sklearn.datasets iris数据集绘图

sklearn.datasets iris数据集绘图

导入数据

from sklearn.datasets import load_iris
import matplotlib.pyplot as plt
import pandas as pd
import warnings
warnings.filterwarnings('ignore')

data = load_iris()
df = pd.DataFrame(data['data'], columns=data['feature_names'])
df['species'] = data['target']

df.head()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	species
0	5.1	3.5	1.4	0.2	0
1	4.9	3.0	1.4	0.2	0
2	4.7	3.2	1.3	0.2	0
3	4.6	3.1	1.5	0.2	0
4	5.0	3.6	1.4	0.2	0

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 150 entries, 0 to 149
Data columns (total 5 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   sepal length (cm)  150 non-null    float64
 1   sepal width (cm)   150 non-null    float64
 2   petal length (cm)  150 non-null    float64
 3   petal width (cm)   150 non-null    float64
 4   species            150 non-null    int32  
dtypes: float64(4), int32(1)
memory usage: 5.4 KB

df.describe()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	species
count	150.000000	150.000000	150.000000	150.000000	150.000000
mean	5.843333	3.057333	3.758000	1.199333	1.000000
std	0.828066	0.435866	1.765298	0.762238	0.819232
min	4.300000	2.000000	1.000000	0.100000	0.000000
25%	5.100000	2.800000	1.600000	0.300000	0.000000
50%	5.800000	3.000000	4.350000	1.300000	1.000000
75%	6.400000	3.300000	5.100000	1.800000	2.000000
max	7.900000	4.400000	6.900000	2.500000	2.000000

数据可视化

df.plot(kind='box')#箱线图
df.plot(kind='line')#折线图
df.plot(kind='hist',bins=50)#直方图
df.plot(kind='bar')#条形图
df.plot(kind='kde')#Kernel 概率密度线
df.plot(kind='scatter',x='sepal length (cm)',y='sepal width (cm)')

<matplotlib.axes._subplots.AxesSubplot at 0x20a352cbcc8>

配合matplotlib 使用添加子图

fig,axs=plt.subplots(5,1)
df.plot(kind='line',subplots=True,ax=axs)
fig.subplots_adjust(wspace=1, ) 

fig,axs=plt.subplots(1,5)
df.plot(kind='kde',subplots=True,ax=axs,legend=False,sharey=1)

array([<matplotlib.axes._subplots.AxesSubplot object at 0x0000020A3978FE48>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x0000020A3993AA88>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x0000020A3994F6C8>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x0000020A3998DE88>,
       <matplotlib.axes._subplots.AxesSubplot object at 0x0000020A39935288>],
      dtype=object)

matplotlib.pyplot.GridSpec绘制子图

x = df['sepal length (cm)'].values
y = df['sepal width (cm)'].values
plt.figure(figsize=(6,6))
grid = plt.GridSpec(4, 4, wspace=0.5, hspace=0.5)
main_ax = plt.subplot(grid[0:3,1:4])
df.plot(kind='scatter',x='sepal length (cm)',y='sepal width (cm)',ax=main_ax)

y_hist = plt.subplot(grid[0:3,0],xticklabels=[],sharey=main_ax)
plt.hist(y,60,color='green',orientation='horizontal',alpha=0.5)
y_hist.invert_xaxis()

x_hist = plt.subplot(grid[3,1:4],yticklabels=[])
df['sepal length (cm)'].plot(kind='kde',color='red',alpha=0.5,ax=x_hist)
x_hist.invert_yaxis()

plt.subplots_adjust(hspace=1.2, wspace=1)

plt.show()

后续：利用 seaborn 库相关库进行绘制复杂图形