Merge pull request #376 from davidusb-geek/dependabot/pip/skforecast-…

…0.14.0

Bump skforecast from 0.13.0 to 0.14.0

docs/requirements.txt

@@ -10,7 +10,7 @@ beautifulsoup4>=4.9.3
 pulp>=2.4
 pyyaml>=5.4.1
 tables==3.9.1
-skforecast==0.13.0
+skforecast==0.14.0
 markupsafe==3.0.2
 Jinja2<3.2
 plotly>=5.6.0

pyproject.toml

@@ -14,7 +14,6 @@ authors = [
     {name = "David HERNANDEZ", email = "[email protected]"},
 ]
 license = {text = "MIT"}
-homepage = "https://github.com/davidusb-geek/emhass"
 keywords = ["energy", "management", "optimization", "hass"]
 classifiers = [
     "Development Status :: 5 - Production/Stable",
@@ -25,23 +24,28 @@ classifiers = [
     "Operating System :: OS Independent",
 ]
 
-[project.dependencies]
-numpy = "==1.26.4"
-scipy = "==1.12.0"
-pandas = "<=2.0.3"
-pvlib = ">=0.10.2"
-protobuf = ">=3.0.0"
-pytz = ">=2021.1"
-requests = ">=2.25.1"
-beautifulsoup4 = ">=4.9.3"
-h5py = "==3.12.1"
-pulp = ">=2.4"
-pyyaml = ">=5.4.1"
-tables = "<=3.9.1"
-skforecast = "==0.13.0"
-flask = ">=2.0.3"
-waitress = ">=2.1.1"
-plotly = ">=5.6.0"
+dependencies = [
+    "numpy==1.26.4",
+    "scipy==1.12.0",
+    "pandas<=2.0.3",
+    "pvlib>=0.10.2",
+    "protobuf>=3.0.0",
+    "pytz>=2021.1",
+    "requests>=2.25.1",
+    "beautifulsoup4>=4.9.3",
+    "h5py==3.12.1",
+    "pulp>=2.4",
+    "pyyaml>=5.4.1",
+    "tables<=3.9.1",
+    "skforecast==0.14.0",
+    "flask>=2.0.3",
+    "waitress>=2.1.1",
+    "plotly>=5.6.0"
+]
+
+[project.optional-dependencies]
+docs = ["sphinx", "sphinx-rtd-theme", "myst-parser"]
+test = ["requests_mock","pytest","coverage","snakeviz","ruff"]
 
 [tool.setuptools.packages]
 find = {where = ["src"]}
@@ -69,3 +73,6 @@ emhass = [
 
 [project.scripts]
 emhass = "emhass.command_line:main"
+
+[project.urls]
+Homepage = "https://github.com/davidusb-geek/emhass"

requirements.txt

@@ -10,7 +10,7 @@ h5py==3.12.1
 pulp>=2.4
 pyyaml>=5.4.1
 tables<=3.9.1
-skforecast==0.13.0
+skforecast==0.14.0
 # web server packages
 flask>=2.0.3
 waitress>=2.1.1

setup.py

@@ -52,7 +52,7 @@
         'pulp>=2.4',
         'pyyaml>=5.4.1',
         'tables<=3.9.1',
-        'skforecast==0.13.0',
+        'skforecast==0.14.0',
         'flask>=2.0.3',
         'waitress>=2.1.1',
         'plotly>=5.6.0'

src/emhass/machine_learning_forecaster.py

@@ -13,9 +13,8 @@
 from sklearn.neighbors import KNeighborsRegressor
 from sklearn.metrics import r2_score
 
-from skforecast.ForecasterAutoreg import ForecasterAutoreg
-from skforecast.model_selection import bayesian_search_forecaster
-from skforecast.model_selection import backtesting_forecaster
+from skforecast.recursive import ForecasterRecursive
+from skforecast.model_selection import bayesian_search_forecaster, backtesting_forecaster, TimeSeriesFold
 
 import warnings
 warnings.filterwarnings("ignore", category=DeprecationWarning)
@@ -144,7 +143,7 @@ def fit(self, split_date_delta: Optional[str] = '48h', perform_backtest: Optiona
             self.logger.error("Passed sklearn model "+self.sklearn_model+" is not valid. Defaulting to KNeighborsRegressor")
             base_model = KNeighborsRegressor()
         # Define the forecaster object
-        self.forecaster = ForecasterAutoreg(
+        self.forecaster = ForecasterRecursive(
             regressor = base_model,
             lags      = self.num_lags
             )
@@ -168,16 +167,22 @@ def fit(self, split_date_delta: Optional[str] = '48h', perform_backtest: Optiona
             # Using backtesting tool to evaluate the model
             self.logger.info("Performing simple backtesting of fitted model")
             start_time = time.time()
+            cv = TimeSeriesFold(
+                steps                 = self.num_lags,
+                initial_train_size    = None,
+                fixed_train_size      = False,
+                gap                   = 0,
+                allow_incomplete_fold = True,
+                refit                 = False
+            )
             metric, predictions_backtest = backtesting_forecaster(
                 forecaster         = self.forecaster,
                 y                  = self.data_train[self.var_model],
                 exog               = self.data_train.drop(self.var_model, axis=1),
-                initial_train_size = None,
-                fixed_train_size   = False,
-                steps              = self.num_lags,
+                cv                 = cv,
                 metric             = MLForecaster.neg_r2_score,
-                refit              = False,
-                verbose            = False
+                verbose            = False,
+                show_progress      = True
             )
             self.logger.info(f"Elapsed backtesting time: {time.time() - start_time}")
             self.logger.info(f"Backtest R2 score: {-metric}")
@@ -271,21 +276,25 @@ def search_space(trial):
         # The optimization routine call
         self.logger.info("Bayesian hyperparameter optimization with backtesting")
         start_time = time.time()
+        cv = TimeSeriesFold(
+            steps                 = num_lags,
+            initial_train_size    = len(self.data_exo.loc[:self.date_train]),
+            fixed_train_size      = True,
+            gap                   = 0,
+            skip_folds            = None,
+            allow_incomplete_fold = True,
+            refit                 = refit
+        )
         self.optimize_results, self.optimize_results_object = bayesian_search_forecaster(
             forecaster         = self.forecaster,
             y                  = self.data_train[self.var_model],
             exog               = self.data_train.drop(self.var_model, axis=1),
+            cv                 = cv,
             search_space       = search_space,
-            steps              = num_lags,
             metric             = MLForecaster.neg_r2_score,
-            refit              = refit,
-            initial_train_size = len(self.data_exo.loc[:self.date_train]),
-            fixed_train_size   = True,
             n_trials           = 10,
             random_state       = 123,
-            return_best        = True,
-            verbose            = False,
-            engine             = 'optuna'
+            return_best        = True
         )
         self.logger.info(f"Elapsed time: {time.time() - start_time}")
         self.is_tuned = True

tests/test_machine_learning_forecaster.py

@@ -10,7 +10,7 @@
 import pandas as pd
 import numpy as np
 
-from skforecast.ForecasterAutoreg import ForecasterAutoreg
+from skforecast.recursive import ForecasterRecursive
 
 from emhass.command_line import set_input_data_dict
 from emhass.retrieve_hass import RetrieveHass
@@ -82,12 +82,12 @@ def setUp(self):
 
     def test_fit(self):
         df_pred, df_pred_backtest = self.mlf.fit()
-        self.assertIsInstance(self.mlf.forecaster, ForecasterAutoreg)
+        self.assertIsInstance(self.mlf.forecaster, ForecasterRecursive)
         self.assertIsInstance(df_pred, pd.DataFrame)
         self.assertTrue(df_pred_backtest == None)
         # Refit with backtest evaluation
         df_pred, df_pred_backtest = self.mlf.fit(perform_backtest=True)
-        self.assertIsInstance(self.mlf.forecaster, ForecasterAutoreg)
+        self.assertIsInstance(self.mlf.forecaster, ForecasterRecursive)
         self.assertIsInstance(df_pred, pd.DataFrame)
         self.assertIsInstance(df_pred_backtest, pd.DataFrame)