utils directory and rpg utils added

rpg_utils.ipynb

@@ -39,7 +39,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 72,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -49,7 +49,7 @@
     "    df,\n",
     "    \"Bretagne\",\n",
     "    132.5\n",
-    "\n",
+    "    \n",
     ")"
    ]
   },

utils/rpg_utils.py

@@ -0,0 +1,29 @@
+import pandas as pd
+from fuzzywuzzy import process
+from typing import List
+
+
+def get_popular_agriculture(
+    df: pd.DataFrame,
+    region: str,
+    surface_parc: str = None,
+    groups_agri: List[str] = None,
+):  # surface en hectare
+    unique_regions = df["REGION"].unique().tolist()
+    region, _ = process.extractOne(region, unique_regions)
+    df = df[df["REGION"] == region]
+    if groups_agri != None:
+        unique_agri_group = df["LIBELLE_GROUPE_CULTURE"].unique().tolist()
+        groups_agri_new = []
+        for group_culture in groups_agri:
+            groups_agri_new.append(process.extractOne(group_culture, unique_agri_group)[0])
+        df = df[df["LIBELLE_GROUPE_CULTURE"].isin(groups_agri_new)]
+    if surface_parc != None:
+        popular_cultures = df["LIBELLE_CULTURE"].value_counts().head(10).index
+        df = df[df["LIBELLE_CULTURE"].isin(popular_cultures)]
+        df["proximity"] = abs(df["SURF_PARC"] - surface_parc)
+        sorted_df = df.sort_values(by="proximity").drop(columns="proximity")
+        return popular_cultures, sorted_df[["LIBELLE_CULTURE","LIBELLE_GROUPE_CULTURE","SURF_PARC"]]
+    popular_cultures = df["LIBELLE_CULTURE"].value_counts().head(10).index
+    df = df[df["LIBELLE_CULTURE"].isin(popular_cultures)]
+    return popular_cultures, df[["LIBELLE_CULTURE","LIBELLE_GROUPE_CULTURE","SURF_PARC"]]