improve ds tutorial

AlexanderVNikitin · Jun 15, 2024 · 3b09e33 · 3b09e33
1 parent b91cf21
commit 3b09e33
Show file tree

Hide file tree

Showing 4 changed files with 305 additions and 59 deletions.
diff --git a/tests/test_utils.py b/tests/test_utils.py
@@ -222,7 +222,6 @@ def test_mmd_3_test():
     "Coffee",
     "ECG200",
     "ElectricDevices",
-    "GunPoint",
     "MixedShapesRegularTrain",
     "StarLightCurves",
     "Wafer"

diff --git a/tsgm/utils/datasets.py b/tsgm/utils/datasets.py
@@ -431,7 +431,7 @@ def get_physionet2012() -> T.Tuple[TensorLike, TensorLike, TensorLike, TensorLik
     This function downloads and retrieves the Physionet 2012 dataset, which consists of physiological data
     and corresponding outcomes. It returns the training, testing, and validation datasets along with their labels.
 
-    :return: A tuple containing the training, testing, and validation datasets along with their labels.
+    :return: A tuple containing the training, testing, and validation datasets along with their labels. (train_X, train_y, test_X, test_y, val_X, val_y)
     :rtype: tuple[TensorLike, TensorLike, TensorLike, TensorLike, TensorLike, TensorLike]
     """
     download_physionet2012()

diff --git a/tutorials/Datasets.ipynb b/tutorials/Datasets.ipynb
diff --git a/tutorials/Model Selection.ipynb b/tutorials/Model Selection.ipynb
@@ -6,7 +6,7 @@
    "metadata": {},
    "source": [
     "## Model selection.\n",
-    "This is a minimal example of model selection via hyperparameters optimization."
+    "This is a simple example of model selection through hyperparameter optimization."
    ]
   },
   {
@@ -36,7 +36,9 @@
    "id": "0290b339",
    "metadata": {},
    "source": [
-    "#### 0. Install optuna"
+    "#### 0. Install optuna\n",
+    "\n",
+    "Let's first install Optuna."
    ]
   },
   {
@@ -66,7 +68,7 @@
    "metadata": {},
    "source": [
     "#### 1. Load data\n",
-    "We are working with a toy dataset, and use `tsgm` utility called `tsgm.utils.gen_sine_dataset` to generate the data. We define a function that generates the dataset and then featurewise scale it using `tsgm.utils.TSFeatureWiseScaler`, so that each feature is in $[0, 1]$."
+    "We are using a small dataset generated by the `tsgm.utils.gen_sine_dataset` function. We scale the features using `tsgm.utils.TSFeatureWiseScaler` to ensure each feature falls within the range of $[0, 1]$."
    ]
   },
   {