Two feature extraction methods
TfidfVectorizer
HashingVectorizer
Two algorithms are demoed: ordinary k-means and its more scalable cousin minibatch k-means.
from __future__ import print_function
from sklearn.datasets import fetch_20newsgroups
from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import Normalizer
from sklearn import metrics
from sklearn.cluster import KMeans, MiniBatchKMeans
import logging
from optparse import OptionParser
import sys
from time import time
import numpy as np
# Display progress logs on stdout
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s') # 记录日志
# parse commandline arguments
op = OptionParser() # 得到OptionParser实例对象
op.add_option("--lsa",
dest="n_components", type="int",
help="Preprocess documents with latent semantic analysis.")
op.add_option("--no-minibatch",
action="store_false", dest="minibatch", default=True,
help="Use ordinary k-means algorithm (in batch mode).")
op.add_option("--no-idf",
action="store_false", dest="use_idf", default=True,
help="Disable Inverse Document Frequency feature weighting.")
op.add_option("--use-hashing",
action="store_true", default=False,
help="Use a hashing feature vectorizer")
op.add_option("--n-features", type=int, default=10000,
help="Maximum number of features (dimensions)"
" to extract from text.")
op.add_option("--verbose",
action="store_true", dest="verbose", default=False,
help="Print progress reports inside k-means algorithm.")
# 执行其父类中的add_option(*args,**kwargs)方法
print(__doc__)
op.print_help()
def is_interactive():
return not hasattr(sys.modules['__main__'], '__file__')
# work-around for Jupyter notebook and IPython console
argv = [] if is_interactive() else sys.argv[1:]
(opts, args) = op.parse_args(argv)
if len(args) > 0:
op.error("this script takes no arguments.")
sys.exit(1)
# #############################################################################
# Load some categories from the training set
categories = [
'alt.atheism',
'talk.religion.misc',
'comp.graphics',
'sci.space',
]
# Uncomment the following to do the analysis on all the categories
# categories = None
print("Loading 20 newsgroups dataset for categories:")
print(categories)
dataset = fetch_20newsgroups(subset='all', categories=categories,
shuffle=True, random_state=42)
# fetch_20newsgroups() Load the filenames and data from the 20 newsgroups dataset.
print("%d documents" % len(dataset.data))
print("%d categories" % len(dataset.target_names))
print()
labels = dataset.target
true_k = np.unique(labels).shape[0]
# Find the unique elements of an array.
'''
Returns the sorted unique elements of an array. There are three optional
outputs in addition to the unique elements: the indices of the input array
that give the unique values, the indices of the unique array that
reconstruct the input array, and the number of times each unique value
comes up in the input array.
'''
print("Extracting features from the training dataset using a sparse vectorizer")
t0 = time()
if opts.use_hashing:
if opts.use_idf:
# Perform an IDF normalization on the output of HashingVectorizer
hasher = HashingVectorizer(n_features=opts.n_features,
stop_words='english', alternate_sign=False,
norm=None, binary=False)
vectorizer = make_pipeline(hasher, TfidfTransformer())
"""Construct a Pipeline from the given estimators.
This is a shorthand for the Pipeline constructor; it does not require, and
does not permit, naming the estimators. Instead, their names will be set
to the lowercase of their types automatically.
"""
else:
vectorizer = HashingVectorizer(n_features=opts.n_features,
stop_words='english',
alternate_sign=False, norm='l2',
binary=False)
else:
vectorizer = TfidfVectorizer(max_df=0.5, max_features=opts.n_features,
min_df=2, stop_words='english',
use_idf=opts.use_idf)
X = vectorizer.fit_transform(dataset.data)
print("done in %fs" % (time() - t0))
print("n_samples: %d, n_features: %d" % X.shape)
print()
if opts.n_components:
print("Performing dimensionality reduction using LSA")
t0 = time()
# Vectorizer results are normalized, which makes KMeans behave as
# spherical k-means for better results. Since LSA/SVD results are
# not normalized, we have to redo the normalization.
svd = TruncatedSVD(opts.n_components)
normalizer = Normalizer(copy=False)
'''
Each sample (i.e. each row of the data matrix) with at least one
non zero component is rescaled independently of other samples so
that its norm (l1 or l2) equals one.
This transformer is able to work both with dense numpy arrays and
scipy.sparse matrix (use CSR format if you want to avoid the burden of
a copy / conversion).
Scaling inputs to unit norms is a common operation for text
classification or clustering for instance. For instance the dot
product of two l2-normalized TF-IDF vectors is the cosine similarity
of the vectors and is the base similarity metric for the Vector
Space Model commonly used by the Information Retrieval community.
'''
lsa = make_pipeline(svd, normalizer)
X = lsa.fit_transform(X)
print("done in %fs" % (time() - t0))
explained_variance = svd.explained_variance_ratio_.sum()
print("Explained variance of the SVD step: {}%".format(
int(explained_variance * 100)))
print()
# #############################################################################
# Do the actual clustering
if opts.minibatch:
km = MiniBatchKMeans(n_clusters=true_k, init='k-means++', n_init=1,
init_size=1000, batch_size=1000, verbose=opts.verbose)
else:
km = KMeans(n_clusters=true_k, init='k-means++', max_iter=100, n_init=1,
verbose=opts.verbose)
print("Clustering sparse data with %s" % km)
t0 = time()
km.fit(X)
print("done in %0.3fs" % (time() - t0))
print()
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels, km.labels_))
print("Completeness: %0.3f" % metrics.completeness_score(labels, km.labels_))
print("V-measure: %0.3f" % metrics.v_measure_score(labels, km.labels_))
print("Adjusted Rand-Index: %.3f"
% metrics.adjusted_rand_score(labels, km.labels_))
print("Silhouette Coefficient: %0.3f"
% metrics.silhouette_score(X, km.labels_, sample_size=1000))
print()
if not opts.use_hashing:
print("Top terms per cluster:")
if opts.n_components:
original_space_centroids = svd.inverse_transform(km.cluster_centers_)
order_centroids = original_space_centroids.argsort()[:, ::-1]
else:
order_centroids = km.cluster_centers_.argsort()[:, ::-1]
terms = vectorizer.get_feature_names()
for i in range(true_k):
print("Cluster %d:" % i, end='')
for ind in order_centroids[i, :10]:
print(' %s' % terms[ind], end='')
print()
