seaborn可视化：使用德国银行信用数据

from mpl_toolkits.mplot3d import Axes3D
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt # plotting
import numpy as np # linear algebra
import os # accessing directory structure
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import seaborn as sns
pd.options.display.float_format = '{:,.2f}'.format  
pd.options.display.max_columns = 999

df1 = pd.read_csv("/Users/a182501/datas/german_credit_data.csv")

df1.shape

(1000, 10)

df1.head()

	Unnamed: 0	Age	Sex	Job	Housing	Saving accounts	Checking account	Credit amount	Duration	Purpose
0	0	67	male	2	own	NaN	little	1169	6	radio/TV
1	1	22	female	2	own	little	moderate	5951	48	radio/TV
2	2	49	male	1	own	little	NaN	2096	12	education
3	3	45	male	2	free	little	little	7882	42	furniture/equipment
4	4	53	male	2	free	little	little	4870	24	car

df1.describe()

	Unnamed: 0	Age	Job	Credit amount	Duration
count	1,000.00	1,000.00	1,000.00	1,000.00	1,000.00
mean	499.50	35.55	1.90	3,271.26	20.90
std	288.82	11.38	0.65	2,822.74	12.06
min	0.00	19.00	0.00	250.00	4.00
25%	249.75	27.00	2.00	1,365.50	12.00
50%	499.50	33.00	2.00	2,319.50	18.00
75%	749.25	42.00	2.00	3,972.25	24.00
max	999.00	75.00	3.00	18,424.00	72.00

df1.isnull().sum()

Unnamed: 0            0
Age                   0
Sex                   0
Job                   0
Housing               0
Saving accounts     183
Checking account    394
Credit amount         0
Duration              0
Purpose               0
dtype: int64

df1['Sex'].value_counts()
df1['Credit amount'].describe()

count    1,000.00
mean     3,271.26
std      2,822.74
min        250.00
25%      1,365.50
50%      2,319.50
75%      3,972.25
max     18,424.00
Name: Credit amount, dtype: float64

df1.groupby('Job')['Credit amount'].mean()

Job
0   2,745.14
1   2,358.52
2   3,070.97
3   5,435.49
Name: Credit amount, dtype: float64

sns.countplot(data=df1, x='Job', hue='Sex')
plt.title("Count of Job Class on Sex", size=15)
plt.xlabel("Job Class", size=15)
plt.ylabel("Count", size=15)
plt.show()

其中的hue也是对变量的填充，是对分类变量的填充，同时sns中还包括其他一些参数 - order、hue_order：绘制类别变量的顺序，若没有，则会从数据对象中推断绘图顺序； - estimator：统计函数中用于估计的值 - ci：表示的是置信区间的大小 - orient：v或h，对坐标轴的设置；

sns.lmplot(data=df1, x='Credit amount', y='Job', hue='Sex')

plt.title("Credit amount on Job", size=15)
plt.xlabel("Credit amount", size=15)
plt.ylabel("Job Class", size=15)

plt.show()

sns.countplot(data=df1, x='Checking account', hue='Sex')

plt.title("Checking account on Sex", size=15)
plt.xlabel("Checking Account", size=15)
plt.ylabel("Count")

plt.show()

这里就将原有的hue顺序进行调换

sns.countplot(data=df1, x='Checking account', hue='Sex',hue_order=['female','male'],palette="Blues_d",saturation=0.9)


plt.title("Checking account on Sex", size=15)
plt.xlabel("Checking Account", size=15)
plt.ylabel("Count")

plt.show()

palette="Blues_d"可对现有的色彩管理进行调整。saturation=0.2调整的是现有的颜色饱和度。

sns.regplot(data=df1, x='Credit amount', y='Duration')

plt.title("Relation between Credit Amount and Duration", size=15)
plt.xlabel("Credit Amount", size=15)
plt.ylabel("Duration", size=15)

plt.show()

sns.barplot(data=df1, x='Duration', y='Purpose', hue='Sex',ci=99)

plt.title("Purpose on Duration by Sex", size=15)
plt.xlabel("Duration", size=15)
plt.ylabel("Purpose", size=15)

plt.show()

/var/folders/sn/g01cvq2j72j6tbq2pmmm074h0000gq/T/ipykernel_58568/1764674419.py:1: FutureWarning: 

The `ci` parameter is deprecated. Use `errorbar=('ci', 99)` for the same effect.

  sns.barplot(data=df1, x='Duration', y='Purpose', hue='Sex',ci=99)

其中的黑色条为误差项，默认为ci=95