Commit
•
871abaf
1
Parent(s):
306642b
Upload spamemailfinder_159.py
Browse files- spamemailfinder_159.py +86 -0
spamemailfinder_159.py
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# -*- coding: utf-8 -*-
|
2 |
+
"""spamemailfinder.159
|
3 |
+
|
4 |
+
Automatically generated by Colab.
|
5 |
+
|
6 |
+
Original file is located at
|
7 |
+
https://colab.research.google.com/drive/1VK3x8uRt-HA3ZSip5FllNRtdqeRZ-X8y
|
8 |
+
"""
|
9 |
+
|
10 |
+
import string
|
11 |
+
import numpy as np
|
12 |
+
import pandas as pd
|
13 |
+
import nltk
|
14 |
+
from nltk.corpus import stopwords
|
15 |
+
from nltk.stem.porter import PorterStemmer
|
16 |
+
from sklearn.feature_extraction.text import CountVectorizer
|
17 |
+
from sklearn.model_selection import train_test_split
|
18 |
+
from sklearn.naive_bayes import MultinomialNB,BernoulliNB,GaussianNB
|
19 |
+
|
20 |
+
nltk.download('stopwords')
|
21 |
+
|
22 |
+
df = pd.read_csv("spam_ham_dataset.csv")
|
23 |
+
|
24 |
+
df.head()
|
25 |
+
|
26 |
+
df.info()
|
27 |
+
|
28 |
+
df.isna().sum()
|
29 |
+
|
30 |
+
df['text'] = df['text'].apply(lambda x: x.replace('\r\n', ' '))
|
31 |
+
|
32 |
+
df.head()
|
33 |
+
|
34 |
+
stemmer = PorterStemmer()
|
35 |
+
|
36 |
+
corpus = []
|
37 |
+
|
38 |
+
stopwords_set = set(stopwords.words('english'))
|
39 |
+
|
40 |
+
for i in range(len(df)):
|
41 |
+
text = df['text'].iloc[i].lower()
|
42 |
+
text = text.translate(str.maketrans('', '',string.punctuation)).split()
|
43 |
+
text = [stemmer.stem(word) for word in text if word not in stopwords_set]
|
44 |
+
text = ''.join(text)
|
45 |
+
corpus.append(text)
|
46 |
+
|
47 |
+
vectorizer = CountVectorizer()
|
48 |
+
|
49 |
+
X = vectorizer.fit_transform(corpus).toarray()
|
50 |
+
y = df.label_num
|
51 |
+
|
52 |
+
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
53 |
+
|
54 |
+
mnb = MultinomialNB()
|
55 |
+
bnb = BernoulliNB()
|
56 |
+
gnb = GaussianNB()
|
57 |
+
|
58 |
+
mnb.fit(X_train, y_train)
|
59 |
+
|
60 |
+
bnb.fit(X_train, y_train)
|
61 |
+
|
62 |
+
gnb.fit(X_train, y_train)
|
63 |
+
|
64 |
+
mnb.score(X_test, y_test)
|
65 |
+
|
66 |
+
bnb.score(X_test, y_test)
|
67 |
+
|
68 |
+
gnb.score(X_test, y_test)
|
69 |
+
|
70 |
+
email_to_classify = df.text.values[19]
|
71 |
+
|
72 |
+
email_to_classify
|
73 |
+
|
74 |
+
email_text = email_to_classify.lower().translate(str.maketrans('', '',string.punctuation)).split()
|
75 |
+
email_text = [stemmer.stem(word) for word in text if word not in stopwords_set]
|
76 |
+
email_text = ''.join(email_text)
|
77 |
+
|
78 |
+
email_corpus = [email_text]
|
79 |
+
|
80 |
+
X_email = vectorizer.transform(email_corpus)
|
81 |
+
|
82 |
+
mnb.predict(X_email)
|
83 |
+
|
84 |
+
bnb.predict(X_email)
|
85 |
+
|
86 |
+
gnb.predict(X_email.toarray())
|