12.3

import csv

 

file_path = r'EmailData.txt'

EmailData = open(file_path,'r',encoding='utf-8')

Email_data = []

Email_target = []

csv_reader = csv.reader(EmailData,delimiter='\t')

 

for line in csv_reader:

    Email_data.append(line[1])

    Email_target.append(line[0])

EmailData.close()

 

Email_data_clear = []

for line in Email_data:

    for char in line:

        if char.isalpha() is False:

            newString = line.replace(char," ")

    tempList = newString.split(" ")




 

    Email_data_clear.append(tempList)

 

 

Email_data_clear2 = []

for line in Email_data_clear:

    tempList = []

    for word in line:

        if word != '' and len(word) > 3 and word.isalpha():

            tempList.append(word)

    tempString = ' '.join(tempList)

    Email_data_clear2.append(tempString)

Email_data_clear = Email_data_clear2

 

from sklearn.model_selection import train_test_split

x_train,x_test,y_train,y_test = train_test_split(Email_data_clear2,Email_target,test_size=0.3,random_state=0,stratify=Email_target)

 

from sklearn.feature_extraction.text import TfidfVectorizer

tfidf = TfidfVectorizer()

X_train = tfidf.fit_transform(x_train)

X_test = tfidf.transform(x_test)

 

import numpy as np

X_train = X_train.toarray()

X_test = X_test.toarray()

X_train.shape

 

for i in range(X_train.shape[0]):

    for j in range(X_train.shape[1]):

        if X_train[i][j] != 0:

            print(i,j,X_train[i][j])

 

 

from sklearn.naive_bayes import GaussianNB

gnb = GaussianNB()

module = gnb.fit(X_train,y_train)

y_predict = module.predict(X_test)

 

from sklearn.metrics import classification_report

cr = classification_report(y_predict,y_test)

print(cr)