def test_pred(self):
print("test_pred")
nb = NaiveBayesClassifier()
nb.mean = [1, 2]
nb.variance = [3, 1]
# testing condition where it is not trained
self.assertEqual(nb.predict([1.4, 12, 3, 9]), None)
self.assertEqual(nb.predict([2, 3, 4, 5]), None)
self.assertEqual(nb.predict([1]), None)
self.assertEqual(nb.predict([2, -3, 4, -5, -7, -7]), None)
nb.mean = [1, 1]
nb.variance = [1, 5]
nb.in_classes = [1, 0]
nb.prior_probs = [0.3, 0.2]
pred = nb.predict([5, 3, 4, 7])
# Testing condition simulating trained model.
self.assertEqual(pred[0], [0])
self.assertEqual(pred[1], [0])
self.assertEqual(pred[2], [0])
self.assertEqual(pred[3], [0])
from NaiveBayes import NaiveBayesClassifier
#importing the class
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn import datasets
import matplotlib.pyplot as plt
#Calculating accuracy --(actual-prediction)/(total no of samples)
def accuracy(y_actual, yhat):
accuracy = np.sum(y_actual == yhat) / len(y_actual)
return accuracy
X, y = datasets.make_classification(n_samples=1000,
n_features=10,
n_classes=2,
random_state=123)
#Dividing the dataset into train and test -80-20 division
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2,
random_state=123)
nb = NaiveBayesClassifier()
nb.fit(X_train, y_train) #fitting the model
predictions = nb.predict(X_test) #predicting on the test set
print("Accuracy", accuracy(y_test, predictions)) #calculating the accuracy
class SentimentAnalyzer:
threshold = 1
def __init__(self, file_location):
self.features = set([])
raw_data = []
training_data = []
word_freq = {}
#self.word_freq = {}
with open(file_location, 'rb') as data:
data_reader = csv.DictReader(data)
for row in data_reader:
# print row
h_tokens = nltk.word_tokenize(row['headline'].lower())
#self.features = self.features.union(set(h_tokens))
for token in h_tokens:
if token in word_freq:
word_freq[token] += 1
else:
word_freq[token] = 1
#for token in h_tokens:
# if token in self.word_freq:
# self.word_freq[token] += 1
# else:
# self.word_freq[token] = 1
raw_data.append(
(h_tokens, 0, float(row[' anger']) / 100)) # anger
raw_data.append(
(h_tokens, 1, float(row[' disgust']) / 100)) # disgust
raw_data.append(
(h_tokens, 2, float(row[' fear']) / 100)) # fear
raw_data.append((h_tokens, 3, float(row[' joy']) / 100)) # joy
raw_data.append(
(h_tokens, 4, float(row[' sadness']) / 100)) # sadness
raw_data.append(
(h_tokens, 5, float(row[' surprise']) / 100)) # surprise
for key in word_freq.keys():
if word_freq[key] > self.threshold:
self.features.add(key)
print "F-vec size: " + str(len(self.features))
for data in raw_data:
f_vector = []
for f in self.features:
f_vector.append(1 if f in data[0] else 0)
training_data.append((f_vector, data[1], data[2]))
self.classifier = NaiveBayesClassifier(6, len(self.features))
self.classifier.train(training_data)
def predict(self, text):
token_set = set(nltk.word_tokenize(text.lower()))
f_vector = []
for f in self.features:
f_vector.append(1 if f in token_set else 0)
return self.classifier.predict(f_vector)
def predict_all(self, text):
token_set = set(nltk.word_tokenize(text.lower()))
f_vector = []
for f in self.features:
f_vector.append(1 if f in token_set else 0)
return self.classifier.predict_all(f_vector)
def test(self, test_file_location):
test_data = open(test_file_location, 'rb')
test_reader = csv.DictReader(test_data)
total = 0
correct = 0
for row in test_reader:
total += 1
emotions = map(float, [
row[' anger'], row[' disgust'], row[' fear'], row[' joy'],
row[' sadness'], row[' surprise']
])
acceptable_emotions = []
for i in xrange(len(emotions)):
if emotions[i] > 1:
acceptable_emotions.append(i)
acceptable_emotions = sorted(acceptable_emotions,
reverse=True,
key=lambda x: emotions[x])[:3]
#print acceptable_emotions
#print emotion
prediction = self.predict(row['headline'])[0]
#print prediction
if prediction in acceptable_emotions:
correct += 1
return float(correct) / total