From 1b1d7e80b6896c51ce259dc9a4f7e064e97a3aeb Mon Sep 17 00:00:00 2001 From: f3525de4a1a18e7596f7a06bd19c9fc1 Date: Thu, 17 Nov 2022 10:08:10 +0000 Subject: [PATCH] Update Readme.md --- journal/Readme.md | 67 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 67 insertions(+) diff --git a/journal/Readme.md b/journal/Readme.md index 4ce9e93..48be896 100644 --- a/journal/Readme.md +++ b/journal/Readme.md @@ -201,3 +201,70 @@ data = data_raw MARKDOWN : "Une fois nos données disponibles, je vais chercher les lignes des pays nous intéressant avec la fonction `.loc()` de la bibliothèque Pandas. Une fois ces données localisées, je vais les regrouper sous forme de DataFrame afin de pouvoir les traiter." Pour avoir le `.loc()` écrire ``.loc()`` + +Nous pouvons maintenant extraire les données pour chaque pays. Pour cela, il faut tout d'abord les localiser avec la fonction `.loc()` en écrivant le code suivant : + +``` +Row_Belgium = data.loc[data['Country/Region'] == 'Belgium'] +Series_Belgium = pd.Series(data.loc[Row_Belgium.index[0]], name = 'Belgium', dtype = int) + +Row_China = data.loc[(data['Country/Region'] == 'China') & (data['Province/State'] != 'Hong Kong')] +Series_China_Total = Row_China.sum() + +Row_HongKong = data.loc[data['Province/State'] == 'Hong Kong'] +Series_HongKong = pd.Series(data.loc[Row_HongKong.index[0]], name = 'HongKong', dtype = int) + +Row_France = data.loc[(data['Province/State'].isna()) & (data['Country/Region'] == 'France')] +Series_France = pd.Series(data.loc[Row_France.index[0]], name = 'France', dtype = int) + +Row_Germany = data.loc[data['Country/Region'] == 'Germany'] +Series_Germany = pd.Series(data.loc[Row_Germany.index[0]], name = 'Germany', dtype = int) + +Row_Iran = data.loc[data['Country/Region'] == 'Iran'] +Series_Iran = pd.Series(data.loc[Row_Iran.index[0]], name = 'Iran', dtype = int) + +Row_Italy = data.loc[data['Country/Region'] == 'Italy'] +Series_Italy = pd.Series(data.loc[Row_Italy.index[0]], name = 'Italy', dtype = int) + +Row_Japan = data.loc[data['Country/Region'] == 'Japan'] +Series_Japan = pd.Series(data.loc[Row_Japan.index[0]], name = 'Japan', dtype = int) + +Row_KoreaSouth = data.loc[data['Country/Region'] == 'Korea, South'] +Series_KoreaSouth = pd.Series(data.loc[Row_KoreaSouth.index[0]], name = 'Korea, South', dtype = int) + +Row_Netherlands = data.loc[(data['Province/State'].isna()) & (data['Country/Region'] == 'Netherlands')] +Series_Netherlands = pd.Series(data.loc[Row_Netherlands.index[0]], name = 'Netherlands', dtype = int) + +Row_Portugal = data.loc[data['Country/Region'] == 'Portugal'] +Series_Portugal = pd.Series(data.loc[Row_Portugal.index[0]], name = 'Portugal', dtype = int) + +Row_Spain = data.loc[data['Country/Region'] == 'Spain'] +Series_Spain = pd.Series(data.loc[Row_Spain.index[0]], name = 'Spain', dtype = int) + +Row_UnitedKingdom = data.loc[(data['Province/State'].isna()) & (data['Country/Region'] == 'United Kingdom')] +Series_UnitedKingdom = pd.Series(data.loc[Row_UnitedKingdom.index[0]], name = 'United Kingdom', dtype = int) + +Row_US = data.loc[data['Country/Region'] == 'US'] +Series_US = pd.Series(data.loc[Row_US.index[0]], name = 'US', dtype = int) + +frame = {'Belgium': Series_Belgium, + 'China': Series_China_Total, + 'Hong Kong': Series_HongKong, + 'France': Series_France, + 'Germany': Series_Germany, + 'Iran': Series_Iran, + 'Italy': Series_Italy, + 'Japan': Series_Japan, + 'Korea, South': Series_KoreaSouth, + 'Netherlands': Series_Netherlands, + 'Portugal': Series_Portugal, + 'Spain': Series_Spain, + 'United Kingdom': Series_UnitedKingdom, + 'US': Series_US} + +selected_data_raw = pd.DataFrame(frame) +selected_data = selected_data_raw[4:].reset_index() +selected_data = selected_data.rename(columns={'index': 'Date'}) +# display(selected_data) +``` + -- 2.18.1