/
svm_linear.py
44 lines (35 loc) · 1.52 KB
/
svm_linear.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
# Dataset: Polarity dataset v2.0
# http://www.cs.cornell.edu/people/pabo/movie-review-data/
#
# Discussion at https://medium.com/@vasista/sentiment-analysis-textblob-vs-svm-338d418e3ff1
from sklearn.feature_extraction.text import TfidfVectorizer
import time
from sklearn import svm
from sklearn.metrics import classification_report
import pandas as pd
# train Data
trainData = pd.read_csv("https://raw.githubusercontent.com/Vasistareddy/sentiment_analysis/master/data/train.csv")
# test Data
testData = pd.read_csv("https://raw.githubusercontent.com/Vasistareddy/sentiment_analysis/master/data/test.csv")
# Create feature vectors
vectorizer = TfidfVectorizer(min_df = 5,
max_df = 0.8,
sublinear_tf = True,
use_idf = True)
train_vectors = vectorizer.fit_transform(trainData['Content'])
test_vectors = vectorizer.transform(testData['Content'])
# Perform classification with SVM, kernel=linear
classifier_linear = svm.SVC(kernel='linear')
t0 = time.time()
classifier_linear.fit(train_vectors, trainData['Label'])
t1 = time.time()
prediction_linear = classifier_linear.predict(test_vectors)
t2 = time.time()
time_linear_train = t1-t0
time_linear_predict = t2-t1
# results
print("Results for SVC(kernel=linear)")
print("Training time: %fs; Prediction time: %fs" % (time_linear_train, time_linear_predict))
report = classification_report(testData['Label'], prediction_linear, output_dict=True)
print('positive: ', report['pos'])
print('negative: ', report['neg'])