pandas常用操作以及eda分析笔记（自用）

pandas学习笔记

以sklearn自带的boston数据集转为dataframe为例（这样就不用总是换示例数据了🤔），记录一下常用的pandas操作，包括查找、删减、列数据操作、eda绘图等等。

import pandas as pd
import numpy as np
from  sklearn.datasets import load_boston

from sklearn import datasets
import pandas as pd 
dataset = datasets.load_boston()
print("数据集包含的信息项：")
print("  ".join(dataset.keys()))
# print("数据集描述信息：")


#转为df文件
data = dataset["data"]
target = dataset["target"]
df = pd.DataFrame(data, columns=dataset["feature_names"])
df["target"] = target

数据集包含的信息项：
data  target  feature_names  DESCR  filename

df.info()  #数据表基本信息（维度、列名称、数据格式、所占空间等）

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 506 entries, 0 to 505
Data columns (total 14 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   CRIM     506 non-null    float64
 1   ZN       506 non-null    float64
 2   INDUS    506 non-null    float64
 3   CHAS     506 non-null    float64
 4   NOX      506 non-null    float64
 5   RM       506 non-null    float64
 6   AGE      506 non-null    float64
 7   DIS      506 non-null    float64
 8   RAD      506 non-null    float64
 9   TAX      506 non-null    float64
 10  PTRATIO  506 non-null    float64
 11  B        506 non-null    float64
 12  LSTAT    506 non-null    float64
 13  target   506 non-null    float64
dtypes: float64(14)
memory usage: 55.5 KB

df.describe()   #各个字段的描述

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
count	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000	506.000000
mean	3.613524	11.363636	11.136779	0.069170	0.554695	6.284634	68.574901	3.795043	9.549407	408.237154	18.455534	356.674032	12.653063	22.532806
std	8.601545	23.322453	6.860353	0.253994	0.115878	0.702617	28.148861	2.105710	8.707259	168.537116	2.164946	91.294864	7.141062	9.197104
min	0.006320	0.000000	0.460000	0.000000	0.385000	3.561000	2.900000	1.129600	1.000000	187.000000	12.600000	0.320000	1.730000	5.000000
25%	0.082045	0.000000	5.190000	0.000000	0.449000	5.885500	45.025000	2.100175	4.000000	279.000000	17.400000	375.377500	6.950000	17.025000
50%	0.256510	0.000000	9.690000	0.000000	0.538000	6.208500	77.500000	3.207450	5.000000	330.000000	19.050000	391.440000	11.360000	21.200000
75%	3.677083	12.500000	18.100000	0.000000	0.624000	6.623500	94.075000	5.188425	24.000000	666.000000	20.200000	396.225000	16.955000	25.000000
max	88.976200	100.000000	27.740000	1.000000	0.871000	8.780000	100.000000	12.126500	24.000000	711.000000	22.000000	396.900000	37.970000	50.000000

df.sample(3) #随机抽样

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
500	0.22438	0.0	9.69	0.0	0.585	6.027	79.7	2.4982	6.0	391.0	19.2	396.90	14.33	16.8
159	1.42502	0.0	19.58	0.0	0.871	6.510	100.0	1.7659	5.0	403.0	14.7	364.31	7.39	23.3
243	0.12757	30.0	4.93	0.0	0.428	6.393	7.8	7.0355	6.0	300.0	16.6	374.71	5.19	23.7

df.tail(3)  #最后n个样本

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

df.head(3)   #最前N个样本

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7

1.定位到行、列

1.1直接索引

df[3:4]  #将数字切片放入一个中括号，输出这一行的所有列。
#错误示范：
#df[3] 

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4

df['B']  #将列名字符串放入一个中括号，输出这一列的所有行

0      396.90
1      396.90
2      392.83
3      394.63
4      396.90
        ...  
501    391.99
502    396.90
503    396.90
504    393.45
505    396.90
Name: B, Length: 506, dtype: float64

df[2:5][["B","ZN"]] #两个中括号分别表示行和列的索引范围，要输出多个列的时候用中括号括起来

	B	ZN
2	392.83	0.0
3	394.63	0.0
4	396.90	0.0

经过上述例子，上面一种索引方式有很多达不到的功能，比如要输出4到8列就要把这几列的字段名输入进去，比较麻烦；要输出不连续的行列也没法实现。这时候就有了功能更完善的loc和iloc

1.2 用loc和iloc，其中loc是用字段定位，iloc是用数字索引定位

注意两个函数都是用一个中括号，而不是圆括号or两个中括号，行和列的区别是逗号

#多个列按列名定位
df.loc[2:5,['CRIM','ZN','INDUS']]

	CRIM	ZN	INDUS
2	0.02729	0.0	7.07
3	0.03237	0.0	2.18
4	0.06905	0.0	2.18
5	0.02985	0.0	2.18

#多个列按列索引定位
df.iloc[2:5,:3]

	CRIM	ZN	INDUS
2	0.02729	0.0	7.07
3	0.03237	0.0	2.18
4	0.06905	0.0	2.18

# 注：指定某一行列返回的是一个具体的值如(df.iloc[1,2])，如果用到了切片返回的是一个series(如df.iloc[:,2])
#返回特定行列位置的值而非pd切片
print('示例一：df.iloc[3,4]。返回的为该位置的值')
print(df.iloc[3,4])  #返回的是该位置的值
print(type(df.iloc[3,4]))


print('示例二：df.iloc[3:5,4]。返回的是一个series')
print(df.iloc[3:5,4])  #返回的是该位置的值
print(type(df.iloc[3:5,4]))
#注：和df直接用两个中括号索引不同，如果是df[3][4]会报错

示例一：df.iloc[3,4]。返回的为该位置的值
0.458
<class 'numpy.float64'>
示例二：df.iloc[3:5,4]。返回的是一个series
3    0.458
4    0.458
Name: NOX, dtype: float64
<class 'pandas.core.series.Series'>

#目标行/列不连续,用[]选出目标行/列
df.iloc[[4,5,6,7,8,10],[1,3,5]]  

	ZN	CHAS	RM
4	0.0	0.0	7.147
5	0.0	0.0	6.430
6	12.5	0.0	6.012
7	12.5	0.0	6.172
8	12.5	0.0	5.631
10	12.5	0.0	6.377

1.3 按多个条件选择列

#按多个条件选择列，多个条件之间用&并起来
df.loc[(df['target']<10) & (df['target']>5)]

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
384	20.08490	0.0	18.10	0.0	0.700	4.368	91.2	1.4395	24.0	666.0	20.2	285.83	30.63	8.8
385	16.81180	0.0	18.10	0.0	0.700	5.277	98.1	1.4261	24.0	666.0	20.2	396.90	30.81	7.2
387	22.59710	0.0	18.10	0.0	0.700	5.000	89.5	1.5184	24.0	666.0	20.2	396.90	31.99	7.4
392	11.57790	0.0	18.10	0.0	0.700	5.036	97.0	1.7700	24.0	666.0	20.2	396.90	25.68	9.7
397	7.67202	0.0	18.10	0.0	0.693	5.747	98.9	1.6334	24.0	666.0	20.2	393.10	19.92	8.5
399	9.91655	0.0	18.10	0.0	0.693	5.852	77.8	1.5004	24.0	666.0	20.2	338.16	29.97	6.3
400	25.04610	0.0	18.10	0.0	0.693	5.987	100.0	1.5888	24.0	666.0	20.2	396.90	26.77	5.6
401	14.23620	0.0	18.10	0.0	0.693	6.343	100.0	1.5741	24.0	666.0	20.2	396.90	20.32	7.2
403	24.80170	0.0	18.10	0.0	0.693	5.349	96.0	1.7028	24.0	666.0	20.2	396.90	19.77	8.3
404	41.52920	0.0	18.10	0.0	0.693	5.531	85.4	1.6074	24.0	666.0	20.2	329.46	27.38	8.5
414	45.74610	0.0	18.10	0.0	0.693	4.519	100.0	1.6582	24.0	666.0	20.2	88.27	36.98	7.0
415	18.08460	0.0	18.10	0.0	0.679	6.434	100.0	1.8347	24.0	666.0	20.2	27.25	29.05	7.2
416	10.83420	0.0	18.10	0.0	0.679	6.782	90.8	1.8195	24.0	666.0	20.2	21.57	25.79	7.5
418	73.53410	0.0	18.10	0.0	0.679	5.957	100.0	1.8026	24.0	666.0	20.2	16.45	20.62	8.8
419	11.81230	0.0	18.10	0.0	0.718	6.824	76.5	1.7940	24.0	666.0	20.2	48.45	22.74	8.4
425	15.86030	0.0	18.10	0.0	0.679	5.896	95.4	1.9096	24.0	666.0	20.2	7.68	24.39	8.3
429	9.33889	0.0	18.10	0.0	0.679	6.380	95.6	1.9682	24.0	666.0	20.2	60.72	24.08	9.5
436	14.42080	0.0	18.10	0.0	0.740	6.461	93.3	2.0026	24.0	666.0	20.2	27.49	18.05	9.6
437	15.17720	0.0	18.10	0.0	0.740	6.152	100.0	1.9142	24.0	666.0	20.2	9.32	26.45	8.7
438	13.67810	0.0	18.10	0.0	0.740	5.935	87.9	1.8206	24.0	666.0	20.2	68.95	34.02	8.4
489	0.18337	0.0	27.74	0.0	0.609	5.414	98.3	1.7554	4.0	711.0	20.1	344.05	23.97	7.0
490	0.20746	0.0	27.74	0.0	0.609	5.093	98.0	1.8226	4.0	711.0	20.1	318.43	29.68	8.1

#or
df.loc[(df['target']<10) | (df['target']>5)]

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0.0	0.458	7.147	54.2	6.0622	3.0	222.0	18.7	396.90	5.33	36.2
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
501	0.06263	0.0	11.93	0.0	0.573	6.593	69.1	2.4786	1.0	273.0	21.0	391.99	9.67	22.4
502	0.04527	0.0	11.93	0.0	0.573	6.120	76.7	2.2875	1.0	273.0	21.0	396.90	9.08	20.6
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

506 rows × 14 columns

空值处理：展示与填充

#每一列0值个数
df.isna().sum()

CRIM       0
ZN         0
INDUS      0
CHAS       0
NOX        0
RM         0
AGE        0
DIS        0
RAD        0
TAX        0
PTRATIO    0
B          0
LSTAT      0
target     0
dtype: int64

#用0填充
df.fillna(0)

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0.0	0.458	7.147	54.2	6.0622	3.0	222.0	18.7	396.90	5.33	36.2
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
501	0.06263	0.0	11.93	0.0	0.573	6.593	69.1	2.4786	1.0	273.0	21.0	391.99	9.67	22.4
502	0.04527	0.0	11.93	0.0	0.573	6.120	76.7	2.2875	1.0	273.0	21.0	396.90	9.08	20.6
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

506 rows × 14 columns

##或者只需要填补特定列的空值
df.loc[:,"B"].fillna(0)

0      396.90
1      396.90
2      392.83
3      394.63
4      396.90
        ...  
501    391.99
502    396.90
503    396.90
504    393.45
505    396.90
Name: B, Length: 506, dtype: float64

获取行列属性

#方法1：
print(df.columns.values) #输出列的值
#print(df.index.values) #输出行的值

['CRIM' 'ZN' 'INDUS' 'CHAS' 'NOX' 'RM' 'AGE' 'DIS' 'RAD' 'TAX' 'PTRATIO'
 'B' 'LSTAT' 'target']

#方法2：
list(df)

['CRIM',
 'ZN',
 'INDUS',
 'CHAS',
 'NOX',
 'RM',
 'AGE',
 'DIS',
 'RAD',
 'TAX',
 'PTRATIO',
 'B',
 'LSTAT',
 'target']

df.columns[0]  #返回的是对应列的名称

'CRIM'

print(df.shape[0]) #输出行的个数
print(df.shape[1])#输出列的个数

506
14

新增与删除

注：用于删除的drop函数并不会直接替代原来的df文件，要替换的话可以重新赋值或者将inplace改成true
删除都要用axis选定轴

df["测试列"] = 0 #新增一列直接赋值就行，默认加在最后一列
df

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target	测试列
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0	0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6	0
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7	0
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4	0
4	0.06905	0.0	2.18	0.0	0.458	7.147	54.2	6.0622	3.0	222.0	18.7	396.90	5.33	36.2	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
501	0.06263	0.0	11.93	0.0	0.573	6.593	69.1	2.4786	1.0	273.0	21.0	391.99	9.67	22.4	0
502	0.04527	0.0	11.93	0.0	0.573	6.120	76.7	2.2875	1.0	273.0	21.0	396.90	9.08	20.6	0
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9	0
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0	0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9	0

506 rows × 15 columns

##方法1：用列名来删除
df.drop(["测试列"],axis = 1,inplace=True)  #axis=1是删除列，axis参数为0是行，为1是列
df

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	18.0	2.31	0.0	0.538	6.575	65.2	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	0.0	7.07	0.0	0.469	6.421	78.9	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	0.0	7.07	0.0	0.469	7.185	61.1	4.9671	2.0	242.0	17.8	392.83	4.03	34.7
3	0.03237	0.0	2.18	0.0	0.458	6.998	45.8	6.0622	3.0	222.0	18.7	394.63	2.94	33.4
4	0.06905	0.0	2.18	0.0	0.458	7.147	54.2	6.0622	3.0	222.0	18.7	396.90	5.33	36.2
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
501	0.06263	0.0	11.93	0.0	0.573	6.593	69.1	2.4786	1.0	273.0	21.0	391.99	9.67	22.4
502	0.04527	0.0	11.93	0.0	0.573	6.120	76.7	2.2875	1.0	273.0	21.0	396.90	9.08	20.6
503	0.06076	0.0	11.93	0.0	0.573	6.976	91.0	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	0.0	11.93	0.0	0.573	6.794	89.3	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	0.0	11.93	0.0	0.573	6.030	80.8	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

506 rows × 14 columns

#target这一列都加上10，所有这类操作都可以用apply+匿名函数实现
df['target'].apply(lambda x:x+10)

0      34.0
1      31.6
2      44.7
3      43.4
4      46.2
       ... 
501    32.4
502    30.6
503    33.9
504    32.0
505    21.9
Name: target, Length: 506, dtype: float64

##方法2：用列索引来删除
list = [1,3,5,6]
df.drop(df.columns[list],axis =1)

	CRIM	INDUS	NOX	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
0	0.00632	2.31	0.538	4.0900	1.0	296.0	15.3	396.90	4.98	24.0
1	0.02731	7.07	0.469	4.9671	2.0	242.0	17.8	396.90	9.14	21.6
2	0.02729	7.07	0.469	4.9671	2.0	242.0	17.8	392.83	4.03	34.7
3	0.03237	2.18	0.458	6.0622	3.0	222.0	18.7	394.63	2.94	33.4
4	0.06905	2.18	0.458	6.0622	3.0	222.0	18.7	396.90	5.33	36.2
...	...	...	...	...	...	...	...	...	...	...
501	0.06263	11.93	0.573	2.4786	1.0	273.0	21.0	391.99	9.67	22.4
502	0.04527	11.93	0.573	2.2875	1.0	273.0	21.0	396.90	9.08	20.6
503	0.06076	11.93	0.573	2.1675	1.0	273.0	21.0	396.90	5.64	23.9
504	0.10959	11.93	0.573	2.3889	1.0	273.0	21.0	393.45	6.48	22.0
505	0.04741	11.93	0.573	2.5050	1.0	273.0	21.0	396.90	7.88	11.9

506 rows × 10 columns

##字段的新建，用原有的字段得到一个新字段

# df.eval("""新字段1=字段1+字段2
#          新字段2=字段1+字段2
#          新字段3=字段1+字段2""",inplace=False)

文件导出与处理

#df.to_csv()

其他应用

返回pandas列数据对应的数组

np.array(df)
df.values

array([[6.3200e-03, 1.8000e+01, 2.3100e+00, ..., 3.9690e+02, 4.9800e+00,
        2.4000e+01],
       [2.7310e-02, 0.0000e+00, 7.0700e+00, ..., 3.9690e+02, 9.1400e+00,
        2.1600e+01],
       [2.7290e-02, 0.0000e+00, 7.0700e+00, ..., 3.9283e+02, 4.0300e+00,
        3.4700e+01],
       ...,
       [6.0760e-02, 0.0000e+00, 1.1930e+01, ..., 3.9690e+02, 5.6400e+00,
        2.3900e+01],
       [1.0959e-01, 0.0000e+00, 1.1930e+01, ..., 3.9345e+02, 6.4800e+00,
        2.2000e+01],
       [4.7410e-02, 0.0000e+00, 1.1930e+01, ..., 3.9690e+02, 7.8800e+00,
        1.1900e+01]])

强制转化类型

df.iloc[:,1].astype("int")

0      18
1       0
2       0
3       0
4       0
       ..
501     0
502     0
503     0
504     0
505     0
Name: ZN, Length: 506, dtype: int32

相关度分析

df.corr()

	CRIM	ZN	INDUS	CHAS	NOX	RM	AGE	DIS	RAD	TAX	PTRATIO	B	LSTAT	target
CRIM	1.000000	-0.200469	0.406583	-0.055892	0.420972	-0.219247	0.352734	-0.379670	0.625505	0.582764	0.289946	-0.385064	0.455621	-0.388305
ZN	-0.200469	1.000000	-0.533828	-0.042697	-0.516604	0.311991	-0.569537	0.664408	-0.311948	-0.314563	-0.391679	0.175520	-0.412995	0.360445
INDUS	0.406583	-0.533828	1.000000	0.062938	0.763651	-0.391676	0.644779	-0.708027	0.595129	0.720760	0.383248	-0.356977	0.603800	-0.483725
CHAS	-0.055892	-0.042697	0.062938	1.000000	0.091203	0.091251	0.086518	-0.099176	-0.007368	-0.035587	-0.121515	0.048788	-0.053929	0.175260
NOX	0.420972	-0.516604	0.763651	0.091203	1.000000	-0.302188	0.731470	-0.769230	0.611441	0.668023	0.188933	-0.380051	0.590879	-0.427321
RM	-0.219247	0.311991	-0.391676	0.091251	-0.302188	1.000000	-0.240265	0.205246	-0.209847	-0.292048	-0.355501	0.128069	-0.613808	0.695360
AGE	0.352734	-0.569537	0.644779	0.086518	0.731470	-0.240265	1.000000	-0.747881	0.456022	0.506456	0.261515	-0.273534	0.602339	-0.376955
DIS	-0.379670	0.664408	-0.708027	-0.099176	-0.769230	0.205246	-0.747881	1.000000	-0.494588	-0.534432	-0.232471	0.291512	-0.496996	0.249929
RAD	0.625505	-0.311948	0.595129	-0.007368	0.611441	-0.209847	0.456022	-0.494588	1.000000	0.910228	0.464741	-0.444413	0.488676	-0.381626
TAX	0.582764	-0.314563	0.720760	-0.035587	0.668023	-0.292048	0.506456	-0.534432	0.910228	1.000000	0.460853	-0.441808	0.543993	-0.468536
PTRATIO	0.289946	-0.391679	0.383248	-0.121515	0.188933	-0.355501	0.261515	-0.232471	0.464741	0.460853	1.000000	-0.177383	0.374044	-0.507787
B	-0.385064	0.175520	-0.356977	0.048788	-0.380051	0.128069	-0.273534	0.291512	-0.444413	-0.441808	-0.177383	1.000000	-0.366087	0.333461
LSTAT	0.455621	-0.412995	0.603800	-0.053929	0.590879	-0.613808	0.602339	-0.496996	0.488676	0.543993	0.374044	-0.366087	1.000000	-0.737663
target	-0.388305	0.360445	-0.483725	0.175260	-0.427321	0.695360	-0.376955	0.249929	-0.381626	-0.468536	-0.507787	0.333461	-0.737663	1.000000

eda画图分析

import seaborn as sns
from matplotlib import pyplot as plt
plt.figure(dpi = 100)
plt.title('target')
sns.distplot(df['target'])

### 查看一个列的唯一值，以RAD列为例
df['RAD'].unique()

array([ 1.,  2.,  3.,  5.,  4.,  8.,  6.,  7., 24.])

# 查看标签分布情况
sns.countplot(df['RAD'])