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


ly_avg = pd.read_csv('fp_daily_avg_ly_April10.csv', encoding = "ISO-8859-1")
today = pd.read_csv('fp_today_April10.csv', encoding = "ISO-8859-1")

all_tracks = pd.merge(ly_avg,today, on=['TRACKID','TRACKNAME','ARTISTNAME'])

#print(all_tracks[:10])

all_tracks['zscore'] = (all_tracks['TODAY']-all_tracks['AVG(SUMS)'])/all_tracks['STDDEV(SUMS)']

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

print(all_tracks[:50])

all_tracks.to_csv('fp_zscore_trending_April10.csv')