code:
import re? #正則表達式
from bs4 import BeautifulSoup? #html標簽處理
import pandas as pd
def review_to_wordlist(review):
'''
把IMDB的評論轉成詞序列
'''
# 去掉HTML標簽，拿到內容
review_text = BeautifulSoup(review).get_text()
# 用正則表達式取出符合規范的部分
review_text = re.sub("[^a-zA-Z]"," ", review_text)
# 小寫化所有的詞，并轉成詞list
words = review_text.lower().split()
# 返回words
return words
# 使用pandas讀入訓練和測試csv文件
train = pd.read_csv('labeledTrainData.tsv', header=0, delimiter="\t", quoting=3)
test = pd.read_csv('testData.tsv', header=0, delimiter="\t", quoting=3 )
# 取出情感標簽，positive/褒 或者 negative/貶
y_train = train['sentiment']
# 將訓練和測試數據都轉成詞list
train_data = []
for i in range(0,len(train['review'])):
train_data.append(" ".join(review_to_wordlist(train['review'][i])))
test_data = []
for i in range(0,len(test['review'])):
test_data.append(" ".join(review_to_wordlist(test['review'][i])))
#train_data
from sklearn.feature_extraction.text import TfidfVectorizer as TFIV
# 初始化TFIV對象，去停用詞，加2元語言模型
tfv = TFIV(min_df=3,? max_features=None, strip_accents='unicode', analyzer='word',token_pattern=r'\w{1,}', ngram_range=(1, 2), use_idf=1,smooth_idf=1,sublinear_tf=1, stop_words = 'english')
# 合并訓練和測試集以便進行TFIDF向量化操作
X_all = train_data + test_data
len_train = len(train_data)
# 這一步有點慢，去喝杯茶刷會兒微博知乎歇會兒...
tfv.fit(X_all)
X_all = tfv.transform(X_all)
# 恢復成訓練集和測試集部分
X = X_all[:len_train]
X_test = X_all[len_train:]
#X_test
# 多項式樸素貝葉斯
from sklearn.naive_bayes import MultinomialNB as MNB
model_NB = MNB()
model_NB.fit(X, y_train) #特征數據直接灌進來
MNB(alpha=1.0, class_prior=None, fit_prior=True)
from sklearn.cross_validation import cross_val_score
import numpy as np
print ("多項式貝葉斯分類器20折交叉驗證得分: ", np.mean(cross_val_score(model_NB, X, y_train, cv=20, scoring='roc_auc')))
# 多項式貝葉斯分類器20折交叉驗證得分: 0.950837239
