[Visualization] Plotly_Part2

data.csv

2.52MB

us_simplified.zip

12.33MB

 

 

 

plotly

https://plotly.com/python/

 

In [1]:

# interactive graphs
import plotly.express as px
import pandas as pd
import numpy as np

 

 

practical example

https://www.kaggle.com/datasets/davincermak/quarterly-census-of-employment-and-wages-may-2020?resource=download

 

 

choropleth_mapbox

 

In [2]:

df_practice = pd.read_csv('data.csv') # 2020년 5월의 실업데이터

 

In [3]:

df_practice.head(1)

 

Out[3]:

	area_fips	area_title	may2020_empl_yy_pc	may2020_empl	naics_1111	naics_1114	naics_1119	naics_1121	naics_1129	naics_1132	...	naics_5211	naics_5251	naics_7114	naics_7213	naics_3162	naics_3341	naics_3343	naics_3352	naics_3161	naics_9999
0	1001	Autauga County, Alabama	-5.4	10580	0.0	0.0	0.0	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

1 rows × 307 columns

 

In [4]:

df_practice.isnull().sum()

 

Out[4]:

area_fips             0
area_title            0
may2020_empl_yy_pc    0
may2020_empl          0
naics_1111            0
                     ..
naics_3341            0
naics_3343            0
naics_3352            0
naics_3161            0
naics_9999            0
Length: 307, dtype: int64

 

In [5]:

df_practice[df_practice.duplicated()]

 

Out[5]:

	area_fips	area_title	may2020_empl_yy_pc	may2020_empl	naics_1111	naics_1114	naics_1119	naics_1121	naics_1129	naics_1132	...	naics_5211	naics_5251	naics_7114	naics_7213	naics_3162	naics_3341	naics_3343	naics_3352	naics_3161	naics_9999

0 rows × 307 columns

 

In [6]:

# df_mean = df_practice.groupby('area_fips', as_index=False)['may2020_empl'].mean()
# df_mean

 

In [8]:

# 정확한 fips code 정의
df_practice['area_fips'] = df_practice['area_fips'].apply(lambda x: '%05d' % (int(x)))

 

In [9]:

df_practice.head(10)

 

Out[9]:

	area_fips	area_title	may2020_empl_yy_pc	may2020_empl	naics_1111	naics_1114	naics_1119	naics_1121	naics_1129	naics_1132	...	naics_5211	naics_5251	naics_7114	naics_7213	naics_3162	naics_3341	naics_3343	naics_3352	naics_3161	naics_9999
0	01001	Autauga County, Alabama	-5.4	10580	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
1	01003	Baldwin County, Alabama	-10.8	69631	0.0	5.78	1.26	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
2	01005	Barbour County, Alabama	-3.7	7868	0.0	0.00	10.56	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
3	01007	Bibb County, Alabama	-3.8	4459	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
4	01009	Blount County, Alabama	-4.6	8344	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
5	01011	Bullock County, Alabama	-5.8	2827	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
6	01013	Butler County, Alabama	-18.3	5885	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
7	01015	Calhoun County, Alabama	-9.7	40426	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
8	01017	Chambers County, Alabama	-9.1	7741	0.0	0.00	0.00	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0
9	01019	Cherokee County, Alabama	-12.0	4663	0.0	23.76	4.39	0.0	0.0	0.0	...	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0	0.0

10 rows × 307 columns

 

In [10]:

from urllib.request import urlopen
import json

with urlopen('https://raw.githubusercontent.com/plotly/datasets/master/geojson-counties-fips.json') as response:
    counties = json.load(response)

fig = px.choropleth_mapbox(df_practice, geojson=counties, locations='area_fips', color='may2020_empl', color_continuous_scale='Viridis',
                           range_color=(0, 100000),
                           mapbox_style="carto-positron",
                           zoom=2, center= {'lat': 37.0902, 'lon':-95.7129},
                           opacity=0.6,
                           labels={'may2020_empl'})


fig.update_layout(margin={"r":0,"t":0,"l":0,"b":0})
fig.show()

 

 

 

 

 

Plotly animation

 

 

covid 19

https://www.kaggle.com/datasets/gauravduttakiit/covid-19

 

In [11]:

df_ani = pd.read_csv('us_simplified.csv')
df_ani.head(10)

 

Out[11]:

	Date	Admin2	Province/State	Confirmed	Deaths	Country/Region
0	2020-01-22	Autauga	Alabama	0	0	US
1	2020-01-23	Autauga	Alabama	0	0	US
2	2020-01-24	Autauga	Alabama	0	0	US
3	2020-01-25	Autauga	Alabama	0	0	US
4	2020-01-26	Autauga	Alabama	0	0	US
5	2020-01-27	Autauga	Alabama	0	0	US
6	2020-01-28	Autauga	Alabama	0	0	US
7	2020-01-29	Autauga	Alabama	0	0	US
8	2020-01-30	Autauga	Alabama	0	0	US
9	2020-01-31	Autauga	Alabama	0	0	US

 

In [12]:

df_ani.isnull().sum()

 

Out[12]:

Date                 0
Admin2            4896
Province/State       0
Confirmed            0
Deaths               0
Country/Region       0
dtype: int64

 

In [13]:

df_ani_updated = df_ani.dropna()

 

In [14]:

df_ani_updated['Province/State'].unique()

 

Out[14]:

array(['Alabama', 'Alaska', 'Arizona', 'Arkansas', 'California',
       'Colorado', 'Connecticut', 'Delaware', 'District of Columbia',
       'Florida', 'Georgia', 'Hawaii', 'Idaho', 'Illinois', 'Indiana',
       'Iowa', 'Kansas', 'Kentucky', 'Louisiana', 'Maine', 'Maryland',
       'Massachusetts', 'Michigan', 'Minnesota', 'Mississippi',
       'Missouri', 'Montana', 'Nebraska', 'Nevada', 'New Hampshire',
       'New Jersey', 'New Mexico', 'New York', 'North Carolina',
       'North Dakota', 'Ohio', 'Oklahoma', 'Oregon', 'Pennsylvania',
       'Puerto Rico', 'Rhode Island', 'South Carolina', 'South Dakota',
       'Tennessee', 'Texas', 'Utah', 'Vermont', 'Virginia', 'Washington',
       'West Virginia', 'Wisconsin', 'Wyoming'], dtype=object)

 

In [15]:

county_search = pd.DataFrame(df_ani_updated.groupby('Province/State')['Admin2'].unique())
county_search.reset_index(inplace=True)
county_search.head()

 

Out[15]:

	Province/State	Admin2
0	Alabama	[Autauga, Baldwin, Barbour, Bibb, Blount, Bull...
1	Alaska	[Aleutians East, Aleutians West, Anchorage, Be...
2	Arizona	[Apache, Cochise, Coconino, Gila, Graham, Gree...
3	Arkansas	[Arkansas, Ashley, Baxter, Benton, Boone, Brad...
4	California	[Alameda, Alpine, Amador, Butte, Calaveras, Co...

 

In [16]:

county_search[county_search['Province/State']=='New York']['Admin2']

 

Out[16]:

32    [Albany, Allegany, Bronx, Broome, Cattaraugus,...
Name: Admin2, dtype: object

 

In [17]:

county_search[county_search['Province/State']=='New Jersey']['Admin2']

 

Out[17]:

30    [Atlantic, Bergen, Burlington, Camden, Cape Ma...
Name: Admin2, dtype: object

 

In [18]:

scope = ['Texas', 'New Jersey']
df_new = df_ani_updated[df_ani_updated['Province/State'].isin(scope)]

 

In [19]:

# 확인 하고 싶은 지역 
scope_county = ['Anderson', 'Andrews', 'Angelina', 'Aransas', 'Atlantic', 'Bergen', 'Burlington', 'Camden']
df_county = df_new[df_new['Admin2'].isin(scope_county)]

 

In [20]:

df_county.head(10)

 

Out[20]:

	Date	Admin2	Province/State	Confirmed	Deaths	Country/Region
1504704	2020-01-22	Atlantic	New Jersey	0	0	US
1504705	2020-01-23	Atlantic	New Jersey	0	0	US
1504706	2020-01-24	Atlantic	New Jersey	0	0	US
1504707	2020-01-25	Atlantic	New Jersey	0	0	US
1504708	2020-01-26	Atlantic	New Jersey	0	0	US
1504709	2020-01-27	Atlantic	New Jersey	0	0	US
1504710	2020-01-28	Atlantic	New Jersey	0	0	US
1504711	2020-01-29	Atlantic	New Jersey	0	0	US
1504712	2020-01-30	Atlantic	New Jersey	0	0	US
1504713	2020-01-31	Atlantic	New Jersey	0	0	US

 

In [21]:

px.scatter(df_county, x='Confirmed', y='Deaths', animation_frame='Date', animation_group='Admin2', color='Province/State', 
           hover_name='Admin2', size='Confirmed', range_x=[1,100000], range_y=[1,5000], height=700)