Last active
November 18, 2015 13:24
-
-
Save zermelozf/d4670d6cffea09f6e6f3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
================================ | |
Classification of text documents | |
================================ | |
""" | |
from os.path import dirname, realpath | |
import sys | |
sys.path.append(dirname(realpath(__file__)) + "/../lightning/impl/tests") | |
import time | |
import numpy as np | |
from sklearn.datasets import fetch_20newsgroups_vectorized | |
from sklearn.cross_validation import train_test_split | |
from sklearn.linear_model import LogisticRegression | |
from sklearn.linear_model.sag import get_auto_step_size | |
from lightning.impl.sag import SAGClassifier, SAGAClassifier | |
from test_sag import PySAGAClassifier | |
# Load News20 dataset from scikit-learn. | |
bunch = fetch_20newsgroups_vectorized(subset="all") | |
X = bunch.data | |
y = bunch.target | |
# y[y < y.mean()] = -1 | |
# y[y >= y.mean()] = 1 | |
# n_samples = 100 | |
# X = X[:n_samples] | |
# y = y[:n_samples] | |
# X = X.toarray() | |
print X.shape | |
print type(X) | |
# Train / test split. | |
X_tr, X_te, y_tr, y_te = train_test_split(X, y, | |
train_size=0.75, | |
test_size=0.25, | |
random_state=0) | |
max_squared_sum = np.max(np.sum(X_tr.toarray() * X_tr.toarray(), axis=1)) | |
print(max_squared_sum) | |
alpha_scaled = .1 / X_tr.shape[0] | |
step = get_auto_step_size(max_squared_sum, alpha_scaled, 'log', False) | |
alpha = .1 | |
clfs = (SAGClassifier(loss="log", eta=step, alpha=alpha, max_iter=100, verbose=False, random_state=0), | |
SAGAClassifier(loss="log", eta=step, alpha=alpha, beta=0.0, max_iter=100, verbose=False, random_state=0), | |
LogisticRegression(C=1. / (X_tr.shape[0] * alpha), solver='sag', max_iter=100, fit_intercept=False, random_state=0), | |
# PySAGAClassifier(eta=1e-3, alpha=0.0, beta=1e-4, penalty=None, max_iter=10), | |
) | |
print "--- Sparse ---" | |
for clf in clfs: | |
print clf.__class__.__name__ | |
t = time.time() | |
clf.fit(X_tr, y_tr) | |
print "time = {}".format(time.time() - t) | |
print "score = {}".format(clf.score(X_te, y_te)) | |
# print clf.coef_[0, :5] | |
# print clf.predict(X_te) | |
# clf.loss | |
# print "--- Dense ---" | |
# X_tr = X_tr.toarray() | |
# X_te = X_te.toarray() | |
# for clf in clfs: | |
# print clf.__class__.__name__ | |
# t = time.time() | |
# clf.fit(X_tr, y_tr) | |
# print "time = {}".format(time.time() - t) | |
# print "score = {}".format(clf.score(X_te, y_te)) | |
# # print clf.coef_ | |
# # print clf.predict(X_te) | |
# clf.loss |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment