# -*- coding: utf-8 -*-
"""spamemailfinder.159

Automatically generated by Colab.

Original file is located at
    https://colab.research.google.com/drive/1VK3x8uRt-HA3ZSip5FllNRtdqeRZ-X8y
"""

import string
import numpy as np
import pandas as pd
import nltk
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import MultinomialNB,BernoulliNB,GaussianNB

nltk.download('stopwords')

df = pd.read_csv("spam_ham_dataset.csv")

df.head()

df.info()

df.isna().sum()

df['text'] = df['text'].apply(lambda x: x.replace('\r\n', ' '))

df.head()

stemmer = PorterStemmer()

corpus = []

stopwords_set = set(stopwords.words('english'))

for i in range(len(df)):
  text = df['text'].iloc[i].lower()
  text = text.translate(str.maketrans('', '',string.punctuation)).split()
  text = [stemmer.stem(word) for word in text if word not in stopwords_set]
  text = ''.join(text)
  corpus.append(text)

vectorizer = CountVectorizer()

X = vectorizer.fit_transform(corpus).toarray()
y = df.label_num

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

mnb = MultinomialNB()
bnb = BernoulliNB()
gnb = GaussianNB()

mnb.fit(X_train, y_train)

bnb.fit(X_train, y_train)

gnb.fit(X_train, y_train)

mnb.score(X_test, y_test)

bnb.score(X_test, y_test)

gnb.score(X_test, y_test)

email_to_classify = df.text.values[19]

email_to_classify

email_text = email_to_classify.lower().translate(str.maketrans('', '',string.punctuation)).split()
email_text = [stemmer.stem(word) for word in text if word not in stopwords_set]
email_text = ''.join(email_text)

email_corpus = [email_text]

X_email = vectorizer.transform(email_corpus)

mnb.predict(X_email)

bnb.predict(X_email)

gnb.predict(X_email.toarray())