traffic_sample_comparison.py

import pandas as pd

df_l = pd.read_csv('20180220.csv',
                   names=['TimeInterval', 'GantryFrom', 'GantryTo',
                          'VehicleType', 'SpaceMeanSpeed', '交通量'])
df_2l = pd.read_csv('20180219.csv',
                    names=['TimeInterval', 'GantryFrom', 'GantryTo',
                           'VehicleType', 'SpaceMeanSpeed', '交通量'])

def print_summary(df, field):
    # import pdb;pdb.set_trace()
    summary = {
        "mean": df[field].mean(),
        "median": df[field].median(),
        "p50": df[field].quantile(0.5),
        "p90": df[field].quantile(0.5)
    }
    print(summary)

print('last day')
print_summary(df_l, 'SpaceMeanSpeed')

print('2nd last day')
print_summary(df_2l, 'SpaceMeanSpeed')