SVM

train_test_svm.py

#!/usr/bin/python

import sys
from numpy import loadtxt
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import Pipeline
from sklearn.svm.sparse import LinearSVC

my_data = loadtxt(sys.argv[1], delimiter='\t', dtype='S')
my_test_data = loadtxt(sys.argv[2], delimiter='\t', dtype='S')

text_clf = Pipeline([
	    ('vect', CountVectorizer()),
	    ('tfidf', TfidfTransformer()),
	    ('clf', LinearSVC()),
	])
print("Training...")
my_clf = text_clf.fit(my_data[:,4], my_data[:,3])

print("Done! \nClassifying test set...")
predicted = my_clf.predict(my_test_data[:,4])


print(np.mean(predicted == my_test_data[:,3]))