DCIC2021--17分

感谢datawhale提供的baseline!

// A code block
var foo = 'bar';

import os, codecs
import pandas as pd
import numpy as np

bike_track = pd.concat([
    pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_gj20201221.csv'),
    pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_gj20201222.csv'),
    pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_gj20201223.csv'),
    pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_gj20201224.csv'),
    pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_gj20201225.csv')

])
bike_track = bike_track.sort_values(['BICYCLE_ID', 'LOCATING_TIME'])
def bike_fence_format(s):
    s = s.replace('[', '').replace(']', '').split(',')
    s = np.array(s).astype(float).reshape(5, -1)
    return s
bike_fence = pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_tcd.csv')
bike_fence['FENCE_LOC'] = bike_fence['FENCE_LOC'].apply(bike_fence_format)

bike_order = pd.read_csv(r'C:\Users\Administrator\Desktop\数据竞赛\dcic\gxdc_dd.csv')
bike_order = bike_order.sort_values(['BICYCLE_ID', 'UPDATE_TIME'])

bike_fence['MIN_LATITUDE'] = bike_fence['FENCE_LOC'].apply(lambda x: np.min(x[:, 1]))
bike_fence['MAX_LATITUDE'] = bike_fence['FENCE_LOC'].apply(lambda x: np.max(x[:, 1]))
bike_fence['MIN_LONGITUDE'] = bike_fence['FENCE_LOC'].apply(lambda x: np.min(x[:, 0]))
bike_fence['MAX_LONGITUDE'] = bike_fence['FENCE_LOC'].apply(lambda x: np.max(x[:, 0]))
from geopy.distance import geodesic
# 根据停车点 范围 计算具体的面积
bike_fence['FENCE_AREA'] = bike_fence.apply(lambda x: geodesic(
    (x['MIN_LATITUDE'], x['MIN_LONGITUDE']), (x['MAX_LATITUDE'], x['MAX_LONGITUDE'])
).meters, axis=1)

# 根据停车点 计算中心经纬度
bike_fence['FENCE_CENTER'] = bike_fence['FENCE_LOC'].apply(
    lambda x: np.mean(x[:-1, ::-1], 0)
)
import geohash
bike_order['geohash'] = bike_order.apply(
    lambda x: geohash.encode(x['LATITUDE'], x['LONGITUDE'], precision=6), 
axis=1)

bike_fence['geohash'] = bike_fence['FENCE_CENTER'].apply(
    lambda x: geohash.encode(x[0], x[1], precision=6)
)

bike_order['UPDATE_TIME'] = pd.to_datetime(bike_order['UPDATE_TIME'])
bike_order['DAY'] = bike_order['UPDATE_TIME'].dt.day.astype(object)
bike_order['DAY'] = bike_order['DAY'].apply(str)
bike_order['HOUR'] = bike_order['UPDATE_TIME'].dt.hour.astype(object)
bike_order['HOUR'] = bike_order['HOUR'].apply(str)
bike_order['HOUR'] = bike_order['HOUR'].str.pad(width=2,side='left',fillchar='0')
bike_order['DAY_HOUR'] = bike_order['DAY'] + bike_order['HOUR']
bike_inflow = pd.pivot_table(bike_order[bike_order['LOCK_STATUS'] == 1], 
                   values='LOCK_STATUS', index=['geohash'],
                    columns=['DAY_HOUR'], aggfunc='count', fill_value=0
)
bike_outflow = pd.pivot_table(bike_order[bike_order['LOCK_STATUS'] == 0], 
                   values='LOCK_STATUS', index=['geohash'],
                    columns=['DAY_HOUR'], aggfunc='count', fill_value=0
)
bike_inflow.loc['wsk593'].plot()
bike_outflow.loc['wsk593'].plot()
plt.xticks(list(range(bike_inflow.shape[1])), bike_inflow.columns, rotation=40)
plt.legend(['入流量', '出流量'])
bike_inflow.loc['wsk52r'].plot()
bike_outflow.loc['wsk52r'].plot()
plt.xticks(list(range(bike_inflow.shape[1])), bike_inflow.columns, rotation=40)
plt.legend(['入流量', '出流量'])
from sklearn.neighbors import NearestNeighbors

# https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.DistanceMetric.html
knn = NearestNeighbors(metric = "haversine", n_jobs=-1, algorithm='brute')
knn.fit(np.stack(bike_fence['FENCE_CENTER'].values))
#时间警告 较长
dist, index = knn.kneighbors(bike_order[['LATITUDE','LONGITUDE']].values[:], n_neighbors=1)
bike_order['fence'] = bike_fence.iloc[index.flatten()]['FENCE_ID'].values

bike_inflow = pd.pivot_table(bike_order[bike_order['LOCK_STATUS'] == 1], 
                   values='LOCK_STATUS', index=['fence'],
                    columns=['DAY'], aggfunc='count', fill_value=0
)

bike_outflow = pd.pivot_table(bike_order[bike_order['LOCK_STATUS'] == 0], 
                   values='LOCK_STATUS', index=['fence'],
                    columns=['DAY'], aggfunc='count', fill_value=0
)
bike_remain = (bike_inflow - bike_outflow).fillna(0)
bike_remain[bike_remain < 0] = 0  
bike_remain = bike_remain.sum(1)
bike_fence = bike_fence.set_index('FENCE_ID')
bike_density = bike_remain / bike_fence.set_index('FENCE_ID')['FENCE_AREA']
bike_density = bike_density.sort_values(ascending=False).reset_index()
bike_density = bike_density.fillna(0)
bike_density['label'] = '0'
bike_density.iloc[:100, -1] = '1'
bike_density['BELONG_AREA'] ='厦门'
bike_density = bike_density.drop(0, axis=1)
bike_density.columns = ['FENCE_ID', 'FENCE_TYPE', 'BELONG_AREA']
bike_density.to_csv('result123123.txt', index=None, sep='|')

代码来源：https://coggle.club/learn/dcic2021/