Untitled1

最新推荐文章于 2024-04-19 20:43:43 发布

Cazkeen

最新推荐文章于 2024-04-19 20:43:43 发布

阅读量169

点赞数

分类专栏： python

本文链接：https://blog.csdn.net/weixin_51775736/article/details/114887351

版权

python 专栏收录该内容

15 篇文章 1 订阅

订阅专栏

import pandas as pd
df=pd.read_csv("../Desktop/train.csv")
df.head(10)

	Loan_ID	Gender	Married	Dependents	Education	Self_Employed	ApplicantIncome	CoapplicantIncome	LoanAmount	Loan_Amount_Term	Credit_History	Property_Area	Loan_Status
0	LP001002	Male	No	0	Graduate	No	5849	0.0	NaN	360.0	1.0	Urban	Y
1	LP001003	Male	Yes	1	Graduate	No	4583	1508.0	128.0	360.0	1.0	Rural	N
2	LP001005	Male	Yes	0	Graduate	Yes	3000	0.0	66.0	360.0	1.0	Urban	Y
3	LP001006	Male	Yes	0	Not Graduate	No	2583	2358.0	120.0	360.0	1.0	Urban	Y
4	LP001008	Male	No	0	Graduate	No	6000	0.0	141.0	360.0	1.0	Urban	Y
5	LP001011	Male	Yes	2	Graduate	Yes	5417	4196.0	267.0	360.0	1.0	Urban	Y
6	LP001013	Male	Yes	0	Not Graduate	No	2333	1516.0	95.0	360.0	1.0	Urban	Y
7	LP001014	Male	Yes	3+	Graduate	No	3036	2504.0	158.0	360.0	0.0	Semiurban	N
8	LP001018	Male	Yes	2	Graduate	No	4006	1526.0	168.0	360.0	1.0	Urban	Y
9	LP001020	Male	Yes	1	Graduate	No	12841	10968.0	349.0	360.0	1.0	Semiurban	N

df1=df[(df['Education']=='Not Graduate')&(df['Loan_Status']=='Y')&(df['Gender']=='Female')][['Gender','Education','Loan_Status']]
df1.head()

	Gender	Education	Loan_Status
50	Female	Not Graduate	Y
197	Female	Not Graduate	Y
205	Female	Not Graduate	Y
279	Female	Not Graduate	Y
403	Female	Not Graduate	Y

df.loc[:,'new_col']=df['Loan_Status']

df

	Loan_ID	Gender	Married	Dependents	Education	Self_Employed	ApplicantIncome	CoapplicantIncome	LoanAmount	Loan_Amount_Term	Credit_History	Property_Area	Loan_Status	new_col
0	LP001002	Male	No	0	Graduate	No	5849	0.0	NaN	360.0	1.0	Urban	Y	Y
1	LP001003	Male	Yes	1	Graduate	No	4583	1508.0	128.0	360.0	1.0	Rural	N	N
2	LP001005	Male	Yes	0	Graduate	Yes	3000	0.0	66.0	360.0	1.0	Urban	Y	Y
3	LP001006	Male	Yes	0	Not Graduate	No	2583	2358.0	120.0	360.0	1.0	Urban	Y	Y
4	LP001008	Male	No	0	Graduate	No	6000	0.0	141.0	360.0	1.0	Urban	Y	Y
5	LP001011	Male	Yes	2	Graduate	Yes	5417	4196.0	267.0	360.0	1.0	Urban	Y	Y
6	LP001013	Male	Yes	0	Not Graduate	No	2333	1516.0	95.0	360.0	1.0	Urban	Y	Y
7	LP001014	Male	Yes	3+	Graduate	No	3036	2504.0	158.0	360.0	0.0	Semiurban	N	N
8	LP001018	Male	Yes	2	Graduate	No	4006	1526.0	168.0	360.0	1.0	Urban	Y	Y
9	LP001020	Male	Yes	1	Graduate	No	12841	10968.0	349.0	360.0	1.0	Semiurban	N	N
10	LP001024	Male	Yes	2	Graduate	No	3200	700.0	70.0	360.0	1.0	Urban	Y	Y
11	LP001027	Male	Yes	2	Graduate	NaN	2500	1840.0	109.0	360.0	1.0	Urban	Y	Y
12	LP001028	Male	Yes	2	Graduate	No	3073	8106.0	200.0	360.0	1.0	Urban	Y	Y
13	LP001029	Male	No	0	Graduate	No	1853	2840.0	114.0	360.0	1.0	Rural	N	N
14	LP001030	Male	Yes	2	Graduate	No	1299	1086.0	17.0	120.0	1.0	Urban	Y	Y
15	LP001032	Male	No	0	Graduate	No	4950	0.0	125.0	360.0	1.0	Urban	Y	Y
16	LP001034	Male	No	1	Not Graduate	No	3596	0.0	100.0	240.0	NaN	Urban	Y	Y
17	LP001036	Female	No	0	Graduate	No	3510	0.0	76.0	360.0	0.0	Urban	N	N
18	LP001038	Male	Yes	0	Not Graduate	No	4887	0.0	133.0	360.0	1.0	Rural	N	N
19	LP001041	Male	Yes	0	Graduate	NaN	2600	3500.0	115.0	NaN	1.0	Urban	Y	Y
20	LP001043	Male	Yes	0	Not Graduate	No	7660	0.0	104.0	360.0	0.0	Urban	N	N
21	LP001046	Male	Yes	1	Graduate	No	5955	5625.0	315.0	360.0	1.0	Urban	Y	Y
22	LP001047	Male	Yes	0	Not Graduate	No	2600	1911.0	116.0	360.0	0.0	Semiurban	N	N
23	LP001050	NaN	Yes	2	Not Graduate	No	3365	1917.0	112.0	360.0	0.0	Rural	N	N
24	LP001052	Male	Yes	1	Graduate	NaN	3717	2925.0	151.0	360.0	NaN	Semiurban	N	N
25	LP001066	Male	Yes	0	Graduate	Yes	9560	0.0	191.0	360.0	1.0	Semiurban	Y	Y
26	LP001068	Male	Yes	0	Graduate	No	2799	2253.0	122.0	360.0	1.0	Semiurban	Y	Y
27	LP001073	Male	Yes	2	Not Graduate	No	4226	1040.0	110.0	360.0	1.0	Urban	Y	Y
28	LP001086	Male	No	0	Not Graduate	No	1442	0.0	35.0	360.0	1.0	Urban	N	N
29	LP001087	Female	No	2	Graduate	NaN	3750	2083.0	120.0	360.0	1.0	Semiurban	Y	Y
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
584	LP002911	Male	Yes	1	Graduate	No	2787	1917.0	146.0	360.0	0.0	Rural	N	N
585	LP002912	Male	Yes	1	Graduate	No	4283	3000.0	172.0	84.0	1.0	Rural	N	N
586	LP002916	Male	Yes	0	Graduate	No	2297	1522.0	104.0	360.0	1.0	Urban	Y	Y
587	LP002917	Female	No	0	Not Graduate	No	2165	0.0	70.0	360.0	1.0	Semiurban	Y	Y
588	LP002925	NaN	No	0	Graduate	No	4750	0.0	94.0	360.0	1.0	Semiurban	Y	Y
589	LP002926	Male	Yes	2	Graduate	Yes	2726	0.0	106.0	360.0	0.0	Semiurban	N	N
590	LP002928	Male	Yes	0	Graduate	No	3000	3416.0	56.0	180.0	1.0	Semiurban	Y	Y
591	LP002931	Male	Yes	2	Graduate	Yes	6000	0.0	205.0	240.0	1.0	Semiurban	N	N
592	LP002933	NaN	No	3+	Graduate	Yes	9357	0.0	292.0	360.0	1.0	Semiurban	Y	Y
593	LP002936	Male	Yes	0	Graduate	No	3859	3300.0	142.0	180.0	1.0	Rural	Y	Y
594	LP002938	Male	Yes	0	Graduate	Yes	16120	0.0	260.0	360.0	1.0	Urban	Y	Y
595	LP002940	Male	No	0	Not Graduate	No	3833	0.0	110.0	360.0	1.0	Rural	Y	Y
596	LP002941	Male	Yes	2	Not Graduate	Yes	6383	1000.0	187.0	360.0	1.0	Rural	N	N
597	LP002943	Male	No	NaN	Graduate	No	2987	0.0	88.0	360.0	0.0	Semiurban	N	N
598	LP002945	Male	Yes	0	Graduate	Yes	9963	0.0	180.0	360.0	1.0	Rural	Y	Y
599	LP002948	Male	Yes	2	Graduate	No	5780	0.0	192.0	360.0	1.0	Urban	Y	Y
600	LP002949	Female	No	3+	Graduate	NaN	416	41667.0	350.0	180.0	NaN	Urban	N	N
601	LP002950	Male	Yes	0	Not Graduate	NaN	2894	2792.0	155.0	360.0	1.0	Rural	Y	Y
602	LP002953	Male	Yes	3+	Graduate	No	5703	0.0	128.0	360.0	1.0	Urban	Y	Y
603	LP002958	Male	No	0	Graduate	No	3676	4301.0	172.0	360.0	1.0	Rural	Y	Y
604	LP002959	Female	Yes	1	Graduate	No	12000	0.0	496.0	360.0	1.0	Semiurban	Y	Y
605	LP002960	Male	Yes	0	Not Graduate	No	2400	3800.0	NaN	180.0	1.0	Urban	N	N
606	LP002961	Male	Yes	1	Graduate	No	3400	2500.0	173.0	360.0	1.0	Semiurban	Y	Y
607	LP002964	Male	Yes	2	Not Graduate	No	3987	1411.0	157.0	360.0	1.0	Rural	Y	Y
608	LP002974	Male	Yes	0	Graduate	No	3232	1950.0	108.0	360.0	1.0	Rural	Y	Y
609	LP002978	Female	No	0	Graduate	No	2900	0.0	71.0	360.0	1.0	Rural	Y	Y
610	LP002979	Male	Yes	3+	Graduate	No	4106	0.0	40.0	180.0	1.0	Rural	Y	Y
611	LP002983	Male	Yes	1	Graduate	No	8072	240.0	253.0	360.0	1.0	Urban	Y	Y
612	LP002984	Male	Yes	2	Graduate	No	7583	0.0	187.0	360.0	1.0	Urban	Y	Y
613	LP002990	Female	No	0	Graduate	Yes	4583	0.0	133.0	360.0	0.0	Semiurban	N	N

614 rows × 14 columns

df.Education=='Not Graduate'

0      False
1      False
2      False
3       True
4      False
5      False
6       True
7      False
8      False
9      False
10     False
11     False
12     False
13     False
14     False
15     False
16      True
17     False
18      True
19     False
20      True
21     False
22      True
23      True
24     False
25     False
26     False
27      True
28      True
29     False
       ...  
584    False
585    False
586    False
587     True
588    False
589    False
590    False
591    False
592    False
593    False
594    False
595     True
596     True
597    False
598    False
599    False
600    False
601     True
602    False
603    False
604    False
605     True
606    False
607     True
608    False
609    False
610    False
611    False
612    False
613    False
Name: Education, Length: 614, dtype: bool

def num_missing(x):
    return sum(x.isnull())

sum(df['Gender'].isnull())

df.apply(num_missing,axis=0)

Loan_ID               0
Gender               13
Married               3
Dependents           15
Education             0
Self_Employed        32
ApplicantIncome       0
CoapplicantIncome     0
LoanAmount           22
Loan_Amount_Term     14
Credit_History       50
Property_Area         0
Loan_Status           0
new_col               0
dtype: int64

df.apply(num_missing,axis=1)

0      1
1      0
2      0
3      0
4      0
5      0
6      0
7      0
8      0
9      0
10     0
11     1
12     0
13     0
14     0
15     0
16     1
17     0
18     0
19     2
20     0
21     0
22     0
23     1
24     2
25     0
26     0
27     0
28     0
29     1
      ..
584    0
585    0
586    0
587    0
588    1
589    0
590    0
591    0
592    1
593    0
594    0
595    0
596    0
597    1
598    0
599    0
600    2
601    1
602    0
603    0
604    0
605    1
606    0
607    0
608    0
609    0
610    0
611    0
612    0
613    0
Length: 614, dtype: int64

df2=df.apply(num_missing,axis=1)
df2.head(10)

0    1
1    0
2    0
3    0
4    0
5    0
6    0
7    0
8    0
9    0
dtype: int64

df['Gender'].mode().iloc[0]

'Male'

df['Gender'].fillna(df['Gender'].mode().iloc[0],inplace=True)

sum(df['Gender'].isnull())

import numpy as np
df.pivot_table(values=["LoanAmount"],index=["Gender","Married","Self_Employed"],aggfunc=np.mean)

			LoanAmount
Gender	Married	Self_Employed
Female	No	No	110.596774
	No	Yes	125.800000
	Yes	No	135.480000
	Yes	Yes	282.250000
Male	No	No	127.500000
	No	Yes	180.588235
	Yes	No	153.982699
	Yes	Yes	169.395833

for i ,row in df.loc[data["LoanAmount"].isnull(),:].iterrows():
    ind=tuple([row['Gender'],row['Married'],row['Self_Employed']])
    df.loc[i,"LoanAmount"]=impute_grps.loc{ind}.values[0]

  File "<ipython-input-35-99e2725d767b>", line 3
    df.loc[i,"LoanAmount"]=impute_grps.loc{ind}.values[0]
                                          ^
SyntaxError: invalid syntax

grps=df.groupby(["Gender","Married","Self_Employed"])

grps["LoanAmount"].mean()

Gender  Married  Self_Employed
Female  No       No               110.596774
                 Yes              125.800000
        Yes      No               135.480000
                 Yes              282.250000
Male    No       No               127.500000
                 Yes              180.588235
        Yes      No               153.982699
                 Yes              169.395833
Name: LoanAmount, dtype: float64

Cazkeen

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
Untitled1

import pandas as pddf=pd.read_csv("../Desktop/train.csv")df.head(10) Loan_ID Gender Married Dependents Education Self_Employed ApplicantIncome CoapplicantIncome LoanAmount Loa
复制链接

扫一扫