import numpy as np
import pandas as pd
import seaborn as sns
import statsmodels.formula.api as sm
import statsmodels.imputation.mice as mice
from statsmodels.regression.linear_model import OLS
from collections import defaultdict
import matplotlib.pyplot as plt
from sklearn.feature_selection import VarianceThreshold
from sklearn.preprocessing import PolynomialFeatures
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2


#myds = pd.read_csv('catalog_result.csv')
myds = pd.read_csv('catalog_result_socials.csv', encoding = "ISO-8859-1")




genres = pd.get_dummies(myds['RELEASE_GENRE'])
LABEL_COUNTRY = pd.get_dummies(myds['LABEL_COUNTRY'])


df = pd.DataFrame({
"total_rev": myds['TOTAL_GROSS_REVENUE'],
  "rev_recip": np.reciprocal(myds['TOTAL_GROSS_REVENUE']),
  "rev_log": np.log(myds['TOTAL_GROSS_REVENUE']),
  
#"total_physical_rev": myds['PHYSICAL_GROSS_REVENUE'],
#"num_cds": myds['NUM_OF_CDS'],
"num_active_releases": myds['NUM_ACTIVE_RELEASES'],
#"cd_revenue": myds['CD_REVENUE_UNITS_SOLD'],
"spotify_passive_streams": myds['SPOTIFY_STREAMS_PASSIVE_DISC_TOTAL'],
"spotify_playlist_streams": myds['SPOTIFY_PLAYLISTS_STREAMS_TOTAL'],
"spotify_active_streams": myds['SPOTIFY_STREAMS_ACTIVE_DISC_TOTAL'],
"spotify_collection_streams": myds['SPOTIFY_STREAMS_COLLECTION_TOTAL'],
"spotify_total_streams": myds['SPOTIFY_OVERALL_STREAMS_TOTAL'],
"apple_passive_streams": myds['APPLE_STREAMS_PASSIVE_DISC_TOTAL'],
"apple_active_streams": myds['APPLE_STREAMS_ACTIVE_DISC_TOTAL'],
"apple_collection_streams": myds['APPLE_STREAMS_COLLECTION_TOTAL'],
"apple_total_streams": myds['APPLE_OVERALL_STREAMS_TOTAL'],
"amazon_total_streams": myds['AMAZON_OVERALL_STREAMS_TOTAL'],
"pandora_total_streams": myds['PANDORA_OVERALL_STREAMS_TOTAL'],
"youtube_audio_streams": myds['YOUTUBE_AUDIO_OVERALL_STREAMS_TOTAL'],
"shazam_total_streams": myds['SHAZAM_OVERALL_STREAMS_TOTAL'],
"alexa_total_streams": myds['ALEXA_OVERALL_STREAMS_TOTAL'],
"itunes_total_downloads": myds['ITUNES_TOTAL_DOWNLOADS'],
"amazon_total_downloads": myds['AMAZON_TOTAL_DOWNLOADS'],
"google_total_downloads": myds['GOOGLE_PLAY_DOWNLOADS_TOTAL'],

#social features:
"fb_likes": myds['fb_likes'],
"twitter_followers": myds['twitter_followers'],
"youtube_subs": myds['youtube_subs'],
"wiki_pageviews": myds['wiki_pageviews'],
"insta_followers": myds['insta_followers'],
})



#impute NaN with 0s
#df = df.fillna(0)



av = pd.concat([df, genres, LABEL_COUNTRY] , axis=1)
av1 = pd.concat([av, LABEL_COUNTRY] , axis=1)

corr2 = df.corr()
print(corr2)
sns.heatmap(corr2)

#plots

plot1 = av1.plot(y="total_rev",x="apple_total_streams",kind='scatter')
#plot1.set_ylim(0,200000)
#plot1.set_xlim(0,500000)

plot2 = av1.plot(y="total_rev",x="alexa_total_streams",kind='scatter')
plot2.set_ylim(0,300000)
plot2.set_xlim(0,100000)

plot3 = av1.hist("total_rev", bins=100)
plot4 = av1.hist("rev_log", bins=100)
plot5 = av1.hist("rev_recip", bins=100)

plot6 = av1.plot(y="total_rev",x="spotify_playlist_streams",kind='scatter')


# print("Plot 1:")
# print(plot1)

#plot2, plot3, plot4, plot5, plot6)

#print plt.hist(np.reciprocal(myds['TOTAL_GROSS_REVENUE']), bins=100)
#print plt.hist(myds['TOTAL_GROSS_REVENUE'], bins=100,range=(10000,1000000))



fml = "total_rev ~ num_active_releases  + spotify_playlist_streams + spotify_active_streams + spotify_passive_streams + spotify_collection_streams + spotify_total_streams + apple_active_streams + apple_passive_streams + apple_collection_streams + apple_total_streams + amazon_total_streams + pandora_total_streams + shazam_total_streams + alexa_total_streams + youtube_audio_streams + itunes_total_downloads + amazon_total_downloads + google_total_downloads + fb_likes + twitter_followers + youtube_subs + wiki_pageviews + insta_followers"
#fml = "rev_recip ~ total_physical_rev   + num_cds + num_active_releases + cd_revenue  + spotify_playlist_streams + spotify_active_streams + spotify_collection_streams + spotify_total_streams  + apple_active_streams + apple_collection_streams + apple_total_streams + amazon_total_streams + pandora_total_streams + shazam_total_streams + alexa_total_streams + youtube_audio_streams + itunes_total_downloads + amazon_total_downloads + google_total_downloads"
#fml = "rev_log ~ total_physical_rev   + num_cds + num_active_releases + cd_revenue  + spotify_playlist_streams + spotify_active_streams + spotify_passive_streams + spotify_collection_streams + spotify_total_streams  + apple_active_streams + apple_passive_streams + apple_collection_streams + apple_total_streams + amazon_total_streams + pandora_total_streams + shazam_total_streams + alexa_total_streams + youtube_audio_streams + itunes_total_downloads + amazon_total_downloads + google_total_downloads"



result = sm.ols(fml, data=av1).fit()
print(result.summary())

plt.show()