Update app.py to support MCP functionality and enhance Gradio UI; improve error handling and streamline data processing

app.py

@@ -1,9 +1,10 @@
-# 閾値診断アプリ Gradio版
+# 閾値診断アプリ Gradio + MCP対応版
 
 import gradio as gr
 import pandas as pd
 import numpy as np
 import json
+import os
 
 # --- ユーティリティ ---
 def judge_status(value, ll, l, h, hh):
@@ -19,7 +20,6 @@ def judge_status(value, ll, l, h, hh):
         return "OK"
 
 def convert_value(v):
-    """numpy型をPython標準型に変換"""
     if hasattr(v, "item"):
         return v.item()
     return float(v) if isinstance(v, (np.floating, float)) else int(v) if isinstance(v, (np.integer, int)) else v
@@ -27,24 +27,20 @@ def convert_value(v):
 # --- 診断関数 ---
 def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, window_minutes):
     try:
-        # CSV読み込み（3行ヘッダー）
         df = pd.read_csv(csv_file.name, header=[0, 1, 2])
         timestamp_col = df.iloc[:, 0]
         df = df.drop(df.columns[0], axis=1)
         df.insert(0, "timestamp", timestamp_col)
         df["timestamp"] = pd.to_datetime(df["timestamp"], errors="coerce")
 
-        # 閾値テーブル
         thresholds_df = pd.read_excel(excel_file.name)
         thresholds_df["Important"] = thresholds_df["Important"].astype(str).str.upper().map({"TRUE": True, "FALSE": False})
         for col in ["LL", "L", "H", "HH"]:
             if col in thresholds_df.columns:
                 thresholds_df[col] = pd.to_numeric(thresholds_df[col], errors="coerce")
-
     except Exception as e:
         return None, None, None, f"❌ 入力ファイルの読み込みに失敗しました: {e}", None
 
-    # 対象期間抽出
     try:
         target_time = pd.to_datetime(datetime_str)
     except Exception:
@@ -60,7 +56,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
     if proc_thresholds.empty:
         return None, None, None, f"⚠ プロセス {process_name} の閾値が設定されていません。", None
 
-    # --- 判定結果 ---
     all_results = []
     for _, row in df_window.iterrows():
         for _, thr in proc_thresholds.iterrows():
@@ -77,7 +72,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
                 "時刻": str(row["timestamp"])
             })
 
-    # --- 集計（全項目） ---
     total = len(all_results)
     status_counts = pd.Series([r["判定"] for r in all_results]).value_counts().reindex(
         ["LOW-LOW", "LOW", "OK", "HIGH", "HIGH-HIGH"], fill_value=0
@@ -89,7 +83,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
         "割合(%)": status_ratio.values
     })
 
-    # --- 集計（重要項目全体） ---
     important_results = [r for r in all_results if r["重要項目"]]
     if important_results:
         total_imp = len(important_results)
@@ -106,7 +99,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
         result_df_imp = pd.DataFrame(columns=["状態", "件数", "割合(%)"])
         status_ratio_imp = pd.Series(dtype=float)
 
-    # --- 集計（重要項目ごと） ---
     result_per_item = []
     for item in [r["ItemName"] for r in important_results]:
         item_results = [r for r in important_results if r["ItemName"] == item]
@@ -121,7 +113,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
             result_per_item.append({"ItemName": item, "状態": s, "件数": c, "割合(%)": r})
     result_df_imp_items = pd.DataFrame(result_per_item)
 
-    # --- サマリー ---
     summary = (
         f"✅ {process_name} の診断完了（{start_time} ～ {end_time}）\n"
         + "[全項目] " + " / ".join([f"{s}:{r:.1f}%" for s, r in status_ratio.items()]) + "\n"
@@ -131,7 +122,6 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
         )
     )
 
-    # --- JSON（集計結果のみ、UIと一致） ---
     json_data = {
         "集計結果": {
             "全項目割合": {k: convert_value(v) for k, v in status_ratio.to_dict().items()},
@@ -145,17 +135,16 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
 
     return result_df_all, result_df_imp, result_df_imp_items, summary, result_json
 
-
 # --- Gradio UI ---
 with gr.Blocks() as demo:
-    gr.Markdown("## 閾値診断アプリ")
+    gr.Markdown("## 閾値診断アプリ (MCP対応)")
 
     with gr.Row():
         csv_input = gr.File(label="CSVファイルをアップロード", file_types=[".csv"], type="filepath")
         excel_input = gr.File(label="Excel閾値ファイルをアップロード", file_types=[".xlsx"], type="filepath")
 
     process_name = gr.Textbox(label="プロセス名", value="E018-A012_除害RO")
-    datetime_str = gr.Textbox(label="診断基準日時 (例: 2025/8/1 1:05)", value="2025/8/1 1:05")
+    datetime_str = gr.Textbox(label="診断基準日時", value="2025/8/1 1:05")
     window_minutes = gr.Number(label="さかのぼる時間幅（分）", value=60)
 
     run_btn = gr.Button("診断を実行")
@@ -173,4 +162,8 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", share=False)
+    use_mcp = os.getenv("USE_MCP", "0") == "1"
+    if use_mcp:
+        demo.launch(mcp_server=True)
+    else:
+        demo.launch(server_name="0.0.0.0", share=False)