initial commit

app.py

@@ -0,0 +1,132 @@
+# app_trend.py
+import os
+import json
+import pandas as pd
+import numpy as np
+from sklearn.linear_model import LinearRegression
+import gradio as gr
+
+# --- 傾向検出関数 ---
+def detect_trends(process_name, datetime_str, window_minutes, csv_file, excel_file):
+    try:
+        # CSV読み込み（3行ヘッダー維持）
+        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")
+
+        # 閾値テーブル読み込み
+        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")
+
+        # --- 診断対象期間 ---
+        target_time = pd.to_datetime(datetime_str)
+        start_time = target_time - pd.Timedelta(minutes=window_minutes)
+        end_time = target_time
+        df_window = df[(df["timestamp"] >= start_time) & (df["timestamp"] <= end_time)]
+
+        if df_window.empty:
+            return pd.DataFrame(), f"⚠ 指定時間幅にデータなし", "{}"
+
+        proc_thresholds = thresholds_df[(thresholds_df["ProcessNo_ProcessName"] == process_name) &
+                                        (thresholds_df["Important"] == True)]
+        if proc_thresholds.empty:
+            return pd.DataFrame(), f"⚠ プロセス {process_name} の重要項目なし", "{}"
+
+        results = []
+        for _, thr in proc_thresholds.iterrows():
+            col_tuple = (thr["ColumnID"], thr["ItemName"], thr["ProcessNo_ProcessName"])
+            if col_tuple not in df.columns:
+                continue
+
+            series = df_window[col_tuple].dropna()
+            if len(series) < 3:
+                continue
+
+            # 線形回帰
+            x = np.arange(len(series)).reshape(-1, 1)
+            y = series.values.reshape(-1, 1)
+            model = LinearRegression().fit(x, y)
+            slope = model.coef_[0][0]
+
+            last_val = series.iloc[-1]
+            l, ll, h, hh = thr.get("L"), thr.get("LL"), thr.get("H"), thr.get("HH")
+
+            status = "安定"
+            if slope < 0 and pd.notna(ll):
+                if last_val > ll:
+                    status = "LL接近下降傾向"
+                elif last_val <= ll:
+                    status = "LL逸脱下降傾向"
+            if slope > 0 and pd.notna(hh):
+                if last_val < hh:
+                    status = "HH接近上昇傾向"
+                elif last_val >= hh:
+                    status = "HH逸脱上昇傾向"
+
+            results.append({
+                "ItemName": thr["ItemName"],
+                "傾向": status,
+                "傾き": round(float(slope), 4),
+                "最終値": round(float(last_val), 3) if pd.notna(last_val) else None,
+                "LL": ll, "L": l, "H": h, "HH": hh
+            })
+
+        if not results:
+            return pd.DataFrame(), f"⚠ データ不足のため傾向検出不可", "{}"
+
+        result_df = pd.DataFrame(results)
+        result_json = json.dumps(results, ensure_ascii=False, indent=2)
+
+        # JSONファイル保存（ダウンロード用）
+        json_path = "trend_result.json"
+        with open(json_path, "w", encoding="utf-8") as f:
+            f.write(result_json)
+
+        summary = f"✅ {process_name} の傾向検出完了（{start_time} ～ {end_time}）"
+        return result_df, summary, json_path
+
+    except Exception as e:
+        return pd.DataFrame(), f"❌ エラー: {str(e)}", "{}"
+
+
+# --- Gradio UI ---
+def create_demo():
+    with gr.Blocks() as demo:
+        gr.Markdown("## 📈 傾向検出アプリ")
+
+        with gr.Row():
+            csv_input = gr.File(label="CSVファイルをアップロード", type="filepath")
+            excel_input = gr.File(label="閾値テーブルExcelをアップロード", type="filepath")
+
+        process_name = gr.Textbox(label="プロセス名 (例: E018-A012_除害RO)")
+        datetime_input = gr.Textbox(label="基準日時 (例: 2025/8/1 0:05)")
+        window_minutes = gr.Number(label="さかのぼる時間幅 (分)", value=60)
+
+        run_btn = gr.Button("傾向検出を実行")
+
+        result_table = gr.Dataframe(label="傾向検出結果", interactive=False)
+        summary_out = gr.Textbox(label="サマリー")
+        json_file = gr.File(label="結果JSONダウンロード", interactive=False)
+
+        run_btn.click(
+            detect_trends,
+            inputs=[process_name, datetime_input, window_minutes, csv_input, excel_input],
+            outputs=[result_table, summary_out, json_file]
+        )
+
+    return demo
+
+
+# --- 起動設定 ---
+if __name__ == "__main__":
+    demo = create_demo()
+    if os.getenv("USE_MCP") == "1":
+        demo.launch(server_name="0.0.0.0", mcp_server=True, ssr_mode=False)
+    else:
+        demo.launch(server_name="0.0.0.0", share=False, ssr_mode=False)
+        

requirements.txt

@@ -0,0 +1,13 @@
+# Webアプリ/UI
+gradio>=4.44.0
+
+# データ処理
+pandas>=2.2.0
+numpy>=1.26.0
+openpyxl>=3.1.2
+
+# 機械学習（回帰や予兆解析で利用）
+scikit-learn>=1.5.0
+
+# 可視化（将来グラフ表示を追加する可能性を考慮）
+matplotlib>=3.8.0

trend_result.json

@@ -0,0 +1,202 @@
+[
+  {
+    "ItemName": "除害RO_A処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0024,
+    "最終値": 5.577,
+    "LL": 6.738,
+    "L": 7.062,
+    "H": 7.65,
+    "HH": 7.988
+  },
+  {
+    "ItemName": "除害RO_B処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0953,
+    "最終値": 27.245,
+    "LL": 9.45,
+    "L": 19.888,
+    "H": 39.938,
+    "HH": 41.225
+  },
+  {
+    "ItemName": "除害RO_C処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0055,
+    "最終値": 0.0,
+    "LL": 6.388,
+    "L": 7.088,
+    "H": 7.962,
+    "HH": 9.275
+  },
+  {
+    "ItemName": "除害RO_D処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0277,
+    "最終値": 11.999,
+    "LL": 9.4,
+    "L": 49.888,
+    "H": 49.9,
+    "HH": 49.9
+  },
+  {
+    "ItemName": "除害RO_E処理水_導電率",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.0172,
+    "最終値": 11.747,
+    "LL": 6.612,
+    "L": 7.225,
+    "H": 8.612,
+    "HH": 9.638
+  },
+  {
+    "ItemName": "除害RO_F処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.003,
+    "最終値": 2.882,
+    "LL": 8.062,
+    "L": 8.988,
+    "H": 10.15,
+    "HH": 10.588
+  },
+  {
+    "ItemName": "除害RO_G処理水_導電率",
+    "傾向": "HH逸脱上昇傾向",
+    "傾き": 0.0444,
+    "最終値": 19.593,
+    "LL": 6.212,
+    "L": 7.3,
+    "H": 8.862,
+    "HH": 12.562
+  },
+  {
+    "ItemName": "除害RO_H処理水_導電率",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.012,
+    "最終値": 8.729,
+    "LL": 7.075,
+    "L": 8.025,
+    "H": 8.988,
+    "HH": 9.438
+  },
+  {
+    "ItemName": "除害RO_I処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0043,
+    "最終値": 7.273,
+    "LL": 6.388,
+    "L": 6.75,
+    "H": 7.538,
+    "HH": 7.9
+  },
+  {
+    "ItemName": "除害RO_J処理水_導電率",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.0109,
+    "最終値": 9.212,
+    "LL": 8.362,
+    "L": 8.612,
+    "H": 9.075,
+    "HH": 9.438
+  },
+  {
+    "ItemName": "除害RO_K処理水_導電率",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.0296,
+    "最終値": 46.721,
+    "LL": 23.625,
+    "L": 38.525,
+    "H": 49.925,
+    "HH": 49.938
+  },
+  {
+    "ItemName": "除害RO_L処理水_導電率",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.0069,
+    "最終値": 8.673,
+    "LL": 8.35,
+    "L": 8.762,
+    "H": 10.125,
+    "HH": 10.588
+  },
+  {
+    "ItemName": "除害RO_M処理水_導電率",
+    "傾向": "HH逸脱上昇傾向",
+    "傾き": 0.0034,
+    "最終値": 7.614,
+    "LL": 5.575,
+    "L": 5.738,
+    "H": 6.35,
+    "HH": 7.125
+  },
+  {
+    "ItemName": "除害RO_N処理水_導電率",
+    "傾向": "HH逸脱上昇傾向",
+    "傾き": 0.0292,
+    "最終値": 15.671,
+    "LL": 5.662,
+    "L": 6.25,
+    "H": 7.1,
+    "HH": 7.59
+  },
+  {
+    "ItemName": "除害RO_O処理水_導電率",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0001,
+    "最終値": 49.93,
+    "LL": 49.925,
+    "L": 49.925,
+    "H": 49.938,
+    "HH": 49.95
+  },
+  {
+    "ItemName": "除害RO_処理水_流量1",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.2861,
+    "最終値": 199.512,
+    "LL": 210.9,
+    "L": 214.05,
+    "H": 218.7,
+    "HH": 298.05
+  },
+  {
+    "ItemName": "除害RO_処理水_流量2",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0919,
+    "最終値": 290.703,
+    "LL": 217.35,
+    "L": 280.5,
+    "H": 289.65,
+    "HH": 349.35
+  },
+  {
+    "ItemName": "除害RO 処理水 流量3",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.2295,
+    "最終値": 147.618,
+    "LL": 64.95,
+    "L": 143.025,
+    "H": 150.075,
+    "HH": 153.0
+  },
+  {
+    "ItemName": "除害RO_処理水_TOC1",
+    "傾向": "LL接近下降傾向",
+    "傾き": -0.0559,
+    "最終値": 44.986,
+    "LL": 39.75,
+    "L": 48.0,
+    "H": 63.25,
+    "HH": 82.0
+  },
+  {
+    "ItemName": "除害RO_処理水_TOC2",
+    "傾向": "HH接近上昇傾向",
+    "傾き": 0.0686,
+    "最終値": 46.997,
+    "LL": 37.5,
+    "L": 43.5,
+    "H": 56.0,
+    "HH": 74.75
+  }
+]