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
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]
print "The # of positive instances in all data: ", np.sum(y)
print "The ratio of positive instances: ", np.sum(y)/float(num_inst)
print "The ratio of negative instances: ", 1-(np.sum(y)/float(len(y)))
print ""
ss = ShuffleSplit(num_inst, n_iter=1, test_size=0.33, random_state=2)
for i, j in ss:
train_index = i
test_index = j
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_
import numpy as np
import pickle
t0 = time()
vect = Vectorizer(min_df=5, max_df=1.0, binary=False, ngram_range=(1, 1))
X_train, y_train, X_val, y_val, X_test, y_test, train_corpus, val_corpus, test_corpus = load_imdb("./aclImdb", shuffle=True, vectorizer=vect)
y_test_na = y_test[:, np.newaxis]
y_test_na = np.append(y_test_na, 1-y_test_na, axis=1)
y_val_na = y_val[:, np.newaxis]
y_val_na = np.append(y_val_na, 1-y_val_na, axis=1)
clf = Classifier()
clf.fit(X_train, y_train)
ctrl_clf = clf
ctrl_error = ce_squared(y_test_na, clf.predict_proba(X_test))
ctrl_acc = clf.score(X_test, y_test)
duration = time() - t0
print("Loading the dataset took {:0.2f}s.".format(duration), '\n')
with open('clf12.arch', 'rb') as f:
clf_arch = pickle.load(f)
clf_arch.stats()
ctrl_clf = clf_arch.ctrl_clf
best_clf = clf_arch.classifiers[-1]
