作业六

numpy数据集

#安装scipy，numpy，sklearn包
from sklearn.datasets import load_iris
import numpy as np
import pandas as pd
#从sklearn包自带的数据集中读出鸢尾花数据集data
data=load_iris()
#.查看data类型
print(type(data))
print(data.keys())
#取出鸢尾花特征和鸢尾花类别数据
iris_feature=data['data']
print(type(iris_feature))
print(iris_feature)
n_sample,n_features=data.data.shape
print(n_sample,n_features)
#查看第一组数据
print(data.data[0]
print(data.target.shape)
l=data['target']
print(l)
print(data.target_names)
# 列名称
print("feature_names:",data.feature_names)
# 取出所有花的花萼长度(cm)的数据
D=data.data
X=[x[0] for x in D]
print(X)
# 取出所有花的花瓣长度(cm)+花瓣宽度(cm)的数据
Y=[x[2] for x in D]
print(Y)
Z=[x[3] for x in D]
print(Z)
z=np.array([Y+Z])
print(z)

#.取出某朵花的四个特征及其类别
print(iris_feature[0], l[0])


#将所有花的特征和类别分成三组，每组50个
issetosa=[]
isversicolor=[]
isvirginica=[]
for i in range(0,150):
    if l[i] == 0:
        data = iris_feature[i].tolist()
        data.append('setosa')
        issetosa.append(data)
    elif l[i] == 1:
        data = iris_feature[i].tolist()
        data.append('versicolor')
        isversicolor.append(data)
    else:
        data = iris_feature[i].tolist()
        data.append('virginica')
        isvirginica.append(data)

#生成新的数组，每个数组包含四个特征和类别
iris_re = np.array([issetosa,isversicolor,isvirginica])
print(iris_re)

 

 

转载于:https://www.cnblogs.com/jun11/p/9777414.html