Chapter22FileClassify.py

# -*- coding: utf-8 -*-
"""
Created on Wed Aug 15 16:08:28 2018

@author: Administrator
"""

import matplotlib.pyplot as plt

from sklearn.datasets import load_files
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import MultinomialNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import accuracy_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier


# 1) 导入数据
categories = ['alt.atheism',
              'rec.sport.hockey',
              'comp.graphics',
              'sci.crypt',
              'comp.os.ms-windows.misc',
              'sci.electronics',
              'comp.sys.ibm.pc.hardware',
              'sci.med',
              'comp.sys.mac.hardware',
              'sci.space',
              'comp.windows.x',
              'soc.religion.christian',
              'misc.forsale',
              'talk.politics.guns',
              'rec.autos' 
              'talk.politics.mideast',
              'rec.motorcycles',
              'talk.politics.misc',
              'rec.sport.baseball',
              'talk.religion.misc']
# 导入训练数据
train_path = '20news-bydate-train'
dataset_train = load_files(container_path=train_path, categories=categories)
# 导入评估数据
test_path = '20news-bydate-test'
dataset_test = load_files(container_path=test_path, categories=categories)


# 2）数据准备与理解

# 计算词频
count_vect = CountVectorizer(stop_words='english', decode_error='ignore')
X_train_counts = count_vect.fit_transform(dataset_train.data)
# 查看数据维度
print(X_train_counts.shape)

# 计算TF-IDF
tf_transformer = TfidfVectorizer(stop_words='english', decode_error='ignore')
X_train_counts_tf = tf_transformer.fit_transform(dataset_train.data)
# 查看数据维度
print(X_train_counts_tf.shape)


# 设置评估算法的基准
num_folds = 10
seed = 7
scoring = 'accuracy'


# 3）评估算法
# 生成算法模型
models = {}
models['LR'] = LogisticRegression()
models['SVM'] = SVC()
models['CART'] = DecisionTreeClassifier()
models['MNB'] = MultinomialNB()
models['KNN'] = KNeighborsClassifier()

# 比较算法
results = []
for key in models:
    kfold = KFold(n_splits=num_folds, random_state=seed)
    cv_results = cross_val_score(models[key], X_train_counts_tf, dataset_train.target, cv=kfold, scoring=scoring)
    results.append(cv_results)
    print('%s : %f (%f)' % (key, cv_results.mean(), cv_results.std()))

# 箱线图比较算法
fig = plt.figure()
fig.suptitle('Algorithm Comparision')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(models.keys())
plt.show()

# 4）算法调参
# 调参LR
param_grid = {}
param_grid['C'] = [0.1, 5, 13, 15]
model = LogisticRegression()
kfold = KFold(n_splits=num_folds, random_state=seed)
grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring=scoring, cv=kfold)
grid_result = grid.fit(X=X_train_counts_tf, y=dataset_train.target)
print('最优 : %s 使用 %s' % (grid_result.best_score_, grid_result.best_params_))

# 调参MNB
param_grid = {}
param_grid['alpha'] = [0.001, 0.01, 0.1, 1.5]
model = MultinomialNB()
kfold = KFold(n_splits=num_folds, random_state=seed)
grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring=scoring, cv=kfold)
grid_result = grid.fit(X=X_train_counts_tf, y=dataset_train.target)
print('最优 : %s 使用 %s' % (grid_result.best_score_, grid_result.best_params_))

# 5）集成算法
ensembles = {}
ensembles['RF'] = RandomForestClassifier()
ensembles['AB'] = AdaBoostClassifier()
# 比较集成算法
results = []
for key in ensembles:
    kfold = KFold(n_splits=num_folds, random_state=seed)
    cv_results = cross_val_score(ensembles[key], X_train_counts_tf, dataset_train.target, cv=kfold, scoring=scoring)
    results.append(cv_results)
    print('%s : %f (%f)' % (key, cv_results.mean(), cv_results.std()))

# 箱线图比较算法
fig = plt.figure()
fig.suptitle('Algorithm Comparision')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(ensembles.keys())
plt.show()

# 调参RF
param_grid = {}
param_grid['n_estimators'] = [10, 100, 150, 200]
model = RandomForestClassifier()
kfold = KFold(n_splits=num_folds, random_state=seed)
grid = GridSearchCV(estimator=model, param_grid=param_grid, scoring=scoring, cv=kfold)
grid_result = grid.fit(X=X_train_counts_tf, y=dataset_train.target)
print('最优 : %s 使用 %s' % (grid_result.best_score_, grid_result.best_params_))

# 6）生成模型
model = LogisticRegression(C=13)
model.fit(X_train_counts_tf, dataset_train.target)
X_test_counts = tf_transformer.transform(dataset_test.data)
predictions = model.predict(X_test_counts)
print(accuracy_score(dataset_test.target, predictions))
print(classification_report(dataset_test.target, predictions))