def train(self,train_target,train_samples):
self._prepared = False;
self.tfidf = TfidfVectorizer(stop_words='english')
self.tfidf.fit_transform(train_samples[1]+train_samples[2]); #title and description
#Classifier Model
self.classifyers={};
classes=[];
if not self.keyword_detection_list :
for each in train_target: classes.extend(x for x in each);
classes = set(classes);
else:
classes = self.keyword_detection_list;
print 'Total number of classes for this model ', len(classes)
class_example_count = []
for each in classes:
Y =[1 if each in x else 0 for x in train_target ];
class_example_count.append(sum(Y));
print 'examples seen for each class during training ' ,class_example_count
self.bow = feature.feature(self.featurename,train_samples,keywords=self.keyword_detection_list);
metric = [];
#Classifier Model : Train
for each in classes:
#Balancing dataset
target_y = [1 if each in x else 0 for x in train_target ];
[target_y_balanced, train_balanced]=load.split_equally(target_y,train_samples)
#[target_y_balanced, train_balanced] = [target_y,train_samples]
#print 'Not balancing test/train'
print 'Training to tag %s from %d samples' %(each ,len(target_y_balanced))
Y =np.array(target_y_balanced);
X = self.bow.get_incremental_features(train_balanced);
assert(X.shape[0] == len(train_balanced))
assert(Y.shape[0] == len(train_balanced))
#if not LOGISTIC_REGRESSION:
# clf = MultinomialNB(fit_prior=False);# onlu MultinomialNB takes sparse matrix , to offset hughe neg samples
#else:
clf = LogisticRegression();
clf.fit(X,Y);
#pred = cross_validation.cross_val_predict(clf, X , Y, cv=3);
self.classifyers[each] = clf;
#eval.confused_examples(each,train_target,train_balanced,Y.tolist(),pred,3)
#metric.append((each,prec,rec,acc,tp,tn,fp,fn))
self.train_target = train_target;
x = [eachtraindoc[1] for eachtraindoc in train_samples]
print 'tfidf ..'
self.tfidfVec = self.tfidf.fit_transform(x);
self.tfidfVec = self.tfidfVec.transpose();
print self.tfidfVec.shape
self._prepared = True;
print 'examples seen for each class during training ', class_example_count
classes = ['python']
#Feature Model
if not LOGISTIC_REGRESSION:
bow = feature.feature("bow", train_samples)
else:
bow_trimmed = feature.feature("bow_bigram", train_samples)
metric = []
#Classifier Model : Train
for each in classes:
#Balancing dataset
target_y = [1 if each in x else 0 for x in train_target]
[target_y_balanced,
train_balanced] = load.split_equally(target_y, train_samples)
print 'Training to tag %s from %d samples' % (each, len(target_y_balanced))
Y = np.array(target_y_balanced)
if not LOGISTIC_REGRESSION:
X = bow.get_incremental_features(train_balanced)
else:
X = bow_trimmed.get_incremental_features(train_balanced)
assert (X.shape[0] == len(train_balanced))
assert (Y.shape[0] == len(train_balanced))
if not LOGISTIC_REGRESSION:
clf = MultinomialNB(fit_prior=False)
# onlu MultinomialNB takes sparse matrix , to offset hughe neg samples
else:
clf = LogisticRegression()
#clf.fit(X,Y);
#assert(sum(class_example_count) == len(train_target))
print 'examples seen for each class during training ' ,class_example_count
classes=['python']
#Feature Model
if not LOGISTIC_REGRESSION:
bow = feature.feature("bow",train_samples);
else:
bow_trimmed = feature.feature("bow_bigram",train_samples);
metric = [];
#Classifier Model : Train
for each in classes:
#Balancing dataset
target_y = [1 if each in x else 0 for x in train_target ];
[target_y_balanced, train_balanced]=load.split_equally(target_y,train_samples)
print 'Training to tag %s from %d samples' %(each ,len(target_y_balanced))
Y =np.array(target_y_balanced);
if not LOGISTIC_REGRESSION:
X = bow.get_incremental_features(train_balanced);
else:
X = bow_trimmed.get_incremental_features(train_balanced);
assert(X.shape[0] == len(train_balanced))
assert(Y.shape[0] == len(train_balanced))
if not LOGISTIC_REGRESSION:
clf = MultinomialNB(fit_prior=False);# onlu MultinomialNB takes sparse matrix , to offset hughe neg samples
else:
clf = LogisticRegression();
#clf.fit(X,Y);
pred = cross_validation.cross_val_predict(clf, X , Y, cv=3);
