from sklearn import svm from clean_data import CleanData __author__ = "Yacine Sibous" cd = CleanData() print "Getting the training data." training_data = cd.bag_of_words(in_file="data/clean_train_input.csv") print "Done collecting data." X = [x[1] for x in training_data] y = [y[2] for y in training_data] print X[0:5] print y[0:5] clf = svm.SVC() clf.fit(X, y)
def plot_feature_size(num_iter):
"""Tests various feature sizes and plots the error.
Args:
num_iter: Number of times to test for each point.
"""
points = [100, 500, 1000, 2000, 3000, 4000, 5000, 6000, 7000,
8000, 9000, 10000]
errors = []
train_errors = []
# Iterate over all points defined.
for point in points:
print "Testing for point", point, "features."
error = 0
train_error = 0
# Repeat the test the desired number of times.
for i in range(0, num_iter):
cd = CleanData(tfidf=True, max_train_size=25000, max_features=point)
try:
# Get and train data.
training_data = cd.bag_of_words(in_file="data/clean_train_input.csv")
ids, X, y = get_numpy_matrices(training_data)
del training_data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.4, random_state=0)
del X, y, ids
nb = NaiveBayes()
nb.train(X_train, y_train)
# Calculate training and validation errors.
out = nb.classify(X_test)
error += nb.compute_error(out, y_test)
train_out = nb.classify(X_train)
train_error += nb.compute_error(train_out, y_train)
except MemoryError:
print "Memory error. Continuing."
continue
del X_train, X_test, y_train, y_test
errors.append(error / num_iter)
train_errors.append(train_error / num_iter)
# PLOT.
plt.figure(2)
plt.title("Error vs Features")
plt.xlabel("Number of features")
plt.ylabel("Error")
# plt.xscale('log')
plt.plot(points, errors, '-ro')
plt.plot(points, train_errors, '-bo')
plt.show()
from sklearn import svm from sklearn.cross_validation import cross_val_score from clean_data import CleanData import numpy as np import csv __author__ = "Yacine Sibous, Jana Pavlasek" # Initialize data for final submission. cd = CleanData(tfidf=True, max_features=2500000, n_grams=3) # Geat features and output. print 'Getting Training data.' X, y = cd.bag_of_words(in_file="data/clean_train_input.csv", sparse=True) print 'Done collecting data.' # Train. print 'Training the model.' lin_clf = svm.LinearSVC() lin_clf.fit(X, y) print 'Done training.' # 3-fold cross validation. print 'Cross Validation' c_validation = cross_val_score(lin_clf, X, y, scoring='accuracy') print c_validation.mean() # Get and predict on the final test data. print 'Collecting test data.' test = cd.get_x_in(sparse=True) print 'Done collecting data.'