feat: infer input size of forward and LSTM layers (#808)

### Summary of Changes * Users no longer need to specify input sizes of forward and LSTM layers. * The constructor parameter `output_size` of these two layers has been renamed to `neuron_count`.
Safe-DS · May 29, 2024 · 098a07f · 098a07f
1 parent 69a780c
commit 098a07f
Show file tree

Hide file tree

Showing 26 changed files with 504 additions and 648 deletions.
diff --git a/docs/tutorials/classification.ipynb b/docs/tutorials/classification.ipynb
@@ -32,8 +32,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -55,8 +55,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -80,8 +80,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -98,8 +98,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -118,8 +118,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -139,8 +139,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -166,8 +166,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -189,8 +189,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   }
  ],
  "metadata": {

diff --git a/docs/tutorials/convolutional_neural_network_for_image_classification.ipynb b/docs/tutorials/convolutional_neural_network_for_image_classification.ipynb
@@ -52,12 +52,12 @@
    "metadata": {
     "collapsed": true
    },
-   "outputs": [],
    "source": [
     "from safeds.data.image.containers import ImageList\n",
     "\n",
     "images, filepaths = ImageList.from_files(\"data/shapes\", return_filenames=True)"
-   ]
+   ],
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -71,7 +71,6 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "import re\n",
     "from safeds.data.tabular.containers import Column\n",
@@ -85,7 +84,8 @@
     "collapsed": false
    },
    "id": "66dcf95a3fa51f23",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -99,7 +99,6 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "from safeds.data.labeled.containers import ImageDataset\n",
     "\n",
@@ -109,7 +108,8 @@
     "collapsed": false
    },
    "id": "32056ddf5396e070",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -131,7 +131,6 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "from safeds.ml.nn.layers import (Convolutional2DLayer, FlattenLayer,\n",
     "                                 ForwardLayer, MaxPooling2DLayer)\n",
@@ -142,15 +141,16 @@
     "    Convolutional2DLayer(output_channel=32, kernel_size=3, padding=1),\n",
     "    MaxPooling2DLayer(kernel_size=2, stride=2),\n",
     "    FlattenLayer(),\n",
-    "    ForwardLayer(output_size=128),\n",
-    "    ForwardLayer(output_size=3),\n",
+    "    ForwardLayer(neuron_count=128),\n",
+    "    ForwardLayer(neuron_count=3),\n",
     "]"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "806a8091249d533a",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -162,7 +162,6 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "from safeds.ml.nn import NeuralNetworkClassifier\n",
     "from safeds.ml.nn.converters import InputConversionImageToColumn\n",
@@ -176,7 +175,8 @@
     "collapsed": false
    },
    "id": "af68cc0d32655d32",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -198,15 +198,15 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "cnn_fitted = cnn.fit(dataset, epoch_size=32, batch_size=16)"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "381627a94d500675",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -220,15 +220,15 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "prediction = cnn_fitted.predict(dataset.get_input())"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "62f63dd68362c8b7",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -242,15 +242,15 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "shuffled_prediction = prediction.shuffle()"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "779277d73e30554d",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -264,15 +264,15 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "shuffled_prediction.get_input().remove_image_by_index(list(range(9, len(prediction))))"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "a5ddbbfba41aa7f",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -286,15 +286,15 @@
   },
   {
    "cell_type": "code",
-   "outputs": [],
    "source": [
     "shuffled_prediction.get_output().to_list()[0:9]"
    ],
    "metadata": {
     "collapsed": false
    },
    "id": "7081595d7100fb42",
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   }
  ],
  "metadata": {

diff --git a/docs/tutorials/machine_learning.ipynb b/docs/tutorials/machine_learning.ipynb
@@ -35,8 +35,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -60,8 +60,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -87,8 +87,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -158,8 +158,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -199,8 +199,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -240,8 +240,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",
@@ -281,8 +281,8 @@
    "metadata": {
     "collapsed": false
    },
-   "outputs": [],
-   "execution_count": null
+   "execution_count": null,
+   "outputs": []
   },
   {
    "cell_type": "markdown",

diff --git a/src/safeds/data/labeled/containers/_tabular_dataset.py b/src/safeds/data/labeled/containers/_tabular_dataset.py
@@ -196,8 +196,8 @@ def _into_dataloader_with_classes(self, batch_size: int, num_of_classes: int) ->
         if num_of_classes <= 2:
             return DataLoader(
                 dataset=_create_dataset(
-                    torch.Tensor(self.features._data_frame.to_numpy()).to(_get_device()),
-                    torch.Tensor(self.target._series.to_numpy()).to(_get_device()).unsqueeze(dim=-1),
+                    self.features._data_frame.to_torch().to(_get_device()),
+                    self.target._series.to_torch().to(_get_device()).unsqueeze(dim=-1),
                 ),
                 batch_size=batch_size,
                 shuffle=True,
@@ -206,9 +206,9 @@ def _into_dataloader_with_classes(self, batch_size: int, num_of_classes: int) ->
         else:
             return DataLoader(
                 dataset=_create_dataset(
-                    torch.Tensor(self.features._data_frame.to_numpy()).to(_get_device()),
+                    self.features._data_frame.to_torch().to(_get_device()),
                     torch.nn.functional.one_hot(
-                        torch.LongTensor(self.target._series.to_numpy()).to(_get_device()),
+                        self.target._series.to_torch().to(_get_device()),
                         num_classes=num_of_classes,
                     ),
                 ),

diff --git a/src/safeds/data/tabular/transformation/__init__.py b/src/safeds/data/tabular/transformation/__init__.py
@@ -18,7 +18,7 @@
     __name__,
     {
         "Discretizer": "._discretizer:Discretizer",
-        "InvertibleTableTransformer": "._table_transformer:InvertibleTableTransformer",
+        "InvertibleTableTransformer": "._invertible_table_transformer:InvertibleTableTransformer",
         "LabelEncoder": "._label_encoder:LabelEncoder",
         "OneHotEncoder": "._one_hot_encoder:OneHotEncoder",
         "RangeScaler": "._range_scaler:RangeScaler",

diff --git a/src/safeds/data/tabular/transformation/_discretizer.py b/src/safeds/data/tabular/transformation/_discretizer.py
@@ -63,10 +63,12 @@ def __hash__(self) -> int:
 
     @property
     def is_fitted(self) -> bool:
+        """Whether the transformer is fitted."""
         return self._wrapped_transformer is not None
 
     @property
     def bin_count(self) -> int:
+        """The number of bins to be created."""
         return self._bin_count
 
     # ------------------------------------------------------------------------------------------------------------------