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 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145
|
"""
========================================================
Classification of text documents: using a MLComp dataset
========================================================
This is an example showing how the scikit-learn can be used to classify
documents by topics using a bag-of-words approach. This example uses
a scipy.sparse matrix to store the features instead of standard numpy arrays.
The dataset used in this example is the 20 newsgroups dataset and should be
downloaded from the http://mlcomp.org (free registration required):
http://mlcomp.org/datasets/379
Once downloaded unzip the archive somewhere on your filesystem.
For instance in::
% mkdir -p ~/data/mlcomp
% cd ~/data/mlcomp
% unzip /path/to/dataset-379-20news-18828_XXXXX.zip
You should get a folder ``~/data/mlcomp/379`` with a file named ``metadata``
and subfolders ``raw``, ``train`` and ``test`` holding the text documents
organized by newsgroups.
Then set the ``MLCOMP_DATASETS_HOME`` environment variable pointing to
the root folder holding the uncompressed archive::
% export MLCOMP_DATASETS_HOME="~/data/mlcomp"
Then you are ready to run this example using your favorite python shell::
% ipython examples/mlcomp_sparse_document_classification.py
"""
# Author: Olivier Grisel <olivier.grisel@ensta.org>
# License: BSD 3 clause
from __future__ import print_function
from time import time
import sys
import os
import numpy as np
import scipy.sparse as sp
import matplotlib.pyplot as plt
from sklearn.datasets import load_mlcomp
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.naive_bayes import MultinomialNB
print(__doc__)
if 'MLCOMP_DATASETS_HOME' not in os.environ:
print("MLCOMP_DATASETS_HOME not set; please follow the above instructions")
sys.exit(0)
# Load the training set
print("Loading 20 newsgroups training set... ")
news_train = load_mlcomp('20news-18828', 'train')
print(news_train.DESCR)
print("%d documents" % len(news_train.filenames))
print("%d categories" % len(news_train.target_names))
print("Extracting features from the dataset using a sparse vectorizer")
t0 = time()
vectorizer = TfidfVectorizer(encoding='latin1')
X_train = vectorizer.fit_transform((open(f).read()
for f in news_train.filenames))
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_train.shape)
assert sp.issparse(X_train)
y_train = news_train.target
print("Loading 20 newsgroups test set... ")
news_test = load_mlcomp('20news-18828', 'test')
t0 = time()
print("done in %fs" % (time() - t0))
print("Predicting the labels of the test set...")
print("%d documents" % len(news_test.filenames))
print("%d categories" % len(news_test.target_names))
print("Extracting features from the dataset using the same vectorizer")
t0 = time()
X_test = vectorizer.transform((open(f).read() for f in news_test.filenames))
y_test = news_test.target
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X_test.shape)
###############################################################################
# Benchmark classifiers
def benchmark(clf_class, params, name):
print("parameters:", params)
t0 = time()
clf = clf_class(**params).fit(X_train, y_train)
print("done in %fs" % (time() - t0))
if hasattr(clf, 'coef_'):
print("Percentage of non zeros coef: %f"
% (np.mean(clf.coef_ != 0) * 100))
print("Predicting the outcomes of the testing set")
t0 = time()
pred = clf.predict(X_test)
print("done in %fs" % (time() - t0))
print("Classification report on test set for classifier:")
print(clf)
print()
print(classification_report(y_test, pred,
target_names=news_test.target_names))
cm = confusion_matrix(y_test, pred)
print("Confusion matrix:")
print(cm)
# Show confusion matrix
plt.matshow(cm)
plt.title('Confusion matrix of the %s classifier' % name)
plt.colorbar()
print("Testbenching a linear classifier...")
parameters = {
'loss': 'hinge',
'penalty': 'l2',
'n_iter': 50,
'alpha': 0.00001,
'fit_intercept': True,
}
benchmark(SGDClassifier, parameters, 'SGD')
print("Testbenching a MultinomialNB classifier...")
parameters = {'alpha': 0.01}
benchmark(MultinomialNB, parameters, 'MultinomialNB')
plt.show()
|