外卖配送时间预测项目

注意：本文引用自专业人工智能社区Venus AI

项目背景

外卖服务的兴起: 随着互联网技术和移动应用的发展，外卖成为一种日益普及的餐饮服务方式。顾客通过餐厅、杂货店的网站或移动应用，或通过外卖订餐公司下单。
配送方式的多样性: 根据地理位置的不同，配送方式包括汽车、自行车或电动滑板车。在大城市，由于餐馆和住宅的密集，非机动车辆成为更常见的配送方式。

项目目标

优化配送效率: 研究不同区域和时间段的配送数据，以提高配送效率和客户满意度。
提升用户体验: 分析用户订单习惯，优化点餐和配送流程，提升整体用户体验。
预测配送时间: 预测外面的配送时间。

项目应用

智能配送系统: 利用数据分析和机器学习技术，开发智能配送系统，自动优化配送路线和时间。
客户行为分析: 分析客户的订单偏好和习惯，为餐厅和配送公司提供有价值的洞察，帮助他们更好地调整菜单和服务。

数据集

数据集主要特征

Delivery_person_ID (配送员ID): 配送员的唯一标识符。
Delivery_person_Age (配送员年龄): 配送员的年龄。
Delivery_person_Ratings (配送员评分): 配送员的服务评分，反映其配送效率和服务质量。
Restaurant_latitude, Restaurant_longitude (餐厅纬度, 餐厅经度): 餐厅的地理位置坐标。
Delivery_location_latitude, Delivery_location_longitude (配送地点经纬度): 订单配送地点的地理位置坐标。
Order_Date (订单日期): 下单的日期。
Time_Orderd (订单下单时间): 客户下单的具体时间。
Time_Order_picked (接单时间): 配送员接单的时间。
Weatherconditions (天气状况): 下单当天的天气状况，可能影响配送速度和安全。
Road_traffic_density (道路交通密度): 配送路线上的交通密度情况。
Vehicle_condition (交通工具状况): 配送员使用的交通工具的状况。
Type_of_order (订单类型): 订单的类型，如餐饮、杂货等。
Type_of_vehicle (交通工具类型): 配送员用于配送的交通工具类型，如汽车、自行车或电动滑板车。
multiple_deliveries (多重配送): 是否为一次性配送多个订单。
Festival (节日): 下单当天是否为节日，节日可能影响订单量和配送速度。
City (城市): 订单配送所在的城市。
Time_taken(min) (配送用时): 从接单到完成配送所需的时间，以分钟计。

模型和依赖库

Models:

RandomForestRegressor
Linear Regression
Lasso Regression
Ensemble learning

Libraries:

Pandas
Numpy
Seaborn
Matplotlib
sk-learn
haversine

代码实现

import pandas as pd
import numpy as np
import haversine as hs
from datetime import datetime
import matplotlib.pyplot as plt
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.width', 1000)

data = pd.read_csv('train.csv')
data

ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)
0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24
1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33
2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26
3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21
4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32
45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36
45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16
45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26
45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36

45593 rows × 20 columns

data.replace({"NaN": np.nan}, regex=True, inplace = True)
data

	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)
0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24
1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33
2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26
3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21
4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32
45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36
45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16
45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26
45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36

45593 rows × 20 columns

data.isna().sum()

ID                                0
Delivery_person_ID                0
Delivery_person_Age            1854
Delivery_person_Ratings        1908
Restaurant_latitude               0
Restaurant_longitude              0
Delivery_location_latitude        0
Delivery_location_longitude       0
Order_Date                        0
Time_Orderd                    1731
Time_Order_picked                 0
Weatherconditions               616
Road_traffic_density            601
Vehicle_condition                 0
Type_of_order                     0
Type_of_vehicle                   0
multiple_deliveries             993
Festival                        228
City                           1200
Time_taken(min)                   0
dtype: int64

data['Distance'] = 0
data

	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance
0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	0
1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	0
2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	0
3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	0
4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	0
45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	0
45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	0
45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	0
45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	0

45593 rows × 21 columns

haversine 是一个 Python 库，用于计算地球上两点之间的大圆距离。这个距离是指在地球表面两点之间的最短路径，考虑到地球的曲率。这个库在进行地理位置数据的处理和分析时特别有用，比如在确定两个地理坐标（经度和纬度）之间的直线距离时。

def calculate_distance(row):loc1 = (row['Restaurant_latitude'], row['Restaurant_longitude'])loc2 = (row['Delivery_location_latitude'], row['Delivery_location_longitude'])return hs.haversine(loc1, loc2)
# Apply the function to each row
data['Distance'] = data.apply(calculate_distance, axis=1)

data['Time_prep'] = 0
data

	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep
0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	0
1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	0
2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	0
3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	0
4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	0
45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	0
45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	0
45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	0
45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	0

45593 rows × 22 columns

data.dropna(axis = 0, how = 'all', inplace = True)
data

	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep
0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	0
1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	0
2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	0
3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	0
4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	0
45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	0
45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	0
45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	0
45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	0

45593 rows × 22 columns

data = data[data["Time_Orderd"].str.contains("NaN") == False].reset_index()
data = data[data["Time_Order_picked"].str.contains("NaN") == False].reset_index() 
data.head(50)

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance
0	0	0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153
1	1	1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147
5	5	5	0x9bb4	HYDRES09DEL03	22	4.8	17.431668	78.408321	17.461668	78.438321	11-03-2022	21:20:00	21:30:00	conditions Cloudy	Jam	0	Buffet	motorcycle	1	No	Urban	(min) 26	4.610372
6	6	6	0x95b4	RANCHIRES15DEL01	33	4.7	23.369746	85.339820	23.479746	85.449820	04-03-2022	19:15:00	19:30:00	conditions Fog	Jam	1	Meal	scooter	1	No	Metropolitian	(min) 40	16.600384
7	7	7	0x9eb2	MYSRES15DEL02	35	4.6	12.352058	76.606650	12.482058	76.736650	14-03-2022	17:25:00	17:30:00	conditions Cloudy	Medium	2	Meal	motorcycle	1	No	Metropolitian	(min) 32	20.205281
8	8	8	0x1102	HYDRES05DEL02	22	4.8	17.433809	78.386744	17.563809	78.516744	20-03-2022	20:55:00	21:05:00	conditions Stormy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 34	19.975548
9	9	9	0xcdcd	DEHRES17DEL01	36	4.2	30.327968	78.046106	30.397968	78.116106	12-02-2022	21:55:00	22:10:00	conditions Fog	Jam	2	Snack	motorcycle	3	No	Metropolitian	(min) 46	10.280596
10	10	10	0xd987	KOCRES16DEL01	21	4.7	10.003064	76.307589	10.043064	76.347589	13-02-2022	14:55:00	15:05:00	conditions Stormy	High	1	Meal	motorcycle	1	No	Metropolitian	(min) 23	6.242327
11	11	11	0x2784	PUNERES13DEL03	23	4.7	18.562450	73.916619	18.652450	74.006619	04-03-2022	17:30:00	17:40:00	conditions Sandstorms	Medium	1	Drinks	scooter	1	No	Metropolitian	(min) 21	13.787879
12	12	12	0xc8b6	LUDHRES15DEL02	34	4.3	30.899584	75.809346	30.919584	75.829346	13-02-2022	09:20:00	09:30:00	conditions Sandstorms	Low	0	Buffet	motorcycle	0	No	Metropolitian	(min) 20	2.930262
13	13	13	0xdb64	KNPRES14DEL02	24	4.7	26.463504	80.372929	26.593504	80.502929	14-02-2022	19:50:00	20:05:00	conditions Fog	Jam	1	Snack	scooter	1	No	Metropolitian	(min) 41	19.396645
14	14	14	0x3af3	MUMRES15DEL03	29	4.5	19.176269	72.836721	19.266269	72.926721	02-04-2022	20:25:00	20:35:00	conditions Sandstorms	Jam	2	Buffet	electric_scooter	1	No	Metropolitian	(min) 20	13.763996
15	15	15	0x3aab	MYSRES01DEL01	35	4	12.311072	76.654878	12.351072	76.694878	01-03-2022	14:55:00	15:10:00	conditions Windy	High	1	Meal	scooter	1	No	Metropolitian	(min) 33	6.218010
16	16	16	0x689b	PUNERES20DEL01	33	4.2	18.592718	73.773572	18.702718	73.883572	16-03-2022	20:30:00	20:40:00	conditions Sandstorms	Jam	2	Snack	motorcycle	1	No	Metropolitian	(min) 40	16.849963
17	17	17	0x6f67	HYDRES14DEL01	34	4.9	17.426228	78.407495	17.496228	78.477495	20-03-2022	20:40:00	20:50:00	conditions Cloudy	Jam	0	Snack	motorcycle	NaN	No	Metropolitian	(min) 41	10.757124
18	18	18	0xc9cf	KOLRES15DEL03	21	4.7	22.552672	88.352885	22.582672	88.382885	15-02-2022	21:15:00	21:30:00	conditions Windy	Jam	0	Meal	motorcycle	1	No	Urban	(min) 15	4.540581
19	19	19	0x36b8	PUNERES19DEL02	25	4.1	18.563934	73.915367	18.643935	73.995367	16-03-2022	20:20:00	20:25:00	conditions Sandstorms	Jam	0	Snack	motorcycle	2	No	Metropolitian	(min) 36	12.256093
20	20	20	0x5795	RANCHIRES06DEL02	31	4.7	23.357804	85.325146	23.487804	85.455146	10-03-2022	22:30:00	22:45:00	conditions Sandstorms	Low	2	Meal	electric_scooter	0	No	Metropolitian	(min) 26	19.618766
21	21	21	0x6c6b	COIMBRES13DEL01	37	5	11.003669	76.976494	11.013669	76.986494	11-03-2022	08:15:00	08:30:00	conditions Sandstorms	Low	1	Snack	motorcycle	1	No	Metropolitian	(min) 20	1.558134
22	22	22	0xb816	CHENRES19DEL02	33	4.3	12.986047	80.218114	13.116047	80.348114	27-03-2022	19:30:00	19:45:00	conditions Windy	Jam	2	Meal	scooter	1	No	Metropolitian	(min) 39	20.180663
23	23	23	0x539b	MUMRES02DEL01	25	4	19.221315	72.862381	19.261315	72.902381	26-03-2022	12:25:00	12:30:00	conditions Cloudy	High	1	Buffet	motorcycle	1	No	Metropolitian	(min) 34	6.116980
24	24	24	0xa1b2	CHENRES01DEL01	29	4.5	13.005801	80.250744	13.115801	80.360744	27-03-2022	18:35:00	18:50:00	conditions Sunny	Medium	2	Meal	electric_scooter	1	No	Metropolitian	(min) 15	17.075618
25	25	25	0x3231	JAPRES16DEL03	27	5	26.849596	75.800512	26.879596	75.830512	05-04-2022	20:35:00	20:40:00	conditions Stormy	Jam	0	Snack	motorcycle	0	No	Urban	(min) 18	4.470293
26	26	26	0x8bc0	SURRES15DEL03	35	4.3	21.160522	72.771477	21.250522	72.861477	12-03-2022	23:20:00	23:30:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 38	13.682063
27	27	27	0x2288	BANGRES09DEL03	32	4	12.934179	77.615797	13.024179	77.705797	16-03-2022	21:20:00	21:35:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 47	13.973202
28	28	28	0x3c5e	PUNERES04DEL01	23	4.8	18.514210	73.838429	18.624210	73.948429	02-04-2022	23:35:00	23:45:00	conditions Windy	Low	2	Buffet	electric_scooter	0	No	Urban	(min) 12	16.853642
29	29	29	0x3e60	COIMBRES02DEL03	31	4.8	11.022477	76.995667	11.052477	77.025667	01-04-2022	22:35:00	22:50:00	conditions Sandstorms	Low	2	Drinks	motorcycle	1	No	Metropolitian	(min) 26	4.674179
30	30	30	0xbff	SURRES16DEL02	36	4.1	21.160437	72.774209	21.210437	72.824209	05-03-2022	22:35:00	22:40:00	conditions Stormy	Low	0	Drinks	motorcycle	1	No	Urban	(min) 22	7.601627
31	31	31	0xd936	GOARES15DEL02	26	4.3	15.513150	73.783460	15.563150	73.833460	11-02-2022	23:25:00	23:35:00	conditions Sandstorms	Low	0	Buffet	motorcycle	0	No	Urban	(min) 21	7.720335
32	32	32	0xd681	GOARES07DEL01	38	4.9	15.561295	73.749478	15.601295	73.789478	11-02-2022	13:35:00	13:40:00	conditions Cloudy	High	1	Drinks	scooter	1	No	Urban	(min) 25	6.175645
33	33	33	0x2876	RANCHIRES02DEL01	32	3.5	0.000000	0.000000	0.110000	0.110000	08-03-2022	21:35:00	21:45:00	conditions Stormy	Jam	1	Snack	scooter	0	No	Urban	(min) 35	17.297890
34	34	34	0x30c8	PUNERES19DEL02	32	4.6	18.563934	73.915367	18.693935	74.045367	02-04-2022	22:35:00	22:45:00	conditions Cloudy	Low	2	Drinks	scooter	1	No	Metropolitian	(min) 30	19.914714
35	35	35	0xb843	PUNERES02DEL01	33	4.9	18.551440	73.804855	18.621440	73.874855	08-03-2022	18:55:00	19:10:00	conditions Sunny	Medium	1	Snack	motorcycle	1	No	Metropolitian	(min) 22	10.724533
36	36	36	0xb3a0	PUNERES18DEL01	20	4.7	18.593481	73.785901	18.633481	73.825901	03-04-2022	14:15:00	14:25:00	conditions Windy	High	1	Snack	scooter	0	No	Urban	(min) 10	6.127844
37	37	37	0x6531	SURRES08DEL01	20	4.8	21.173343	72.792731	21.183343	72.802731	30-03-2022	11:00:00	11:10:00	conditions Sandstorms	Low	2	Meal	scooter	1	No	Metropolitian	(min) 19	1.520359
38	38	38	0x4bda	HYDRES17DEL02	35	5	17.451976	78.385883	17.471976	78.405883	01-04-2022	09:45:00	09:55:00	conditions Sunny	Low	2	Snack	scooter	1	No	Urban	(min) 11	3.073458
39	39	39	0x9d26	BANGRES17DEL02	26	4.9	12.972532	77.608179	12.992532	77.628179	28-03-2022	08:40:00	08:55:00	conditions Stormy	Low	2	Buffet	scooter	0	No	Metropolitian	(min) 11	3.105136
40	40	40	0x9b18	BANGRES17DEL01	22	4.8	12.972532	77.608179	13.042532	77.678179	18-03-2022	23:00:00	23:10:00	conditions Fog	Low	1	Snack	motorcycle	1	No	Metropolitian	(min) 28	10.867442
41	41	41	0x5d99	CHENRES11DEL01	35	4.3	13.064181	80.236442	13.134181	80.306442	14-03-2022	17:25:00	17:30:00	conditions Cloudy	Medium	1	Snack	motorcycle	1	No	Metropolitian	(min) 33	10.865480
42	42	43	0xb796	SURRES17DEL03	37	4.7	21.149569	72.772697	21.239569	72.862697	04-04-2022	19:45:00	19:50:00	conditions Sandstorms	Jam	0	Snack	motorcycle	3	No	Metropolitian	(min) 52	13.682535
43	43	44	0x85b4	MUMRES07DEL01	28	4.6	19.091458	72.827808	19.201458	72.937808	08-03-2022	19:10:00	19:25:00	conditions Stormy	Jam	1	Snack	scooter	1	No	Metropolitian	(min) 22	16.826265
44	44	45	0xc644	KOLRES16DEL02	37	4.9	22.539129	88.365507	22.559129	88.385507	13-02-2022	10:55:00	11:00:00	conditions Fog	Low	1	Snack	scooter	1	No	Urban	(min) 16	3.027241
45	45	46	0x6999	MUMRES02DEL03	23	4.9	19.221315	72.862381	19.281315	72.922381	24-03-2022	21:40:00	21:45:00	conditions Sunny	Jam	2	Drinks	electric_scooter	0	No	Metropolitian	(min) 11	9.175207
46	46	47	0x63b6	BANGRES05DEL03	27	4.9	12.970324	77.645748	13.030324	77.705748	19-03-2022	19:00:00	19:15:00	conditions Windy	Medium	1	Drinks	scooter	1	No	Metropolitian	(min) 25	9.315082
47	47	48	0xa30b	CHENRES11DEL01	37	4.8	13.064181	80.236442	13.104181	80.276442	09-03-2022	16:45:00	16:55:00	conditions Cloudy	Medium	0	Drinks	motorcycle	1	No	Urban	(min) 26	6.209030
48	48	49	0x3556	SURRES09DEL01	33	5	21.175975	72.795503	21.185975	72.805503	19-03-2022	11:30:00	11:40:00	conditions Sunny	High	2	Snack	scooter	1	No	Metropolitian	(min) 18	1.520347
49	49	50	0x5554	RANCHIRES15DEL01	31	4.9	23.369746	85.339820	23.409746	85.379820	03-04-2022	15:10:00	15:15:00	conditions Fog	Medium	1	Snack	motorcycle	1	No	Metropolitian	(min) 16	6.037234

# 计算配送时间
for i in range(len(data)):t1 = datetime.strptime(data['Time_Orderd'][i], "%H:%M:%S")t2  =datetime.strptime(data['Time_Order_picked'][i], "%H:%M:%S")diff = t2-t1sec = diff.total_seconds()minute = sec/60data['Time_prep'][i] = minutedata

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Restaurant_latitude	Restaurant_longitude	Delivery_location_latitude	Delivery_location_longitude	Order_Date	Time_Orderd	Time_Order_picked	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep
0	0	0	0x4607	INDORES13DEL02	37	4.9	22.745049	75.892471	22.765049	75.912471	19-03-2022	11:30:00	11:45:00	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	15
1	1	1	0xb379	BANGRES18DEL02	34	4.5	12.913041	77.683237	13.043041	77.813237	25-03-2022	19:45:00	19:50:00	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	5
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	12.914264	77.678400	12.924264	77.688400	19-03-2022	08:30:00	08:45:00	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	15
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	11.003669	76.976494	11.053669	77.026494	05-04-2022	18:00:00	18:10:00	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	10
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	12.972793	80.249982	13.012793	80.289982	26-03-2022	13:30:00	13:45:00	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	15
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	26.902328	75.794257	26.912328	75.804257	24-03-2022	11:35:00	11:45:00	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	10
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	0.000000	0.000000	0.070000	0.070000	16-02-2022	19:55:00	20:10:00	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	15
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	13.022394	80.242439	13.052394	80.272439	11-03-2022	23:50:00	00:05:00	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	-1425
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	11.001753	76.986241	11.041753	77.026241	07-03-2022	13:35:00	13:40:00	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	5
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	23.351058	85.325731	23.431058	85.405731	02-03-2022	17:10:00	17:15:00	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	5

43862 rows × 24 columns

data = data.drop(['Restaurant_latitude', 'Restaurant_longitude', 'Delivery_location_latitude', 'Delivery_location_longitude'], axis=1)
data = data.drop(['Time_Orderd', 'Time_Order_picked'], axis=1)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Order_Date	Weatherconditions	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep
0	0	0	0x4607	INDORES13DEL02	37	4.9	19-03-2022	conditions Sunny	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	15
1	1	1	0xb379	BANGRES18DEL02	34	4.5	25-03-2022	conditions Stormy	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	5
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	19-03-2022	conditions Sandstorms	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	15
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	05-04-2022	conditions Sunny	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	10
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	26-03-2022	conditions Cloudy	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	15
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	24-03-2022	conditions Windy	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	10
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	16-02-2022	conditions Windy	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	15
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	11-03-2022	conditions Cloudy	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	-1425
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	07-03-2022	conditions Cloudy	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	5
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	02-03-2022	conditions Fog	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	5

43862 rows × 18 columns

# 将一个名为data的数据框(DataFrame)中的Weatherconditions列的值进行处理，然后将处理后的结果存储到一个名为Weather的新列中，最后删除原始的Weatherconditions列。
data['Weather'] = 0
for i in range(len(data)):str1 = data['Weatherconditions'][i]cond = str1.split(' ')data['Weather'][i] = cond[1]data = data.drop(['Weatherconditions'], axis=1)

data = data.drop(['Order_Date'], axis=1)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep	Weather
0	0	0	0x4607	INDORES13DEL02	37	4.9	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	15	Sunny
1	1	1	0xb379	BANGRES18DEL02	34	4.5	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	5	Stormy
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	15	Sandstorms
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	10	Sunny
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	15	Cloudy
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	10	Windy
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	15	Windy
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	-1425	Cloudy
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	5	Cloudy
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	5	Fog

43862 rows × 17 columns

data['Time_taken'] = 0
for i in range(len(data)):list2 = data['Time_taken(min)'][i]str2 = list2.split(' ')data['Time_taken'][i] = int(str2[1])
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Time_taken(min)	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	High	2	Snack	motorcycle	0	No	Urban	(min) 24	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	Jam	2	Snack	scooter	1	No	Metropolitian	(min) 33	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	Low	0	Drinks	motorcycle	1	No	Urban	(min) 26	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	Medium	0	Buffet	motorcycle	1	No	Metropolitian	(min) 21	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	High	1	Snack	scooter	1	No	Metropolitian	(min) 30	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	High	1	Meal	motorcycle	0	No	Metropolitian	(min) 32	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	Jam	0	Buffet	motorcycle	1	No	Metropolitian	(min) 36	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	Low	1	Drinks	scooter	0	No	Metropolitian	(min) 16	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	High	0	Snack	motorcycle	1	No	Metropolitian	(min) 26	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	Medium	2	Snack	scooter	1	No	Metropolitian	(min) 36	12.074412	5	Fog	36

43862 rows × 18 columns

data = data.drop(['Time_taken(min)'], axis=1)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	High	2	Snack	motorcycle	0	No	Urban	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	Jam	2	Snack	scooter	1	No	Metropolitian	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	Low	0	Drinks	motorcycle	1	No	Urban	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	Medium	0	Buffet	motorcycle	1	No	Metropolitian	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	High	1	Snack	scooter	1	No	Metropolitian	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	High	1	Meal	motorcycle	0	No	Metropolitian	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	Jam	0	Buffet	motorcycle	1	No	Metropolitian	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	Low	1	Drinks	scooter	0	No	Metropolitian	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	High	0	Snack	motorcycle	1	No	Metropolitian	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	Medium	2	Snack	scooter	1	No	Metropolitian	12.074412	5	Fog	36

43862 rows × 17 columns

order_type = data['Type_of_order'].unique()
for i in range(len(order_type)):data['Type_of_order'] = data['Type_of_order'].replace(order_type[i], i)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	High	2	0	motorcycle	0	No	Urban	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	Jam	2	0	scooter	1	No	Metropolitian	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	Low	0	1	motorcycle	1	No	Urban	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	Medium	0	2	motorcycle	1	No	Metropolitian	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	High	1	0	scooter	1	No	Metropolitian	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	High	1	3	motorcycle	0	No	Metropolitian	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	Jam	0	2	motorcycle	1	No	Metropolitian	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	Low	1	1	scooter	0	No	Metropolitian	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	High	0	0	motorcycle	1	No	Metropolitian	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	Medium	2	0	scooter	1	No	Metropolitian	12.074412	5	Fog	36

43862 rows × 17 columns

data['Type_of_vehicle'] = data['Type_of_vehicle'].replace('motorcycle ', 0)
data['Type_of_vehicle'] = data['Type_of_vehicle'].replace('scooter ', 1)
data['Type_of_vehicle'] = data['Type_of_vehicle'].replace('electric_scooter ', 2)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	High	2	0	0	0	No	Urban	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	Jam	2	0	1	1	No	Metropolitian	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	Low	0	1	0	1	No	Urban	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	Medium	0	2	0	1	No	Metropolitian	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	High	1	0	1	1	No	Metropolitian	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	High	1	3	0	0	No	Metropolitian	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	Jam	0	2	0	1	No	Metropolitian	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	Low	1	1	1	0	No	Metropolitian	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	High	0	0	0	1	No	Metropolitian	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	Medium	2	0	1	1	No	Metropolitian	12.074412	5	Fog	36

43862 rows × 17 columns

road_traffic = data['Road_traffic_density'].unique()
for i in range(len(road_traffic)):data['Road_traffic_density'] = data['Road_traffic_density'].replace(road_traffic[i], i)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	0	2	0	0	0	No	Urban	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	1	2	0	1	1	No	Metropolitian	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	2	0	1	0	1	No	Urban	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	3	0	2	0	1	No	Metropolitian	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	0	1	0	1	1	No	Metropolitian	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	0	1	3	0	0	No	Metropolitian	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	1	0	2	0	1	No	Metropolitian	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	2	1	1	1	0	No	Metropolitian	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	0	0	0	0	1	No	Metropolitian	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	3	2	0	1	1	No	Metropolitian	12.074412	5	Fog	36

43862 rows × 17 columns

festival = data['Festival'].unique()
for i in range(len(festival)):data['Festival'] = data['Festival'].replace(festival[i], i)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	0	2	0	0	0	0.0	Urban	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	1	2	0	1	1	0.0	Metropolitian	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	2	0	1	0	1	0.0	Urban	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	3	0	2	0	1	0.0	Metropolitian	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	0	1	0	1	1	0.0	Metropolitian	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	0	1	3	0	0	0.0	Metropolitian	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	1	0	2	0	1	0.0	Metropolitian	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	2	1	1	1	0	0.0	Metropolitian	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	0	0	0	0	1	0.0	Metropolitian	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	3	2	0	1	1	0.0	Metropolitian	12.074412	5	Fog	36

43862 rows × 17 columns

city = data['City'].unique()
for i in range(len(city)):data['City'] = data['City'].replace(city[i], i)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	0	2	0	0	0	0.0	0.0	3.025153	15	Sunny	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	1	2	0	1	1	0.0	1.0	20.183558	5	Stormy	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	2	0	1	0	1	0.0	0.0	1.552760	15	Sandstorms	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	3	0	2	0	1	0.0	1.0	7.790412	10	Sunny	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	0	1	0	1	1	0.0	1.0	6.210147	15	Cloudy	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	0	1	3	0	0	0.0	1.0	1.489848	10	Windy	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	1	0	2	0	1	0.0	1.0	11.007750	15	Windy	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	2	1	1	1	0	0.0	1.0	4.657202	-1425	Cloudy	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	0	0	0	0	1	0.0	1.0	6.232402	5	Cloudy	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	3	2	0	1	1	0.0	1.0	12.074412	5	Fog	36

43862 rows × 17 columns

weather = data['Weather'].unique()
for i in range(len(weather)):data['Weather'] = data['Weather'].replace(weather[i], i)
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	0	2	0	0	0	0.0	0.0	3.025153	15	0	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	1	2	0	1	1	0.0	1.0	20.183558	5	1	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	2	0	1	0	1	0.0	0.0	1.552760	15	2	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	3	0	2	0	1	0.0	1.0	7.790412	10	0	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	0	1	0	1	1	0.0	1.0	6.210147	15	3	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	0	1	3	0	0	0.0	1.0	1.489848	10	5	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	1	0	2	0	1	0.0	1.0	11.007750	15	5	36
43859	43859	45590	0x4f8d	CHENRES08DEL03	30	4.9	2	1	1	1	0	0.0	1.0	4.657202	-1425	3	16
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	0	0	0	0	1	0.0	1.0	6.232402	5	3	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	3	2	0	1	1	0.0	1.0	12.074412	5	4	36

43862 rows × 17 columns

data = data[data['Time_prep']>0]
data = data[data['Delivery_person_Age']!="NaN "]
data = data[data['Delivery_person_Ratings']!="NaN "]
data = data[data['Road_traffic_density']!="NaN "]
data = data[data['Vehicle_condition']!="NaN"]
data = data[data['Type_of_order']!="NaN"]
data = data[data['Type_of_vehicle']!="NaN"]
data = data[data['multiple_deliveries']!="NaN"]
data = data[data['Festival']!="NaN"]
data = data[data['City']!="NaN"]
data = data[data['Distance']!="NaN"]
data = data[data['Time_prep']!="NaN"]
data = data[data['Weather']!="NaN"]
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37	4.9	0	2	0	0	0	0.0	0.0	3.025153	15	0	24
1	1	1	0xb379	BANGRES18DEL02	34	4.5	1	2	0	1	1	0.0	1.0	20.183558	5	1	33
2	2	2	0x5d6d	BANGRES19DEL01	23	4.4	2	0	1	0	1	0.0	0.0	1.552760	15	2	26
3	3	3	0x7a6a	COIMBRES13DEL02	38	4.7	3	0	2	0	1	0.0	1.0	7.790412	10	0	21
4	4	4	0x70a2	CHENRES12DEL01	32	4.6	0	1	0	1	1	0.0	1.0	6.210147	15	3	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43856	43856	45587	0x1178	RANCHIRES16DEL01	35	4.2	1	2	1	0	1	0.0	1.0	16.600295	10	5	33
43857	43857	45588	0x7c09	JAPRES04DEL01	30	4.8	0	1	3	0	0	0.0	1.0	1.489848	10	5	32
43858	43858	45589	0xd641	AGRRES16DEL01	21	4.6	1	0	2	0	1	0.0	1.0	11.007750	15	5	36
43860	43860	45591	0x5eee	COIMBRES11DEL01	20	4.7	0	0	0	0	1	0.0	1.0	6.232402	5	3	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23	4.9	3	2	0	1	1	0.0	1.0	12.074412	5	4	36

43031 rows × 17 columns

data['Delivery_person_Age'] = pd.to_numeric(data['Delivery_person_Age'])
data['Delivery_person_Ratings'] = pd.to_numeric(data['Delivery_person_Ratings'])
data['multiple_deliveries'] = pd.to_numeric(data['multiple_deliveries'])
data

	level_0	index	ID	Delivery_person_ID	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	0	0x4607	INDORES13DEL02	37.0	4.9	0	2	0	0	0.0	0.0	0.0	3.025153	15	0	24
1	1	1	0xb379	BANGRES18DEL02	34.0	4.5	1	2	0	1	1.0	0.0	1.0	20.183558	5	1	33
2	2	2	0x5d6d	BANGRES19DEL01	23.0	4.4	2	0	1	0	1.0	0.0	0.0	1.552760	15	2	26
3	3	3	0x7a6a	COIMBRES13DEL02	38.0	4.7	3	0	2	0	1.0	0.0	1.0	7.790412	10	0	21
4	4	4	0x70a2	CHENRES12DEL01	32.0	4.6	0	1	0	1	1.0	0.0	1.0	6.210147	15	3	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
43856	43856	45587	0x1178	RANCHIRES16DEL01	35.0	4.2	1	2	1	0	1.0	0.0	1.0	16.600295	10	5	33
43857	43857	45588	0x7c09	JAPRES04DEL01	30.0	4.8	0	1	3	0	0.0	0.0	1.0	1.489848	10	5	32
43858	43858	45589	0xd641	AGRRES16DEL01	21.0	4.6	1	0	2	0	1.0	0.0	1.0	11.007750	15	5	36
43860	43860	45591	0x5eee	COIMBRES11DEL01	20.0	4.7	0	0	0	0	1.0	0.0	1.0	6.232402	5	3	26
43861	43861	45592	0x5fb2	RANCHIRES09DEL02	23.0	4.9	3	2	0	1	1.0	0.0	1.0	12.074412	5	4	36

43031 rows × 17 columns

data = data.drop(['Delivery_person_ID', 'ID', 'index', 'level_0'], axis=1)
data

	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	37.0	4.9	0	2	0	0	0.0	0.0	0.0	3.025153	15	0	24
1	34.0	4.5	1	2	0	1	1.0	0.0	1.0	20.183558	5	1	33
2	23.0	4.4	2	0	1	0	1.0	0.0	0.0	1.552760	15	2	26
3	38.0	4.7	3	0	2	0	1.0	0.0	1.0	7.790412	10	0	21
4	32.0	4.6	0	1	0	1	1.0	0.0	1.0	6.210147	15	3	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...
43856	35.0	4.2	1	2	1	0	1.0	0.0	1.0	16.600295	10	5	33
43857	30.0	4.8	0	1	3	0	0.0	0.0	1.0	1.489848	10	5	32
43858	21.0	4.6	1	0	2	0	1.0	0.0	1.0	11.007750	15	5	36
43860	20.0	4.7	0	0	0	0	1.0	0.0	1.0	6.232402	5	3	26
43861	23.0	4.9	3	2	0	1	1.0	0.0	1.0	12.074412	5	4	36

43031 rows × 13 columns

data['Distance'].describe()
data = data[data['Distance']<100]
data = data.reset_index()
data

	index	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather	Time_taken
0	0	37.0	4.9	0	2	0	0	0.0	0.0	0.0	3.025153	15	0	24
1	1	34.0	4.5	1	2	0	1	1.0	0.0	1.0	20.183558	5	1	33
2	2	23.0	4.4	2	0	1	0	1.0	0.0	0.0	1.552760	15	2	26
3	3	38.0	4.7	3	0	2	0	1.0	0.0	1.0	7.790412	10	0	21
4	4	32.0	4.6	0	1	0	1	1.0	0.0	1.0	6.210147	15	3	30
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
42872	43856	35.0	4.2	1	2	1	0	1.0	0.0	1.0	16.600295	10	5	33
42873	43857	30.0	4.8	0	1	3	0	0.0	0.0	1.0	1.489848	10	5	32
42874	43858	21.0	4.6	1	0	2	0	1.0	0.0	1.0	11.007750	15	5	36
42875	43860	20.0	4.7	0	0	0	0	1.0	0.0	1.0	6.232402	5	3	26
42876	43861	23.0	4.9	3	2	0	1	1.0	0.0	1.0	12.074412	5	4	36

42877 rows × 14 columns

data.isna().sum()

index                        0
Delivery_person_Age        211
Delivery_person_Ratings    257
Road_traffic_density         0
Vehicle_condition            0
Type_of_order                0
Type_of_vehicle              0
multiple_deliveries        927
Festival                     0
City                         0
Distance                     0
Time_prep                    0
Weather                      0
Time_taken                   0
dtype: int64

data['multiple_deliveries'].head(30)

0     0.0
1     1.0
2     1.0
3     1.0
4     1.0
5     1.0
6     1.0
7     1.0
8     1.0
9     3.0
10    1.0
11    1.0
12    0.0
13    1.0
14    1.0
15    1.0
16    1.0
17    NaN
18    1.0
19    2.0
20    0.0
21    1.0
22    1.0
23    1.0
24    1.0
25    0.0
26    0.0
27    1.0
28    0.0
29    1.0
Name: multiple_deliveries, dtype: float64

data['Delivery_person_Age'] = data['Delivery_person_Age'].fillna(data['Delivery_person_Age'].mean()) 
data['Delivery_person_Ratings'] = data['Delivery_person_Ratings'].fillna(data['Delivery_person_Ratings'].mean()) 
data['multiple_deliveries'].unique()
data['multiple_deliveries'].median()
data['multiple_deliveries'] = data['multiple_deliveries'].fillna(data['multiple_deliveries'].median())

data.isna().sum()

index                      0
Delivery_person_Age        0
Delivery_person_Ratings    0
Road_traffic_density       0
Vehicle_condition          0
Type_of_order              0
Type_of_vehicle            0
multiple_deliveries        0
Festival                   0
City                       0
Distance                   0
Time_prep                  0
Weather                    0
Time_taken                 0
dtype: int64

import seaborn as sns

plt.figure(figsize=(15,7))
ax = sns.heatmap(data.corr(), annot=True)

columns=data[['Delivery_person_Age','Delivery_person_Ratings','Road_traffic_density','Vehicle_condition','Type_of_order','Time_taken']]
sns.pairplot(columns)
plt.show()

from sklearn.model_selection import train_test_split

x = data.drop(['Time_taken', 'index'], axis=1)
x

	Delivery_person_Age	Delivery_person_Ratings	Road_traffic_density	Vehicle_condition	Type_of_order	Type_of_vehicle	multiple_deliveries	Festival	City	Distance	Time_prep	Weather
0	37.0	4.9	0	2	0	0	0.0	0.0	0.0	3.025153	15	0
1	34.0	4.5	1	2	0	1	1.0	0.0	1.0	20.183558	5	1
2	23.0	4.4	2	0	1	0	1.0	0.0	0.0	1.552760	15	2
3	38.0	4.7	3	0	2	0	1.0	0.0	1.0	7.790412	10	0
4	32.0	4.6	0	1	0	1	1.0	0.0	1.0	6.210147	15	3
...	...	...	...	...	...	...	...	...	...	...	...	...
42872	35.0	4.2	1	2	1	0	1.0	0.0	1.0	16.600295	10	5
42873	30.0	4.8	0	1	3	0	0.0	0.0	1.0	1.489848	10	5
42874	21.0	4.6	1	0	2	0	1.0	0.0	1.0	11.007750	15	5
42875	20.0	4.7	0	0	0	0	1.0	0.0	1.0	6.232402	5	3
42876	23.0	4.9	3	2	0	1	1.0	0.0	1.0	12.074412	5	4

42877 rows × 12 columns

y = data[['Time_taken']]
y

	Time_taken
0	24
1	33
2	26
3	21
4	30
...	...
42872	33
42873	32
42874	36
42875	26
42876	36

42877 rows × 1 columns

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=42)

from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import GridSearchCV
from sklearn import metrics
import warnings

warnings.filterwarnings('ignore')

随机森林回归

forest = RandomForestRegressor(n_estimators= 200, min_samples_split= 4, min_samples_leaf= 1)
forest.fit(x_train, y_train)

RandomForestRegressor

RandomForestRegressor(min_samples_split=4, n_estimators=200)

forest.score(x_test, y_test)

0.8366806837953505

线性回归

from sklearn.linear_model import LinearRegression
reg = LinearRegression()
reg.fit(x_train, y_train)
reg.score(x_test, y_test)

0.46966387660478515

from sklearn import linear_model
reg2=linear_model.LassoLars(alpha=.1, normalize=False)
reg2.fit(x_train,y_train)

LassoLars

LassoLars(alpha=0.1, normalize=False)

reg2.score(x_train, y_train)

0.4674006811969696

完整代码详见源网站：外卖配送时间预测项目-VenusAI (aideeplearning.cn)