用knn进行汽车目的地预测（python实现）
题目来源
一、预测思路：
- 把开始时间，如“20:20:34”，按小时划分为0-23，把日期，如“2018-09-09 ”，按照工作日、休息日、小长假依次划分为0、1、2；
- 把训练集的结束位置的经纬度用geohash（python的一个工具包）转化为字符串作为标签;
- 把按以上步骤处理好的数据带入knn即可.
二、数据集格式
训练集部分数据
r_key,out_id,start_time,end_time,start_lat,start_lon,end_lat,end_lon
SDK-XJ_609994b4d50a8a07a64d41d1f70bbb05,2016061820000b,2018-01-20 10:13:43,2018-01-20 10:19:04,33.783415000000005,111.60366,33.779810999999995,111.60588500000001
SDK-XJ_4c2f29d94c9478623711756e4ae34cc5,2016061820000b,2018-02-12 17:40:51,2018-02-12 17:58:13,34.810763,115.549264,34.814875,115.549374
SDK-XJ_3570183177536a575b9da67a86efcd62,2016061820000b,2018-02-13 14:52:24,2018-02-13 15:24:33,34.640284,115.539024,34.813136,115.559243
测试集部分数据
r_key,out_id,start_time,start_lat,start_lon
f6fa6b2a1fa250b3_SDK-XJ_eed80f24f496fc9a59f49e031edfe9b8,358962079107966,2018-09-01 15:54:12,43.943356,125.37771799999999
a584728d1eb0fb5b_SDK-XJ_d60de6f0b8121b07383e80c0b176d0fa,358962079111695,2018-09-01 13:16:11,43.886501,125.272971
7308d46abc5ec4d0_SDK-XJ_6dd3f0f118e9813c51ed224ed09444c2,358962079120563,2018-09-01 18:08:36,43.867917,125.30785300000001
三、代码（可直接运行）
# -*- coding: utf-8 -*-
import datetime
import os
import time
from collections import Counter
import geohash
import pandas as pd
from sklearn.neighbors import KNeighborsClassifier
from sklearn.utils import shuffle
"""
汽车目的地智能预测大赛_knn
"""
def datetime_to_period(date_str):
"""
描述：把时间分为24段
返回：0到23
"""
time_part = date_str.split(" ")[1] # 获取时间部分
hour_part = int(time_part.split(":")[0]) # 获取小时
return hour_part
def date_to_period(date_str):
"""
描述：把日期转化为对应的工作日或者节假日
返回：0:工作日 1：节假日 2:小长假
"""
holiday_list = ['2018-01-01', '2018-02-15', '2018-02-16', '2018-02-17', '2018-02-18', '2018-02-19',
'2018-02-20', '2018-02-21', '2018-04-05', '2018-04-06', '2018-04-07', '2018-04-29',
'2018-04-30', '2018-05-01', '2018-06-16', '2018-06-17', '2018-06-18'] # 小长假
switch_workday_list = ['2018-02-11', '2018-02-24', '2018-04-08', '2018-04-28'] # 小长假补班
workday_list = ['1', '2', '3', '4', '5'] # 周一到周五
weekday_list = ['0', '6'] # 周六、周日，其中0表示周日
date = date_str.split(" ")[0] # 获取日期部分
whatday = datetime.datetime.strptime(date_str, '%Y-%m-%d %H:%M:%S').strftime("%w") # 把日期转化为星期
if date in holiday_list:
return 2
elif date in switch_workday_list:
return 0
elif whatday in workday_list:
return 0
elif whatday in weekday_list:
return 1
time_start = time.asctime(time.localtime(time.time())) # 程序开始时间
# ---删除相关文件---
path = "C:\\Users\\yang\\Desktop\\" # 文件路径
lst = ['predict', 'predict_result', 'view', 'score', 'train'] # 文件名列表
for file_name in lst:
file_path = path + file_name + '.csv'
if os.path.exists(file_path):
os.remove(file_path)
train_data_path = "C:\\Users\\yang\\Desktop\\train_new.csv"
train_data = pd.read_csv(train_data_path, low_memory=False)
test_data_path = "C:\\Users\\yang\\Desktop\\test_new.csv"
test_data = pd.read_csv(test_data_path, low_memory=False)
n = 0
test_out_id = Counter(test_data['out_id'])
for out_id in test_out_id.keys():
# ----train_new数据补充字段 begin----
train = train_data[train_data['out_id'] == out_id] # 选择出同一个out_id的数据
train = shuffle(train) # 打乱顺序
train['start_code'] = None # 开始位置的geohash编码
train['end_code'] = None # 结束位置的geohash编码
train['period'] = None # 时间段编码（0-23）
train['week_code'] = None # 工作日和休息日编码
for i in range(len(train)):
train.iloc[i, 8] = geohash.encode(train.iloc[i, 4], train.iloc[i, 5], 8) # 开始geohash编码
train.iloc[i, 9] = geohash.encode(train.iloc[i, 6], train.iloc[i, 7], 8) # 结束geohash编码
train.iloc[i, 10] = datetime_to_period(train.iloc[i, 2]) # 添加时间段
train.iloc[i, 11] = date_to_period(train.iloc[i, 2]) # 添加工作日、休息日编码
# ----train_new数据补充字段 end----
# ----test_new数据补充字段 begin----
test = test_data[test_data['out_id'] == out_id]
test = shuffle(test) # 打乱顺序
test['period'] = None
test['week_code'] = None
test['start_code'] = None
test['predict'] = None
for i in range(len(test)):
test.iloc[i, 5] = datetime_to_period(test.iloc[i, 2]) # 添加时间段
test.iloc[i, 6] = date_to_period(test.iloc[i, 2]) # 添加工作日、休息日编码
test.iloc[i, 7] = geohash.encode(test.iloc[i, 3], test.iloc[i, 4], 8) # 开始geohash编码
# ----test_new数据补充字段 end----
# ---knn begin---
knn = KNeighborsClassifier(n_neighbors=10, weights='distance', algorithm='auto', p=2)
knn.fit(train[['start_lat', 'start_lon', 'period', 'week_code']], train['end_code'])
predict = knn.predict(test[['start_lat', 'start_lon', 'period', 'week_code']])
test['predict'] = predict
# ---knn end---
if n == 0:
test.to_csv("C:\\Users\\yang\\Desktop\\predict.csv", mode='a', encoding='utf-8', index=False,
header=True)
else:
test.to_csv("C:\\Users\\yang\\Desktop\\predict.csv", mode='a', encoding='utf-8', index=False,
header=False)
if n % 500 == 0:
print("已运行：" + str(n) + " " + time.asctime(time.localtime(time.time())))
n = n + 1
print("输出结果：\n")
df = pd.read_csv("C:\\Users\\yang\\Desktop\\predict.csv") # 预测结果文件
df['end_lat'] = None
df['end_lon'] = None
for i in range(len(df)):
site = geohash.decode(df.iloc[i, 8])
df.iloc[i, 9] = site[0] # 预测横坐标
df.iloc[i, 10] = site[1] # 预测纵坐标
if i % 5000 == 0:
print("已运行" + str(i))
df = df[['r_key', 'end_lat', 'end_lon']]
df.to_csv("C:\\Users\\yang\\Desktop\\predict_result.csv", encoding='utf-8', index=False)
print('\r程序运行开始时间：', time_start)
print('\r程序运行结束时间：', time.asctime(time.localtime(time.time())))
备注：该代码运行时间约1.5小时