from textblob.classifiers import MaxEntClassifier
with open('data/train-toy.csv', 'r') as fp:
cl = MaxEntClassifier(fp, format="csv")
with open('data/test-toy.csv', 'r') as gp:
print cl.accuracy(gp, format="csv")
print(len(words), len(tags))
for i in range(1000):
if (i < 800):
temp = (words[i], tags[i])
train.append(temp)
else:
temp = (words[i], tags[i])
test.append(temp)
print(train)
print(test)
naive = NaiveBayesClassifier(train)
dtc = DecisionTreeClassifier(train)
mec = MaxEntClassifier(train)
print("NaiveBayesClassifier Accuracy: {0}".format(naive.accuracy(test)))
print("DecisionTreeClassifier Accuracy: {0}".format(dtc.accuracy(test)))
print("MaxEntClassifier Accuracy: {0}".format(mec.accuracy(test)))
cl = NaiveBayesClassifier(train)
print("NaiveBayesClassifier Accuracy: {0}".format(cl.accuracy(test)))
for i in range(0, len(test)):
tag = cl.classify(test[i])
pred_tags.append(tag)
if (tag == test_tags[i]):
count += 1
print(len(pred_tags), len(test_tags))
print(count)
test = []
temp = ()
file1 = open("train_utterance", "r")
file_data = file1.readlines()
for i in range(0, len(file_data)):
m = file_data[i].strip().split("\t\t")
n = m[2].split(":")
temp = (m[1], n[0])
train.append(temp)
file1.close()
file1 = open("test_utterance", "r")
file_data = file1.readlines()
for i in range(0, len(file_data)):
m = file_data[i].strip().split("\t\t")
n = m[2].split(":")
temp = (m[1], n[0])
test.append(temp)
cl = NaiveBayesClassifier(train)
mec = MaxEntClassifier(train)
#dtc = DecisionTreeClassifier(train)
# Compute accuracy
print("Accuracy: {0}".format(cl.accuracy(test)))
print("Accuracy: {0}".format(mec.accuracy(test)))
# Show 5 most informative features
cl.show_informative_features(5)
# trains.append(train[i])
trains = train
if choice == "1":
print("\n" + "#NaiveBayesClassifier")
cl1 = NaiveBayesClassifier(trains)
print("Classifier: Naive Bayes -- Accuracy: ", cl1.accuracy(test), "\n")
elif choice == "2":
print("\n" + "#DecisionTreeClassifier")
cl2 = DecisionTreeClassifier(trains)
print("Classifier: Decision Tree -- Accuracy: ", cl2.accuracy(test), "\n")
elif choice == "3":
print("\n" + "#MaxEntClassifier")
cl3 = MaxEntClassifier(trains)
print("Classifier: Maximum Entropy -- Accuracy: ", cl3.accuracy(test),
"\n")
elif choice == "4":
print("\n" + "#NLTKClassifier")
cl4 = NLTKClassifier(trains)
print("Classifier: NLTK -- Accuracy: ", cl4.accuracy(test), "\n")
else:
print("Bad input!")
# most repeated words (most important properties)
totalDictPosSorted = sorted(totalDictPos.items(), key=operator.itemgetter(1))
totalDictNegSorted = sorted(totalDictNeg.items(), key=operator.itemgetter(1))
from textblob.classifiers import MaxEntClassifier
with open('data/train-toy.csv', 'r') as fp:
cl = MaxEntClassifier(fp, format="csv")
with open('data/test-toy.csv', 'r') as gp:
print cl.accuracy(gp, format="csv")
