导入load_datasets模块

from model_insight.load_datasets import *

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np

数据集

评价数据集

load_supplier

load_supplier().head()

	Warranty Terms	Payment Terms	Technical Support	Sustainability Efforts	Finp.nancial Stability	Unit Cost	Lead Time (Days)	On Time Delivery
1	2.42	2.80	8.25	3.09	8.21	1.05	8.0	0.75
2	6.51	1.88	3.60	6.45	4.31	1.21	13.0	0.83
3	8.51	1.06	2.97	9.36	5.06	1.22	12.0	0.91
4	4.63	4.60	5.84	7.34	9.20	1.01	9.0	0.72
5	4.62	7.44	1.50	8.93	4.01	1.03	7.0	0.97

load_supplier().info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 100 entries, 1 to 100
Data columns (total 8 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   Warranty Terms          100 non-null    float64
 1   Payment Terms           100 non-null    float64
 2   Technical Support       100 non-null    float64
 3   Sustainability Efforts  100 non-null    float64
 4   Finp.nancial Stability  100 non-null    float64
 5   Unit Cost               100 non-null    float64
 6   Lead Time (Days)        100 non-null    float64
 7   On Time Delivery        100 non-null    float64
dtypes: float64(8)
memory usage: 7.0 KB

load_supplier().describe()

	Warranty Terms	Payment Terms	Technical Support	Sustainability Efforts	Finp.nancial Stability	Unit Cost	Lead Time (Days)	On Time Delivery
count	100.000000	100.000000	100.000000	100.000000	100.000000	100.00000	100.000000	100.000000
mean	5.740600	5.374800	5.593800	5.469400	5.482100	1.15300	7.980000	0.844700
std	2.681567	2.749968	2.685119	2.538964	2.593445	0.08597	4.235444	0.090436
min	1.220000	1.060000	1.070000	1.090000	1.040000	1.01000	2.000000	0.700000
25%	3.427500	2.740000	3.307500	3.065000	3.307500	1.07000	4.000000	0.775000
50%	6.170000	5.265000	5.575000	5.530000	5.240000	1.15000	8.000000	0.840000
75%	7.930000	7.880000	7.950000	7.485000	7.922500	1.22000	11.250000	0.920000
max	9.970000	9.970000	9.890000	9.870000	9.810000	1.30000	15.000000	1.000000

load_supplier().to_excel('load_supplier.xlsx',index_label='Supplier')

load_roller20

load_roller20().head()

	Name	Park	City/Region	City/State/Region	Country/Region	Geographic Region	Construction	Type	Status	Year/Date Opened	Height (feet)	Speed (mph)	Length (feet)	Inversions (YES or NO)	Number of Inversions	Drop (feet)	Duration (min:sec)	G Force	Vertical Angle (degrees)
0	10 Inversion Roller Coaster	Chimelong Paradise	Panyu	Guangzhou, Guangdong	China	Asia	Steel	Sit Down	Operating	2006	98.4	45.0	2788.8	YES	10.0	NaN	01:32:00	NaN	NaN
1	Abismo	Parque de Atracciones de Madrid	Madrid	Madrid	Spain	Europe	Steel	Sit Down	Operating	2006	151.6	65.2	1476.4	YES	2.0	NaN	01:00:00	4.0	NaN
2	Adrenaline Peak	Oaks Amusement Park	Portland	Oregon	United States	North America	Steel	Sit Down	Operating	2018	72.0	45.0	1050.0	YES	3.0	NaN	NaN	NaN	97.0
3	Afterburn	Carowinds	Charlotte	North Carolina	United States	North America	Steel	Inverted	Operating	1999	113.0	62.0	2956.0	YES	6.0	NaN	02:47:00	NaN	NaN
4	Alpengeist	Busch Gardens Williamsburg	Williamsburg	Virginia	United States	North America	Steel	Inverted	Operating	1997	195.0	67.0	3828.0	YES	6.0	170.0	03:10:00	3.7	NaN

load_roller20().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20 entries, 0 to 19
Data columns (total 19 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Name                      20 non-null     object 
 1   Park                      20 non-null     object 
 2   City/Region               20 non-null     object 
 3   City/State/Region         20 non-null     object 
 4   Country/Region            20 non-null     object 
 5   Geographic Region         20 non-null     object 
 6   Construction              20 non-null     object 
 7   Type                      20 non-null     object 
 8   Status                    20 non-null     object 
 9   Year/Date Opened          20 non-null     object 
 10  Height (feet)             20 non-null     float64
 11   Speed (mph)              20 non-null     float64
 12  Length (feet)             20 non-null     float64
 13  Inversions (YES or NO)    20 non-null     object 
 14  Number of Inversions      20 non-null     float64
 15  Drop (feet)               9 non-null      float64
 16  Duration (min:sec)        17 non-null     object 
 17  G Force                   4 non-null      float64
 18  Vertical Angle (degrees)  4 non-null      float64
dtypes: float64(7), object(12)
memory usage: 3.1+ KB

load_roller20().describe()

	Height (feet)	Speed (mph)	Length (feet)	Number of Inversions	Drop (feet)	G Force	Vertical Angle (degrees)
count	20.000000	20.000000	20.000000	20.000000	9.000000	4.000	4.000000
mean	113.620000	55.395000	2935.780000	2.800000	111.911111	4.025	71.750000
std	35.357506	8.802301	1050.537719	3.488326	60.582329	0.250	17.951323
min	45.200000	40.000000	1050.000000	0.000000	31.200000	3.700	55.000000
25%	97.550000	49.925000	2357.175000	0.000000	81.700000	3.925	62.500000
50%	108.300000	53.900000	2878.400000	1.000000	90.000000	4.050	67.500000
75%	120.325000	62.800000	3661.275000	5.250000	150.000000	4.150	76.750000
max	195.000000	73.000000	4882.000000	10.000000	210.000000	4.300	97.000000

load_roller20().to_excel('load_roller20.xlsx',index=False)

load_aircraft

load_aircraft()

	最大速度(马赫)	飞行范围(km)	最大负载(磅)	费用(美元)	可靠性	灵敏性
A	2.0	1500.0	20000.0	5500000.0	0.5	1.0
B	2.5	2700.0	18000.0	6500000.0	0.3	0.5
C	1.8	2000.0	21000.0	4500000.0	0.7	0.7
D	2.2	1800.0	20000.0	5000000.0	0.5	0.5

load_aircraft().info()

<class 'pandas.core.frame.DataFrame'>
Index: 4 entries, A to D
Data columns (total 6 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   最大速度(马赫)  4 non-null      float64
 1   飞行范围(km)  4 non-null      float64
 2   最大负载(磅)   4 non-null      float64
 3   费用(美元)    4 non-null      float64
 4   可靠性       4 non-null      float64
 5   灵敏性       4 non-null      float64
dtypes: float64(6)
memory usage: 224.0+ bytes

load_aircraft().describe()

	最大速度(马赫)	飞行范围(km)	最大负载(磅)	费用(美元)	可靠性	灵敏性
count	4.000000	4.000000	4.000000	4.000000e+00	4.000000	4.000000
mean	2.125000	2000.000000	19750.000000	5.375000e+06	0.500000	0.675000
std	0.298608	509.901951	1258.305739	8.539126e+05	0.163299	0.236291
min	1.800000	1500.000000	18000.000000	4.500000e+06	0.300000	0.500000
25%	1.950000	1725.000000	19500.000000	4.875000e+06	0.450000	0.500000
50%	2.100000	1900.000000	20000.000000	5.250000e+06	0.500000	0.600000
75%	2.275000	2175.000000	20250.000000	5.750000e+06	0.550000	0.775000
max	2.500000	2700.000000	21000.000000	6.500000e+06	0.700000	1.000000

load_aircraft().to_excel('load_aircraft.xlsx')

load_hospital

load_hospital().head()

	X1	X2	X3	X4	X5	X6	X7	X8	X9
A	100.0	90.0	100.0	84.0	90.0	100.0	100.0	100.0	100.0
B	100.0	100.0	78.6	100.0	90.0	100.0	100.0	100.0	100.0
C	75.0	100.0	85.7	100.0	90.0	100.0	100.0	100.0	100.0
D	100.0	100.0	78.6	100.0	90.0	100.0	94.4	100.0	100.0
E	100.0	90.0	100.0	100.0	100.0	90.0	100.0	100.0	80.0

load_hospital().info()

<class 'pandas.core.frame.DataFrame'>
Index: 11 entries, A to K
Data columns (total 9 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   X1      11 non-null     float64
 1   X2      11 non-null     float64
 2   X3      11 non-null     float64
 3   X4      11 non-null     float64
 4   X5      11 non-null     float64
 5   X6      11 non-null     float64
 6   X7      11 non-null     float64
 7   X8      11 non-null     float64
 8   X9      11 non-null     float64
dtypes: float64(9)
memory usage: 880.0+ bytes

load_hospital().describe()

	X1	X2	X3	X4	X5	X6	X7	X8	X9
count	11.000000	11.000000	11.000000	11.000000	11.000000	11.000000	11.000000	11.000000	11.000000
mean	96.590909	97.272727	90.272727	98.545455	91.818182	99.090909	95.454545	98.700000	98.181818
std	8.083372	4.670994	9.180751	4.824182	6.030227	3.015113	13.324591	4.311612	6.030227
min	75.000000	90.000000	78.600000	84.000000	80.000000	90.000000	55.600000	85.700000	80.000000
25%	100.000000	95.000000	82.150000	100.000000	90.000000	100.000000	100.000000	100.000000	100.000000
50%	100.000000	100.000000	92.900000	100.000000	90.000000	100.000000	100.000000	100.000000	100.000000
75%	100.000000	100.000000	100.000000	100.000000	95.000000	100.000000	100.000000	100.000000	100.000000
max	100.000000	100.000000	100.000000	100.000000	100.000000	100.000000	100.000000	100.000000	100.000000

load_battery

load_battery().head()

	Price(USD)	Weight(pounds)	Power Rating Capability(kWh)	steady	peak	Length(inch)	Width(inch)	Height(inch)	Depth of Discharge(DoD)%	Circles of Life Time	Round Trip Efficiency(RET)%	Warranty(year)	Low Temperature	High Temperature	Battery Type
1	10000.0	297.0	14.0	5.0	5.0	20.8	15.7	41.0	90.0	6000.0	97.0	15.0	0.00	50.00	LFP
2	13000.0	297.0	13.0	2.0	3.3	20.8	15.7	41.0	90.0	6000.0	97.0	10.0	0.00	50.00	NMC
3	9500.0	348.0	10.0	2.0	3.3	68.0	26.0	11.0	100.0	10000.0	85.0	10.0	-4.24	36.72	LFP
4	5950.0	331.0	2.5	2.0	3.3	25.0	15.0	56.0	90.0	10000.0	81.6	10.0	-4.24	36.72	LFP
5	11900.0	381.0	5.0	2.0	3.3	25.0	15.0	56.0	90.0	10000.0	81.6	10.0	-4.24	36.72	LFP

load_battery().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 36 entries, 1 to 36
Data columns (total 15 columns):
 #   Column                        Non-Null Count  Dtype  
---  ------                        --------------  -----  
 0   Price(USD)                    36 non-null     float64
 1   Weight(pounds)                36 non-null     float64
 2   Power Rating Capability(kWh)  36 non-null     float64
 3   steady                        36 non-null     float64
 4   peak                          36 non-null     float64
 5   Length(inch)                  36 non-null     float64
 6   Width(inch)                   36 non-null     float64
 7   Height(inch)                  36 non-null     float64
 8   Depth of Discharge(DoD)%      36 non-null     float64
 9   Circles of Life Time          36 non-null     float64
 10  Round Trip Efficiency(RET)%   36 non-null     float64
 11  Warranty(year)                36 non-null     float64
 12  Low Temperature               36 non-null     float64
 13  High Temperature              36 non-null     float64
 14  Battery Type                  36 non-null     object 
dtypes: float64(14), object(1)
memory usage: 4.3+ KB

load_battery().describe()

	Price(USD)	Weight(pounds)	Power Rating Capability(kWh)	steady	peak	Length(inch)	Width(inch)	Height(inch)	Depth of Discharge(DoD)%	Circles of Life Time	Round Trip Efficiency(RET)%	Warranty(year)	Low Temperature	High Temperature
count	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000	36.000000
mean	11320.882222	318.036667	9.799722	3.870556	6.850000	33.058333	21.211111	34.079722	89.941667	6200.000000	91.171944	10.063889	-4.240000	36.720000
std	5766.240606	146.627600	4.731948	1.907664	3.338028	12.740550	8.771781	34.406330	5.875284	2355.783158	6.067850	1.548004	12.465449	27.508461
min	1976.000000	30.000000	1.200000	1.500000	3.000000	13.500000	9.840000	2.130000	80.000000	1000.000000	80.000000	5.000000	-30.000000	-70.000000
25%	7037.500000	268.250000	6.375000	3.000000	4.800000	25.000000	15.000000	9.000000	89.940000	5000.000000	84.750000	10.000000	-10.000000	36.720000
50%	11320.880000	318.040000	10.000000	3.870000	6.850000	33.060000	20.205000	34.080000	89.970000	6200.000000	91.585000	10.000000	-4.240000	37.360000
75%	15000.000000	351.000000	13.125000	5.000000	7.600000	39.000000	25.250000	45.875000	90.000000	6300.000000	96.500000	10.000000	0.000000	50.000000
max	23800.000000	735.000000	20.000000	12.800000	19.200000	68.000000	50.000000	191.000000	100.000000	10000.000000	100.000000	15.000000	20.000000	60.000000

load_university

load_university().head()

	人均专著	生师比	科研经费	逾期毕业率
院校A	0.1	5	5000	4.7
院校B	0.2	6	6000	5.6
院校C	0.4	7	7000	6.7
院校D	0.9	10	10000	2.3
院校E	1.2	2	400	1.8

load_university().info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, 院校A to 院校E
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   人均专著    5 non-null      float64
 1   生师比     5 non-null      int64  
 2   科研经费    5 non-null      int64  
 3   逾期毕业率   5 non-null      float64
dtypes: float64(2), int64(2)
memory usage: 200.0+ bytes

load_university().describe()

	人均专著	生师比	科研经费	逾期毕业率
count	5.000000	5.000000	5.000000	5.000000
mean	0.560000	6.000000	5680.000000	4.220000
std	0.472229	2.915476	3494.567212	2.111161
min	0.100000	2.000000	400.000000	1.800000
25%	0.200000	5.000000	5000.000000	2.300000
50%	0.400000	6.000000	6000.000000	4.700000
75%	0.900000	7.000000	7000.000000	5.600000
max	1.200000	10.000000	10000.000000	6.700000

load_computer

load_computer().head()

	产品净重(kg)	长mm*宽mm*厚mm	CPU集成显卡	处理器基准频率（GHz）	处理器加速频率	CPU型号	核心数	线程数	内存类型	内存频率(MHz)	...	理论续航时间	处理器	固态硬盘	厚度	机身材质	内存容量(GB)	屏幕尺寸	系列	显卡型号	价格(元）
adolbook13 2021	1.20	304.9*199.9*12.9	intel集成显卡	2.4	4.2	i5-1135G7	4.0	8.0	LPDDR4x	4266.0	...	5-8小时	intel i5	512GB	15.0mm及以下	金属+复合材料	16.0	12.0-13.9英寸	a-豆-adolbook	集成显卡	5099.0
V5200	1.70	360*235*17.6	nan	2.8	4.7	i7-1165G7	4.0	8.0	DDR4	3200.0	...	2-5h	intel i7	512GB	15.1-18.0mm	复合材质	16.0	15.0-15.9英寸	华硕-VivoBook	intel 集成显卡	5299.0
联想S14 2021款	1.50	324*218*17.9	AMD集成显卡	1.8	4.3	R7-5700U	8.0	16.0	DDR4	3200.0	...	5-8小时	AMD R7	512GB	15.1-18.0mm	金属+复合材料	24.0	14.0-14.9英寸	联想-扬天系列	集成显卡	5799.0
U4700	1.19	319*208*13.5	intel集成显卡	2.4	4.2	i5-1135G7	4.0	8.0	LPDDR4x	4266.0	...	5-8小时	intel i5	512GB	15.0mm及以下	金属+复合材料	16.0	14.0-14.9英寸	华硕-灵耀14	集成显卡	4799.0
灵越3511	1.73	358*235*18	intel集成显卡	2.8	4.7	i7-1165G7	4.0	8.0	DDR4	3200.0	...	5-8小时	intel i7	256GB	18.1-20.0mm	复合材质	16.0	15.0-15.9英寸	戴尔-成就系列	MX350	6299.0

5 rows × 24 columns

load_computer().info()

<class 'pandas.core.frame.DataFrame'>
Index: 8 entries, adolbook13 2021 to TPN-W144
Data columns (total 24 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   产品净重(kg)      8 non-null      float64
 1   长mm*宽mm*厚mm   8 non-null      object 
 2   CPU集成显卡       8 non-null      object 
 3   处理器基准频率（GHz）  8 non-null      float64
 4   处理器加速频率       8 non-null      float64
 5   CPU型号         8 non-null      object 
 6   核心数           8 non-null      float64
 7   线程数           8 non-null      float64
 8   内存类型          8 non-null      object 
 9   内存频率(MHz)     7 non-null      float64
 10  显卡类型          8 non-null      object 
 11  屏幕尺寸(英寸)      8 non-null      object 
 12  屏幕类型          8 non-null      object 
 13  电池容量(WH)      8 non-null      float64
 14  理论续航时间        8 non-null      object 
 15  处理器           8 non-null      object 
 16  固态硬盘          8 non-null      object 
 17  厚度            8 non-null      object 
 18  机身材质          8 non-null      object 
 19  内存容量(GB)      8 non-null      float64
 20  屏幕尺寸          8 non-null      object 
 21  系列            8 non-null      object 
 22  显卡型号          8 non-null      object 
 23  价格(元）         8 non-null      float64
dtypes: float64(9), object(15)
memory usage: 1.6+ KB

load_computer().describe()

	产品净重(kg)	处理器基准频率（GHz）	处理器加速频率	核心数	线程数	内存频率(MHz)	电池容量(WH)	内存容量(GB)	价格(元）
count	8.000000	8.000000	8.000000	8.000000	8.000000	7.000000	8.000000	8.000000	8.000000
mean	1.418750	2.237500	4.337500	4.500000	9.000000	3275.857143	48.875000	17.000000	5536.500000
std	0.254415	0.713017	0.250357	1.414214	2.828427	780.606266	10.709642	2.828427	641.287767
min	1.050000	1.000000	4.000000	4.000000	8.000000	2133.000000	37.000000	16.000000	4799.000000
25%	1.197500	1.750000	4.200000	4.000000	8.000000	2933.000000	41.750000	16.000000	5074.000000
50%	1.440000	2.400000	4.250000	4.000000	8.000000	3200.000000	45.500000	16.000000	5349.000000
75%	1.625000	2.800000	4.475000	4.000000	8.000000	3733.000000	53.250000	16.000000	5924.000000
max	1.730000	3.100000	4.700000	8.000000	16.000000	4266.000000	67.000000	24.000000	6599.000000

优化数据集

load_portfolio

load_portfolio().head()

	r(%)	q(%)	p(%)	u(RMB)
s1	28.0	2.5	1.0	103.0
s2	21.0	1.5	2.0	198.0
s3	23.0	5.5	4.5	52.0
s4	25.0	2.6	6.5	40.0

load_portfolio().info()

<class 'pandas.core.frame.DataFrame'>
Index: 4 entries, s1 to s4
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   r(%)    4 non-null      float64
 1   q(%)    4 non-null      float64
 2   p(%)    4 non-null      float64
 3   u(RMB)  4 non-null      float64
dtypes: float64(4)
memory usage: 160.0+ bytes

load_portfolio().describe()

	r(%)	q(%)	p(%)	u(RMB)
count	4.000000	4.000000	4.000000	4.000000
mean	24.250000	3.025000	3.500000	98.250000
std	2.986079	1.723127	2.483277	71.890542
min	21.000000	1.500000	1.000000	40.000000
25%	22.500000	2.250000	1.750000	49.000000
50%	24.000000	2.550000	3.250000	77.500000
75%	25.750000	3.325000	5.000000	126.750000
max	28.000000	5.500000	6.500000	198.000000

load_ambulance

load_ambulance().head()

	0	1	2	3	4	5
0	1	1	0	0	0	0
1	1	1	1	0	0	0
2	0	0	1	0	1	1
3	0	0	1	1	0	0
4	0	0	0	1	1	1

load_ambulance().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 6 entries, 0 to 5
Data columns (total 6 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   0       6 non-null      int32
 1   1       6 non-null      int32
 2   2       6 non-null      int32
 3   3       6 non-null      int32
 4   4       6 non-null      int32
 5   5       6 non-null      int32
dtypes: int32(6)
memory usage: 272.0 bytes

load_ambulance().describe()

	0	1	2	3	4	5
count	6.000000	6.000000	6.000000	6.000000	6.000000	6.000000
mean	0.333333	0.333333	0.666667	0.333333	0.500000	0.500000
std	0.516398	0.516398	0.516398	0.516398	0.547723	0.547723
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	0.000000	0.000000	0.250000	0.000000	0.000000	0.000000
50%	0.000000	0.000000	1.000000	0.000000	0.500000	0.500000
75%	0.750000	0.750000	1.000000	0.750000	1.000000	1.000000
max	1.000000	1.000000	1.000000	1.000000	1.000000	1.000000

load_oil

load_oil().head()

	价格	硬度
VEG1	110.0	8.8
VEG2	120.0	6.1
OIL1	130.0	2.0
OIL2	110.0	4.2
OIL3	115.0	5.0

load_oil().info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, VEG1 to OIL3
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   价格      5 non-null      float64
 1   硬度      5 non-null      float64
dtypes: float64(2)
memory usage: 120.0+ bytes

load_oil().describe()

	价格	硬度
count	5.0000	5.000000
mean	117.0000	5.220000
std	8.3666	2.502399
min	110.0000	2.000000
25%	110.0000	4.200000
50%	115.0000	5.000000
75%	120.0000	6.100000
max	130.0000	8.800000

load_factory_cloths

load_factory_clothes().head()

	设备租金(元)	材料成本(元/件)	销售价格(元/件)	人工工时(小时/件)	设备工时(小时/件)	设备可用工时	人工可用工时
A	5000.0	280.0	400.0	5.0	3.0	300.0	600.0
B	2000.0	30.0	40.0	1.0	0.5	300.0	800.0
C	2000.0	200.0	300.0	4.0	2.0	300.0	600.0

load_factory_clothes().info()

<class 'pandas.core.frame.DataFrame'>
Index: 3 entries, A to C
Data columns (total 7 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   设备租金(元)     3 non-null      float64
 1   材料成本(元/件)   3 non-null      float64
 2   销售价格(元/件)   3 non-null      float64
 3   人工工时(小时/件)  3 non-null      float64
 4   设备工时(小时/件)  3 non-null      float64
 5   设备可用工时      3 non-null      float64
 6   人工可用工时      3 non-null      float64
dtypes: float64(7)
memory usage: 192.0+ bytes

load_factory_clothes().describe()

	设备租金(元)	材料成本(元/件)	销售价格(元/件)	人工工时(小时/件)	设备工时(小时/件)	设备可用工时	人工可用工时
count	3.000000	3.000000	3.000000	3.000000	3.000000	3.0	3.000000
mean	3000.000000	170.000000	246.666667	3.333333	1.833333	300.0	666.666667
std	1732.050808	127.671453	185.831465	2.081666	1.258306	0.0	115.470054
min	2000.000000	30.000000	40.000000	1.000000	0.500000	300.0	600.000000
25%	2000.000000	115.000000	170.000000	2.500000	1.250000	300.0	600.000000
50%	2000.000000	200.000000	300.000000	4.000000	2.000000	300.0	600.000000
75%	3500.000000	240.000000	350.000000	4.500000	2.500000	300.0	700.000000
max	5000.000000	280.000000	400.000000	5.000000	3.000000	300.0	800.000000

load_swim

load_swim().head()

	泳姿1	泳姿2	泳姿3	泳姿4
A	56	74	61	63
B	63	69	65	71
C	57	77	63	67
D	55	76	62	62
E	60	71	62	68

load_swim().info()

<class 'pandas.core.frame.DataFrame'>
Index: 5 entries, A to E
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   泳姿1     5 non-null      int64
 1   泳姿2     5 non-null      int64
 2   泳姿3     5 non-null      int64
 3   泳姿4     5 non-null      int64
dtypes: int64(4)
memory usage: 200.0+ bytes

load_swim().describe()

	泳姿1	泳姿2	泳姿3	泳姿4
count	5.000000	5.000000	5.000000	5.000000
mean	58.200000	73.400000	62.600000	66.200000
std	3.271085	3.361547	1.516575	3.701351
min	55.000000	69.000000	61.000000	62.000000
25%	56.000000	71.000000	62.000000	63.000000
50%	57.000000	74.000000	62.000000	67.000000
75%	60.000000	76.000000	63.000000	68.000000
max	63.000000	77.000000	65.000000	71.000000

load_plant

load_plant().head()

	unique_id	Benefit	Taxonomic Uniqueness	Feasibility of Success	Year 1 cost	Year 2 cost	Year 3 cost	Year 4 cost	Year 5 cost	Year 6 cost	...	Year 16 cost	Year 17 cost	Year 18 cost	Year 19 cost	Year 20 cost	Year 21 cost	Year 22 cost	Year 23 cost	Year 24 cost	Year 25 cost
0	1-Flowering Plants-502	0.66	0.67	0.60	11616.17065	6053.241613	5993.308527	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	1-Flowering Plants-436	0.66	0.67	0.22	12356.61827	10136.971140	10036.605090	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	1-Flowering Plants-536	0.99	0.67	0.87	20849.60760	20643.175840	20438.787970	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	1-Flowering Plants-486	0.66	0.67	0.71	27820.04342	16009.423390	10659.566790	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	1-Flowering Plants-183	0.66	0.67	0.11	22163.13537	18663.079030	18478.296070	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

5 rows × 29 columns

load_plant().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 30 entries, 0 to 29
Data columns (total 29 columns):
 #   Column                  Non-Null Count  Dtype  
---  ------                  --------------  -----  
 0   unique_id               30 non-null     object 
 1   Benefit                 30 non-null     float64
 2   Taxonomic Uniqueness    30 non-null     float64
 3   Feasibility of Success  30 non-null     float64
 4   Year 1 cost             30 non-null     float64
 5   Year 2 cost             30 non-null     float64
 6   Year 3 cost             30 non-null     float64
 7   Year 4 cost             30 non-null     float64
 8   Year 5 cost             30 non-null     float64
 9   Year 6 cost             30 non-null     float64
 10  Year 7 cost             30 non-null     float64
 11  Year 8 cost             30 non-null     float64
 12  Year 9 cost             30 non-null     float64
 13  Year 10 cost            30 non-null     float64
 14  Year  11 cost           30 non-null     float64
 15  Year 12 cost            30 non-null     float64
 16  Year 13 cost            30 non-null     float64
 17  Year 14 cost            30 non-null     float64
 18  Year 15 cost            30 non-null     float64
 19  Year 16 cost            30 non-null     float64
 20  Year 17 cost            30 non-null     float64
 21  Year 18 cost            30 non-null     float64
 22  Year 19 cost            30 non-null     float64
 23  Year 20 cost            30 non-null     float64
 24  Year 21 cost            30 non-null     float64
 25  Year 22 cost            30 non-null     float64
 26  Year 23 cost            30 non-null     float64
 27  Year 24 cost            30 non-null     float64
 28  Year 25 cost            30 non-null     float64
dtypes: float64(28), object(1)
memory usage: 6.9+ KB

load_plant().describe()

	Benefit	Taxonomic Uniqueness	Feasibility of Success	Year 1 cost	Year 2 cost	Year 3 cost	Year 4 cost	Year 5 cost	Year 6 cost	Year 7 cost	...	Year 16 cost	Year 17 cost	Year 18 cost	Year 19 cost	Year 20 cost	Year 21 cost	Year 22 cost	Year 23 cost	Year 24 cost	Year 25 cost
count	30.000000	30.000000	30.000000	30.000000	30.000000	30.000000	30.000000	30.000000	30.000000	30.000000	...	30.000000	30.0	30.0	30.0	30.0	30.0	30.0	30.0	30.0	30.0
mean	0.687000	0.692000	0.531000	75573.157018	68724.205860	60245.414364	16024.663166	14849.274923	542.028767	444.232623	...	406.179579	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
std	0.179658	0.083724	0.247739	47282.794778	48932.509438	45254.236766	24532.181619	23449.894949	2492.802573	2433.162284	...	2224.737176	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
min	0.330000	0.670000	0.110000	11616.170650	6053.241613	5993.308527	0.000000	0.000000	0.000000	0.000000	...	0.000000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
25%	0.660000	0.670000	0.280000	41815.493245	29554.317488	26533.674870	0.000000	0.000000	0.000000	0.000000	...	0.000000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
50%	0.660000	0.670000	0.570000	60693.027140	57344.519770	44535.842565	6121.302150	4715.718128	0.000000	0.000000	...	0.000000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
75%	0.660000	0.670000	0.717500	101029.077045	98632.339030	92289.050550	27077.142335	25124.893505	0.000000	0.000000	...	0.000000	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
max	0.990000	1.000000	0.990000	175872.572400	172674.094400	167575.571300	114071.257200	106405.852700	13460.248480	13326.978690	...	12185.387360	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

8 rows × 28 columns

load_tickets

load_tickets().head()

	A	B	C	D	E	F
A	0	50	0	40	25	10
B	50	0	15	20	0	25
C	0	15	0	10	20	0
D	40	20	10	0	10	25
E	25	0	20	10	0	55

load_tickets().info()

<class 'pandas.core.frame.DataFrame'>
Index: 6 entries, A to F
Data columns (total 6 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   A       6 non-null      int64
 1   B       6 non-null      int64
 2   C       6 non-null      int64
 3   D       6 non-null      int64
 4   E       6 non-null      int64
 5   F       6 non-null      int64
dtypes: int64(6)
memory usage: 336.0+ bytes

load_tickets().describe()

	A	B	C	D	E	F
count	6.000000	6.000000	6.000000	6.000000	6.000000	6.000000
mean	20.833333	18.333333	7.500000	17.500000	18.333333	19.166667
std	21.075262	18.618987	8.803408	14.053469	20.655911	20.836666
min	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	2.500000	3.750000	0.000000	10.000000	2.500000	2.500000
50%	17.500000	17.500000	5.000000	15.000000	15.000000	17.500000
75%	36.250000	23.750000	13.750000	23.750000	23.750000	25.000000
max	50.000000	50.000000	20.000000	40.000000	55.000000	55.000000

load_firestation

load_firestation()

	1	2	3	4	5	6	7	8
1	7	12	18	20	24	26	25	28
2	14	5	8	15	16	18	18	18
3	19	9	4	14	10	22	16	13
4	14	15	15	10	18	15	14	18
5	20	18	12	20	9	25	14	12
6	18	21	20	16	20	6	10	15
7	22	18	20	15	16	15	5	9
8	30	22	15	20	14	18	8	6

load_firestation().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 8 entries, 1 to 8
Data columns (total 8 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   1       8 non-null      int32
 1   2       8 non-null      int32
 2   3       8 non-null      int32
 3   4       8 non-null      int32
 4   5       8 non-null      int32
 5   6       8 non-null      int32
 6   7       8 non-null      int32
 7   8       8 non-null      int32
dtypes: int32(8)
memory usage: 388.0 bytes

load_firestation().describe()

	1	2	3	4	5	6	7	8
count	8.000000	8.00000	8.000000	8.000000	8.00000	8.000000	8.000000	8.000000
mean	18.000000	15.00000	14.000000	16.250000	15.87500	18.125000	13.750000	14.875000
std	6.740072	5.95219	5.732115	3.575712	4.96955	6.446206	6.250714	6.728139
min	7.000000	5.00000	4.000000	10.000000	9.00000	6.000000	5.000000	6.000000
25%	14.000000	11.25000	11.000000	14.750000	13.00000	15.000000	9.500000	11.250000
50%	18.500000	16.50000	15.000000	15.500000	16.00000	18.000000	14.000000	14.000000
75%	20.500000	18.75000	18.500000	20.000000	18.50000	22.750000	16.500000	18.000000
max	30.000000	22.00000	20.000000	20.000000	24.00000	26.000000	25.000000	28.000000

load_carrier

load_carrier()

	length(cm)	weight(kg)	number
C1	48.7	2000.0	8.0
C2	52.0	3000.0	7.0
C3	61.3	1000.0	9.0
C4	72.0	500.0	6.0
C5	48.7	4000.0	6.0
C6	52.0	2000.0	4.0
C7	64.0	1000.0	8.0

load_carrier().info()

<class 'pandas.core.frame.DataFrame'>
Index: 7 entries, C1 to C7
Data columns (total 3 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   length(cm)  7 non-null      float64
 1   weight(kg)  7 non-null      float64
 2   number      7 non-null      float64
dtypes: float64(3)
memory usage: 224.0+ bytes

load_carrier().describe()

	length(cm)	weight(kg)	number
count	7.000000	7.000000	7.000000
mean	56.957143	1928.571429	6.857143
std	8.946667	1239.239398	1.676163
min	48.700000	500.000000	4.000000
25%	50.350000	1000.000000	6.000000
50%	52.000000	2000.000000	7.000000
75%	62.650000	2500.000000	8.000000
max	72.000000	4000.000000	9.000000

load_pipeline

load_pipline().head()

	1	2	3	4	5	6	7	8	9	10
1	0	5	6	0	0	0	0	0	9	0
2	5	0	1	2	12	0	5	0	0	2
3	6	1	0	6	0	7	0	0	0	0
4	0	2	6	0	8	0	4	0	0	3
5	0	12	0	8	0	0	0	1	0	0

load_pipline().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 10 entries, 1 to 10
Data columns (total 10 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   1       10 non-null     int32
 1   2       10 non-null     int32
 2   3       10 non-null     int32
 3   4       10 non-null     int32
 4   5       10 non-null     int32
 5   6       10 non-null     int32
 6   7       10 non-null     int32
 7   8       10 non-null     int32
 8   9       10 non-null     int32
 9   10      10 non-null     int32
dtypes: int32(10)
memory usage: 532.0 bytes

load_petroleum

load_petroleum().head()

	a	b	c	d	e	f	g	h	i	j
a	0	6	8	3	0	3	0	0	0	0
b	0	0	0	0	0	0	0	7	10	5
c	0	0	0	4	0	4	0	0	3	0
d	0	0	0	0	3	0	6	4	0	0
e	0	7	0	0	0	0	0	0	3	4

load_petroleum().info()

<class 'pandas.core.frame.DataFrame'>
Index: 10 entries, a to j
Data columns (total 10 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   a       10 non-null     int32
 1   b       10 non-null     int32
 2   c       10 non-null     int32
 3   d       10 non-null     int32
 4   e       10 non-null     int32
 5   f       10 non-null     int32
 6   g       10 non-null     int32
 7   h       10 non-null     int32
 8   i       10 non-null     int32
 9   j       10 non-null     int32
dtypes: int32(10)
memory usage: 480.0+ bytes

load_petroleum().describe()

	a	b	c	d	e	f	g	h	i	j
count	10.0	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.00000	10.00000	10.000000
mean	0.0	1.300000	0.800000	0.700000	1.000000	0.700000	0.700000	1.50000	1.90000	1.300000
std	0.0	2.750757	2.529822	1.494434	2.309401	1.494434	1.888562	2.54951	3.17805	1.946507
min	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.00000	0.000000
25%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.00000	0.000000
50%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.00000	0.00000	0.000000
75%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3.00000	3.00000	2.500000
max	0.0	7.000000	8.000000	4.000000	7.000000	4.000000	6.000000	7.00000	10.00000	5.000000

load_petroleum_weights

load_petroleum_weights().head()

	a	b	c	d	e	f	g	h	i	j
a	0	3	5	7	0	1	0	0	0	0
b	0	0	0	0	0	0	0	9	6	2
c	0	0	0	3	0	2	0	0	1	0
d	0	0	0	0	3	0	6	4	0	0
e	0	1	0	0	0	0	0	0	4	6

load_petroleum_weights().info()

<class 'pandas.core.frame.DataFrame'>
Index: 10 entries, a to j
Data columns (total 10 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   a       10 non-null     int32
 1   b       10 non-null     int32
 2   c       10 non-null     int32
 3   d       10 non-null     int32
 4   e       10 non-null     int32
 5   f       10 non-null     int32
 6   g       10 non-null     int32
 7   h       10 non-null     int32
 8   i       10 non-null     int32
 9   j       10 non-null     int32
dtypes: int32(10)
memory usage: 480.0+ bytes

load_petroleum_weights().describe()

	a	b	c	d	e	f	g	h	i	j
count	10.0	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000	10.000000
mean	0.0	0.400000	0.500000	1.000000	1.000000	0.300000	0.700000	1.700000	1.200000	1.400000
std	0.0	0.966092	1.581139	2.309401	2.309401	0.674949	1.888562	3.056868	2.097618	2.065591
min	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
25%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
50%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000
75%	0.0	0.000000	0.000000	0.000000	0.000000	0.000000	0.000000	3.000000	1.000000	2.750000
max	0.0	3.000000	5.000000	7.000000	7.000000	2.000000	6.000000	9.000000	6.000000	6.000000

load_hospital_efficiency

load_hospital_efficiency().head()

	全职非主治医师	提供的经费(千元)	可提供的住院床位数(千张)	开诊日的药物治疗(千次)	开诊日的非药物治疗(千次)	接受过培训的护士数目	接受过培训的实习医师数目
普通医院	285.20	123.8	106.72	48.14	43.10	253.0	41.0
学校医院	162.30	128.7	64.21	34.62	27.11	148.0	27.0
乡镇医院	275.70	348.5	104.10	36.72	45.98	175.0	23.0
国家医院	210.14	154.1	104.04	33.16	56.46	160.0	84.0

load_hospital_efficiency().info()

<class 'pandas.core.frame.DataFrame'>
Index: 4 entries, 普通医院 to 国家医院
Data columns (total 7 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   全职非主治医师        4 non-null      float64
 1   提供的经费(千元)      4 non-null      float64
 2   可提供的住院床位数(千张)  4 non-null      float64
 3   开诊日的药物治疗(千次)   4 non-null      float64
 4   开诊日的非药物治疗(千次)  4 non-null      float64
 5   接受过培训的护士数目     4 non-null      float64
 6   接受过培训的实习医师数目   4 non-null      float64
dtypes: float64(7)
memory usage: 256.0+ bytes

load_hospital_efficiency().describe()

	全职非主治医师	提供的经费(千元)	可提供的住院床位数(千张)	开诊日的药物治疗(千次)	开诊日的非药物治疗(千次)	接受过培训的护士数目	接受过培训的实习医师数目
count	4.000000	4.000000	4.000000	4.000000	4.000000	4.000000	4.00000
mean	233.335000	188.775000	94.767500	38.160000	43.162500	184.000000	43.75000
std	57.933153	107.308259	20.409948	6.811892	12.144251	47.307505	27.92102
min	162.300000	123.800000	64.210000	33.160000	27.110000	148.000000	23.00000
25%	198.180000	127.475000	94.082500	34.255000	39.102500	157.000000	26.00000
50%	242.920000	141.400000	104.070000	35.670000	44.540000	167.500000	34.00000
75%	278.075000	202.700000	104.755000	39.575000	48.600000	194.500000	51.75000
max	285.200000	348.500000	106.720000	48.140000	56.460000	253.000000	84.00000

load_aircraft_efficiency

load_aircraft_efficiency().head()

	Aircraft	Fuel	Employee	Passenger	Freight
A	109	392	8259	23756	870
B	115	381	9628	24183	1359
C	767	2673	70923	163483	12449
D	90	282	9683	10370	509
E	461	1608	40630	99047	3726

load_aircraft_efficiency().info()

<class 'pandas.core.frame.DataFrame'>
Index: 13 entries, A to M
Data columns (total 5 columns):
 #   Column     Non-Null Count  Dtype
---  ------     --------------  -----
 0   Aircraft   13 non-null     int32
 1   Fuel       13 non-null     int32
 2   Employee   13 non-null     int32
 3   Passenger  13 non-null     int32
 4   Freight    13 non-null     int32
dtypes: int32(5)
memory usage: 364.0+ bytes

load_aircraft_efficiency().describe()

	Aircraft	Fuel	Employee	Passenger	Freight
count	13.000000	13.000000	13.000000	13.000000	13.000000
mean	345.538462	1162.846154	27757.307692	69351.846154	4540.769231
std	244.196511	901.954715	20772.814311	53252.863729	4211.595287
min	81.000000	75.000000	7115.000000	10370.000000	509.000000
25%	109.000000	392.000000	9628.000000	23756.000000	870.000000
50%	423.000000	1217.000000	29124.000000	74106.000000	3726.000000
75%	547.000000	1722.000000	40630.000000	99636.000000	6597.000000
max	767.000000	2673.000000	70923.000000	163483.000000	12449.000000

变化数据集

load_shanghaicases

load_shanghaicases().head()

	新增确诊	新增无症状	无症状者转归	隔离管控确诊	隔离管控无症状
0	1.0	1.0	NaN	NaN	1.0
1	3.0	5.0	NaN	NaN	5.0
2	2.0	14.0	NaN	NaN	14.0
3	3.0	16.0	NaN	NaN	15.0
4	0.0	28.0	NaN	NaN	28.0

load_shanghaicases().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 42 entries, 0 to 41
Data columns (total 5 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   新增确诊     42 non-null     float64
 1   新增无症状    42 non-null     float64
 2   无症状者转归   19 non-null     float64
 3   隔离管控确诊   33 non-null     float64
 4   隔离管控无症状  42 non-null     float64
dtypes: float64(5)
memory usage: 1.8 KB

load_shanghaicases().describe()

	新增确诊	新增无症状	无症状者转归	隔离管控确诊	隔离管控无症状
count	42.000000	42.000000	19.000000	33.000000	42.000000
mean	198.142857	5273.642857	81.789474	70.636364	4981.142857
std	312.025450	7965.607756	124.857509	144.689715	7743.999164
min	0.000000	1.000000	1.000000	0.000000	1.000000
25%	4.000000	76.500000	7.000000	4.000000	61.750000
50%	30.000000	921.000000	20.000000	10.000000	813.500000
75%	319.250000	5952.250000	72.000000	27.000000	5334.250000
max	1015.000000	25173.000000	420.000000	564.000000	24230.000000

load_population

load_population().head()

	年份	人口
0	1790	3.9
1	1800	5.3
2	1810	7.2
3	1820	9.6
4	1830	12.9

load_population().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 22 entries, 0 to 21
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   年份      22 non-null     int64  
 1   人口      22 non-null     float64
dtypes: float64(1), int64(1)
memory usage: 480.0 bytes

load_population().describe()

	年份	人口
count	22.000000	22.000000
mean	1895.000000	94.772727
std	64.935866	87.506768
min	1790.000000	3.900000
25%	1842.500000	18.625000
50%	1895.000000	69.450000
75%	1947.500000	145.950000
max	2000.000000	281.400000

load_yeast

load_yeast().head()

	time	number
0	0	9.6
1	1	18.3
2	2	29.0
3	3	47.2
4	4	71.1

load_yeast().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 19 entries, 0 to 18
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   time    19 non-null     int64  
 1   number  19 non-null     float64
dtypes: float64(1), int64(1)
memory usage: 432.0 bytes

load_yeast().describe()

	time	number
count	19.000000	19.000000
mean	9.000000	372.857895
std	5.627314	264.569158
min	0.000000	9.600000
25%	4.500000	95.100000
50%	9.000000	441.000000
75%	13.500000	635.100000
max	18.000000	661.800000

预测数据集

load_restaurant

load_restaurant().head()

	day	sales
1	1	3023
2	2	3039
3	3	3056
4	4	3138
5	5	3188

load_restaurant().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 37 entries, 1 to 37
Data columns (total 2 columns):
 #   Column  Non-Null Count  Dtype
---  ------  --------------  -----
 0   day     37 non-null     int32
 1   sales   37 non-null     int32
dtypes: int32(2)
memory usage: 428.0 bytes

load_restaurant().describe()

	day	sales
count	37.000000	37.000000
mean	19.000000	3542.486486
std	10.824355	543.918633
min	1.000000	2859.000000
25%	10.000000	3142.000000
50%	19.000000	3421.000000
75%	28.000000	3707.000000
max	37.000000	4817.000000

load_titanic

load_titanic().head()

	PassengerId	Survived	Pclass	Name	Sex	Age	SibSp	Parch	Ticket	Fare	Cabin	Embarked
0	1	0	3.0	Braund, Mr. Owen Harris	male	22.0	1.0	0.0	A/5 21171	7.2500	nan	S
1	2	1	1.0	Cumings, Mrs. John Bradley (Florence Briggs Th...	female	38.0	1.0	0.0	PC 17599	71.2833	C85	C
2	3	1	3.0	Heikkinen, Miss. Laina	female	26.0	0.0	0.0	STON/O2. 3101282	7.9250	nan	S
3	4	1	1.0	Futrelle, Mrs. Jacques Heath (Lily May Peel)	female	35.0	1.0	0.0	113803	53.1000	C123	S
4	5	0	3.0	Allen, Mr. William Henry	male	35.0	0.0	0.0	373450	8.0500	nan	S

load_titanic().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 80 entries, 0 to 79
Data columns (total 12 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   PassengerId  80 non-null     int32  
 1   Survived     80 non-null     int32  
 2   Pclass       80 non-null     float64
 3   Name         80 non-null     object 
 4   Sex          80 non-null     object 
 5   Age          61 non-null     float64
 6   SibSp        80 non-null     float64
 7   Parch        80 non-null     float64
 8   Ticket       80 non-null     object 
 9   Fare         80 non-null     float64
 10  Cabin        80 non-null     object 
 11  Embarked     80 non-null     object 
dtypes: float64(5), int32(2), object(5)
memory usage: 7.0+ KB

load_titanic().describe()

	PassengerId	Survived	Pclass	Age	SibSp	Parch	Fare
count	80.0000	80.000000	80.00000	61.000000	80.000000	80.000000	80.000000
mean	40.5000	0.425000	2.41250	26.366066	0.787500	0.437500	28.482291
std	23.2379	0.497462	0.80652	15.365874	1.229323	0.991658	36.336522
min	1.0000	0.000000	1.00000	0.830000	0.000000	0.000000	7.225000
25%	20.7500	0.000000	2.00000	17.000000	0.000000	0.000000	8.050000
50%	40.5000	0.000000	3.00000	26.000000	0.000000	0.000000	15.750000
75%	60.2500	1.000000	3.00000	35.000000	1.000000	0.000000	31.303125
max	80.0000	1.000000	3.00000	66.000000	5.000000	5.000000	263.000000

load_golf

load_golf().head()

	Outlook	Temperature	Humidity	Windy	Play Golf
0	Rainy	Hot	High	False	No
1	Rainy	Hot	High	True	No
2	Overcast	Hot	High	False	Yes
3	Sunny	Mild	High	False	Yes
4	Sunny	Cool	Normal	False	Yes

load_golf().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 14 entries, 0 to 13
Data columns (total 5 columns):
 #   Column       Non-Null Count  Dtype 
---  ------       --------------  ----- 
 0   Outlook      14 non-null     object
 1   Temperature  14 non-null     object
 2   Humidity     14 non-null     object
 3   Windy        14 non-null     object
 4   Play Golf    14 non-null     object
dtypes: object(5)
memory usage: 688.0+ bytes

load_golf().describe()

	Outlook	Temperature	Humidity	Windy	Play Golf
count	14	14	14	14	14
unique	3	3	2	2	2
top	Rainy	Mild	High	False	Yes
freq	5	6	7	8	9

load_oil_field

load_oil_field().head()

	时间	月产油量/万吨	月产水量/万吨	月注水量/万吨	地层压力/MPa
0	94.02	7.123	0.796	13.108	27.475
1	94.03	7.994	0.832	12.334	27.473
2	94.04	8.272	0.917	12.216	27.490
3	94.05	7.960	0.976	12.201	27.500
4	94.06	7.147	1.075	12.132	27.510

load_oil_field().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 13 entries, 0 to 12
Data columns (total 5 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   时间        13 non-null     float64
 1   月产油量/万吨   13 non-null     float64
 2   月产水量/万吨   13 non-null     float64
 3   月注水量/万吨   13 non-null     float64
 4   地层压力/MPa  13 non-null     float64
dtypes: float64(5)
memory usage: 648.0 bytes

load_oil_field().describe()

	时间	月产油量/万吨	月产水量/万吨	月注水量/万吨	地层压力/MPa
count	13.000000	13.000000	13.000000	13.000000	13.00000
mean	94.080000	6.780154	1.220538	11.659462	27.54300
std	0.038944	0.946614	0.283479	1.062462	0.05158
min	94.020000	5.197000	0.796000	9.176000	27.47300
25%	94.050000	6.254000	0.976000	11.143000	27.50000
50%	94.080000	6.858000	1.281000	11.990000	27.54200
75%	94.110000	7.147000	1.432000	12.216000	27.58400
max	94.140000	8.272000	1.611000	13.108000	27.63000

load_passagers_flow

load_passagers_flow().head()

	人口数量/万人	机动车数量/万辆	公路面积/万平方千米	客运量/万人	货运量/万吨
年份
1990	20.55	0.60	0.09	5126.0	1237.0
1991	22.44	0.75	0.11	6217.0	1379.0
1992	25.37	0.85	0.11	7730.0	1385.0
1993	27.13	0.90	0.14	9145.0	1399.0
1994	29.45	1.05	0.20	10460.0	1663.0

load_passagers_flow().info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 20 entries, 1990 to 2009
Data columns (total 5 columns):
 #   Column      Non-Null Count  Dtype  
---  ------      --------------  -----  
 0   人口数量/万人     20 non-null     float64
 1   机动车数量/万辆    20 non-null     float64
 2   公路面积/万平方千米  20 non-null     float64
 3   客运量/万人      20 non-null     float64
 4   货运量/万吨      20 non-null     float64
dtypes: float64(5)
memory usage: 960.0 bytes

load_passagers_flow().describe()

	人口数量/万人	机动车数量/万辆	公路面积/万平方千米	客运量/万人	货运量/万吨
count	20.000000	20.000000	20.000000	20.000000	20.000000
mean	39.634500	1.887500	0.378500	21108.750000	9401.400000
std	12.508626	0.790881	0.212188	12346.831479	7402.108899
min	20.550000	0.600000	0.090000	5126.000000	1237.000000
25%	29.937500	1.275000	0.222500	11155.250000	1701.250000
50%	38.610000	2.000000	0.350000	19663.000000	9730.000000
75%	48.697500	2.525000	0.567500	27190.750000	14180.500000
max	60.630000	3.100000	0.790000	43462.000000	21804.000000

统计模型

load_adult

load_adult().head()

	sex	age	educ	hours	income_more_50K
0	Male	39	13	40	0
1	Male	50	13	13	0
2	Male	38	9	40	0
3	Male	53	7	40	0
4	Female	28	13	40	0

load_adult().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100 entries, 0 to 99
Data columns (total 5 columns):
 #   Column           Non-Null Count  Dtype 
---  ------           --------------  ----- 
 0   sex              100 non-null    object
 1   age              100 non-null    int32 
 2   educ             100 non-null    int32 
 3   hours            100 non-null    int32 
 4   income_more_50K  100 non-null    int32 
dtypes: int32(4), object(1)
memory usage: 2.5+ KB

load_adult().describe()

	age	educ	hours	income_more_50K
count	100.000000	100.000000	100.000000	100.000000
mean	38.390000	10.220000	41.250000	0.250000
std	12.198605	2.787345	11.539458	0.435194
min	18.000000	3.000000	2.000000	0.000000
25%	29.750000	9.000000	40.000000	0.000000
50%	37.500000	10.000000	40.000000	0.000000
75%	48.000000	13.000000	45.000000	0.250000
max	79.000000	16.000000	80.000000	1.000000

load_cement

load_cement().head()

	x1	x2	y
0	7.0	26.0	78.5
1	1.0	29.0	74.3
2	11.0	56.0	104.3
3	11.0	31.0	87.6
4	7.0	52.0	95.9

load_cement().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 13 entries, 0 to 12
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   x1      13 non-null     float64
 1   x2      13 non-null     float64
 2   y       13 non-null     float64
dtypes: float64(3)
memory usage: 440.0 bytes

load_cement().describe()

	x1	x2	y
count	13.000000	13.000000	13.000000
mean	7.461538	48.153846	95.423077
std	5.882394	15.560881	15.043723
min	1.000000	26.000000	72.500000
25%	2.000000	31.000000	83.800000
50%	7.000000	52.000000	95.900000
75%	11.000000	56.000000	109.200000
max	21.000000	71.000000	115.900000

load_economics

load_economics().head()

	国内总产值	存储量	消费量	进口总额
0	149.3	4.2	108.1	15.9
1	171.5	4.1	114.8	16.4
2	175.5	3.1	123.2	19.0
3	180.8	3.1	126.9	19.1
4	190.7	1.1	132.1	18.8

load_economics().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 11 entries, 0 to 10
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   国内总产值   11 non-null     float64
 1   存储量     11 non-null     float64
 2   消费量     11 non-null     float64
 3   进口总额    11 non-null     float64
dtypes: float64(4)
memory usage: 480.0 bytes

load_economics().describe()

	国内总产值	存储量	消费量	进口总额
count	11.000000	11.000000	11.000000	11.000000
mean	198.309091	3.300000	139.736364	21.890909
std	27.908904	1.649242	20.634402	4.543667
min	149.300000	0.700000	108.100000	15.900000
25%	178.150000	2.150000	125.050000	18.900000
50%	202.100000	3.100000	137.700000	20.400000
75%	219.250000	4.600000	158.200000	26.400000
max	239.000000	5.600000	167.600000	28.100000

load_car

load_car()

	城镇居民家庭人均可支配收入/元	全国城镇人口/亿人	全国汽车产量/万量	全国公路长度/万公里	中国私人轿车拥有量/万辆
1994	3496.2	3.43	136.69	111.78	205.42
1995	4283.0	3.52	145.27	115.70	249.96
1996	4838.9	3.73	147.52	118.58	289.67
1997	5160.3	3.94	158.25	122.64	358.36
1998	5425.1	4.16	163.00	127.85	423.65
1999	5854.0	4.37	183.20	135.17	533.88
2000	6280.0	4.59	207.00	140.27	625.33
2001	6859.6	4.81	234.17	169.80	770.78
2002	7702.8	5.02	325.10	176.52	968.98

load_car().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9 entries, 1994 to 2002
Data columns (total 5 columns):
 #   Column           Non-Null Count  Dtype  
---  ------           --------------  -----  
 0   城镇居民家庭人均可支配收入/元  9 non-null      float64
 1   全国城镇人口/亿人        9 non-null      float64
 2    全国汽车产量/万量       9 non-null      float64
 3   全国公路长度/万公里       9 non-null      float64
 4   中国私人轿车拥有量/万辆     9 non-null      float64
dtypes: float64(5)
memory usage: 492.0 bytes

load_car().describe()

	城镇居民家庭人均可支配收入/元	全国城镇人口/亿人	全国汽车产量/万量	全国公路长度/万公里	中国私人轿车拥有量/万辆
count	9.000000	9.000000	9.000000	9.000000	9.000000
mean	5544.433333	4.174444	188.911111	135.367778	491.781111
std	1297.649310	0.566240	60.116460	23.309606	257.132957
min	3496.200000	3.430000	136.690000	111.780000	205.420000
25%	4838.900000	3.730000	147.520000	118.580000	289.670000
50%	5425.100000	4.160000	163.000000	127.850000	423.650000
75%	6280.000000	4.590000	207.000000	140.270000	625.330000
max	7702.800000	5.020000	325.100000	176.520000	968.980000

load_house

load_house()

	家庭年收入/万元	签订意向书人数/人	实际购房人数/人
0	1.5	25.0	8.0
1	2.5	32.0	13.0
2	3.5	58.0	26.0
3	4.5	52.0	22.0
4	5.5	43.0	20.0
5	6.5	39.0	22.0
6	7.5	28.0	16.0
7	8.5	21.0	12.0
8	9.5	15.0	10.0

load_house().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 9 entries, 0 to 8
Data columns (total 3 columns):
 #   Column     Non-Null Count  Dtype  
---  ------     --------------  -----  
 0   家庭年收入/万元   9 non-null      float64
 1   签订意向书人数/人  9 non-null      float64
 2   实际购房人数/人   9 non-null      float64
dtypes: float64(3)
memory usage: 344.0 bytes

load_house().describe()

	家庭年收入/万元	签订意向书人数/人	实际购房人数/人
count	9.000000	9.000000	9.000000
mean	5.500000	34.777778	16.555556
std	2.738613	14.368175	6.227181
min	1.500000	15.000000	8.000000
25%	3.500000	25.000000	12.000000
50%	5.500000	32.000000	16.000000
75%	7.500000	43.000000	22.000000
max	9.500000	58.000000	26.000000

load_loan

load_loan()

	指标1	指标2	指标3	是否贷款
0	-62.3	-89.5	1.7	0.0
1	3.3	-3.5	1.1	0.0
2	-120.8	-103.2	2.5	0.0
3	-18.1	-28.8	1.1	0.0
4	-3.8	-50.6	0.9	0.0
5	-61.2	-56.2	1.7	0.0
6	-20.3	-17.4	1.0	0.0
7	-194.5	-25.8	0.5	0.0
8	20.8	-4.3	1.0	0.0
9	-106.1	-22.9	1.5	0.0
10	43.0	16.4	1.3	1.0
11	47.0	16.0	1.9	1.0
12	-3.3	4.0	2.7	1.0
13	35.0	20.8	1.9	1.0
14	46.7	12.6	0.9	1.0
15	20.8	12.5	2.4	1.0
16	33.0	23.6	1.5	1.0
17	26.1	10.4	2.1	1.0
18	68.6	13.8	1.6	1.0
19	37.3	33.4	3.5	1.0

load_loan().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20 entries, 0 to 19
Data columns (total 4 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   指标1     20 non-null     float64
 1   指标2     20 non-null     float64
 2   指标3     20 non-null     float64
 3   是否贷款    20 non-null     float64
dtypes: float64(4)
memory usage: 768.0 bytes

load_loan().describe()

	指标1	指标2	指标3	是否贷款
count	20.000000	20.000000	20.000000	20.000000
mean	-10.440000	-11.935000	1.640000	0.500000
std	67.316811	37.796634	0.732982	0.512989
min	-194.500000	-103.200000	0.500000	0.000000
25%	-30.525000	-26.550000	1.075000	0.000000
50%	12.050000	0.250000	1.550000	0.500000
75%	35.575000	14.350000	1.950000	1.000000
max	68.600000	33.400000	3.500000	1.000000

load_height_weight

load_height_weight()

	height/cm	weight/kg
0	172	75
1	169	55
2	169	64
3	171	65
4	167	47
...	...	...
95	177	64
96	184	70
97	166	49
98	171	71
99	170	59

100 rows × 2 columns

load_height_weight().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 100 entries, 0 to 99
Data columns (total 2 columns):
 #   Column     Non-Null Count  Dtype
---  ------     --------------  -----
 0   height/cm  100 non-null    int32
 1   weight/kg  100 non-null    int32
dtypes: int32(2)
memory usage: 928.0 bytes

load_height_weight().describe()

	height/cm	weight/kg
count	100.000000	100.000000
mean	170.250000	61.270000
std	5.401786	6.892911
min	155.000000	47.000000
25%	167.000000	57.000000
50%	170.000000	62.000000
75%	173.000000	65.250000
max	186.000000	77.000000

概率模型

load_activity

load_activity()

	Sleep	Icecream	Run
Sleep	0.2	0.6	0.2
Icecream	0.1	0.6	0.3
Run	0.2	0.7	0.1

load_activity().info()

<class 'pandas.core.frame.DataFrame'>
Index: 3 entries, Sleep to Run
Data columns (total 3 columns):
 #   Column    Non-Null Count  Dtype  
---  ------    --------------  -----  
 0   Sleep     3 non-null      float64
 1   Icecream  3 non-null      float64
 2   Run       3 non-null      float64
dtypes: float64(3)
memory usage: 96.0+ bytes

load_activity().describe()

	Sleep	Icecream	Run
count	3.000000	3.000000	3.00
mean	0.166667	0.633333	0.20
std	0.057735	0.057735	0.10
min	0.100000	0.600000	0.10
25%	0.150000	0.600000	0.15
50%	0.200000	0.600000	0.20
75%	0.200000	0.650000	0.25
max	0.200000	0.700000	0.30

load_party

load_party()

	工党	保守党	自由党
工党	0.5	0.4	0.1
保守党	0.7	0.2	0.1
自由党	0.2	0.4	0.4

load_party().info()

<class 'pandas.core.frame.DataFrame'>
Index: 3 entries, 工党 to 自由党
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   工党      3 non-null      float64
 1   保守党     3 non-null      float64
 2   自由党     3 non-null      float64
dtypes: float64(3)
memory usage: 96.0+ bytes

load_party().describe()

	工党	保守党	自由党
count	3.000000	3.000000	3.000000
mean	0.466667	0.333333	0.200000
std	0.251661	0.115470	0.173205
min	0.200000	0.200000	0.100000
25%	0.350000	0.300000	0.100000
50%	0.500000	0.400000	0.100000
75%	0.600000	0.400000	0.250000
max	0.700000	0.400000	0.400000

load_education

load_education()

	Junior school	High school	College
Junior school	0.7	0.2	0.1
High school	0.4	0.4	0.2
College	0.1	0.2	0.7

load_education().info()

<class 'pandas.core.frame.DataFrame'>
Index: 3 entries, Junior school to College
Data columns (total 3 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Junior school  3 non-null      float64
 1   High school    3 non-null      float64
 2   College        3 non-null      float64
dtypes: float64(3)
memory usage: 96.0+ bytes

load_education().describe()

	Junior school	High school	College
count	3.00	3.000000	3.000000
mean	0.40	0.266667	0.333333
std	0.30	0.115470	0.321455
min	0.10	0.200000	0.100000
25%	0.25	0.200000	0.150000
50%	0.40	0.200000	0.200000
75%	0.55	0.300000	0.450000
max	0.70	0.400000	0.700000

其他数据集

load_ted

load_ted().head()

	comments	duration	event	languages	main_speaker	name	num_speaker	published_date	speaker_occupation	tags	title	views
0	4553	1164	TED2006	60	Ken Robinson	Ken Robinson: Do schools kill creativity?	1	1151367060	Author/educator	['children', 'creativity', 'culture', 'dance',...	Do schools kill creativity?	47227110
1	265	977	TED2006	43	Al Gore	Al Gore: Averting the climate crisis	1	1151367060	Climate advocate	['alternative energy', 'cars', 'climate change...	Averting the climate crisis	3200520
2	124	1286	TED2006	26	David Pogue	David Pogue: Simplicity sells	1	1151367060	Technology columnist	['computers', 'entertainment', 'interface desi...	Simplicity sells	1636292
3	200	1116	TED2006	35	Majora Carter	Majora Carter: Greening the ghetto	1	1151367060	Activist for environmental justice	['MacArthur grant', 'activism', 'business', 'c...	Greening the ghetto	1697550
4	593	1190	TED2006	48	Hans Rosling	Hans Rosling: The best stats you've ever seen	1	1151440680	Global health expert; data visionary	['Africa', 'Asia', 'Google', 'demo', 'economic...	The best stats you've ever seen	12005869

load_ted().info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 243 entries, 0 to 242
Data columns (total 12 columns):
 #   Column              Non-Null Count  Dtype 
---  ------              --------------  ----- 
 0   comments            243 non-null    int32 
 1   duration            243 non-null    int32 
 2   event               243 non-null    object
 3   languages           243 non-null    object
 4   main_speaker        243 non-null    object
 5   name                243 non-null    object
 6   num_speaker         243 non-null    object
 7   published_date      243 non-null    object
 8   speaker_occupation  243 non-null    object
 9   tags                243 non-null    object
 10  title               243 non-null    object
 11  views               243 non-null    int32 
dtypes: int32(3), object(9)
memory usage: 20.1+ KB

load_ted().describe()

	comments	duration	views
count	243.000000	243.000000	2.430000e+02
mean	233.115226	999.345679	2.097025e+06
std	547.555412	422.429382	4.000388e+06
min	9.000000	135.000000	8.248800e+04
25%	60.000000	845.500000	6.721835e+05
50%	108.000000	1056.000000	1.044185e+06
75%	230.500000	1212.000000	1.833844e+06
max	6404.000000	2678.000000	4.722711e+07