numpy数据集练习

#1.安装scipy，numpy，sklearn包
#2.从sklearn包自带的数据集中读出鸢尾花数据集data
#3.查看data类型，包含哪些数据
import numpy
from sklearn.datasets import load_iris

data = load_iris()
type(data)
print(data.keys())

 

4、取出花的特性和类别数据，查看数据类型

data_tgs=data ['target']##鸢尾花特征
data_tgsname=data['target_names']##鸢尾花的类别数据
data_ts=data_tgsname,data_tgs#鸢尾花特征和鸢尾花的类别数据
print(data_ts)#形状
print(type(data_ts))#数据类型
#4.取出鸢尾花特征和鸢尾花类别数据，查看其形状及数据类型
#特征
iris_feature = data['data']
print(iris_feature)


#类别数据
iris_target = data.target,data.target_names
print('类型：',iris_target)

#取出所有花的花萼长度
sepal_len = numpy.array(list(len[0] for len in data['data']))
print('所有长度：',sepal_len)

# 6.取出所有花的花瓣长度(cm)+花瓣宽度(cm)的数据
#宽
iris_width=numpy.array(list(len[3] for len in data['data']))
print(iris_width)
# 长
iris_length=numpy.array(list(len[2] for len in data['data']))
print(iris_length)

#8定义三个列表来存放不同类型花朵的类别
data_setosa=[]
data_versicolor=[]
data_virginica=[]
len(data['data'])
for i in  range(0,150):
    if data['target'][i]==0:
        datas=data['data'][i].tolist()
        datas.append('setosa')
        print(data_setosa.append(datas))
    elif data['target'][i]==1:
        datas=data['data'][i].tolist()
        datas.append('versicolor')
        data_versicolor.append(datas)
    else:
        data1=data['data'][i].tolist()
        data1.append('virginica')
        data_virginica.append(datas)

Go_data=(numpy.array([data_setosa,data_versicolor,data_virginica]))
print(Go_data)

 

#计算鸢尾花花瓣长度最大值
import numpy as np
from sklearn.datasets import load_iris
data = load_iris()

petal_length=numpy.array(list(len[2]for len in data['data']))

print(np.max(petal_length))
print(np.mean(petal_length))
print(np.std(petal_length))
print(np.median(petal_length))


np.random.normal(1,5,60)

np.random.randn(3,3)

#正态分布图

import numpy as np
import matplotlib.pyplot as plt

mu = 1
sigma = 3
num = 10000

rand_data = np.random.normal(mu, sigma, num)
print(rand_data.shape,type(rand_data))

count, bins, ignored=plt.hist(rand_data, 30, normed=True)
plt.plot(bins, 1/(sigma * np.sqrt(2 * np.pi)) *np.exp( - (bins - mu)**2 / (2 * sigma**2)), linewidth=2, color='r')
plt.show()

#曲线图
plt.plot(np.linspace(0,150,num=150),petal_length,'r')
plt.show()

#散点图

import numpy as np
import matplotlib.pyplot as plt
plt.scatter(np.linspace(0,150,num=150),petal_length,alpha=0.5,marker='x')
plt.show()

 

 

 

 

 

转载于:https://www.cnblogs.com/a1234tt/p/9869788.html