2019

Statistics on the number of boarders and disembarkers

Question1：

it needs python3.5_SDK and pandas,numpy,time,csv

pip install pandas
pip install numpy
pip install time
pip install csv

1).question1.py

2).nyc_taxi_data.csv（input file）

3).nyc_taxi_grid_data.csv（output file）（Too big to upload，If necessary, leave a message.）

Its general format is

passengers	up_y	up_x	off_y	off_x
2	0.53887	0.19438	0.59258	0.38546
2	0.47723	0.1544	0.66402	0.23383
1	0.54305	0.19637	0.56799	0.1602
1	0.66716	0.28892	0.86638	0.36459
1	0.48768	0.1421	0.3928	0.14926
1	0.54387	0.11972	0.53457	0.15514
6	0.59364	0.22532	0.54208	0.14972
.....

totally time cost 26.219933032989502 s

Question2：

Two-dimensional missing data prediction

it needs python3.6_SDK and pandas,numpy,time,csv

pip install pandas
pip install numpy
pip install time
pip install csv
pip install scikit-surprise

1).question2.py

3).pm25.csv(input file)

2).pm25_predicted.csv(output file)

RMSE: 0.0376

totally cost 27.054699659347534