Skip to content
Snippets Groups Projects
Commit e8b7601a authored by Elias Chetouane's avatar Elias Chetouane
Browse files

Mise à jour suppression des dois de version. Version fonctionnelle.

parent 0f1c52ce
No related branches found
No related tags found
1 merge request!3Prise en compte des relations des jeux de données, versions, jeux identiques...
...@@ -56,14 +56,23 @@ for doi in dois : #[:300] ...@@ -56,14 +56,23 @@ for doi in dois : #[:300]
## if new datasets has been founded ## if new datasets has been founded
if temp_rows : if temp_rows :
df_fresh = pd.DataFrame(temp_rows) df_fresh = pd.DataFrame(temp_rows)
i_to_drop = []
dois_added = list(df_old["doi"])
to_del = []
for i in range(0, len(df_fresh)): for i in range(0, len(df_fresh)):
result = my_functions.get_origin_version(df_fresh.loc[df_fresh.index[i], "doi"]) result = my_functions.get_origin_version(df_fresh.loc[df_fresh.index[i], "doi"])
if result[0] is in df_old["doi"]: df_fresh.drop(df_fresh.index[i]) if result[0] not in dois_added:
else: dois_added.append(result[0])
df_fresh.loc[df_fresh.index[i], "doi"] = result[0] df_fresh.loc[df_fresh.index[i], "doi"] = result[0]
df_fresh.loc[df_fresh.index[i], "relation_nbInstances"] = result[1] df_fresh.loc[df_fresh.index[i], "relation_nbInstances"] = result[1]
df_fresh.loc[df_fresh.index[i], "relation_nbCitation"] = result[2] df_fresh.loc[df_fresh.index[i], "relation_nbCitation"] = result[2]
else:
to_del.append(i)
df_fresh.drop(to_del, inplace=True)
print("Nombre de dois supprimés : " + str(len(to_del)))
print("Nb dois a garder : " + str(len(dois_added)))
df_concat = pd.concat([df_old, df_fresh], ignore_index=True) df_concat = pd.concat([df_old, df_fresh], ignore_index=True)
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment