In [37]:
import numpy as np
import pandas as pd
mbc_df = pd.read_csv('mbc-web.tsv', sep='\t', names=['mbc title', 'date', 'mbc ratings'])
mbc_df = mbc_df.set_index(pd.DatetimeIndex(mbc_df['date']))
mbc_df.drop('date', axis=1, inplace=True)
sbs_df = pd.read_csv('sbs-web.tsv', sep='\t', names=['sbs title', 'date', 'sbs ratings'])
sbs_df = sbs_df.set_index(pd.DatetimeIndex(sbs_df['date']))
sbs_df.drop('date', axis=1, inplace=True)
# print(sbs_df.head())
kbs_df = pd.read_csv('kbs-web.tsv', sep='\t', names=['kbs title', 'date', 'kbs ratings'])
kbs_df = kbs_df.set_index(pd.DatetimeIndex(kbs_df['date']))
kbs_df.drop('date', axis=1, inplace=True)
# print(sbs_df.head())
ratings_df = kbs_df.join([sbs_df, mbc_df], how='inner')[['kbs ratings', 'sbs ratings', 'mbc ratings']]
# ratings_df.drop
ratings_df['total rating'] = ratings_df.apply(np.sum, axis=1)
# ratings_df.describe()
ratings_df.boxplot()
# ratings_df.plot(figsize=(12,8), style='o--')
Out[37]:
In [ ]: