graph last days added

2-produce-graph/all_datacite_clients.csv

+client,count
+cern.zenodo,936
+inist.sshade,468
+inist.osug,238
+figshare.ars,183
+dryad.dryad,156
+inist.resif,78
+inist.persyval,55
+rdg.prod,45
+inist.humanum,28
+figshare.sage,16
+mcdy.dohrmi,12
+rg.rg,4
+vqpf.dris,3
+tib.gfzbib,3
+iris.iris,3
+ugraz.unipub,2
+inist.epure,2
+bl.nerc,2
+tib.repod,2
+estdoi.ttu,1
+inist.omp,1
+tib.gfz,1
+edi.edi,1
+inist.opgc,1
+bl.iita,1
+ardcx.nci,1
+umass.uma,1
+crui.ingv,1
+bl.mendeley,1
+ethz.zora,1
+inist.ird,1
+inist.eost,1
+ihumi.pub,1
+tug.openlib,1

2-produce-graph/hist-last-datasets-by-client.py

+import pandas as pd, matplotlib, matplotlib.pyplot  as plt
+import z_my_functions as my_fct
+from datetime import datetime, timezone
+
+
+
+temp_date = pd.to_datetime('2024-02-01', format='%Y-%m-%d')
+
+df = my_fct.load_and_treat_csv()
+
+# sort df to the most recent
+df.sort_values(by = "registered", ascending = False, inplace = True, ignore_index = True )
+print(df.columns)
+
+## transform to date format
+df["registered_date"] = pd.to_datetime( df["registered"], errors='coerce')
+
+## age of deposit is current time - date of registration
+# df["age_of_deposit_days"] = datetime.now(timezone.utc) - df["registered_date"] ## this give a full time difference
+df["age_of_deposit_days"] = (datetime.now(timezone.utc) - df['registered_date']).dt.total_seconds() / 60 / 60 / 24
+
+
+# depot sur les 30 derniers jours
+df_last_weeks = df[ df["age_of_deposit_days"] <= 30]
+
+
+df_graph = pd.crosstab(df_last_weeks["registered"].str[5:10], df_last_weeks["client"])
+df_graph.index.rename("Day of registration", inplace = True)
+
+## ______0______ produce graphs
+
+## a set of color via plt
+### see color palett https://matplotlib.org/stable/users/explain/colors/colormaps.html
+colors = [plt.cm.Set3(i) for i in range(len(df_graph.columns))]
+
+ax = df_graph.plot(
+    kind = "bar", 
+    figsize = (10, 7),
+    stacked = True,
+    width = 0.3,
+    color = colors,
+    rot = 80
+    )
+
+
+## _______ configurer l'afichage
+ax.spines['top'].set_visible(False)
+ax.spines['right'].set_visible(False)
+ax.set_ylabel("Number of datasets", labelpad = 2)
+ax.yaxis.grid(ls=":", alpha=0.2)
+ax.tick_params(axis='both', which='major', labelsize=8)
+# plt.xlabel(None)
+
+plt.legend(reverse = False)
+
+plt.title(f"Datasets registered over the last 30 days\ndistributed by DataCite client",
+	fontsize = 18, x = 0.5, y = 1.03, alpha = 0.8)
+plt.suptitle(f"n = {len(df_last_weeks)}", fontsize = 12, x = 0.5, y = 0.89, alpha = 0.6)
+
+plt.savefig("hist-last-datasets-by-client.png")
\ No newline at end of file

2-produce-graph/pie-datacite-client.py

@@ -5,24 +5,24 @@ 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
 df_client = df_client_raw[df_client_raw > treshold]
 
 ## rework client name (eg cern.zenodo)
-clients_name = []
-for item in df_client.index :
-	short_name = item[: item.find(".")]
-	if short_name not in ["inist", "jbru"] : 
-		clients_name.append( short_name.capitalize())
-	else : 
-		clients_name.append(item)
+## used before to rework client name, but finally we used the raw datacite client eg cern.zenodo
+# clients_name = []
+# for item in df_client.index :
+# 	short_name = item[: item.find(".")]
+# 	if short_name not in ["inist", "jbru"] : 
+# 		clients_name.append( short_name.upper())
+# 	else : 
+# 		clients_name.append(item)
 
-print(clients_name)
 
 df_client["other"] = df_client_raw[df_client_raw <= treshold].sum()
-clients_name.append("other")
 
 
 # a set of color via plt
@@ -31,7 +31,7 @@ colors = [plt.cm.Set3(i) for i in range(len(df_client))]
 
 #colors = sns.color_palette('pastel')[0:len(df_client)]
 
-plt.pie(df_client, labels = clients_name, colors = colors, autopct='%.0f%%')
+plt.pie(df_client, labels = df_client.index, colors = colors, autopct='%.0f%%')
 plt.title(f"Distribution of datasets by DataCite client", fontsize = 20, x = 0.5, y = 1.03, alpha = 0.6)
 plt.suptitle(f"n = {len(df)}", fontsize = 11, x = 0.5, y = 0.90, alpha = 0.6)
 plt.savefig("pie--datacite-client.png")

README.md

-# UGA Open Research Data monitor
+# Codes for the UGA Open research data monitor
 
-Let's describe open research data produced by Grenoble Alpes University !
+view contextualized results on the website : [mlarrieu.gricad-pages.univ-grenoble-alpes.fr/open-research-data-monitor](https://mlarrieu.gricad-pages.univ-grenoble-alpes.fr/open-research-data-monitor)
 
-We name "open research data" a dataset registred with DataCite. 
-
-_work in progress_
-
-
-## Examples
-
-![](2-produce-graph/hist-evol-datasets-per-repo.png)
-
-![](2-produce-graph/hist-quantity-year-type.png)
-
-![](2-produce-graph/pie--datacite-client.png)
-
-![](2-produce-graph/pie--datacite-type.png)
 
 ## Sources
 
 (so far) 
 
-|    		|Dataset numbers| UGA perimeter  |
-|-----------|---------------|---------------|
-|RDG		|42 |contact, auteurs, producteur et contributeurs avec "UGA" OR "Grenoble" |
-|DataCite	|1247| creator et contributor avec ROR + clients & publisher		    			|
-|Zenodo		|1041|creator et contributor avec "grenoble" 						|
-|Nakala		|32 |UGA user identifiers											|
-|BSO via HAL|32 |NA 															|
-|... 		|   |
+|    		| UGA perimeter |
+|-----------|---------------|
+|RDG		|contact, auteurs, producteur et contributeurs avec "UGA" OR "Grenoble" |
+|DataCite	|creator et contributor avec ROR + clients & publisher		    		|
+|Zenodo		|creator et contributor avec "grenoble" 						|
+|Nakala		|UGA user identifiers											|
+|BSO via HAL|NA 															|
+|... 		|    |
 
 
 
 
-## Credit
+## Credits
 
 * Élias Chetouane: collecting data, program automation
 * Maxence Larrieu: collecting data, enrichment & visualisation
 
-as members of the [Cellule Data Grenoble Alpes](https://scienceouverte.univ-grenoble-alpes.fr/donnees/accompagner/cellule-data-grenoble-alpes/)
+as members of GRICAD & CDGA
\ No newline at end of file