diff --git a/0-collect-data/datacite.py b/0-collect-data/datacite.py
index 5218822b3aba3fc349424c2550eb411e4d34316f..5d9f3cdcd87a81a7f077278eaf97b7b489f5e312 100644
--- a/0-collect-data/datacite.py
+++ b/0-collect-data/datacite.py
@@ -4,6 +4,7 @@
"""
## todo
- recherche par affiliation contributeurs ?
+- v2 : périmètre UGA : ajouter les ROR des unités, des établissements/laboratoires associés (par exemple Grenoble INP)
## Documentation
* Doc générale API Datacite : https://support.datacite.org/docs/api
diff --git a/0-collect-data/rdg.py b/0-collect-data/rdg.py
index 1f1e9e717a2de5e5307851e0db2d727322239cd8..84ec29903104abb34d677bf159212b96f9f03a04 100644
--- a/0-collect-data/rdg.py
+++ b/0-collect-data/rdg.py
@@ -75,14 +75,12 @@ for url in urls:
# on supprime les doublons
-for i in dois:
- while(dois.count(i) > 1):
- dois.remove(i)
+unique_dois = list(set(dois))
-print("Nombre de dois différents trouvés : " + str(len(dois)))
+print("Nombre de dois différents trouvés : " + str(len(unique_dois)))
# exporter la liste de DOI au format txt
with open("rdg-dois.txt", 'w') as f :
- [f.write(f"{line[4:]}\n") for line in dois] # [4:] pour retirer "doi:" au début de chaque ligne
+ [f.write(f"{line[4:]}\n") for line in unique_dois] # [4:] pour retirer "doi:" au début de chaque ligne
diff --git a/0-collect-data/z-datacite-demo.ipynb b/0-collect-data/z-datacite-demo.ipynb
index 1de20a75f06aa67ceec513dcb92c430e38623ab2..b17617f26a197950d2c6c402ebff8e87a5c2be88 100644
--- a/0-collect-data/z-datacite-demo.ipynb
+++ b/0-collect-data/z-datacite-demo.ipynb
@@ -17,7 +17,7 @@
},
{
"cell_type": "code",
- "execution_count": 15,
+ "execution_count": 26,
"id": "d229201d-4e79-40a8-9472-9ea46b344b1c",
"metadata": {},
"outputs": [],
@@ -27,7 +27,7 @@
},
{
"cell_type": "code",
- "execution_count": 16,
+ "execution_count": 27,
"id": "7ce19b89-d5b7-4dbe-9fab-a15a81b42078",
"metadata": {},
"outputs": [],
@@ -43,7 +43,7 @@
},
{
"cell_type": "code",
- "execution_count": 17,
+ "execution_count": 28,
"id": "ec73be41-21df-4448-b58e-e21306f6b9fa",
"metadata": {},
"outputs": [
@@ -65,10 +65,10 @@
"authors = []\n",
"\n",
"# boucler pour ajouter les informations relatives à chaque dépôt\n",
- "num_dois = results[\"data\"]\n",
- "nb_dois = len(num_dois)\n",
+ "all_md_list = results[\"data\"]\n",
+ "nb_dois = len(all_md_list)\n",
"\n",
- "for item in num_dois :\n",
+ "for item in all_md_list :\n",
" doi = item[\"id\"]\n",
" # si l'identifiant n'est pas un doi, on ne le prend pas\n",
" if item.get(\"type\") != \"dois\":\n",
@@ -91,64 +91,183 @@
},
{
"cell_type": "code",
- "execution_count": 19,
+ "execution_count": 29,
"id": "e0722b5b-0059-4842-8e8a-2125239a7b7d",
"metadata": {},
"outputs": [
{
- "name": "stdout",
- "output_type": "stream",
- "text": [
- " DOI \\\n",
- "0 10.7280/d11h3x \n",
- "1 10.7280/d1mm37 \n",
- "2 10.7280/d1595v \n",
- "3 10.7280/d1667w \n",
- "4 10.7280/d1b114 \n",
- ".. ... \n",
- "137 10.6084/m9.figshare.23488967 \n",
- "138 10.18150/wyyjk6 \n",
- "139 10.13127/efsm20 \n",
- "140 10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa \n",
- "141 10.5285/634ee206-258f-4b47-9237-efff4ef9eedd \n",
- "\n",
- " Titre Date \\\n",
- "0 Annual Ice Velocity of the Greenland Ice Sheet... 2019-03-29T12:53:36Z \n",
- "1 Annual Ice Velocity of the Greenland Ice Sheet... 2018-12-14T09:39:45Z \n",
- "2 Annual Ice Velocity of the Greenland Ice Sheet... 2019-03-29T10:37:23Z \n",
- "3 Greenland Marine-Terminating Glacier Retreat Data 2020-12-01T18:09:19Z \n",
- "4 Dataset for: Fast retreat of Pope, Smith, and ... 2021-11-01T23:46:08Z \n",
- ".. ... ... \n",
- "137 Additional file 1 of 3DVizSNP: a tool for rapi... 2023-06-10T03:21:52Z \n",
- "138 Estimates for recombination coefficients from ... 2022-04-21T14:17:28Z \n",
- "139 European Fault-Source Model 2020 (EFSM20): onl... 2022-10-30T16:28:46Z \n",
- "140 Ice radar data from Little Dome C, Antarctica,... 2022-03-04T09:26:18Z \n",
- "141 Polarimetric ApRES data on a profile across Do... 2021-09-16T11:17:15Z \n",
- "\n",
- " Auteurs \n",
- "0 [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be... \n",
- "1 [Mouginot, Jeremie, Rignot, Eric, Millan, Roma... \n",
- "2 [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be... \n",
- "3 [Wood, Michael, Rignot, Eric, Bjørk, Anders, V... \n",
- "4 [Milillo, Pietro, Rignot, Eric, Rizzoli, Paola... \n",
- ".. ... \n",
- "137 [Sierk, Michael, Ratnayake, Shashikala, Wagle,... \n",
- "138 [Sakowski, Konrad, Borowik, Lukasz, Rochat, Né... \n",
- "139 [Basili, Roberto, Danciu, Laurentiu, Beauval, ... \n",
- "140 [Mulvaney, Robert, King, Edward, Martin, Carlo... \n",
- "141 [Corr, Hugh, Ritz, Catherine, Martin, Carlos] \n",
- "\n",
- "[142 rows x 4 columns]\n"
- ]
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>DOI</th>\n",
+ " <th>Titre</th>\n",
+ " <th>Date</th>\n",
+ " <th>Auteurs</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>10.7280/d11h3x</td>\n",
+ " <td>Annual Ice Velocity of the Greenland Ice Sheet...</td>\n",
+ " <td>2019-03-29T12:53:36Z</td>\n",
+ " <td>[Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>10.7280/d1mm37</td>\n",
+ " <td>Annual Ice Velocity of the Greenland Ice Sheet...</td>\n",
+ " <td>2018-12-14T09:39:45Z</td>\n",
+ " <td>[Mouginot, Jeremie, Rignot, Eric, Millan, Roma...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>10.7280/d1667w</td>\n",
+ " <td>Greenland Marine-Terminating Glacier Retreat Data</td>\n",
+ " <td>2020-12-01T18:09:19Z</td>\n",
+ " <td>[Wood, Michael, Rignot, Eric, Bjørk, Anders, V...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>10.7280/d1595v</td>\n",
+ " <td>Annual Ice Velocity of the Greenland Ice Sheet...</td>\n",
+ " <td>2019-03-29T10:37:23Z</td>\n",
+ " <td>[Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>10.7280/d1b114</td>\n",
+ " <td>Dataset for: Fast retreat of Pope, Smith, and ...</td>\n",
+ " <td>2021-11-01T23:46:08Z</td>\n",
+ " <td>[Milillo, Pietro, Rignot, Eric, Rizzoli, Paola...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>137</th>\n",
+ " <td>10.6084/m9.figshare.23488967</td>\n",
+ " <td>Additional file 1 of 3DVizSNP: a tool for rapi...</td>\n",
+ " <td>2023-06-10T03:21:52Z</td>\n",
+ " <td>[Sierk, Michael, Ratnayake, Shashikala, Wagle,...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>138</th>\n",
+ " <td>10.18150/wyyjk6</td>\n",
+ " <td>Estimates for recombination coefficients from ...</td>\n",
+ " <td>2022-04-21T14:17:28Z</td>\n",
+ " <td>[Sakowski, Konrad, Borowik, Lukasz, Rochat, Né...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>139</th>\n",
+ " <td>10.13127/efsm20</td>\n",
+ " <td>European Fault-Source Model 2020 (EFSM20): onl...</td>\n",
+ " <td>2022-10-30T16:28:46Z</td>\n",
+ " <td>[Basili, Roberto, Danciu, Laurentiu, Beauval, ...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>140</th>\n",
+ " <td>10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa</td>\n",
+ " <td>Ice radar data from Little Dome C, Antarctica,...</td>\n",
+ " <td>2022-03-04T09:26:18Z</td>\n",
+ " <td>[Mulvaney, Robert, King, Edward, Martin, Carlo...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>141</th>\n",
+ " <td>10.5285/634ee206-258f-4b47-9237-efff4ef9eedd</td>\n",
+ " <td>Polarimetric ApRES data on a profile across Do...</td>\n",
+ " <td>2021-09-16T11:17:15Z</td>\n",
+ " <td>[Corr, Hugh, Ritz, Catherine, Martin, Carlos]</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>142 rows × 4 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " DOI \\\n",
+ "0 10.7280/d11h3x \n",
+ "1 10.7280/d1mm37 \n",
+ "2 10.7280/d1667w \n",
+ "3 10.7280/d1595v \n",
+ "4 10.7280/d1b114 \n",
+ ".. ... \n",
+ "137 10.6084/m9.figshare.23488967 \n",
+ "138 10.18150/wyyjk6 \n",
+ "139 10.13127/efsm20 \n",
+ "140 10.5285/3ea504d8-41c2-40dc-86dc-284c341badaa \n",
+ "141 10.5285/634ee206-258f-4b47-9237-efff4ef9eedd \n",
+ "\n",
+ " Titre Date \\\n",
+ "0 Annual Ice Velocity of the Greenland Ice Sheet... 2019-03-29T12:53:36Z \n",
+ "1 Annual Ice Velocity of the Greenland Ice Sheet... 2018-12-14T09:39:45Z \n",
+ "2 Greenland Marine-Terminating Glacier Retreat Data 2020-12-01T18:09:19Z \n",
+ "3 Annual Ice Velocity of the Greenland Ice Sheet... 2019-03-29T10:37:23Z \n",
+ "4 Dataset for: Fast retreat of Pope, Smith, and ... 2021-11-01T23:46:08Z \n",
+ ".. ... ... \n",
+ "137 Additional file 1 of 3DVizSNP: a tool for rapi... 2023-06-10T03:21:52Z \n",
+ "138 Estimates for recombination coefficients from ... 2022-04-21T14:17:28Z \n",
+ "139 European Fault-Source Model 2020 (EFSM20): onl... 2022-10-30T16:28:46Z \n",
+ "140 Ice radar data from Little Dome C, Antarctica,... 2022-03-04T09:26:18Z \n",
+ "141 Polarimetric ApRES data on a profile across Do... 2021-09-16T11:17:15Z \n",
+ "\n",
+ " Auteurs \n",
+ "0 [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be... \n",
+ "1 [Mouginot, Jeremie, Rignot, Eric, Millan, Roma... \n",
+ "2 [Wood, Michael, Rignot, Eric, Bjørk, Anders, V... \n",
+ "3 [Mouginot, Jeremie, Rignot, Eric, Scheuchl, Be... \n",
+ "4 [Milillo, Pietro, Rignot, Eric, Rizzoli, Paola... \n",
+ ".. ... \n",
+ "137 [Sierk, Michael, Ratnayake, Shashikala, Wagle,... \n",
+ "138 [Sakowski, Konrad, Borowik, Lukasz, Rochat, Né... \n",
+ "139 [Basili, Roberto, Danciu, Laurentiu, Beauval, ... \n",
+ "140 [Mulvaney, Robert, King, Edward, Martin, Carlo... \n",
+ "141 [Corr, Hugh, Ritz, Catherine, Martin, Carlos] \n",
+ "\n",
+ "[142 rows x 4 columns]"
+ ]
+ },
+ "execution_count": 29,
+ "metadata": {},
+ "output_type": "execute_result"
}
],
"source": [
"# construction du DataFrame\n",
"df = pandas.DataFrame({'DOI':dois, 'Titre':titles, 'Date':dates, 'Auteurs':authors})\n",
"\n",
- "print(df)\n",
- "df.to_csv(\"z-resultats-demo-datacite.csv\")"
+ "df.to_csv(\"z-resultats-demo-datacite.csv\")\n",
+ "df"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "0308feea-2560-4e33-836a-285a65db2429",
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {