【学习笔记】Scikit-learn文本聚类实例

# -*- coding=utf-8 -*-
"""
text category
"""
from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.naive_bayes import MultinomialNB
categories = ['alt.atheism', 'soc.religion.christian', 'comp.graphics', 'sci.med']
twenty_train = fetch_20newsgroups(subset='train', categories=categories, shuffle=True, random_state=42)
print len(twenty_train.data)
len(twenty_train.filenames)
count_vect = CountVectorizer()
X_train_counts = count_vect.fit_transform(twenty_train.data)
print X_train_counts.shape
print count_vect.vocabulary_.get('algorithm')
tf_transformer = TfidfTransformer(use_idf=False).fit(X_train_counts)
X_train_tf = tf_transformer.transform(X_train_counts)
print X_train_tf.shape
tfidf_transformer = TfidfTransformer()
X_train_tfidf = tf_transformer.fit_transform(X_train_counts)
print X_train_tfidf.shape
clf = MultinomialNB().fit(X_train_tfidf, twenty_train.target)
docs_new = ['God is love', 'OpenGl on the Gpu is fast']
X_new_counts = count_vect.transform(docs_new)
X_new_tfidf = tfidf_transformer.fit_transform(X_new_counts)
predicted = clf.predict(X_new_tfidf)
for doc, category in zip(docs_new, predicted):
print '%r=>%s' % (doc, twenty_train.target_names[category]

对fetch_20newsgroups中的2257条文档进行分类
统计每个词出现的次数

用tf-idf统计词频，tf是在一个文档里每个单词出现的次数除以文档的单词总数，idf是总的文档数除以包含该单词的文档数，再取对数；tf * idf就是这里用到的值，值越大表明单词越重要，或越相关。

例子具体做法：
先计算了每个单词出现的次数

然后计算了tf-idf值

然后带入模型进行训练

最后预测了两个新文档的类型

结果：

'God is love'=> soc.religion.christian
'OpenGL on the GPU is fast'=> comp.graphics