#!/usr/bin/env python
# coding: utf-8

# # Load Classfier

# In[1]:


# Importing the libraries
import numpy as np
import re
import pickle 
import nltk
from nltk.corpus import stopwords
from sklearn.datasets import load_files
nltk.download('stopwords')


# In[3]:


# Using our classifier
with open('pre-trained-model/tfidfmodel.pickle','rb') as f:
    tfidf = pickle.load(f)
    
with open('pre-trained-model/classifier.pickle','rb') as f:
    clf = pickle.load(f)
    


# # Test on a new Data

# In[4]:


sample = ["You are a nice person man, have a good life"]
sample = tfidf.transform(sample).toarray()
sentiment = clf.predict(sample)
sentiment


# In[5]:


sample = ["Logistic regression is not good! "]
sample = tfidf.transform(sample).toarray()
sentiment = clf.predict(sample)
sentiment


# # Test on Twitter

# In[6]:


import json
import tweepy
import time
from tweepy import OAuthHandler


consumer_key = 'yoIwFkjZGYDa49aO16XqSNqcN'
consumer_secret = 'gl4LQOItV7Z1aFwNrlvaiKJ3t8o8h99blMIAmnmdHxYjzjRAxO' 
access_token = '624310916-E7fDF2IE8P6bfY1oVFglASf6F8RnxMd3vgSXFqnZ'
access_token_secret ='ID9JcoXHsDcKtvNcnmBGcCQhUlO0wmwAxBJ6LCesiUAas'
 
auth = OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
 
#api = tweepy.API(auth)
api = tweepy.API(auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True, retry_count=3, retry_delay=60)


# In[7]:


# Creates the user object. The me() method returns the user whose authentication keys were used.
user = api.me()
 
print('Name: ' + user.name)
print('ID: ' + str(user.id))
print('Location: ' + user.location)


# In[8]:


args = ['Khashoggi'];
api = tweepy.API(auth,timeout=10)

# Fetching the tweets
list_tweets = []

query = args[0]
if len(args) == 1:
    for status in tweepy.Cursor(api.search,q=query+" -filter:retweets",lang='en',result_type='recent',geocode="22.1568,89.4332,500km").items(100):
        list_tweets.append(status.text)


# In[9]:


list_tweets[:4]


# In[10]:


mapping = {0:'positive', 1:'negative'}


# # Twitter Data Claening

# In[11]:


# Preprocessing the tweets

sent_tweets = []
for tweet in list_tweets:
    tweet = re.sub(r"^https://t.co/[a-zA-Z0-9]*\s", " ", tweet)
    tweet = re.sub(r"\s+https://t.co/[a-zA-Z0-9]*\s", " ", tweet)
    tweet = re.sub(r"\s+https://t.co/[a-zA-Z0-9]*$", " ", tweet)
    tweet = tweet.lower()
    tweet = re.sub(r"that's","that is",tweet)
    tweet = re.sub(r"there's","there is",tweet)
    tweet = re.sub(r"what's","what is",tweet)
    tweet = re.sub(r"where's","where is",tweet)
    tweet = re.sub(r"it's","it is",tweet)
    tweet = re.sub(r"who's","who is",tweet)
    tweet = re.sub(r"i'm","i am",tweet)
    tweet = re.sub(r"she's","she is",tweet)
    tweet = re.sub(r"he's","he is",tweet)
    tweet = re.sub(r"they're","they are",tweet)
    tweet = re.sub(r"who're","who are",tweet)
    tweet = re.sub(r"ain't","am not",tweet)
    tweet = re.sub(r"wouldn't","would not",tweet)
    tweet = re.sub(r"shouldn't","should not",tweet)
    tweet = re.sub(r"can't","can not",tweet)
    tweet = re.sub(r"couldn't","could not",tweet)
    tweet = re.sub(r"won't","will not",tweet)
    tweet = re.sub(r"\W"," ",tweet)
    tweet = re.sub(r"\d"," ",tweet)
    tweet = re.sub(r"\s+[a-z]\s+"," ",tweet)
    tweet = re.sub(r"\s+[a-z]$"," ",tweet)
    tweet = re.sub(r"^[a-z]\s+"," ",tweet)
    tweet = re.sub(r"\s+"," ",tweet)
    
    sent = clf.predict(tfidf.transform([tweet]).toarray())
    sent_tweets.append((tweet, mapping[int(sent)]))

sent_tweets[:4]


# ## Positive/negative Split

# In[12]:


pos = len([s for t, s in sent_tweets if s == 'positive'])
neg = len(sent_tweets) - pos
pos, neg


# In[14]:


# Visualizing the results
import matplotlib.pyplot as plt
import numpy as np
plt.bar(['Positive','Negative'], [pos, neg], alpha = 0.5)
#plt.xticks(y_pos,objects)
plt.ylabel('Number')
plt.title('Number of Postive and NEgative Tweets')


plt.show()


# In[ ]:





# In[15]:


sample = ["You are a nice person man, have a good life"]
sample = tfidf.transform(sample).toarray()
sentiment = clf.predict(sample)
sentiment


# In[19]:


from textblob import TextBlob


# In[20]:


sample = []
yorum = "Kampanya berbat. kötü ya!"
blob = TextBlob(yorum)
sample.append(str(blob.translate(to="en")))


# In[21]:


print(sample)


# In[22]:


sample = tfidf.transform(sample).toarray()
sentiment = clf.predict(sample)
sentiment


# In[ ]: