Refactor diagnose_process_range function to remove file input parameters and utilize global variables for dataframes. Improved column access logic and streamlined data aggregation for important items. Enhanced JSON output formatting for clarity.

app.py

@@ -78,21 +78,10 @@ def judge_status(value, ll, l, h, hh):
     else:
         return "OK"
 
-def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, window_minutes):
-    try:
-        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")
-
-        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
+def diagnose_process_range(process_name, datetime_str, window_minutes):
+    global df, thresholds_df
+    if df is None or thresholds_df is None:
+        return None, None, None, "⚠ ファイル未読み込み", None
 
     try:
         target_time = pd.to_datetime(datetime_str)
@@ -112,10 +101,10 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
     all_results = []
     for _, row in df_window.iterrows():
         for _, thr in proc_thresholds.iterrows():
-            col_tuple = (thr["ColumnID"], thr["ItemName"], thr["ProcessNo_ProcessName"])
-            if col_tuple not in df.columns:
+            col_name = f"{thr['ColumnID']}_{thr['ItemName']}_{thr['ProcessNo_ProcessName']}"
+            if col_name not in df.columns:
                 continue
-            value = row[col_tuple]
+            value = row[col_name]
             status = judge_status(value, thr.get("LL"), thr.get("L"), thr.get("H"), thr.get("HH"))
             all_results.append({
                 "ColumnID": thr["ColumnID"],
@@ -131,13 +120,9 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
         ["LOW-LOW", "LOW", "OK", "HIGH", "HIGH-HIGH"], fill_value=0
     )
     status_ratio = (status_counts / total * 100).round(1)
-    result_df_all = pd.DataFrame({
-        "状態": status_counts.index,
-        "件数": status_counts.values,
-        "割合(%)": status_ratio.values
-    })
+    result_df_all = pd.DataFrame({"状態": status_counts.index, "件数": status_counts.values, "割合(%)": status_ratio.values})
 
-    # --- 重要項目全体集計 ---
+    # --- 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)
@@ -145,43 +130,29 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
             ["LOW-LOW", "LOW", "OK", "HIGH", "HIGH-HIGH"], fill_value=0
         )
         status_ratio_imp = (status_counts_imp / total_imp * 100).round(1)
-        result_df_imp = pd.DataFrame({
-            "状態": status_counts_imp.index,
-            "件数": status_counts_imp.values,
-            "割合(%)": status_ratio_imp.values
-        })
+        result_df_imp = pd.DataFrame({"状態": status_counts_imp.index, "件数": status_counts_imp.values, "割合(%)": status_ratio_imp.values})
     else:
         result_df_imp = pd.DataFrame(columns=["状態", "件数", "割合(%)"])
         status_ratio_imp = pd.Series(dtype=float)
 
-    # --- 重要項目ごと集計 ---
+    # --- 重要項目ごと ---
     result_per_item = []
-    for item in set([r["ItemName"] for r in important_results]):  # setで重複除去
+    for item in set([r["ItemName"] for r in important_results]):
         item_results = [r for r in important_results if r["ItemName"] == item]
-        if not item_results:
-            continue
         total_item = len(item_results)
         status_counts_item = pd.Series([r["判定"] for r in item_results]).value_counts().reindex(
             ["LOW-LOW", "LOW", "OK", "HIGH", "HIGH-HIGH"], fill_value=0
         )
         status_ratio_item = (status_counts_item / total_item * 100).round(1)
         for s, c, r in zip(status_counts_item.index, status_counts_item.values, status_ratio_item.values):
-            result_per_item.append({
-                "ItemName": item,
-                "状態": s,
-                "件数": int(c),
-                "割合(%)": float(r)
-            })
+            result_per_item.append({"ItemName": item, "状態": s, "件数": int(c), "割合(%)": float(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"
-        + "[重要項目全体] " + (
-            " / ".join([f"{s}:{r:.1f}%" for s, r in status_ratio_imp.items()])
-            if not result_df_imp.empty else "対象データなし"
-        )
+        + "[重要項目全体] " + (" / ".join([f"{s}:{r:.1f}%" for s, r in status_ratio_imp.items()]) if not result_df_imp.empty else "対象データなし")
     )
 
     # --- JSON ---
@@ -189,9 +160,7 @@ def diagnose_process_range(csv_file, excel_file, process_name, datetime_str, win
         "集計結果": {
             "全項目割合": {k: float(v) for k, v in status_ratio.to_dict().items()},
             "重要項目全体割合": {k: float(v) for k, v in status_ratio_imp.to_dict().items()} if not result_df_imp.empty else {},
-            "重要項目ごと割合": [
-                {k: v for k, v in row.items()} for _, row in result_df_imp_items.iterrows()
-            ]
+            "重要項目ごと割合": [dict(row) for _, row in result_df_imp_items.iterrows()]
         }
     }
     result_json = json.dumps(json_data, ensure_ascii=False, indent=2)