matplotlib可视化练习

%matplotlib inline

import matplotlib as mpl

from matplotlib import pyplot as plt

import seaborn as sns

import pandas as pd

import numpy as np

萼片(sepal)和花瓣(petal)的大小关系(散点图)

不同种类(species)鸢尾花萼片和花瓣的大小关系(分类散点子图)

不同种类鸢尾花萼片和花瓣大小的分布情况(柱状图或者箱式图)

data = sns.load_dataset("iris")

data.head()

# 萼片长度，萼片宽度，花瓣长度，花瓣宽度，种类

Paste_Image.png

萼片(sepal)和花瓣(petal)的大小关系(散点图)

data['sepal_size'] = data['sepal_length'] * data['sepal_width']

data['petal_size'] = data['petal_length'] * data['petal_width']

plt.scatter(data['sepal_size'],data['petal_size'])

output_14_1.png

不同种类(species)鸢尾花萼片和花瓣的大小关系(分类散点子图)

先来看下有多少种类

t = data.groupby(['species']).size()#3种

t.index

Index(['setosa', 'versicolor', 'virginica'], dtype='object', name='species')

data[data['species'].values == 'setosa']['sepal_size']

0 17.85

1 14.70

2 15.04

3 14.26

4 18.00

5 21.06

6 15.64

7 17.00

8 12.76

9 15.19

10 19.98

11 16.32

12 14.40

13 12.90

14 23.20

15 25.08

16 21.06

17 17.85

18 21.66

19 19.38

20 18.36

21 18.87

22 16.56

23 16.83

24 16.32

25 15.00

26 17.00

27 18.20

28 17.68

29 15.04

30 14.88

31 18.36

32 21.32

33 23.10

34 15.19

35 16.00

36 19.25

37 17.64

38 13.20

39 17.34

40 17.50

41 10.35

42 14.08

43 17.50

44 19.38

45 14.40

46 19.38

47 14.72

48 19.61

49 16.50

Name: sepal_size, dtype: float64

plt.figure()

flag = 1

for name in data.groupby(['species']).size().index:

sepal_size = data[data['species'].values == name]['sepal_size']

petal_size = data[data['species'].values == name]['petal_size']

plt.subplot(2,2,flag)

plt.scatter(sepal_size.values,petal_size.values)

flag += 1

plt.show()

output_19_0.png

不同种类鸢尾花萼片和花瓣大小的分布情况(柱状图或者箱式图)

柱状图

plt.figure(figsize=(20,20))

flag = 1

for name in data.groupby(['species']).size().index:

sepal_size = data[data['species'].values == name]['sepal_size']

petal_size = data[data['species'].values == name]['petal_size']

plt.subplot(2,2,flag)

plt.bar(sepal_size.values,petal_size.values)

plt.title(name)

flag += 1

plt.show()

output_22_0.png

箱式图

plt.figure(figsize=(20,20))

flag = 1

for name in data.groupby(['species']).size().index:

sepal_size = data[data['species'].values == name]['sepal_size']

petal_size = data[data['species'].values == name]['petal_size']

plt.subplot(3,3,flag)

plt.boxplot(sepal_size.values

,patch_artist = True

# 中位数线颜色

, medianprops = {'color': 'b'}

# 箱子颜色设置，color：边框颜色，facecolor：填充颜色

, boxprops = {'color': 'b', 'facecolor': 'r'}

# 猫须颜色whisker

, whiskerprops = {'color': 'r'}

# 猫须界限颜色whisker cap

, capprops = {'color': 'b'})

plt.title(name +'+sepal_size')

plt.subplot(3,3,flag * 2)

plt.boxplot(sepal_size.values,

patch_artist = True

# 中位数线颜色

, medianprops = {'color': 'b'}

# 箱子颜色设置，color：边框颜色，facecolor：填充颜色

, boxprops = {'color': 'b', 'facecolor': 'r'}

# 猫须颜色whisker

, whiskerprops = {'color': 'r'}

# 猫须界限颜色whisker cap

, capprops = {'color': 'b'})

plt.title(name +'+petal_size')

flag += 1

plt.show()

output_24_0.png