Update tools/forecaster.py

tools/forecaster.py

@@ -6,61 +6,55 @@ import plotly.graph_objects as go
 
 def forecast_metric_tool(file_path: str, date_col: str, value_col: str):
     """
-    Forecast next 3 periods for any numeric metric, and return a textual table.
-    Saves a date-indexed PNG under /tmp via our safe monkey-patch.
+    Forecast next 3 periods for any numeric metric, saving
+    the PNG under /tmp and returning the forecast table as text.
     """
-    # 1) Load & parse
+    # 1) Load & parse dates
     df = pd.read_csv(file_path)
     try:
         df[date_col] = pd.to_datetime(df[date_col])
     except Exception:
         return f"❌ Could not parse '{date_col}' as dates."
-    
-    # 2) Coerce metric to numeric & drop invalid
+
+    # 2) Coerce metric to numeric & drop invalid rows
     df[value_col] = pd.to_numeric(df[value_col], errors="coerce")
     df = df.dropna(subset=[date_col, value_col])
-    
     if df.empty:
         return f"❌ No valid data for '{value_col}'."
-    
-    # 3) Sort and set index, infer frequency
-    df = df.sort_values(date_col)
-    df.set_index(date_col, inplace=True)
+
+    # 3) Sort by date, set index, then collapse any duplicate timestamps
+    df = df.sort_values(date_col).set_index(date_col)
+    # If you have multiple rows for the same timestamp, take their mean
+    df = df[[value_col]].groupby(level=0).mean()
+
+    # 4) Infer frequency (e.g. 'D', 'M', etc.) and reindex
     freq = pd.infer_freq(df.index)
     if freq is None:
-        # fallback to daily if pandas can't infer
-        freq = "D"
+        freq = "D"  # fallback to daily
     df = df.asfreq(freq)
-    
-    # 4) Fit ARIMA
+
+    # 5) Fit ARIMA
     try:
         model     = ARIMA(df[value_col], order=(1, 1, 1))
         model_fit = model.fit()
     except Exception as e:
         return f"❌ ARIMA fitting failed: {e}"
-    
-    # 5) Get a proper date-indexed forecast
+
+    # 6) Forecast with a proper DatetimeIndex
     fc_res   = model_fit.get_forecast(steps=3)
-    forecast = fc_res.predicted_mean  # a pd.Series with a DatetimeIndex
-    
-    # 6) Plot historical + forecast
+    forecast = fc_res.predicted_mean  # pd.Series indexed by future dates
+
+    # 7) Plot history + forecast
     fig = go.Figure()
-    fig.add_scatter(
-        x=df.index, y=df[value_col],
-        mode="lines", name=value_col
-    )
-    fig.add_scatter(
-        x=forecast.index, y=forecast,
-        mode="lines+markers", name="Forecast"
-    )
+    fig.add_scatter(x=df.index,       y=df[value_col], mode="lines", name=value_col)
+    fig.add_scatter(x=forecast.index, y=forecast,     mode="lines+markers", name="Forecast")
     fig.update_layout(
         title=f"{value_col} Forecast",
-        xaxis_title=str(date_col),
-        yaxis_title=str(value_col),
-        template="plotly_dark"
+        xaxis_title=date_col,
+        yaxis_title=value_col,
+        template="plotly_dark",
     )
-    fig.write_image("forecast_plot.png")
-    
-    # 7) Return the forecast table as text
-    tbl = forecast.to_frame(name="Forecast")
-    return tbl.to_string()
+    fig.write_image("forecast_plot.png")  # safely lands in /tmp via monkey-patch
+
+    # 8) Return the forecast table as plain text
+    return forecast.to_frame(name="Forecast").to_string()