mwitiderrick

Create a repo. Make sure there is at least one file in it (even just the README) Generate ssh key:

ssh-keygen -t rsa -C "your_email@example.com"

Copy the contents of the file ~/.ssh/id_rsa.pub to your SSH keys in your GitHub account settings. Test SSH key:

ssh -T git@github.com

mwitiderrick

#!flask/bin/python
from flask import Flask, jsonify, abort, request, make_response, url_for
from flask.ext.httpauth import HTTPBasicAuth

app = Flask(__name__, static_url_path = "")
auth = HTTPBasicAuth()

@auth.get_password
def get_password(username):
    if username == 'miguel':

mwitiderrick

import numpy as np
import pandas as pd
df = pd.read_csv('imdb_labelled.txt', delimiter = '\t', engine='python', quoting = 3)

mwitiderrick

import re
import nltk
nltk.download('stopwords')
nltk.download('wordnet')
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer

mwitiderrick

for i in range(0, 1000):
  review = re.sub('[^a-zA-Z]', ' ', df['Review'][i])
  review = review.lower()
  review = review.split()
  lemmatizer = WordNetLemmatizer()
  review = [lemmatizer.lemmatize(word) for word in review if not word in set(stopwords.words('english'))]
  review = ' '.join(review)
  corpus.append(review)

mwitiderrick

from sklearn.feature_extraction.text import CountVectorizer
cv = CountVectorizer(max_features = 2000)
X = cv.fit_transform(corpus).toarray()
y = dataset.iloc[:, 1].values

mwitiderrick

from sklearn.feature_extraction.text import TfidfTransformer
tf_transformer = TfidfTransformer()
X = tf_transformer.fit_transform(X).toarray()

mwitiderrick

from sklearn.feature_extraction.text import TfidfVectorizer
tfidfVectorizer = TfidfVectorizer(max_features =2000)
X = tfidfVectorizer.fit_transform(corpus).toarray()

mwitiderrick

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)

mwitiderrick

from sklearn.naive_bayes import GaussianNB
classifier = GaussianNB()
classifier.fit(X_train, y_train)