垃圾郵件分類2

1.讀取

# 1、讀取數據集
def read_dataset():
     file_path = r'SMSSpamCollection'
     sms = open(file_path, encoding='utf-8')
     sms_data = []
     sms_label = []
     csv_reader = csv.reader(sms, delimiter='\t')
     for line in csv_reader:
        sms_label.append(line[0])  # 提取出標籤
        sms_data.append(preprocessing(line[1]))  # 提取出特徵
     sms.close()
     return sms_data, sms_label

2.數據預處理

# 2、數據預處理
def preprocess(text):
     tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]  # 分詞
     stops = stopwords.words('english')  # 使用英文的停用詞表
     tokens = [token for token in tokens if token not in stops]  # 去除停用詞
     tokens = [token.lower() for token in tokens if len(token) >= 3]  # 大小寫，短詞
     wnl = WordNetLemmatizer()
     tag = nltk.pos_tag(tokens)  # 詞性
     tokens = [wnl.lemmatize(token, pos=get_wordnet_pos(tag[i][1])) for i, token in enumerate(tokens)]  # 詞性還原
     preprocessed_text = ' '.join(tokens)
     return preprocessed_text

3.數據劃分—訓練集和測試集數據劃分

from sklearn.model_selection import train_test_split

x_train,x_test, y_train, y_test = train_test_split(data, target, test_size=0.2, random_state=0, stratify=y_train)

# 3、劃分數據集
def split_dataset(data, label):
     x_train, x_test, y_train, y_test = train_test_split(data, label, test_size=0.2, random_state=0, stratify=label)
     return x_train, x_test, y_train, y_test

4.文本特徵提取

sklearn.feature_extraction.text.CountVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.CountVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer

sklearn.feature_extraction.text.TfidfVectorizer

https://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.text.TfidfVectorizer.html?highlight=sklearn%20feature_extraction%20text%20tfidfvectorizer#sklearn.feature_extraction.text.TfidfVectorizer

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf2 = TfidfVectorizer()

觀察郵件與向量的關係

向量還原爲郵件

# 4、文本特徵提取
# 把文本轉化爲tf-idf的特徵矩陣
def tfidf_dataset(x_train,x_test):
     tfidf = TfidfVectorizer()
     X_train = tfidf.fit_transform(x_train)  
     X_test = tfidf.transform(x_test)
     return X_train, X_test, tfidf

# 向量還原成郵件
def revert_mail(x_train, X_train, model):
    s = X_train.toarray()[0]
    print("第一封郵件向量表示爲：", s)
    a = np.flatnonzero(X_train.toarray()[0])  # 非零元素的位置（index）
    print("非零元素的位置:", a)
    print("向量的非零元素的值：", s[a])
    b = model.vocabulary_  # 詞彙表
    key_list = []
    for key, value in b.items():
        if value in a:
            key_list.append(key)  # key非0元素對應的單詞
    print("向量非零元素對應的單詞：", key_list)
    print("向量化之前的郵件：", x_train[0])

5.模型選擇

from sklearn.naive_bayes import GaussianNB

from sklearn.naive_bayes import MultinomialNB

說明爲什麼選擇這個模型？

# 5、模型選擇
def mnb_model(x_train, x_test, y_train, y_test):
    mnb = MultinomialNB()
    mnb.fit(x_train, y_train)
    pre = mnb.predict(x_test)
    print("總數：", len(y_test))
    print("預測正確數：", (pre == y_test).sum())
    print("預測準確率：",sum(pre == y_test) / len(y_test))
    return pre

6.模型評價：混淆矩陣，分類報告

from sklearn.metrics import confusion_matrix

confusion_matrix = confusion_matrix(y_test, y_predict)

說明混淆矩陣的含義

from sklearn.metrics import classification_report

說明準確率、精確率、召回率、F值分別代表的意義

# 6、模型評價
def class_report(pre, y_test):
    conf_matrix = confusion_matrix(y_test, pre)
    print("=====================================================")
    print("混淆矩陣：\n", conf_matrix)
    c = classification_report(y_test, pre)
    print("分類報告：\n", c)
    print("模型準確率：", (conf_matrix[0][0] + conf_matrix[1][1]) / np.sum(conf_matrix))

完整代碼：

# -*- coding:utf-8 -*-
from sklearn.model_selection import train_test_split
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.metrics import confusion_matrix, classification_report
import numpy as np
 
import nltk
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
import csv
def get_wordnet_pos(treebank_tag):# 根據詞性，生成還原參數pos
     if treebank_tag.startswith('J'):  # adj
        return nltk.corpus.wordnet.ADJ
     elif treebank_tag.startswith('V'):  # v
        return nltk.corpus.wordnet.VERB
     elif treebank_tag.startswith('N'):  # n
         return nltk.corpus.wordnet.NOUN
     elif treebank_tag.startswith('R'):  # adv
        return nltk.corpus.wordnet.ADV
     else:
       return nltk.corpus.wordnet.NOUN
 
 # 預處理
def preprocessing(text):
     tokens = [word for sent in nltk.sent_tokenize(text) for word in nltk.word_tokenize(sent)]  # 分詞
     stops = stopwords.words('english')  # 使用英文的停用詞表
     tokens = [token for token in tokens if token not in stops]  # 停用詞
     tokens = [token.lower() for token in tokens if len(token) >= 3]  # 大小寫，短詞
     lmtzr = WordNetLemmatizer()
     tag = nltk.pos_tag(tokens)  # 詞性
     tokens = [lmtzr.lemmatize(token, pos=get_wordnet_pos(tag[i][1])) for i, token in enumerate(tokens)]  # 詞性還原
     preprocessed_text = ' '.join(tokens)
     return preprocessed_text
 
# 讀取數據集
def read_dataset():
     file_path =r'SMSSpamCollection'
     sms = open(file_path, encoding='utf-8')#讀取數據
     sms_label = []  # 存儲標題
     sms_data = []#存儲數據
     csv_reader = csv.reader(sms, delimiter='\t')
     for line in csv_reader:
        sms_label.append(line[0])  # 提取出標籤
        sms_data.append(preprocessing(line[1]))  # 對每封郵件做預處理
     sms.close()
     return sms_data, sms_label
 
# 劃分數據集
def split_dataset(data, label):
     x_train, x_test, y_train, y_test = train_test_split(data, label, test_size=0.2, random_state=0, stratify=label)
     return x_train, x_test, y_train, y_test
 
# 把原始文本轉化爲tf-idf的特徵矩陣
def tfidf_dataset(x_train,x_test):
     tfidf = TfidfVectorizer()
     X_train = tfidf.fit_transform(x_train)  # X_train用fit_transform生成詞彙表
     X_test = tfidf.transform(x_test)  # X_test要與X_train詞彙表相同，因此在X_train進行fit_transform基礎上進行transform操作
     return X_train, X_test, tfidf
 
# 向量還原郵件
def revert_mail(x_train, X_train, model):
    s = X_train.toarray()[0]
    print("第一封郵件向量表示爲：", s)
    # 該函數輸入一個矩陣，返回扁平化後矩陣中非零元素的位置（index）
    a = np.flatnonzero(X_train.toarray()[0])  # 非零元素的位置（index）
    print("非零元素的位置:", a)
    print("向量的非零元素的值：", s[a])
    b = model.vocabulary_  # 詞彙表
    key_list = []
    for key, value in b.items():
        if value in a:
            key_list.append(key)  # key非0元素對應的單詞
    print("向量非零元素對應的單詞：", key_list)
    print("向量化之前的郵件：", x_train[0])
 
# 模型選擇（根據數據特點選擇多項式分佈）
def mnb_model(x_train, x_test, y_train, y_test):
    mnb = MultinomialNB()
    mnb.fit(x_train, y_train)
    ypre_mnb = mnb.predict(x_test)
    print("總數：", len(y_test))
    print("預測正確數：", (ypre_mnb == y_test).sum())
    return ypre_mnb
 
# 模型評價：混淆矩陣，分類報告
def class_report(ypre_mnb, y_test):
    conf_matrix = confusion_matrix(y_test, ypre_mnb)
    print("混淆矩陣：\n", conf_matrix)
    c = classification_report(y_test, ypre_mnb)
    print("------------------------------------------")
    print("分類報告：\n", c)
    print("模型準確率：", (conf_matrix[0][0] + conf_matrix[1][1]) / np.sum(conf_matrix))
 
if __name__ == '__main__':
    sms_data, sms_label = read_dataset() # 讀取數據集
    x_train, x_test, y_train, y_test = split_dataset(sms_data, sms_label) # 劃分數據集
    X_train, X_test,tfidf = tfidf_dataset(x_train, x_test) # 把原始文本轉化爲tf-idf的特徵矩陣
    revert_mail(x_train, X_train, tfidf) # 向量還原成郵件
    y_mnb = mnb_model(X_train, X_test, y_train,y_test) # 模型選擇
    class_report(y_mnb, y_test) # 模型評價

6.比較與總結

如果用CountVectorizer進行文本特徵生成，與TfidfVectorizer相比，效果如何？

CountVectorizer：只考慮詞彙在文本中出現的頻率，屬於詞袋模型特徵。
TfidfVectorizer：除了考量某詞彙在文本出現的頻率，還關注包含這個詞彙的所有文本的數量，能夠削減高頻沒有意義的詞彙出現帶來的影響, 挖掘更有意義的特徵。屬於Tfidf特徵。
CountVectorizer與TfidfVectorizer相比，對於負類的預測更加準確，而正類的預測則稍遜色。但總體預測正確率也比TfidfVectorizer稍高，相比之下似乎CountVectorizer更適合進行預測。

垃圾郵件分類2

抖音去水印超簡單

規範使用線程池與底層原理詳解

centos7安裝mysql（完整）

SpringCloud微服務之Ribbon負載均衡（一）

Java集合多線程安全

https://yachay.unat.edu.pe/blog/index.php?comment_area=format_blog&comment_component=blog&comment_co

linux以太網驅動總結