Adaptation du graphique aux nouvelles sources #32

src/figures.py

@@ -4,13 +4,13 @@ import plotly.express as px
 import polars as pl
 
 
-def get_map_count_marches(lf):
+def get_map_count_marches(lf: pl.LazyFrame):
     lf = lf.with_columns(
         pl.col("lieuExecution_code").str.head(2).str.zfill(2).alias("Département")
     )
     lf = (
-        lf.unique(subset="uid")
-        .select(["uid", "Département"])
+        lf.select(["uid", "Département"])
+        .drop_nulls()
         .unique(subset="uid")
         .group_by("Département")
         .len("uid")
@@ -59,34 +59,56 @@ def get_barchart_sources(lf: pl.LazyFrame, type_date: str):
         "datePublicationDonnees": "publication des données",
     }
 
-    lf = lf.select("uid", type_date, "source")
+    lf = lf.select("uid", type_date, "sourceDataset")
+
     lf = lf.unique("uid")
+
+    # Rassemblement des datasets Atexo pour ne pas surcharger le graphique
+    lf = lf.with_columns(
+        pl.when(pl.col("sourceDataset").str.starts_with("atexo"))
+        .then(pl.lit("plateformes atexo"))
+        .otherwise(pl.col("sourceDataset"))
+        .alias("sourceDataset")
+    )
+
+    # Rassemblement des datasets AWS pour ne pas surcharger le graphique
+    lf = lf.with_columns(
+        pl.when(pl.col("sourceDataset").str.contains(r"aws|marches\-publics.info"))
+        .then(pl.lit("aws"))
+        .otherwise(pl.col("sourceDataset"))
+        .alias("sourceDataset")
+    )
+
     lf = lf.with_columns(pl.col(type_date).dt.year().alias("annee"))
     lf = lf.filter(
-        pl.col(type_date).is_not_null() & pl.col("annee").is_between(2018, 2025)
+        pl.col(type_date).is_not_null() & pl.col("annee").is_between(2019, 2025)
     )
-    lf = lf.sort(by=[type_date, "source"], descending=False)
     lf = lf.with_columns(pl.col(type_date).cast(pl.String).str.head(7))
-
-    lf = lf.group_by([type_date, "source"]).len()
-    lf = lf.with_columns(
-        pl.when(pl.col("source").is_null()).then(
-            pl.lit("Source inconnue").alias("source")
-        )
+    lf = (
+        lf.group_by([type_date, "sourceDataset"])
+        .len()
+        .sort(by=[type_date, "len"], descending=True)
     )
-    lf = lf.sort(by=[type_date, "source"], descending=False)
+
+    # lf = lf.with_columns(
+    #     pl.when(pl.col("sourceDataset").is_null()).then(
+    #         pl.lit("Source inconnue")).alias("sourceDataset")
+    #     )
+
+    lf = lf.sort(by=["sourceDataset"], descending=False)
     df: pl.DataFrame = lf.collect()
 
     fig = px.bar(
         df,
         x=type_date,
         y="len",
-        color="source",
+        color="sourceDataset",
         title=f"Nombre de marchés attribués par date de {labels[type_date]} et source de données",
         labels={
             "len": "Nombre de marchés",
             type_date: f"Mois de {labels[type_date]}",
-            "source": "Source de données",
+            "sourceDataset": "Source de données",
         },
     )
+
     return fig