In [1]:

import plotly.graph_objects as go
import plotly as py
from plotly.subplots import make_subplots
import pandas as pd
import plotly.express as px
import os
import plotly.io as pio
from IPython.display import Image
pio.kaleido.scope.default_format = "svg"

In [2]:

path='D:\'

In [3]:

df=pd.read_csv(path+'项目数据.csv',encoding='gbk')

In [4]:

fig = make_subplots(rows=2, cols=2, column_widths=[0.5, 0.5],row_heights=[0.5,0.5],
    specs=[[{"type": "domain"}, {"type": "polar"}],
           [{"type": "xy","colspan":2}, None]],
                    subplot_titles=("<b>性别</b>","<b>时段</b>",
                                    "<b>年龄</b>"))

饼图¶

In [5]:

feature='GENDER'

In [6]:

data=df[feature].value_counts()
data

Out[6]:

M    233935
F    123874
Name: GENDER, dtype: int64

In [7]:

labels = ['男','女']
values = [233935, 123874]
subfigureGender=go.Pie(labels=labels, values=values, textinfo='label+percent',
                             insidetextorientation='radial')
go.Figure(subfigureGender)

In [8]:

testfigure=go.Figure(subfigureGender)

In [9]:

testfigure.write_image(path+"性别.svg",width=350, height=350, scale=1)

雷达图¶

数据1¶

In [10]:

feature='DEPARTHOUR'
data=df[feature].value_counts()
data

Out[10]:

8     32139
7     29878
9     29280
13    26040
15    24824
10    24529
12    24302
11    24104
14    23992
16    22337
17    20193
18    17431
19    14943
6     13293
20    12411
21     9930
22     6505
23     2587
5      1429
4       503
1       459
0       446
2       438
3       420
Name: DEPARTHOUR, dtype: int64

In [11]:

data=pd.DataFrame(data)
data=data.reset_index(drop=False)
data

Out[11]:

	index	DEPARTHOUR
0	8	32139
1	7	29878
2	9	29280
3	13	26040
4	15	24824
5	10	24529
6	12	24302
7	11	24104
8	14	23992
9	16	22337
10	17	20193
11	18	17431
12	19	14943
13	6	13293
14	20	12411
15	21	9930
16	22	6505
17	23	2587
18	5	1429
19	4	503
20	1	459
21	0	446
22	2	438
23	3	420

In [12]:

data["index"]

Out[12]:

0      8
1      7
2      9
3     13
4     15
5     10
6     12
7     11
8     14
9     16
10    17
11    18
12    19
13     6
14    20
15    21
16    22
17    23
18     5
19     4
20     1
21     0
22     2
23     3
Name: index, dtype: int64

In [13]:

data=data.sort_values(by='index')
data

Out[13]:

	index	DEPARTHOUR
21	0	446
20	1	459
22	2	438
23	3	420
19	4	503
18	5	1429
13	6	13293
1	7	29878
0	8	32139
2	9	29280
5	10	24529
7	11	24104
6	12	24302
3	13	26040
8	14	23992
4	15	24824
9	16	22337
10	17	20193
11	18	17431
12	19	14943
14	20	12411
15	21	9930
16	22	6505
17	23	2587

In [14]:

subfigureDepartTime=go.Scatterpolar(
  theta=data["index"].astype('str'),
  r=data[feature],
  fill='toself',name="出发时段")
subfigureDepartTime_f=go.Figure(subfigureDepartTime)
subfigureDepartTime_f.update_layout(
  polar=dict(
    radialaxis=dict(
      visible=True
    ),
  ),
  showlegend=False
)

subfigureDepartTime_f.show()

数据2¶

In [15]:

feature='ARRIVEHOUR_S'
data=df[feature].value_counts()
data

Out[15]:

15    25908
18    25808
17    25201
14    25189
16    25117
19    24612
20    24139
21    23060
13    22924
22    21581
23    20283
12    19716
11    18058
10    15756
9     13002
0     12789
8      6800
1      5703
7      2761
6      1640
5       854
2       611
4       492
3       409
Name: ARRIVEHOUR_S, dtype: int64

In [16]:

data=pd.DataFrame(data)
data=data.reset_index(drop=False)
data

Out[16]:

	index	ARRIVEHOUR_S
0	15	25908
1	18	25808
2	17	25201
3	14	25189
4	16	25117
5	19	24612
6	20	24139
7	21	23060
8	13	22924
9	22	21581
10	23	20283
11	12	19716
12	11	18058
13	10	15756
14	9	13002
15	0	12789
16	8	6800
17	1	5703
18	7	2761
19	6	1640
20	5	854
21	2	611
22	4	492
23	3	409

In [17]:

data["index"]

Out[17]:

0     15
1     18
2     17
3     14
4     16
5     19
6     20
7     21
8     13
9     22
10    23
11    12
12    11
13    10
14     9
15     0
16     8
17     1
18     7
19     6
20     5
21     2
22     4
23     3
Name: index, dtype: int64

In [18]:

data=data.sort_values(by='index')
data

Out[18]:

	index	ARRIVEHOUR_S
15	0	12789
17	1	5703
21	2	611
23	3	409
22	4	492
20	5	854
19	6	1640
18	7	2761
16	8	6800
14	9	13002
13	10	15756
12	11	18058
11	12	19716
8	13	22924
3	14	25189
0	15	25908
4	16	25117
2	17	25201
1	18	25808
5	19	24612
6	20	24139
7	21	23060
9	22	21581
10	23	20283

In [19]:

subfigureArriveTime=go.Scatterpolar(
  theta=data["index"].astype('str'),
  r=data[feature],
  fill='toself',marker={'color':"lightsalmon"},name="到达时段")
subfigureArriveTime_f=go.Figure(subfigureArriveTime)
subfigureArriveTime_f.update_layout(
  polar=dict(
    radialaxis=dict(
      visible=True
    ),
  ),
  showlegend=False
)

subfigureArriveTime_f.show()

合并两个数据¶

In [20]:

data=[subfigureDepartTime,subfigureArriveTime]
testfigure=go.Figure(data=data)

In [21]:

testfigure.write_image(path+"时段.svg",width=350, height=350, scale=1)
testfigure

直方图¶

In [22]:

feature='AGE'
data=df[(~df[feature].isnull())&(df[feature]<100)][feature]

In [23]:

subfigureAge=go.Histogram(x=data,name="年龄",marker={"color":"lightsalmon"})

In [24]:

testfigure=go.Figure(subfigureAge)
layout = go.Layout(xaxis={"title":'年龄'})
testfigure.update_layout(layout)

In [25]:

testfigure.write_image(path+"年龄.svg",width=500, height=350, scale=1)
testfigure

合并画图¶

In [26]:

fig.add_trace(subfigureGender,1,1)
fig.add_trace(subfigureDepartTime,1,2)
fig.add_trace(subfigureArriveTime,1,2)
fig.add_trace(subfigureAge,2,1)

In [27]:

py.offline.plot(fig,filename="用户画像特征.html")

Out[27]:

'用户画像特征.html'