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
import datetime



df = pd.read_csv('trending track prediction set_2500tracks360days_minavg1000.csv', encoding = "ISO-8859-1")
# COLUMNS: TRACKID, DOWNLOAD_ACTIVITY_DATE, SUM(UNITS)

df.columns = ['TRACKID', 'DATE', 'STREAMS']


for label, df in df.groupby('TRACKID'):
     df.STREAMS.plot(x='DATE', y='STREAMS', use_index=False)
     print(df['TRACKID'])
     plt.show()
     variable = input('hit enter')