pandas 数据预处理实验 莺尾花

import pandas as pd
import numpy as np
from sklearn import datasets
import seaborn as sns

iris = datasets.load_iris()

iris.keys()

dict_keys(['data', 'target', 'target_names', 'DESCR', 'feature_names', 'filename'])

X_train = pd.DataFrame(iris.data,columns=iris.feature_names)
X_train

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)
0	5.1	3.5	1.4	0.2
1	4.9	3.0	1.4	0.2
2	4.7	3.2	1.3	0.2
3	4.6	3.1	1.5	0.2
4	5.0	3.6	1.4	0.2
...	...	...	...	...
145	6.7	3.0	5.2	2.3
146	6.3	2.5	5.0	1.9
147	6.5	3.0	5.2	2.0
148	6.2	3.4	5.4	2.3
149	5.9	3.0	5.1	1.8

150 rows × 4 columns

X_train.describe()

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

X_train.mean()

sepal length (cm)    5.843333
sepal width (cm)     3.057333
petal length (cm)    3.758000
petal width (cm)     1.199333
dtype: float64

X_train.corr()

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)
sepal length (cm)	1.000000	-0.117570	0.871754	0.817941
sepal width (cm)	-0.117570	1.000000	-0.428440	-0.366126
petal length (cm)	0.871754	-0.428440	1.000000	0.962865
petal width (cm)	0.817941	-0.366126	0.962865	1.000000

sns.heatmap(X_train.corr(),annot=True,cmap='RdYlBu')

<matplotlib.axes._subplots.AxesSubplot at 0x1f90f0c96c8>

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-D0nzJOvd-1588916369209)(output_7_1.png)]

Y_train0=pd.DataFrame(iris.target)==0
Y_train1=pd.DataFrame(iris.target)==1
Y_train2=pd.DataFrame(iris.target)==2
Y_train=pd.concat([Y_train0,Y_train1,Y_train2],axis=1)
Y_train.columns=iris.target_names
Y_train

	setosa	versicolor	virginica
0	True	False	False
1	True	False	False
2	True	False	False
3	True	False	False
4	True	False	False
...	...	...	...
145	False	False	True
146	False	False	True
147	False	False	True
148	False	False	True
149	False	False	True

150 rows × 3 columns

Train=pd.concat([X_train,Y_train],axis=1)
Train

	sepal length (cm)	sepal width (cm)	petal length (cm)	petal width (cm)	setosa	versicolor	virginica
0	5.1	3.5	1.4	0.2	True	False	False
1	4.9	3.0	1.4	0.2	True	False	False
2	4.7	3.2	1.3	0.2	True	False	False
3	4.6	3.1	1.5	0.2	True	False	False
4	5.0	3.6	1.4	0.2	True	False	False
...	...	...	...	...	...	...	...
145	6.7	3.0	5.2	2.3	False	False	True
146	6.3	2.5	5.0	1.9	False	False	True
147	6.5	3.0	5.2	2.0	False	False	True
148	6.2	3.4	5.4	2.3	False	False	True
149	5.9	3.0	5.1	1.8	False	False	True

150 rows × 7 columns

sns.heatmap(Train.corr(),annot=True,cmap='RdYlBu')

<matplotlib.axes._subplots.AxesSubplot at 0x1f90f027a48>

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-rcUOxtUa-1588916369212)(output_10_1.png)]