Clean up

app.py

@@ -65,75 +65,86 @@ except Exception:
 
 
 # Searching and filtering
-def update_table(
-    hidden_df: pd.DataFrame,
-    columns: list,
+
+
+def filter_models(
+    df: pd.DataFrame,
     type_query: list,
-    precision_query: str,
     size_query: list,
+    precision_query: list,
     add_special_tokens_query: list,
     num_few_shots_query: list,
     show_deleted: bool,
     show_merges: bool,
     show_flagged: bool,
-    query: str,
-):
-    print(
-        f"Update table called with: type_query={type_query}, precision_query={precision_query}, size_query={size_query}"
-    )
-    print(f"hidden_df shape before filtering: {hidden_df.shape}")
+) -> pd.DataFrame:
+    print(f"Initial df shape: {df.shape}")
+    print(f"Initial df content:\n{df}")
 
-    filtered_df = filter_models(
-        hidden_df,
-        type_query,
-        size_query,
-        precision_query,
-        add_special_tokens_query,
-        num_few_shots_query,
-        show_deleted,
-        show_merges,
-        show_flagged,
-    )
-    print(f"filtered_df shape after filter_models: {filtered_df.shape}")
+    filtered_df = df
 
-    filtered_df = filter_queries(query, filtered_df)
-    print(f"filtered_df shape after filter_queries: {filtered_df.shape}")
+    # Model Type フィルタリング
+    type_column = "T" if "T" in df.columns else "Type_"
+    type_emoji = [t.split()[0] for t in type_query]
+    filtered_df = df[df[type_column].isin(type_emoji)]
+    print(f"After type filter: {filtered_df.shape}")
 
-    print(
-        f"Filter applied: query={query}, columns={columns}, type_query={type_query}, precision_query={precision_query}"
-    )
-    print("Filtered dataframe head:")
-    print(filtered_df.head())
+    # Precision フィルタリング
+    filtered_df = filtered_df[filtered_df["Precision"].isin(precision_query + ["Unknown", "?"])]
+    print(f"After precision filter: {filtered_df.shape}")
 
-    df = select_columns(filtered_df, columns)
-    print(f"Final df shape: {df.shape}")
-    print("Final dataframe head:")
-    print(df.head())
-    return df
+    # Model Size フィルタリング
+    if "Unknown" in size_query:
+        size_mask = filtered_df["#Params (B)"].isna() | (filtered_df["#Params (B)"] == 0)
+    else:
+        size_mask = filtered_df["#Params (B)"].apply(
+            lambda x: any(x in NUMERIC_INTERVALS[s] for s in size_query if s != "Unknown")
+        )
+    filtered_df = filtered_df[size_mask]
+    print(f"After size filter: {filtered_df.shape}")
 
+    # Add Special Tokens フィルタリング
+    filtered_df = filtered_df[filtered_df["Add Special Tokens"].isin(add_special_tokens_query + ["Unknown", "?"])]
+    print(f"After add_special_tokens filter: {filtered_df.shape}")
 
-def load_query(request: gr.Request):  # triggered only once at startup => read query parameter if it exists
-    query = request.query_params.get("query") or ""
-    return (
-        query,
-        query,
-    )  # return one for the "search_bar", one for a hidden component that triggers a reload only if value has changed
+    # Num Few Shots フィルタリング
+    filtered_df = filtered_df[
+        filtered_df["Few-shot"].astype(str).isin([str(x) for x in num_few_shots_query] + ["Unknown", "?"])
+    ]
+    print(f"After num_few_shots filter: {filtered_df.shape}")
+
+    # Show deleted models フィルタリング
+    if not show_deleted:
+        filtered_df = filtered_df[filtered_df["Available on the hub"]]
+    print(f"After show_deleted filter: {filtered_df.shape}")
+
+    print("Filtered dataframe head:")
+    print(filtered_df.head())
+    return filtered_df
 
 
 def search_table(df: pd.DataFrame, query: str) -> pd.DataFrame:
     return df[(df[AutoEvalColumn.dummy.name].str.contains(query, case=False))]
 
 
-# def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
-#     always_here_cols = [
-#         AutoEvalColumn.model_type_symbol.name,
-#         AutoEvalColumn.model.name,
-#     ]
-#     # We use COLS to maintain sorting
-#     filtered_df = df[
-#         always_here_cols + [c for c in COLS if c in df.columns and c in columns]# + [AutoEvalColumn.dummy.name]
-#     ]
-#     return filtered_df
+def filter_queries(query: str, filtered_df: pd.DataFrame):
+    """Added by Abishek"""
+    final_df = []
+    if query != "":
+        queries = [q.strip() for q in query.split(";")]
+        for _q in queries:
+            _q = _q.strip()
+            if _q != "":
+                temp_filtered_df = search_table(filtered_df, _q)
+                if len(temp_filtered_df) > 0:
+                    final_df.append(temp_filtered_df)
+        if len(final_df) > 0:
+            filtered_df = pd.concat(final_df)
+            filtered_df = filtered_df.drop_duplicates(
+                subset=[AutoEvalColumn.model.name, AutoEvalColumn.precision.name, AutoEvalColumn.revision.name]
+            )
+
+    return filtered_df
 
 
 def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
@@ -169,80 +180,59 @@ def select_columns(df: pd.DataFrame, columns: list) -> pd.DataFrame:
     return filtered_df
 
 
-def filter_queries(query: str, filtered_df: pd.DataFrame):
-    """Added by Abishek"""
-    final_df = []
-    if query != "":
-        queries = [q.strip() for q in query.split(";")]
-        for _q in queries:
-            _q = _q.strip()
-            if _q != "":
-                temp_filtered_df = search_table(filtered_df, _q)
-                if len(temp_filtered_df) > 0:
-                    final_df.append(temp_filtered_df)
-        if len(final_df) > 0:
-            filtered_df = pd.concat(final_df)
-            filtered_df = filtered_df.drop_duplicates(
-                subset=[AutoEvalColumn.model.name, AutoEvalColumn.precision.name, AutoEvalColumn.revision.name]
-            )
-
-    return filtered_df
-
-
-def filter_models(
-    df: pd.DataFrame,
+def update_table(
+    hidden_df: pd.DataFrame,
+    columns: list,
     type_query: list,
+    precision_query: str,
     size_query: list,
-    precision_query: list,
     add_special_tokens_query: list,
     num_few_shots_query: list,
     show_deleted: bool,
     show_merges: bool,
     show_flagged: bool,
-) -> pd.DataFrame:
-    print(f"Initial df shape: {df.shape}")
-    print(f"Initial df content:\n{df}")
-
-    filtered_df = df
-
-    # Model Type フィルタリング
-    type_column = "T" if "T" in df.columns else "Type_"
-    type_emoji = [t.split()[0] for t in type_query]
-    filtered_df = df[df[type_column].isin(type_emoji)]
-    print(f"After type filter: {filtered_df.shape}")
+    query: str,
+):
+    print(
+        f"Update table called with: type_query={type_query}, precision_query={precision_query}, size_query={size_query}"
+    )
+    print(f"hidden_df shape before filtering: {hidden_df.shape}")
 
-    # Precision フィルタリング
-    filtered_df = filtered_df[filtered_df["Precision"].isin(precision_query + ["Unknown", "?"])]
-    print(f"After precision filter: {filtered_df.shape}")
+    filtered_df = filter_models(
+        hidden_df,
+        type_query,
+        size_query,
+        precision_query,
+        add_special_tokens_query,
+        num_few_shots_query,
+        show_deleted,
+        show_merges,
+        show_flagged,
+    )
+    print(f"filtered_df shape after filter_models: {filtered_df.shape}")
 
-    # Model Size フィルタリング
-    if "Unknown" in size_query:
-        size_mask = filtered_df["#Params (B)"].isna() | (filtered_df["#Params (B)"] == 0)
-    else:
-        size_mask = filtered_df["#Params (B)"].apply(
-            lambda x: any(x in NUMERIC_INTERVALS[s] for s in size_query if s != "Unknown")
-        )
-    filtered_df = filtered_df[size_mask]
-    print(f"After size filter: {filtered_df.shape}")
+    filtered_df = filter_queries(query, filtered_df)
+    print(f"filtered_df shape after filter_queries: {filtered_df.shape}")
 
-    # Add Special Tokens フィルタリング
-    filtered_df = filtered_df[filtered_df["Add Special Tokens"].isin(add_special_tokens_query + ["Unknown", "?"])]
-    print(f"After add_special_tokens filter: {filtered_df.shape}")
+    print(
+        f"Filter applied: query={query}, columns={columns}, type_query={type_query}, precision_query={precision_query}"
+    )
+    print("Filtered dataframe head:")
+    print(filtered_df.head())
 
-    # Num Few Shots フィルタリング
-    filtered_df = filtered_df[
-        filtered_df["Few-shot"].astype(str).isin([str(x) for x in num_few_shots_query] + ["Unknown", "?"])
-    ]
-    print(f"After num_few_shots filter: {filtered_df.shape}")
+    df = select_columns(filtered_df, columns)
+    print(f"Final df shape: {df.shape}")
+    print("Final dataframe head:")
+    print(df.head())
+    return df
 
-    # Show deleted models フィルタリング
-    if not show_deleted:
-        filtered_df = filtered_df[filtered_df["Available on the hub"]]
-    print(f"After show_deleted filter: {filtered_df.shape}")
 
-    print("Filtered dataframe head:")
-    print(filtered_df.head())
-    return filtered_df
+def load_query(request: gr.Request):  # triggered only once at startup => read query parameter if it exists
+    query = request.query_params.get("query") or ""
+    return (
+        query,
+        query,
+    )  # return one for the "search_bar", one for a hidden component that triggers a reload only if value has changed
 
 
 # Prepare the dataframes