Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update preprocessing_layers.ipynb #2285

Merged
merged 3 commits into from
Sep 4, 2024
Merged

Update preprocessing_layers.ipynb #2285

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
5f3d273
Update preprocessing_layers.ipynb
Mikhaylov-yv Nov 12, 2023
64e7a68
debug
MarkDaoust Aug 6, 2024
87b01f0
Merge branch 'master' into ValueError_indexing
MarkDaoust Aug 6, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 22 additions & 11 deletions site/en/tutorials/structured_data/preprocessing_layers.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -297,7 +297,7 @@
"def df_to_dataset(dataframe, shuffle=True, batch_size=32):\n",
" df = dataframe.copy()\n",
" labels = df.pop('target')\n",
" df = {key: value.values[:,tf.newaxis] for key, value in dataframe.items()}\n",
" df = {key: value.to_numpy()[:,tf.newaxis] for key, value in dataframe.items()}\n",
" ds = tf.data.Dataset.from_tensor_slices((dict(df), labels))\n",
" if shuffle:\n",
" ds = ds.shuffle(buffer_size=len(dataframe))\n",
Expand Down Expand Up @@ -447,7 +447,7 @@
"source": [
"### Categorical columns\n",
"\n",
"Pet `Type`s in the dataset are represented as strings—`Dog`s and `Cat`s—which need to be multi-hot encoded before being fed into the model. The `Age` feature \n",
"Pet `Type`s in the dataset are represented as strings—`Dog`s and `Cat`s—which need to be multi-hot encoded before being fed into the model. The `Age` feature\n",
"\n",
"Define another new utility function that returns a layer which maps values from a vocabulary to integer indices and multi-hot encodes the features using the `tf.keras.layers.StringLookup`, `tf.keras.layers.IntegerLookup`, and `tf.keras.CategoryEncoding` preprocessing layers:"
]
Expand Down Expand Up @@ -589,15 +589,15 @@
},
"outputs": [],
"source": [
"all_inputs = []\n",
"all_inputs = {}\n",
"encoded_features = []\n",
"\n",
"# Numerical features.\n",
"for header in ['PhotoAmt', 'Fee']:\n",
" numeric_col = tf.keras.Input(shape=(1,), name=header)\n",
" normalization_layer = get_normalization_layer(header, train_ds)\n",
" encoded_numeric_col = normalization_layer(numeric_col)\n",
" all_inputs.append(numeric_col)\n",
" all_inputs[header] = numeric_col\n",
" encoded_features.append(encoded_numeric_col)"
]
},
Expand Down Expand Up @@ -625,7 +625,7 @@
" dtype='int64',\n",
" max_tokens=5)\n",
"encoded_age_col = encoding_layer(age_col)\n",
"all_inputs.append(age_col)\n",
"all_inputs['Age'] = age_col\n",
"encoded_features.append(encoded_age_col)"
]
},
Expand Down Expand Up @@ -656,7 +656,7 @@
" dtype='string',\n",
" max_tokens=5)\n",
" encoded_categorical_col = encoding_layer(categorical_col)\n",
" all_inputs.append(categorical_col)\n",
" all_inputs[header] = categorical_col\n",
" encoded_features.append(encoded_categorical_col)"
]
},
Expand All @@ -678,6 +678,17 @@
"The next step is to create a model using the [Keras Functional API](https://www.tensorflow.org/guide/keras/functional). For the first layer in your model, merge the list of feature inputs—`encoded_features`—into one vector via concatenation with `tf.keras.layers.concatenate`."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "EtkwHC-akvcv"
},
"outputs": [],
"source": [
"encoded_features"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand Down Expand Up @@ -713,7 +724,8 @@
"source": [
"model.compile(optimizer='adam',\n",
" loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n",
" metrics=[\"accuracy\"])"
" metrics=[\"accuracy\"],\n",
" run_eagerly=True)"
]
},
{
Expand All @@ -734,7 +746,7 @@
"outputs": [],
"source": [
"# Use `rankdir='LR'` to make the graph horizontal.\n",
"tf.keras.utils.plot_model(model, show_shapes=True, rankdir=\"LR\")"
"tf.keras.utils.plot_model(model, show_shapes=True, show_layer_names=True, rankdir=\"LR\")"
]
},
{
Expand Down Expand Up @@ -765,8 +777,8 @@
},
"outputs": [],
"source": [
"loss, accuracy = model.evaluate(test_ds)\n",
"print(\"Accuracy\", accuracy)"
"result = model.evaluate(test_ds, return_dict=True)\n",
"print(result)"
]
},
{
Expand Down Expand Up @@ -869,7 +881,6 @@
],
"metadata": {
"colab": {
"collapsed_sections": [],
"name": "preprocessing_layers.ipynb",
"toc_visible": true
},
Expand Down
Loading