-
Notifications
You must be signed in to change notification settings - Fork 1
/
spamham_classifier.py
68 lines (48 loc) · 1.85 KB
/
spamham_classifier.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
# -*- coding: utf-8 -*-
"""spamham classifier.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1hjRjETtrpvBpue-2uaEWqVv88_UPJ7gj
"""
import pandas as pd
from google.colab import files
upload=files.upload()
messages=pd.read_csv('SMSSpamCollection',sep='\t',names=['label','message'])
messages.head()
import nltk
nltk.download('punkt')
nltk.download('stopwords')
nltk.download('wordnet')
# Data Cleaning
import re
from nltk.stem import PorterStemmer
from nltk.stem import WordNetLemmatizer
from nltk.corpus import stopwords
ps=PorterStemmer()
lemmatize=WordNetLemmatizer()
#Pre-processing
corpus=[]
for i in range(0,len(messages)):
review=re.sub('[^a-zA-Z]', ' ', messages['message'][i])
review = review.lower()
review = review.split()
review = [ps.stem(word) for word in review if not word in stopwords.words('english')]
review = ' '.join(review)
corpus.append(review)
# Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features=2500)
X = cv.fit_transform(corpus).toarray()
y=pd.get_dummies(messages['label'])
y=y.iloc[:,1].values
# Train Test Split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)
# Training model using Naive bayes classifier
from sklearn.naive_bayes import MultinomialNB
spam_detect_model = MultinomialNB().fit(X_train, y_train)
y_pred=spam_detect_model.predict(X_test)
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
print(confusion_matrix(y_test,y_pred))
print("Accuracy Score {}".format(accuracy_score(y_test,y_pred)))
print("Classification report: {}".format(classification_report(y_test,y_pred)))