# Dependencies
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import json
import tweepy
import seaborn as sns

# Twitter API Keys
from config import consumer_key, consumer_secret, access_token, access_token_secret

# Initialize Sentiment Analyzer
from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
analyzer = SentimentIntensityAnalyzer()


# Setup Tweepy API Authentication
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_token, access_token_secret)
api = tweepy.API(auth, parser=tweepy.parsers.JSONParser())

#List of users to be analyzed
target_users = ["@BBC","@CBS", "@CNN", "@FoxNews", "@nytimes"]

#initiate output lists
compound = []
pos = []
neu = []
neg = []
user = []
tweets_ago = []
date = []


#loop through target_users, and analyze sentiments
for item in target_users:
    
    #initiate counter
    i = 1
    
    #pull last 100 tweets from the user selected
    public_tweets = api.search(item, count=100, result_type = "recent")
    
    #sentiment analysis on 100 tweets
    for tweet in public_tweets["statuses"]:
        
        compound.append(analyzer.polarity_scores(tweet["text"])["compound"])
        pos.append(analyzer.polarity_scores(tweet["text"])["pos"])
        neg.append(analyzer.polarity_scores(tweet["text"])["neg"])
        neu.append(analyzer.polarity_scores(tweet["text"])["neu"])
        user.append(item)
        tweets_ago.append(i)
        date.append(tweet["created_at"])
        

        i = i + 1

print("Analysis Finished")

sentiments = pd.DataFrame({"Media Sources": user,
                          "Date": date,
                          "Tweet Polarity": compound,
                          "Positive": pos,
                          "Negative": neg,
                          "Neutral": neu,
                          "Tweets Ago": tweets_ago})

sentiments=sentiments[["Media Sources","Tweet Polarity","Positive","Negative","Neutral","Tweets Ago","Date"]]

sentiments.head()

#export data in the DataFrame into a CSV file
sentiments.to_csv(path_or_buf="sentiments.csv")

#Create a scatter plot showing sentiment analysis by media sources
sns.set_style("whitegrid")

plot = sns.stripplot(x=sentiments["Tweets Ago"], y=sentiments["Tweet Polarity"], hue=sentiments["Media Sources"],
           size=10,edgecolor="gray", linewidth = .5, alpha=".7")

plt.legend(title = "Media Sources", bbox_to_anchor=(1,1))
plt.title("Sentiment Analysis of Media Tweets (03/26/2018 UTC)")

plt.xticks(np.arange(0,101,step=10),np.arange(0,101,step=10))
plt.xlim(105,-5)

plt.show()
plt.savefig("scatter.png")

grouping = sentiments.groupby("Media Sources").mean()

grouping = grouping.reset_index()

grouping = grouping.drop(["Positive","Negative","Neutral","Tweets Ago"],axis=1)

grouping

#Create a bar plot to show the overall sentiments
#of the last 100 tweets of each organization

sns.set_style("darkgrid")

plt.bar(grouping["Media Sources"], grouping["Tweet Polarity"],color=sns.color_palette())

for index,i in enumerate(grouping["Tweet Polarity"]):
    if i < 0:
        plt.annotate(round(i,3),xy=(index,i-.007),ha="center")
    else:
        plt.annotate(round(i,3),xy=(index,i+.002),ha="center")

plt.xlabel("Media Sources")
plt.ylabel("Tweet Polarity")
plt.title("Overall Media Sentiment based on Twitter (03/27/2018 UTC)")
plt.show()

plt.savefig("bar.png")

variance = sentiments.groupby("Media Sources").var()

variance = variance.drop(["Tweets Ago"],axis=1)

variance