univariate ridge2+plot

Author: thierrymoudiki

Makefile

@@ -75,7 +75,7 @@ dist: clean ## builds source and wheel package
 	ls -l dist
 
 install: clean ## install the package to the active Python's site-packages
-	pip install -e .
+	uv pip install -e .
 
 build-site: docs ## export mkdocs website to a folder		
 	cp -rf ahead-docs/* ../../Pro_Website/Techtonique.github.io/ahead_python

ahead/Base/Base.py

@@ -240,13 +240,13 @@ def get_forecast(self, method=None, xreg=None):
             self.fcast_ = config.AHEAD_PACKAGE.mlarchf(**mlarch_args)
 
 
-    def plot(self, series, type_axis="dates", type_plot="pi"):
+    def plot(self, series=None, type_axis="dates", type_plot="pi"):
         """Plot time series forecast
 
         Parameters:
 
-        series: {integer} or {string}
-            series index or name
+        series: {integer} or {string} or {None}
+            series index or name. Optional when univariate; defaults to the only series.
         """
         assert all(
             [
@@ -257,7 +257,15 @@ def plot(self, series, type_axis="dates", type_plot="pi"):
             ]
         ), "model forecasting must be obtained first (with `forecast` method)"
 
-        if isinstance(series, str):
+        # Auto-select the only series in univariate case if not provided
+        if (self.n_series == 1) and (series is None):
+            series_idx = 0
+            try:
+                series = self.series_names[0]
+            except Exception:
+                series = 0
+
+        elif isinstance(series, str):
             assert (
                 series in self.series_names
             ), f"series {series} doesn't exist in the input dataset"
@@ -268,11 +276,19 @@ def plot(self, series, type_axis="dates", type_plot="pi"):
             ), f"check series index (< {self.n_series})"
             series_idx = series
 
-        y_all = list(self.input_df.iloc[:, series_idx]) + list(
-            self.result_dfs_[series_idx]["mean"].values
-        )
-
-        y_test = list(self.result_dfs_[series_idx]["mean"].values)
+        # Build y vectors depending on storage (multivariate uses result_dfs_, univariate uses mean_/lower_/upper_)
+        if self.result_dfs_ is not None:
+            y_test_arr = self.result_dfs_[series_idx]["mean"].values
+            y_all = list(self.input_df.iloc[:, series_idx]) + list(y_test_arr)
+            y_test = list(y_test_arr)
+            lower_arr = self.result_dfs_[series_idx]["lower"].values
+            upper_arr = self.result_dfs_[series_idx]["upper"].values
+        else:
+            y_test_arr = np.asarray(self.mean_).reshape(-1)
+            lower_arr = np.asarray(self.lower_).reshape(-1)
+            upper_arr = np.asarray(self.upper_).reshape(-1)
+            y_all = list(self.input_df.iloc[:, series_idx]) + list(y_test_arr)
+            y_test = list(y_test_arr)
         n_points_all = len(y_all)
         n_points_train = self.input_df.shape[0]
 
@@ -291,8 +307,8 @@ def plot(self, series, type_axis="dates", type_plot="pi"):
             ax.plot(x_test, y_test, "-", color="orange")
             ax.fill_between(
                 x_test,
-                self.result_dfs_[series_idx]["lower"].values,
-                self.result_dfs_[series_idx]["upper"].values,
+                lower_arr,
+                upper_arr,
                 alpha=0.2,
                 color="orange",
             )

ahead/Ridge2/Ridge2Regressor.py

@@ -10,6 +10,7 @@
 
 from ..Base import Base
 from ..utils import multivariate as mv
+from ..utils import univariate as uv
 from ..utils import unimultivariate as umv
 from .. import config
 
@@ -146,7 +147,7 @@ def __init__(
         self,
         h=5,
         level=95,
-        lags=1,
+        lags=15,
         nb_hidden=5,
         nodes_sim="sobol",
         activation="relu",
@@ -228,26 +229,42 @@ def forecast(self, df, xreg=None):
         self.get_forecast("ridge2")
 
         # result -----
-        (
-            self.averages_,
-            self.ranges_,
-            _,
-        ) = mv.format_multivariate_forecast(
-            n_series=self.n_series,
-            date_formatting=self.date_formatting,
-            output_dates=self.output_dates_,
-            horizon=self.h,
-            fcast=self.fcast_,
-        )
+        try: 
+            (
+                self.averages_,
+                self.ranges_,
+                _,
+            ) = mv.format_multivariate_forecast(
+                n_series=self.n_series,
+                date_formatting=self.date_formatting,
+                output_dates=self.output_dates_,
+                horizon=self.h,
+                fcast=self.fcast_,
+            )
+        except Exception:
+            # result -----
+            (
+                self.averages_,
+                self.ranges_,
+                _,
+            ) = uv.format_univariate_forecast(
+                date_formatting=self.date_formatting,
+                output_dates=self.output_dates_,
+                horizon=self.h,
+                fcast=self.fcast_,
+            )
 
         self.mean_ = np.asarray(self.fcast_.rx2["mean"])
         self.lower_ = np.asarray(self.fcast_.rx2["lower"])
         self.upper_ = np.asarray(self.fcast_.rx2["upper"])
 
-        self.result_dfs_ = tuple(
-            umv.compute_result_df(self.averages_[i], self.ranges_[i])
-            for i in range(self.n_series)
-        )
+        try: 
+            self.result_dfs_ = tuple(
+                umv.compute_result_df(self.averages_[i], self.ranges_[i])
+                for i in range(self.n_series)
+            )
+        except Exception: 
+            self.result_df_ = umv.compute_result_df(self.averages_, self.ranges_)
 
         if self.type_pi in (
             "bootstrap",

examples/ridge2regressor_univariate.py

@@ -0,0 +1,49 @@
+import os 
+import numpy as np
+import pandas as pd
+from ahead import Ridge2Regressor
+from time import time
+
+
+print(f"\n ----- Running: {os.path.basename(__file__)}... ----- \n")
+
+# Forecasting horizon
+h = 20
+
+
+# Data frame containing the time series 
+df = pd.read_csv("https://raw.githubusercontent.com/Techtonique/datasets/refs/heads/main/time_series/univariate/AirPassengers.csv").set_index('date')
+df.index = pd.DatetimeIndex(df.index)
+print(df)
+
+# univariate ts forecasting 
+print("Example 1 -----")
+d1 = Ridge2Regressor(h = h, date_formatting = "original")
+
+start = time()
+d1.forecast(df)
+print(f"Elapsed: {time()-start} \n")
+print("averages: \n")
+print(d1.averages_)
+print("\n")
+print("ranges: \n")
+print(d1.ranges_)
+print("\n")
+d1.plot()
+
+print("Example 2 -----")
+
+d3 = Ridge2Regressor(h = h, date_formatting = "original", 
+type_pi="bootstrap", B=5)
+
+start = time()
+d3.forecast(df)
+print(f"Elapsed: {time()-start} \n")
+
+print(d3.fcast_.rx2['mean'])
+print(d3.averages_[1])
+print(np.asarray(d3.fcast_.rx2['mean']))
+
+print(d3.fcast_.rx2['sims'][0])
+print(d3.fcast_.rx2['sims'][1])
+d3.plot()