ss, bias_ig print prob(bias_ori) print prob(bias_ss)
vect = CountVectorizer(min_df=5, max_df=1.0, binary=True, ngram_range=(1, 1))
X_train, y_train, X_test, y_test, train_corpus, test_corpus = load_imdb("C:\\Users\\Mustafa\\Desktop\\aclImdb", shuffle=True, vectorizer=vect)
feature_names = vect.get_feature_names()
duration = time() - t0
print
print "Loading took %0.2fs." % duration
print
print "Fitting the classifier"
t0 = time()
clf = TransparentLogisticRegression(penalty='l1', C=0.1)
clf.fit(X_train, y_train)
duration = time() - t0
print
print "Fitting took %0.2fs." % duration
print
print "Predicting the evidences"
t0 = time()
neg_evi, pos_evi = clf.predict_evidences(X_test)
duration = time() - t0
print
def testLR():
print "Loading the data"
t0 = time()
vect = CountVectorizer(min_df=5, max_df=1.0, binary=True, ngram_range=(1, 1))
X_train, y_train, X_test, y_test, train_corpus, test_corpus = load_imdb("C:\\Users\\Mustafa\\Desktop\\aclImdb", shuffle=True, vectorizer=vect)
feature_names = vect.get_feature_names()
duration = time() - t0
print
print "Loading took %0.2fs." % duration
print
print "Fitting the classifier"
t0 = time()
clf = TransparentLogisticRegression(penalty='l1', C=0.1)
clf.fit(X_train, y_train)
duration = time() - t0
print
print "Fitting took %0.2fs." % duration
print
print "Predicting the evidences"
t0 = time()
neg_evi, pos_evi = clf.predict_evidences(X_test)
duration = time() - t0
print
print "Predicting evidences took %0.2fs." % duration
print
print "Predicting the probs"
t0 = time()
probs = clf.predict_proba(X_test)
duration = time() - t0
print
print "Predicting probs took %0.2fs." % duration
print
ti = TopInstances(neg_evi, pos_evi, clf.get_bias())
total_evi = neg_evi + pos_evi
print
print "Most negative"
print
i = ti.most_negatives()[0]
print total_evi[i], neg_evi[i], pos_evi[i], probs[i]
print test_corpus[i]
print
print "Most positive"
print
i = ti.most_positives()[0]
print total_evi[i], neg_evi[i], pos_evi[i], probs[i]
print test_corpus[i]
