Update backend/app/services/profiling_service.py

backend/app/services/profiling_service.py

@@ -1,14 +1,33 @@
+from __future__ import annotations
+
 import pandas as pd
 
+
+def _infer_type(series: pd.Series) -> str:
+    if pd.api.types.is_bool_dtype(series):
+        return "boolean"
+    if pd.api.types.is_numeric_dtype(series):
+        return "numeric"
+    return "categorical"
+
+
 def profile_dataframe(df: pd.DataFrame) -> dict:
     columns = []
+
     for col in df.columns:
-        s = df[col]
-        dtype = "numeric" if pd.api.types.is_numeric_dtype(s) else "categorical"
-        columns.append({"name": col, "inferred_type": dtype, "missing_pct": round(float(s.isna().mean()) * 100, 2), "cardinality": int(s.nunique(dropna=True))})
-    recommended = ["kmeans", "birch"]
-    if any(c["inferred_type"] == "categorical" for c in columns):
-        recommended.append("agglomerative")
-    if len(df) >= 50:
-        recommended.append("dbscan")
-    return {"columns": columns, "recommended_algorithms": recommended}
+        series = df[col]
+        columns.append(
+            {
+                "name": col,
+                "inferred_type": _infer_type(series),
+                "missing_pct": round(float(series.isna().mean() * 100), 4),
+                "cardinality": int(series.nunique(dropna=True)),
+            }
+        )
+
+    recommended_algorithms = ["kmeans", "birch", "agglomerative", "dbscan"]
+
+    return {
+        "columns": columns,
+        "recommended_algorithms": recommended_algorithms,
+    }