From 56202a5cccf0e0ef5284ca2905bd48c6fe59adb0 Mon Sep 17 00:00:00 2001
From: Maxence Larrieu <m@larri.eu>
Date: Wed, 14 Feb 2024 17:03:57 +0100
Subject: [PATCH] add datacite clients uga
---
.../all_datacite_clients_for_uga.csv | 0
1-enrich-with-datacite/concatenate-enrich-dois.py | 7 ++++++-
2-produce-graph/pie-datacite-client.py | 1 -
3 files changed, 6 insertions(+), 2 deletions(-)
rename 2-produce-graph/all_datacite_clients.csv => 1-enrich-with-datacite/all_datacite_clients_for_uga.csv (100%)
diff --git a/2-produce-graph/all_datacite_clients.csv b/1-enrich-with-datacite/all_datacite_clients_for_uga.csv
similarity index 100%
rename from 2-produce-graph/all_datacite_clients.csv
rename to 1-enrich-with-datacite/all_datacite_clients_for_uga.csv
diff --git a/1-enrich-with-datacite/concatenate-enrich-dois.py b/1-enrich-with-datacite/concatenate-enrich-dois.py
index 78810fb..08f4529 100644
--- a/1-enrich-with-datacite/concatenate-enrich-dois.py
+++ b/1-enrich-with-datacite/concatenate-enrich-dois.py
@@ -52,10 +52,15 @@ for doi in dois : #[:300]
temp_rows.append(selected_md) ## ajouter ce dictionnaire à une liste
print(f"\tadded\t\t{doi}")
-
+## if new datasets has been founded
if temp_rows :
df_fresh = pd.DataFrame(temp_rows)
df_out = pd.concat([df_old, df_fresh], ignore_index=True)
df_out.to_csv("../dois-uga.csv", index = False)
print(f"\n\nnb of doi exported \t{len(df_out)}")
+ ## output another csv with datacite client and number of datasets
+ df_client_raw = df_out["client"].value_counts()
+ df_client_raw.to_csv("all_datacite_clients_for_uga.csv")
+
+
diff --git a/2-produce-graph/pie-datacite-client.py b/2-produce-graph/pie-datacite-client.py
index 0b4f7a3..7665d0a 100644
--- a/2-produce-graph/pie-datacite-client.py
+++ b/2-produce-graph/pie-datacite-client.py
@@ -5,7 +5,6 @@ df = my_fct.load_and_treat_csv()
#print(df.columns)
df_client_raw = df["client"].value_counts()
-df_client_raw.to_csv("all_datacite_clients.csv")
## regroup small values in "other"
treshold = 20
--
GitLab