numpy数据集练习

#1
import scipy#加载scipy包
import numpy#加载numpy包
from sklearn.datasets import load_iris #加载sklearn包

#2

from sklearn.datasets import load_iris
import numpy as np
import matplotlib.pyplot as plt
data = load_iris()
print(data)

#3

print(type(data))
print(data.keys())

#4

iris_feature = data.feature_names,data.data
iris_target = data.target_names,data.target
print('鸢尾花特征数据：',iris_feature)
print('鸢尾花形状类别：',iris_target)
sepal_len = np.array(list(len[0] for len in data.data))
print('花萼长度：',sepal_len)

 

#5

iris_len=np.array(list(len[0] for len in iris['data']))
print(iris_len)

 

#6

for len_width in iris['data']:
    print(len_width[2],len_width[3])

 

#7

print(iris['data'][0],iris['feature_names'][0])

#8

iris_a=[]
iris_b=[]
iris_c=[]
for i in range(0,150):
    if iris['target'][i]==0:
        data1=iris['data'][i].tolist()
        data1.append('a')
        iris_a.append(data1)
    elif iris['target'][i]==1:
        data1=iris['data'][i].tolist()
        data1.append('b')
        iris_b.append(data1)
    else:
        data1=iris['data'][i].tolist()
        data1.append('c')
        iris_c.append(data1)

#9

datas=np.array([iris_a,iris_b,iris_c])
print(datas)

 

#10

data_len=np.array(list(len[2] for len in iris['data']))
print(data_len)
print(np.max(data_len))
print(np.mean(data_len))
print(np.median(data_len))
print(np.std(data_len))

#11

import matplotlib.pyplot as plt
plt.plot(np.linspace(0,150,num=150),data_len,'b')  #花瓣曲线图
plt.show()
plt.scatter(np.linspace(0,150,num=150),data_len,marker='o')#花瓣图
plt.show()