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


l3m = pd.read_csv('fp_l3m_march20.csv', encoding = "ISO-8859-1")
tw = pd.read_csv('fp_tw_march20.csv', encoding = "ISO-8859-1")
lw = pd.read_csv('fp_lw_march20.csv', encoding = "ISO-8859-1")

frames = [l3m,tw,lw]

all_tracks = pd.merge(l3m,tw, on=['TRACKID','TRACKNAME'])
all_tracks = pd.merge(all_tracks,lw, on=['TRACKID','TRACKNAME'])


#print(all_tracks[:10])


all_tracks['score'] = (all_tracks['tw']-all_tracks['LW'])/all_tracks['LW'] * (all_tracks['tw']/all_tracks['l3m']) * (all_tracks['tw']/all_tracks['label_this_week'])


all_tracks = all_tracks.sort_values('score',ascending=False)

print(all_tracks[:50])

all_tracks.to_csv('fp_bi_trending_March20.csv')