scikit-learn 朴素贝叶斯实现文档分类

随书代码，做些笔记。

• 加载数据集

http://mlcomp.org/datasets/379 下载

%matplotlib inline
import matplotlib.pyplot as plt
import numpy as np
from time import time
from sklearn.datasets import load_files

print("loading train dataset ...")
t = time()
news_train = load_files('datasets/mlcomp/379/train')
print("summary: {0} documents in {1} categories.".format(len(news_train.data), len(news_train.target_names)))
print("done in {0} seconds".format(time() - t))
print()

• 文档向量化

TF-IDF 统计方法， TF表示词频 term frequency, IDF inverse docrment frequency, TF-IDF 标识词在文档中的重要程度。

from sklearn.feature_extraction.text import TfidfVectorizer

print("vectorizing train dataset ...")
t = time()
vectorizer = TfidfVectorizer(encoding='latin-1')
X_train = vectorizer.fit_transform((d for d in news_train.data))
print("n_samples: %d, n_features: %d" % X_train.shape)
print("number of non-zero features in sample [{0}]: {1}".format(news_train.filenames[0], X_train[0].getnnz()))
print("done in {0} seconds".format(time() - t))

fit_transform()是fit() 和 transform()合并起来的结果。

fit()完成语料库分析，提取词典等操作

transform()把每篇文档转换为向量

• 模型训练

from sklearn.naive_bayes import MultinomialNB

print("traning models ...".format(time() - t))
t = time()
y_train = news_train.target
clf = MultinomialNB(alpha=0.0001)
clf.fit(X_train, y_train)
train_score = clf.score(X_train, y_train)
print("train score: {0}".format(train_score))
print("done in {0} seconds".format(time() - t))

使用的是多项式模型，其中alpha值越小，越容易造成过拟合，值越大，容易造成欠拟合。

• 加载测试集，向量化，并测试

向量化的过程中只需要transform()操作就号了。

print("loading test dataset ...")
t = time()
news_test = load_files('datasets/mlcomp/379/test')
print("summary: {0} documents in {1} categories.".format(
    len(news_test.data), len(news_test.target_names)))
print("done in {0} seconds".format(time() - t))

#向量化
print("vectorizing test dataset ...")
t = time()
X_test = vectorizer.transform((d for d in news_test.data))
y_test = news_test.target
print("n_samples: %d, n_features: %d" % X_test.shape)
print("number of non-zero features in sample [{0}]: {1}".format(
    news_test.filenames[0], X_test[0].getnnz()))
print("done in %fs" % (time() - t))

#使用一个文档进行简单测试
pred = clf.predict(X_test[0])
print("predict: {0} is in category {1}".format(
    news_test.filenames[0], news_test.target_names[pred[0]]))
print("actually: {0} is in category {1}".format(
    news_test.filenames[0], news_test.target_names[news_test.target[0]]))

• 模型评价

print("predicting test dataset ...")
t = time()
pred = clf.predict(X_test)
print("done in %fs" % (time() - t))

from sklearn.metrics import classification_report

print("classification report on test set for classifier:")
print(clf)
print(classification_report(y_test, pred,
                            target_names=news_test.target_names))

#生成混淆矩阵
from sklearn.metrics import confusion_matrix

cm = confusion_matrix(y_test, pred)
print("confusion matrix:")
print(cm)

#  confusion matrix:
#  [[224   0   0   0   0   0   0   0   0   0   0   0   0   0   2   5   0   0   1  13]
#   [  1 267   5   5   2   8   1   1   0   0   0   2   3   2   1   0   0   0   0   0]
#   [  1  13 230  24   4  10   5   0   0   0   0   1   2   1   0   0   0   0   1   0]
#   [  0   9  21 242   7   2  10   1   0   0   1   1   7   0   0   0   0   0    0   0]
#   [  0   1   5   5 233   2   2   2   1   0   0   3   1   0   1   0   0   0    0   0]
#   [  0  20   6   3   1 260   0   0   0   2   0   1   0   0   2   0   2   0    0   0]
#   [  0   2   5  12   3   1 235  10   2   3   1   0   7   0   2   0   2   1    4   0]
#   [  0   1   0   0   1   0   8 300   4   1   0   0   1   2   3   0   2   0    1   0]
#   [  0   1   0   0   0   2   2   3 283   0   0   0   1   0   0   0   0   0    1   1]
#   [  0   1   1   0   1   2   1   2   0 297   8   1   0   1   0   0   0   0    0   0]
#   [  0   0   0   0   0   0   0   0   2   2 298   0   0   0   0   0   0   0    0   0]
#   [  0   1   2   0   0   1   1   0   0   0   0 284   2   1   0   0   2   1    2   0]
#   [  0  11   3   5   4   2   4   5   1   1   0   4 266   1   4   0   1   0    1   0]
#   [  1   1   0   1   0   2   1   0   0   0   0   0   1 266   2   1   0   0    1   0]
#   [  0   3   0   0   1   1   0   0   0   0   0   1   0   1 296   0   1   0    1   0]
#   [  3   1   0   1   0   0   0   0   0   0   1   0   0   2   1 280   0   1    1   2]
#   [  1   0   2   0   0   0   0   0   1   0   0   0   0   0   0   0 236   1    4   1]
#   [  1   0   0   0   0   1   0   0   0   0   0   0   0   0   0   3   0 290    1   0]
#   [  2   1   0   0   1   1   0   1   0   0   0   0   0   0   0   1  10   7  212   0]
#   [ 16   0   0   0   0   0   0   0   0   0   0   0   0   0   0  12   4   1    4 134]]

#可视化
# Show confusion matrix
plt.figure(figsize=(8, 8), dpi=144)
plt.title('Confusion matrix of the classifier')
ax = plt.gca()                                  
ax.spines['right'].set_color('none')            
ax.spines['top'].set_color('none')
ax.spines['bottom'].set_color('none')
ax.spines['left'].set_color('none')
ax.xaxis.set_ticks_position('none')
ax.yaxis.set_ticks_position('none')
ax.set_xticklabels([])
ax.set_yticklabels([])
plt.matshow(cm, fignum=1, cmap='gray')
plt.colorbar();

 

扩展：

朴素贝叶斯分为三类：

(1) GauussianNB 高斯模型

sklearn.naive_bayes.GaussianNB(priors=None)

(2) BernoulliNB 伯怒利模型

sklearn.naive_bayes.BernoulliNB(alpha=1.0, binarize=0.0, fit_prior=True, class_prior=None)

只考虑词是否出现，数值就是0或者1

(3) MultinomialNB 多项式模型

sklearn.naive_bayes.MultinomialNB(alpha=1.0, fit_prior=True, class_prior=None)

考虑词频，是一个浮点数