├── README.md
├── Spamclassifier.py
└── smsspamcollection
    ├── SMSSpamCollection
    └── readme


/README.md:
--------------------------------------------------------------------------------
1 | # SpamClassifier


--------------------------------------------------------------------------------
/Spamclassifier.py:
--------------------------------------------------------------------------------
 1 | # importing the Dataset
 2 | 
 3 | import pandas as pd
 4 | 
 5 | messages = pd.read_csv('smsspamcollection/SMSSpamCollection', sep='\t',
 6 |                            names=["label", "message"])
 7 | 
 8 | #Data cleaning and preprocessing
 9 | import re
10 | import nltk
11 | nltk.download('stopwords')
12 | 
13 | from nltk.corpus import stopwords
14 | from nltk.stem.porter import PorterStemmer
15 | ps = PorterStemmer()
16 | corpus = []
17 | for i in range(0, len(messages)):
18 |     review = re.sub('[^a-zA-Z]', ' ', messages['message'][i])
19 |     review = review.lower()
20 |     review = review.split()
21 |     
22 |     review = [ps.stem(word) for word in review if not word in stopwords.words('english')]
23 |     review = ' '.join(review)
24 |     corpus.append(review)
25 |     
26 |     
27 | # Creating the Bag of Words model
28 | from sklearn.feature_extraction.text import CountVectorizer
29 | cv = CountVectorizer(max_features=2500)
30 | X = cv.fit_transform(corpus).toarray()
31 | 
32 | y=pd.get_dummies(messages['label'])
33 | y=y.iloc[:,1].values
34 | 
35 | 
36 | # Train Test Split
37 | 
38 | from sklearn.model_selection import train_test_split
39 | X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)
40 | 
41 | # Training model using Naive bayes classifier
42 | 
43 | from sklearn.naive_bayes import MultinomialNB
44 | spam_detect_model = MultinomialNB().fit(X_train, y_train)
45 | 
46 | y_pred=spam_detect_model.predict(X_test)
47 | 
48 | 
49 | 
50 | 
51 | 
52 | 
53 | 
54 | 
55 | 
56 | 
57 | 
58 | 
59 | 
60 | 
61 | 
62 | 
63 | 
64 | 
65 | 
66 | 
67 | 
68 | 


--------------------------------------------------------------------------------
/smsspamcollection/readme:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/krishnaik06/SpamClassifier/5fa41eaf3ec0d21d3ffced673800d25b6b8ffc20/smsspamcollection/readme


--------------------------------------------------------------------------------