https://www.youtube.com/watch?v=LSgUiWVHPcg&t=22s

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.animation as manimation
import matplotlib.animation as anim

df = pd.read_csv('https://opendata.ecdc.europa.eu/covid19/casedistribution/csv/data.csv')
df.head()

	dateRep	day	month	year	cases	deaths	countriesAndTerritories	geoId	countryterritoryCode	popData2019	continentExp	Cumulative_number_for_14_days_of_COVID-19_cases_per_100000
0	14/12/2020	14	12	2020	746	6	Afghanistan	AF	AFG	38041757.0	Asia	9.013779
1	13/12/2020	13	12	2020	298	9	Afghanistan	AF	AFG	38041757.0	Asia	7.052776
2	12/12/2020	12	12	2020	113	11	Afghanistan	AF	AFG	38041757.0	Asia	6.868768
3	11/12/2020	11	12	2020	63	10	Afghanistan	AF	AFG	38041757.0	Asia	7.134266
4	10/12/2020	10	12	2020	202	16	Afghanistan	AF	AFG	38041757.0	Asia	6.968658

Cleanning Data

Nous n'allons pas utiliser toutes les données.

df = df[['dateRep', 'countriesAndTerritories', 'cases']]
df

	dateRep	countriesAndTerritories	cases
0	14/12/2020	Afghanistan	746
1	13/12/2020	Afghanistan	298
2	12/12/2020	Afghanistan	113
3	11/12/2020	Afghanistan	63
4	10/12/2020	Afghanistan	202
...	...	...	...
61895	25/03/2020	Zimbabwe	0
61896	24/03/2020	Zimbabwe	0
61897	23/03/2020	Zimbabwe	0
61898	22/03/2020	Zimbabwe	1
61899	21/03/2020	Zimbabwe	1

61900 rows × 3 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 61900 entries, 0 to 61899
Data columns (total 3 columns):
 #   Column                   Non-Null Count  Dtype 
---  ------                   --------------  ----- 
 0   dateRep                  61900 non-null  object
 1   countriesAndTerritories  61900 non-null  object
 2   cases                    61900 non-null  int64 
dtypes: int64(1), object(2)
memory usage: 1.4+ MB

df.dtypes

dateRep                    object
countriesAndTerritories    object
cases                       int64
dtype: object

df['date'] = pd.to_datetime(df['dateRep'], dayfirst=True)
df

	dateRep	countriesAndTerritories	cases	date
0	14/12/2020	Afghanistan	746	2020-12-14
1	13/12/2020	Afghanistan	298	2020-12-13
2	12/12/2020	Afghanistan	113	2020-12-12
3	11/12/2020	Afghanistan	63	2020-12-11
4	10/12/2020	Afghanistan	202	2020-12-10
...	...	...	...	...
61895	25/03/2020	Zimbabwe	0	2020-03-25
61896	24/03/2020	Zimbabwe	0	2020-03-24
61897	23/03/2020	Zimbabwe	0	2020-03-23
61898	22/03/2020	Zimbabwe	1	2020-03-22
61899	21/03/2020	Zimbabwe	1	2020-03-21

61900 rows × 4 columns

Supprimer la colonne dateRep

df = df.drop(columns = ['dateRep'])
df

	countriesAndTerritories	cases	date
0	Afghanistan	746	2020-12-14
1	Afghanistan	298	2020-12-13
2	Afghanistan	113	2020-12-12
3	Afghanistan	63	2020-12-11
4	Afghanistan	202	2020-12-10
...	...	...	...
61895	Zimbabwe	0	2020-03-25
61896	Zimbabwe	0	2020-03-24
61897	Zimbabwe	0	2020-03-23
61898	Zimbabwe	1	2020-03-22
61899	Zimbabwe	1	2020-03-21

61900 rows × 3 columns

Calculer les cumules des cases

df['total_cases'] = df.sort_values('date').groupby('countriesAndTerritories').cumsum().sort_index()
df

	countriesAndTerritories	cases	date	total_cases
0	Afghanistan	746	2020-12-14	49273
1	Afghanistan	298	2020-12-13	48527
2	Afghanistan	113	2020-12-12	48229
3	Afghanistan	63	2020-12-11	48116
4	Afghanistan	202	2020-12-10	48053
...	...	...	...	...
61895	Zimbabwe	0	2020-03-25	2
61896	Zimbabwe	0	2020-03-24	2
61897	Zimbabwe	0	2020-03-23	2
61898	Zimbabwe	1	2020-03-22	2
61899	Zimbabwe	1	2020-03-21	1

61900 rows × 4 columns

Changer de nom de la colonne Countries and Territories

df = df[['date', 'countriesAndTerritories', 'total_cases']]
df = df.rename(columns={'countriesAndTerritories': 'country'})
df

	date	country	total_cases
0	2020-12-14	Afghanistan	49273
1	2020-12-13	Afghanistan	48527
2	2020-12-12	Afghanistan	48229
3	2020-12-11	Afghanistan	48116
4	2020-12-10	Afghanistan	48053
...	...	...	...
61895	2020-03-25	Zimbabwe	2
61896	2020-03-24	Zimbabwe	2
61897	2020-03-23	Zimbabwe	2
61898	2020-03-22	Zimbabwe	2
61899	2020-03-21	Zimbabwe	1

61900 rows × 3 columns

Changer la colonne Country aux noms de pays en utilisant la fonction pivot_table

df = pd.pivot_table(df, index=['date'], columns=['country'], values=['total_cases'])
df

	total_cases
country	Afghanistan	Albania	Algeria	Andorra	Angola	Anguilla	Antigua_and_Barbuda	Argentina	Armenia	Aruba	...	Uruguay	Uzbekistan	Vanuatu	Venezuela	Vietnam	Wallis_and_Futuna	Western_Sahara	Yemen	Zambia	Zimbabwe
date
2019-12-31	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-01	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-02	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-03	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-04	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2020-12-10	48053.0	45188.0	90014.0	7162.0	15804.0	10.0	146.0	1475222.0	145240.0	4996.0	...	8104.0	74498.0	1.0	105852.0	1381.0	3.0	766.0	2079.0	18062.0	11007.0
2020-12-11	48116.0	46061.0	90579.0	7190.0	15925.0	10.0	146.0	1482216.0	146317.0	5011.0	...	8487.0	74664.0	1.0	106280.0	1385.0	3.0	766.0	2081.0	18091.0	11081.0
2020-12-12	48229.0	46863.0	91121.0	7236.0	16061.0	10.0	147.0	1489328.0	147312.0	5031.0	...	8849.0	74811.0	1.0	106715.0	1391.0	3.0	766.0	2082.0	18161.0	11162.0
2020-12-13	48527.0	47742.0	91638.0	7288.0	16161.0	10.0	148.0	1494602.0	148325.0	5044.0	...	9180.0	74956.0	1.0	106715.0	1395.0	3.0	766.0	2083.0	18217.0	11219.0
2020-12-14	49273.0	48530.0	92102.0	7338.0	16188.0	10.0	148.0	1498160.0	148682.0	5049.0	...	9708.0	75094.0	1.0	107177.0	1397.0	3.0	766.0	2083.0	18274.0	11246.0

350 rows × 214 columns

Checking the columns

df.columns

MultiIndex([('total_cases',         'Afghanistan'),
            ('total_cases',             'Albania'),
            ('total_cases',             'Algeria'),
            ('total_cases',             'Andorra'),
            ('total_cases',              'Angola'),
            ('total_cases',            'Anguilla'),
            ('total_cases', 'Antigua_and_Barbuda'),
            ('total_cases',           'Argentina'),
            ('total_cases',             'Armenia'),
            ('total_cases',               'Aruba'),
            ...
            ('total_cases',             'Uruguay'),
            ('total_cases',          'Uzbekistan'),
            ('total_cases',             'Vanuatu'),
            ('total_cases',           'Venezuela'),
            ('total_cases',             'Vietnam'),
            ('total_cases',   'Wallis_and_Futuna'),
            ('total_cases',      'Western_Sahara'),
            ('total_cases',               'Yemen'),
            ('total_cases',              'Zambia'),
            ('total_cases',            'Zimbabwe')],
           names=[None, 'country'], length=214)

Supprimer le nom de l'index

df.index.name = None
df.columns = [col[1] for col in df.columns]
df

	Afghanistan	Albania	Algeria	Andorra	Angola	Anguilla	Antigua_and_Barbuda	Argentina	Armenia	Aruba	...	Uruguay	Uzbekistan	Vanuatu	Venezuela	Vietnam	Wallis_and_Futuna	Western_Sahara	Yemen	Zambia	Zimbabwe
2019-12-31	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-01	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-02	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-03	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
2020-01-04	0.0	NaN	0.0	NaN	NaN	NaN	NaN	NaN	0.0	NaN	...	NaN	NaN	NaN	NaN	0.0	NaN	NaN	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2020-12-10	48053.0	45188.0	90014.0	7162.0	15804.0	10.0	146.0	1475222.0	145240.0	4996.0	...	8104.0	74498.0	1.0	105852.0	1381.0	3.0	766.0	2079.0	18062.0	11007.0
2020-12-11	48116.0	46061.0	90579.0	7190.0	15925.0	10.0	146.0	1482216.0	146317.0	5011.0	...	8487.0	74664.0	1.0	106280.0	1385.0	3.0	766.0	2081.0	18091.0	11081.0
2020-12-12	48229.0	46863.0	91121.0	7236.0	16061.0	10.0	147.0	1489328.0	147312.0	5031.0	...	8849.0	74811.0	1.0	106715.0	1391.0	3.0	766.0	2082.0	18161.0	11162.0
2020-12-13	48527.0	47742.0	91638.0	7288.0	16161.0	10.0	148.0	1494602.0	148325.0	5044.0	...	9180.0	74956.0	1.0	106715.0	1395.0	3.0	766.0	2083.0	18217.0	11219.0
2020-12-14	49273.0	48530.0	92102.0	7338.0	16188.0	10.0	148.0	1498160.0	148682.0	5049.0	...	9708.0	75094.0	1.0	107177.0	1397.0	3.0	766.0	2083.0	18274.0	11246.0

350 rows × 214 columns

Remplacer la valeur NaN par 0

df = df.fillna(0).astype(int)
df

	Afghanistan	Albania	Algeria	Andorra	Angola	Anguilla	Antigua_and_Barbuda	Argentina	Armenia	Aruba	...	Uruguay	Uzbekistan	Vanuatu	Venezuela	Vietnam	Wallis_and_Futuna	Western_Sahara	Yemen	Zambia	Zimbabwe
2019-12-31	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-01	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-02	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-03	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-04	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2020-12-10	48053	45188	90014	7162	15804	10	146	1475222	145240	4996	...	8104	74498	1	105852	1381	3	766	2079	18062	11007
2020-12-11	48116	46061	90579	7190	15925	10	146	1482216	146317	5011	...	8487	74664	1	106280	1385	3	766	2081	18091	11081
2020-12-12	48229	46863	91121	7236	16061	10	147	1489328	147312	5031	...	8849	74811	1	106715	1391	3	766	2082	18161	11162
2020-12-13	48527	47742	91638	7288	16161	10	148	1494602	148325	5044	...	9180	74956	1	106715	1395	3	766	2083	18217	11219
2020-12-14	49273	48530	92102	7338	16188	10	148	1498160	148682	5049	...	9708	75094	1	107177	1397	3	766	2083	18274	11246

350 rows × 214 columns

Supprimer la colonne Cases_on_an_international_conveyance_Japan

Cases_on_an_international_conveyance_Japan: c'est un bateau qui a été considéré comme un pays

df['Cases_on_an_international_conveyance_Japan']

2019-12-31    0
2020-01-01    0
2020-01-02    0
2020-01-03    0
2020-01-04    0
             ..
2020-12-10    0
2020-12-11    0
2020-12-12    0
2020-12-13    0
2020-12-14    0
Name: Cases_on_an_international_conveyance_Japan, Length: 350, dtype: int32

df = df.drop(columns=['Cases_on_an_international_conveyance_Japan'])
df

	Afghanistan	Albania	Algeria	Andorra	Angola	Anguilla	Antigua_and_Barbuda	Argentina	Armenia	Aruba	...	Uruguay	Uzbekistan	Vanuatu	Venezuela	Vietnam	Wallis_and_Futuna	Western_Sahara	Yemen	Zambia	Zimbabwe
2019-12-31	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-01	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-02	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-03	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-04	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2020-12-10	48053	45188	90014	7162	15804	10	146	1475222	145240	4996	...	8104	74498	1	105852	1381	3	766	2079	18062	11007
2020-12-11	48116	46061	90579	7190	15925	10	146	1482216	146317	5011	...	8487	74664	1	106280	1385	3	766	2081	18091	11081
2020-12-12	48229	46863	91121	7236	16061	10	147	1489328	147312	5031	...	8849	74811	1	106715	1391	3	766	2082	18161	11162
2020-12-13	48527	47742	91638	7288	16161	10	148	1494602	148325	5044	...	9180	74956	1	106715	1395	3	766	2083	18217	11219
2020-12-14	49273	48530	92102	7338	16188	10	148	1498160	148682	5049	...	9708	75094	1	107177	1397	3	766	2083	18274	11246

350 rows × 213 columns

Remplacer le '_' par l'espace ' '

df.columns = [col.replace('_', ' ') for col in df.columns]
df

	Afghanistan	Albania	Algeria	Andorra	Angola	Anguilla	Antigua and Barbuda	Argentina	Armenia	Aruba	...	Uruguay	Uzbekistan	Vanuatu	Venezuela	Vietnam	Wallis and Futuna	Western Sahara	Yemen	Zambia	Zimbabwe
2019-12-31	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-01	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-02	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-03	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
2020-01-04	0	0	0	0	0	0	0	0	0	0	...	0	0	0	0	0	0	0	0	0	0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
2020-12-10	48053	45188	90014	7162	15804	10	146	1475222	145240	4996	...	8104	74498	1	105852	1381	3	766	2079	18062	11007
2020-12-11	48116	46061	90579	7190	15925	10	146	1482216	146317	5011	...	8487	74664	1	106280	1385	3	766	2081	18091	11081
2020-12-12	48229	46863	91121	7236	16061	10	147	1489328	147312	5031	...	8849	74811	1	106715	1391	3	766	2082	18161	11162
2020-12-13	48527	47742	91638	7288	16161	10	148	1494602	148325	5044	...	9180	74956	1	106715	1395	3	766	2083	18217	11219
2020-12-14	49273	48530	92102	7338	16188	10	148	1498160	148682	5049	...	9708	75094	1	107177	1397	3	766	2083	18274	11246

350 rows × 213 columns

Nous allons éditer seulement les 10e pays

country_reserved = set()
for index, row in df.iterrows():
    country_reserved |= set(row[row > 0].sort_values(ascending=False).head(10).index)
df = df[list(country_reserved)]

df.shape

(350, 30)

Generer la Video

#!pip install bar-chart-race

import bar_chart_race as bcr

bcr.bar_chart_race(
    df=df,
    filename='video.mp4',
    n_bars=10,
    period_fmt='%B %d, %Y',
    title='COVID-19 Confirmed Cases by Country'
)

C:\Users\Pb\anaconda3\envs\Franckeale04\lib\site-packages\bar_chart_race\_make_chart.py:286: UserWarning: FixedFormatter should only be used together with FixedLocator
  ax.set_yticklabels(self.df_values.columns)
C:\Users\Pb\anaconda3\envs\Franckeale04\lib\site-packages\bar_chart_race\_make_chart.py:287: UserWarning: FixedFormatter should only be used together with FixedLocator
  ax.set_xticklabels([max_val] * len(ax.get_xticks()))

import matplotlib.animation as manimation; manimation.writers.list()

['pillow', 'ffmpeg', 'ffmpeg_file', 'html']