05.作图 - Canvas2018

pandas结合matplotlib作图

 1 # 简单作图
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 students = pd.read_excel('009\Students.xlsx')
 6 students.plot.bar(x = 'Field', y='Number')
 7 plt.show()
 8 
 9 #图中数据排序
10 import pandas as pd
11 import matplotlib.pyplot as plt
12 
13 students = pd.read_excel('009\Students.xlsx')
14 # students.sort_index(by='Number', inplace=True, ascending=False) 将被下面的公式取代
15 students.sort_values(by='Number', inplace=True, ascending=False)
16 students.plot.bar(x = 'Field', y='Number')
17 plt.show()
18 
19 #更改颜色
20 import pandas as pd
21 import matplotlib.pyplot as plt
22 
23 students = pd.read_excel('009\Students.xlsx')
24 # students.sort_index(by='Number', inplace=True, ascending=False) 将被下面的公式取代
25 students.sort_values(by='Number', inplace=True, ascending=False)
26 students.plot.bar(x = 'Field', y='Number', color='green', \
27                   title='International Students in Filed')
28 #  现实X全部名称
29 # plt.tight_layout()
30 plt.show()

使用matplotlib作图

 1 # 使用matplotlib作图
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 students = pd.read_excel('009\Students.xlsx')
 6 # students.sort_index(by='Number', inplace=True, ascending=False) 将被下面的公式取代
 7 students.sort_values(by='Number', inplace=True, ascending=False)
 8 # students.plot.bar(x = 'Field', y='Number', color='green', title='International Students in Filed')
 9 plt.bar(students.Field, students.Number, color='orange')
10 plt.xticks(students.Field, rotation='90')
11 plt.xlabel('Field')
12 plt.ylabel('Number')
13 plt.title('International Students in Filed', fontsize=16)
14 #  现实X全部名称
15 #plt.tight_layout()
16 plt.show()

双柱形作图

 1 # 原010课
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 students = pd.read_excel('010\Students.xlsx')
 6 students.sort_values(by='2017', inplace=True, ascending=False)
 7 # print(students)
 8 students.plot.bar(x='Field', y=['2016','2017'], color=['orange','red'], title = 'International Students by Field')
 9 # plt.tight_layout()
10 plt.show()
11 
12 #改进
13 import pandas as pd
14 import matplotlib.pyplot as plt
15 
16 students = pd.read_excel('010\Students.xlsx')
17 students.sort_values(by='2017', inplace=True, ascending=False)
18 # print(students)
19 students.plot.bar(x='Field', y=['2016','2017'], color=['orange','red'])
20 plt.title('International Students by Field', fontsize=16, fontweight='bold')
21 plt.xlabel('Field', fontweight='bold')
22 plt.ylabel('Number', fontweight='bold')
23 # plt.tight_layout()
24 # 拿到轴
25 ax = plt.gca()
26 # rotation='45'或者不带'‘’都行
27 ax.set_xticklabels(students['Field'], rotation =45,ha='right')
28 f=plt.gcf()
29 f.subplots_adjust(left=0.2,bottom=0.42)
30 plt.show()
31 
32 #最终版 保存图片
33 import pandas as pd
34 import matplotlib.pyplot as plt
35 
36 students = pd.read_excel('010\Students.xlsx')
37 students.sort_values(by='2017', inplace=True, ascending=False)
38 # print(students)
39 students.plot.bar(x='Field', y=['2016','2017'], color=['orange','red'])
40 plt.title('International Students by Field', fontsize=16, fontweight='bold')
41 plt.xlabel('Field', fontweight='bold')
42 plt.ylabel('Number', fontweight='bold')
43 # plt.tight_layout()
44 # 拿到轴
45 ax = plt.gca()
46 # rotation='45'或者不带'‘’都行
47 ax.set_xticklabels(students['Field'], rotation =45,ha='right')
48 f=plt.gcf()
49 f.subplots_adjust(left=0.2,bottom=0.42)
50 plt.savefig('001.jpg', qualities=120)
51 plt.show()

叠加柱状图

 1 # 011  叠加柱状图
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 # 当\不能读取时，尝试使用\\
 6 users = pd.read_excel('011\\Users.xlsx')
 7 users['Total']=users['Oct']+users['Nov']+users['Dec']
 8 # print(users)
 9 users.sort_values(by=['Total'], inplace=True, ascending=False)
10 users.plot.bar(x='Name',y=['Oct','Nov','Dec'], stacked=True, title='User Behavior')
11 plt.tight_layout()
12 # plt.savefig('011\\0111.png')
13 plt.show()
14 
15 #水平放置
16 import pandas as pd
17 import matplotlib.pyplot as plt
18 
19 # 当\不能读取时，尝试使用\\
20 users = pd.read_excel('011\\Users.xlsx')
21 users['Total']=users['Oct']+users['Nov']+users['Dec']
22 # print(users)
23 users.sort_values(by=['Total'], inplace=True, ascending=True)
24 # barh 为 水平
25 users.plot.barh(x='Name',y=['Oct','Nov','Dec'], stacked=True, title='User Behavior', \
26                 color=['red', 'blue', 'orange'])
27 plt.tight_layout()
28 plt.savefig('011\\0111.png', dpi=1200)
29 plt.show()

饼图

 1 # 012 饼图
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 # 当\不能读取时，尝试使用\\，也可使用转义符r
 6 students = pd.read_excel('012\\Students.xlsx', index_col='From')
 7 # print(students)
 8 students['2017'].plot.pie(fontsize=8)
 9 plt.title('Source of International Students',fontsize=16,fontweight='bold')
10 plt.ylabel('2017', fontsize=12,fontweight='bold')
11 # plt.savefig('012\\012.jpg',dpi=500)
12 plt.show()
13 
14 #排序版
15 import pandas as pd
16 import matplotlib.pyplot as plt
17 
18 students = pd.read_excel('012\\Students.xlsx', index_col='From')
19 # startangle=-270 顺时针排序
20 students['2017'].sort_values(ascending=True).plot.pie(fontsize=8, startangle=-270)
21 plt.title('Source of International Students',fontsize=16,fontweight='bold')
22 plt.ylabel('2017', fontsize=12,fontweight='bold')
23 # plt.savefig('012\\012.jpg',dpi=500)
24 plt.show()
25 
26 
27 # 精进版
28 import pandas as pd
29 import matplotlib.pyplot as plt
30 
31 # 当\不能读取时，尝试使用\\
32 students = pd.read_excel('012\\Students.xlsx', index_col='From')
33 # counterclock=False 顺时针排序
34 # autopct='%1.1f%%' 可以加入百分比
35 students['2017'].plot.pie(fontsize=8, counterclock=False,startangle=-270)
36 plt.title('Source of International Students',fontsize=16,fontweight='bold')
37 plt.ylabel('2017', fontsize=12,fontweight='bold')
38 
39 plt.axis('equal')
40 # plt.savefig('012\\012.jpg',dpi=500)
41 plt.show()

波动图

 1 # 013
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 orders = pd.read_excel('013\\Orders.xlsx', index_col='Week')
 6 # print(orders.head(10))
 7 #print(orders.columns)
 8 orders.plot(y=['Accessories', 'Bikes', 'Clothing', 'Components'])
 9 plt.title('Sales Weekly Trend',fontsize = 16, fontweight='bold')
10 plt.xticks(orders.index)
11 # plt.savefig('013\\013.png',dpi=300)
12 plt.savefig('013\\013.pdf')
13 plt.show()
14 
15 # 013叠加
16 import pandas as pd
17 import matplotlib.pyplot as plt
18 
19 orders = pd.read_excel('013\\Orders.xlsx', index_col='Week')
20 #print(orders.columns)
21 
22 # 叠加柱状图
23 #orders.plot.bar(y=['Accessories', 'Bikes', 'Clothing', 'Components'],stacked=True)
24 # 叠加趋势图
25 orders.plot.area(y=['Accessories', 'Bikes', 'Clothing', 'Components'],stacked=True)
26 plt.title('Sales Weekly Trend',fontsize = 16, fontweight='bold')
27 plt.ylabel('Total',fontsize=12,fontweight='bold')
28 plt.xticks(orders.index,fontsize=8)
29 plt.savefig('013\\0131.png',dpi=600)
30 # plt.savefig('013\\0131.pdf')
31 plt.show()

散点图与直方图

 1 # 014 散点与直方图
 2 import pandas as pd
 3 import matplotlib.pyplot as plt
 4 
 5 # 读取成DataFrame
 6 homes = pd.read_excel('014\\home_data.xlsx')
 7 print(homes.head(10))
 8 
 9 # 面积的分布图
10 
11 import pandas as pd
12 import matplotlib.pyplot as plt
13 
14 pd.options.display.max_columns = 777
15 homes = pd.read_excel('014\\home_data.xlsx')
16 
17 homes.sqft_living.plot.hist(bins=100)
18 plt.xticks(range(0,max(homes.sqft_living),500), fontsize=8, rotation=90)
19 plt.show()
20 
21 # 价格的分布图
22 
23 import pandas as pd
24 import matplotlib.pyplot as plt
25 
26 pd.options.display.max_columns = 777
27 homes = pd.read_excel('014\\home_data.xlsx')
28 
29 homes.price.plot.hist(bins=100)
30 plt.xticks(range(0,max(homes.price),100000), fontsize=8, rotation=90)
31 plt.show()
32 
33 # 密度图
34 import pandas as pd
35 import matplotlib.pyplot as plt
36 
37 pd.options.display.max_columns = 777
38 homes = pd.read_excel('014\\home_data.xlsx')
39 
40 homes.sqft_living.plot.kde()
41 plt.xticks(range(0,max(homes.sqft_living),500), fontsize=8, rotation=90)
42 
43 plt.show()
44 
45 # 列之间的相关性
46 import pandas as pd
47 import matplotlib.pyplot as plt
48 
49 pd.options.display.max_columns = 777
50 homes = pd.read_excel('014\\home_data.xlsx')
51 # 显示列之间的相关性
52 # print(homes.corr())
53 corrolation= homes.corr()
54 corrolation.to_excel('014\\corr.xlsx')
55 print('Done!')

posted on 2019-02-21 17:50 Canvas2018 阅读(219) 评论(0) 收藏举报