update docs

georgia-tech-db · Nov 7, 2023 · 7aab727 · 7aab727
1 parent 56a401a
commit 7aab727
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 8 deletions.
diff --git a/docs/source/reference/ai/model-forecasting.rst b/docs/source/reference/ai/model-forecasting.rst
@@ -38,9 +38,6 @@ This trains a forecasting model. The model can be called by providing the horizo
 
    SELECT Forecast();
 
-.. note::
-
-   `Forecasting` function also provides suggestions by default. If you wish to turn it off, send `FALSE` as an optional argument while calling the function. Eg. `SELECT Forecast(FALSE);`
 
 Forecast Parameters
 -------------------
@@ -69,9 +66,12 @@ EvaDB's default forecast framework is `statsforecast <https://nixtla.github.io/s
    * - FREQUENCY (str, default: 'auto')
      - A string indicating the frequency of the data. The common used ones are D, W, M, Y, which respectively represents day-, week-, month- and year- end frequency. The default value is M. Check `pandas available frequencies <https://pandas.pydata.org/pandas-docs/stable/user_guide/timeseries.html#offset-aliases>`_ for all available frequencies. If it is not provided, the frequency is attempted to be determined automatically.
    * - METRICS (str, default: 'True')
-     - Compute NRMSE by performing cross-validation. It is `False` by default if `LIBRARY` is `neuralforecast` as it can take an extensively long time.
+     - Compute NRMSE by performing cross-validation. It is `False` by default if `LIBRARY` is `neuralforecast` as it can take an extensively long time. The metrics are logged locally.
+
+.. note::
 
-Note: If columns other than the ones required as mentioned above are passed while creating the function, they will be treated as exogenous variables if LIBRARY is `neuralforecast`. Otherwise, they would be ignored.
+    Note: If columns other than the ones required as mentioned above are passed while creating the function, they will be treated as exogenous variables if LIBRARY is `neuralforecast`. Otherwise, they would be ignored.
+   `Forecasting` function also logs suggestions. Logged information, such as metrics and suggestions, is sent to STDOUT by default. If you wish not to print it, please send `FALSE` as an optional argument while calling the function. Eg. `SELECT Forecast(FALSE);`
 
 Below is an example query specifying the above parameters:
 

diff --git a/evadb/functions/forecast.py b/evadb/functions/forecast.py
@@ -69,6 +69,7 @@ def setup(
                     self.hypers = "p,d,q: " + f.readline()
 
     def forward(self, data) -> pd.DataFrame:
+        log_str = ""
         if self.library == "statsforecast":
             forecast_df = self.model.predict(
                 h=self.horizon, level=[self.conf]
@@ -92,13 +93,15 @@ def forward(self, data) -> pd.DataFrame:
                         suggestion_list.append(1)
 
             for suggestion in set(suggestion_list):
-                print("\nSUGGESTION: " + self.suggestion_dict[suggestion])
+                log_str += "\nSUGGESTION: " + self.suggestion_dict[suggestion]
 
             # Metrics
             if self.rmse is not None:
-                print("\nMean normalized RMSE: " + str(self.rmse))
+                log_str += "\nMean normalized RMSE: " + str(self.rmse)
             if self.hypers is not None:
-                print("Hyperparameters: " + self.hypers)
+                log_str += "\nHyperparameters: " + self.hypers
+
+            print(log_str)
 
         forecast_df = forecast_df.rename(
             columns={