Datawhale Task05 大作业打卡

导入植物数据集，保持文本不变

import numpy as np
outfile = r'D:\Ajupyter\Dadawhale numpy\iris.csv'
iris_csv = np.loadtxt(outfile,dtype = object,delimiter = ',',skiprows = 1)
print(iris_csv[0:10])

[['5.1' '3.5' '1.4' '0.2' 'Iris-setosa']
 ['4.9' '3' '1.4' '0.2' 'Iris-setosa']
 ['4.7' '3.2' '1.3' '0.2' 'Iris-setosa']
 ['4.6' '3.1' '1.5' '0.2' 'Iris-setosa']
 ['5' '3.6' '1.4' '0.2' 'Iris-setosa']
 ['5.4' '3.9' '1.7' '0.4' 'Iris-setosa']
 ['4.6' '3.4' '1.4' '0.3' 'Iris-setosa']
 ['5' '3.4' '1.5' '0.2' 'Iris-setosa']
 ['4.4' '2.9' '1.4' '0.2' 'Iris-setosa']
 ['4.9' '3.1' '1.5' '0.1' 'Iris-setosa']]

求出鸢尾属植物萼片长度的平均值、中位数和标准差

import numpy as np
outfile = r'D:\Ajupyter\Dadawhale numpy\iris.csv'
sepalLength = np.loadtxt(outfile,dtype = float,delimiter = ',',skiprows = 1,usecols = [0])
print(sepalLength[0:10])

[5.1 4.9 4.7 4.6 5.  5.4 4.6 5.  4.4 4.9]

print(np.mean(sepalLength))

5.843333333333334

print(np.median(sepalLength))

5.8

print(np.std(sepalLength))

0.8253012917851409

创建一种标准化形式的萼片长度

import numpy as np
outfile = r'D:\Ajupyter\Dadawhale numpy\iris.csv'
sepalLength = np.loadtxt(outfile,dtype = float,delimiter = ',',skiprows = 1,usecols = [0])

aMax = np.amax(sepalLength)
aMin = np.amin(sepalLength)
x = (sepalLength - aMin) / (aMax - aMin)
print(x[0:10])

[0.22222222 0.16666667 0.11111111 0.08333333 0.19444444 0.30555556
 0.08333333 0.19444444 0.02777778 0.16666667]