def evaluate(prediction,labels_test):
labels_test = [0 if x=="neutral" else 1 if x=="positive" else -1 for x in labels_test]
#logistic regression evaluation
print "Average F1 : " +str(measures.avgF1(labels_test,prediction,-1,1))
#print "Baseline AverageF1 : " +str(measures.avgF1(labels_test,baseline_prediction))
print "Accuracy : " +str(measures.accuracy(labels_test,prediction))
#print "Baseline Accuracy : "+str(measures.accuracy(labels_test,baseline_prediction))
print "F1 negative : " +str(measures.F1(labels_test,prediction,-1))
print "F1 positive : " +str(measures.F1(labels_test,prediction,1))
print "Precision negative: " +str(measures.precision(labels_test,prediction,-1))
print "Precision positive: " +str(measures.precision(labels_test,prediction,1))
print "Recall negative : " +str(measures.recall(labels_test,prediction,-1))
print "Recall positive : " +str(measures.recall(labels_test,prediction,1))
def C_comparison(length,features_train,labels_train,features_test,labels_test):
C = [0.001,0.05,0.1,0.3,0.5,0.8,1,10,100,350,500,1000,3500,5000,10000,50000,100000]
scores = []
for c in C:
model = LogisticRegression.train(features_train,labels_train,c)
prediction = LogisticRegression.predict(features_test,model)
scores.append((measures.avgF1(labels_test,prediction,0,1)))
plt.plot(C,scores,color="blue",linewidth="2.0")
plt.xticks(C)
plt.ylabel("F1")
plt.xlabel("C")
plt.show()
def plotFeaturesF1(features_train,labels_train,features_test,labels_test):
x = list(np.arange(len(features_train[0])))
#x = list(np.arange(5))
y = []
for i in range(0,len(features_train[0])):
f_train = features_train[:,i]
f_test = features_test[:,i]
f_train = f_train.reshape(f_train.shape[0],1)
f_test = f_test.reshape(f_test.shape[0],1)
model = LogisticRegression.train(f_train,labels_train)
prediction = LogisticRegression.predict(f_test,model)
y.append(measures.avgF1(labels_test,prediction,0,1))
plt.plot(x,y,color="blue",linewidth="2.0")
plt.ylabel("F1")
plt.xlabel("# of Feature")
plt.xticks(x)
plt.show()
