要點：

理解樸素貝葉斯演算法

理解機器學習演算法建模過程

理解文字常用處理流程

理解模型評估方法

 垃圾郵件分類
資料準備：
用csv讀取郵件資料，分解出郵件類別及郵件內容。
對郵件內容進行預處理：去掉長度小於3的詞，去掉沒有語義的詞等
嘗試使用nltk庫：
pip install nltk
nltk.download
不成功：就使用詞頻統計的處理方法
訓練集和測試集資料劃分
from sklearn.model_selection import train_test_split

from nltk.corpue import stopwords
stops=stopwords('english')
stops
tokens
 
=[token for tokens if token not in stops]
' '.join(tokens)

text

#pip install nltk
#nltk.download
from sklearn.model_selection import train_test_split
import nltk
from nltk.stem import WordNetLemmatizer
#lemmatizer=WordNetLemmatizer()
#lemmatizer.lemmatize('leaves')

#垃圾郵件分類
text='''Yes i think so. I am in office but my lap is in room i think thats on for the last few days. I didnt shut that down'''

import
 
 nltk
from nltk.stem import WordNetLemmatizer
#lemmatizer=WordNetLemmatizer()
#lemmatizer.lemmatize('leaves')

#預處理
def preprocessing(text):
    #text=text.decode("utf-8")
    tokens=[word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]
    stops=stopwords.words('english')
    tokens
 
=[token for token in tokens if token not in stops]
 
    tokens=[token.lower() for token in tokens if len(token)>=3]
    lmtzr=WordNetLemmatizer()
    tokens=[lmtzr.lemmatize(token) for  token in tokens]
    preprocessed_text=' '.join(tokens)
    return preprocessed_text

text

#讀取資料集
import csv    #用csv讀取郵件資料，分解出郵件類別及郵件內容
file_path = r'C:\Users\Administrator\Desktop\SMSSpamCollectionjsn.txt'
sms = open(file_path,'r',encoding = 'utf-8')
sms_data = []
sms_label = []
csv_reader = csv.reader(sms,delimiter='\t')
for line in csv_reader:
    sms_label.append(line[0]) 
    sms_data.append(line[1])
sms.close()

#按0.7:0.3比例分為訓練集和測試集
import numpy as np
sms_data=np.array(sms_data)
sms_label=np.array(sms_label)

from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(sms_data,sms_label,test_size=0.3,random_state=0,stratify=sms_label) #訓練集，測試集

#將其向量化
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(min_df = 2,ngram_range=(1,2),stop_words='english',strip_accents='unicode',norm='l2')
X_train = vectorizer.fit_transform(x_train)
X_test = vectorizer.transform(x_test)

#樸素貝葉斯分類群
from sklearn.naive_bayes import MultinomialNB
clf=MultinomialNB().fit(X_train,y_train)
y_nb_pred=clf.predict(X_test)

#分類結果顯示
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

print(y_nb_pred.shape,y_nb_pred)#x_test預測結果
print('nb_confusion_matrik：')
cm=confusion_matrix(y_test,y_nb_pred)#混淆矩陣
print(cm)
print('nb_classification_report:')
cr=classification_report(y_test,y_nb_pred)#主要分類指標的文字報告
print(cr)
feature_names=vectorizer.get_feature_names()#出現過的單詞列表
coefs=clf.coef_#先驗概率 P(x_i|y),6034 feature_log_prob_
intercept=clf.intercept_#P(y),class_log_prior_:array,shape(n_classes,)
coefs_with_fns=sorted(zip(coefs[0],feature_names))#對數概率P(x_i|y)與單詞x_i對映

n=10
top=zip(coefs_with_fns[:n],coefs_with_fns[:-(n+1):-1])
for(coef_1,fn_1),(coef_2,fn_2) in top:
    print('\t%.4f\t%-15s\t\t%.4f\t%-15s'%(coef_1,fn_1,coef_2,fn_2))

sms_label

print(len(x_train),len(x_test))

print(X_train.shape,X_test.shape)

x_train

X_train

a=X_train.toarray()
a

for i in range(1000):
    for j in range(5984):
        if a[i,j]!=0:
            print(i,j,a[i,j])
            
vectorizer.get_feature_names()[1610]