import numpy as np # linear algebra
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import os
import gc # We're gonna be clearing memory a lot
import matplotlib.pyplot as plt
import seaborn as sns


p = sns.color_palette()

print('# File sizes')
for f in os.listdir('../input'):
    if 'zip' not in f:
        print(f.ljust(30) + str(round(os.path.getsize('../input/' + f) / 1000000, 2)) + 'MB')
        
        
df_train = pd.read_csv('../input/clicks_train.csv')
df_test = pd.read_csv('../input/clicks_test.csv')

ad_usage_train = df_train.groupby('ad_id')['ad_id'].count()

for i in [2, 10, 50, 100, 1000]:
    print('Ads that appear less than {} times: {}%'.format(i, round((ad_usage_train < i).mean() * 100, 2)))

plt.figure(figsize=(12, 6))
plt.hist(ad_usage_train.values, bins=50, log=True)
plt.xlabel('Number of times ad appeared', fontsize=12)
plt.ylabel('log(Count of displays with ad)', fontsize=12)
plt.show()