1.读取
2.数据预处理
3.数据划分—训练集和测试集数据划分
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)
4.文本特征提取
sklearn.feature_extraction.text.CountVectorizer
sklearn.feature_extraction.text.TfidfVectorizer
from sklearn.feature_extraction.text import TfidfVectorizer
tfidf2 = TfidfVectorizer()
观察邮件与向量的关系
向量还原为邮件
4.模型选择
from sklearn.naive_bayes import GaussianNB
from sklearn.naive_bayes import MultinomialNB
说明为什么选择这个模型？
5.模型评价：混淆矩阵，分类报告
from sklearn.metrics import confusion_matrix
confusion_matrix = confusion_matrix(y_test, y_predict)
说明混淆矩阵的含义
from sklearn.metrics import classification_report
说明准确率、精确率、召回率、F值分别代表的意义
6.比较与总结
如果用CountVectorizer进行文本特征生成，与TfidfVectorizer相比，效果如何？
# 文本特征提取(向量)
tfidf = TfidfVectorizer()
X_train = tfidf.fit_transform(x_train).toarray()
X_test = tfidf.transform(x_test).toarray()
# 向量还原文件
import numpy as np
a = np.flatnonzero(X_train[0]) # 输入一个矩阵，返回非零元素的下标
# 非零元素对应的单词
b = tfidf.vocabulary_
key_list = []
for key, value in b.items():
if value in a:
key_list.append(key)
print("非零元素对应的单词:", key_list)
# 5、模型的构建、训练、预测
m_model = MultinomialNB()
m_model.fit(X_train, y_train)
y_m_pre = m_model.predict(X_test)
# 模型评价
# 朴素贝叶斯
print("朴素贝叶斯")
m_cm = confusion_matrix(y_test, y_m_pre)
print("混淆矩阵：
", m_cm)
m_cr = classification_report(y_test, y_m_pre)
print("分类报告：
", m_cr)
print("模型准确率：", (m_cm[0][0] + m_cm[1][1]) / np.sum(m_cm))