# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('OpeningLines2.txt', delimiter = '\t')
dataset.head()

# EDA
dataset.describe()
dataset.groupby('Review').describe()
dataset['length'] = dataset['Opening'].apply(len)
dataset.head()

# Cleaning the texts
import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
corpus = []
for i in range(0, 167):
    opening = re.sub('[^a-zA-Z]', ' ', dataset['Opening'][i])
    opening = opening.lower()
    opening = opening.split()
    ps = PorterStemmer()
    opening = [ps.stem(word) for word in opening if not word in set(stopwords.words('english'))]
    opening = ' '.join(opening)
    corpus.append(opening)

# Creating the Bag of Words model
from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features = 1000)
X = cv.fit_transform(corpus).toarray()
y = dataset.iloc[:, 2].values

# Splitting the dataset into the Training set and Test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state = 0)

# Fitting Naive Bayes to the Training set
from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train)

# Predicting the Test set results
y_pred = classifier.predict(X_test)

# Making the Confusion Matrix
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)