In [49]:

    

import pandas as pd  
import matplotlib.pyplot as plt
data = pd.read_csv("../../season_1_sad/training_data/order_data/order_data_2016-01-01.csv")
weather = pd.read_csv("../../season_1_sad/training_data/weather_data/weather_data_2016-01-01.csv")
data['time'] = data["Time"].map(lambda x: x[11:]).astype(int)

combine = pd.merge(data,weather,how='outer',on='time')
# sub_district = combine[combine.start_district==1]
# plt.plot(sub_district.time,sub_district.order_count)
# plt.show()
# plt.scatter(combine.fee_sum,combine.order_count)
# plt.show()

print(combine.tail(2))


    

    




               Time  start_district  order_count  null_count  fee_sum  time  \
8227  2016-01-01-99              65            1           1     35.0    99   
8228  2016-01-01-99              66           17           0    524.0    99   

      Weather  PM2.5  temperature        date  week  
8227        2    168           12  2016-01-01     5  
8228        2    168           12  2016-01-01     5  

In [54]:

    

plt.scatter(combine.Weather,combine.order_count)
plt.show()


    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: