{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "zg02FZzDyEqd" }, "source": [ "##### Copyright 2019 The TensorFlow Authors.\n" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2024-01-12T02:20:49.565258Z", "iopub.status.busy": "2024-01-12T02:20:49.564609Z", "iopub.status.idle": "2024-01-12T02:20:49.568344Z", "shell.execute_reply": "2024-01-12T02:20:49.567783Z" }, "id": "2mapZ9afGJ69" }, "outputs": [], "source": [ "#@title Licensed under the Apache License, Version 2.0 (the \"License\");\n", "# you may not use this file except in compliance with the License.\n", "# You may obtain a copy of the License at\n", "#\n", "# https://www.apache.org/licenses/LICENSE-2.0\n", "#\n", "# Unless required by applicable law or agreed to in writing, software\n", "# distributed under the License is distributed on an \"AS IS\" BASIS,\n", "# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n", "# See the License for the specific language governing permissions and\n", "# limitations under the License." ] }, { "cell_type": "markdown", "metadata": { "id": "sMYQvJuBi7MS" }, "source": [ "# Classify structured data using Keras preprocessing layers" ] }, { "cell_type": "markdown", "metadata": { "id": "8FaL4wnr22oy" }, "source": [ "\n", " \n", " \n", " \n", " \n", "
\n", " \n", " \n", " View on TensorFlow.org\n", " \n", " \n", " \n", " Run in Google Colab\n", " \n", " \n", " \n", " View source on GitHub\n", " \n", " Download notebook\n", "
" ] }, { "cell_type": "markdown", "metadata": { "id": "Nna1tOKxyEqe" }, "source": [ "This tutorial demonstrates how to classify structured data, such as tabular data, using a simplified version of the PetFinder dataset from a Kaggle competition stored in a CSV file.\n", "\n", "You will use [Keras](https://www.tensorflow.org/guide/keras) to define the model, and [Keras preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) as a bridge to map from columns in a CSV file to features used to train the model. The goal is to predict if a pet will be adopted.\n", "\n", "This tutorial contains complete code for:\n", "\n", "* Loading a CSV file into a DataFrame using pandas.\n", "* Building an input pipeline to batch and shuffle the rows using `tf.data`. (Visit [tf.data: Build TensorFlow input pipelines](../../guide/data.ipynb) for more details.)\n", "* Mapping from columns in the CSV file to features used to train the model with the Keras preprocessing layers.\n", "* Building, training, and evaluating a model using the Keras built-in methods." ] }, { "cell_type": "markdown", "metadata": { "id": "h5xkXCicjFQD" }, "source": [ "Note: This tutorial is similar to [Classify structured data with feature columns](../structured_data/feature_columns.ipynb). This version uses the [Keras preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) instead of the `tf.feature_column` API, as the former are more intuitive and can be easily included inside your model to simplify deployment." ] }, { "cell_type": "markdown", "metadata": { "id": "ZHxU1FMNpomc" }, "source": [ "## The PetFinder.my mini dataset\n", "\n", "There are several thousand rows in the PetFinder.my mini's CSV dataset file, where each row describes a pet (a dog or a cat) and each column describes an attribute, such as age, breed, color, and so on.\n", "\n", "In the dataset's summary below, notice there are mostly numerical and categorical columns. In this tutorial, you will only be dealing with those two feature types, dropping `Description` (a free text feature) and `AdoptionSpeed` (a classification feature) during data preprocessing.\n", "\n", "| Column | Pet description | Feature type | Data type |\n", "| --------------- | ----------------------------- | -------------- | --------- |\n", "| `Type` | Type of animal (`Dog`, `Cat`) | Categorical | String |\n", "| `Age` | Age | Numerical | Integer |\n", "| `Breed1` | Primary breed | Categorical | String |\n", "| `Color1` | Color 1 | Categorical | String |\n", "| `Color2` | Color 2 | Categorical | String |\n", "| `MaturitySize` | Size at maturity | Categorical | String |\n", "| `FurLength` | Fur length | Categorical | String |\n", "| `Vaccinated` | Pet has been vaccinated | Categorical | String |\n", "| `Sterilized` | Pet has been sterilized | Categorical | String |\n", "| `Health` | Health condition | Categorical | String |\n", "| `Fee` | Adoption fee | Numerical | Integer |\n", "| `Description` | Profile write-up | Text | String |\n", "| `PhotoAmt` | Total uploaded photos | Numerical | Integer |\n", "| `AdoptionSpeed` | Categorical speed of adoption | Classification | Integer |" ] }, { "cell_type": "markdown", "metadata": { "id": "vjFbdBldyEqf" }, "source": [ "## Import TensorFlow and other libraries\n" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:49.572219Z", "iopub.status.busy": "2024-01-12T02:20:49.571983Z", "iopub.status.idle": "2024-01-12T02:20:51.919435Z", "shell.execute_reply": "2024-01-12T02:20:51.918727Z" }, "id": "LklnLlt6yEqf" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "2024-01-12 02:20:50.190753: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", "2024-01-12 02:20:50.190796: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", "2024-01-12 02:20:50.192423: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n" ] } ], "source": [ "import numpy as np\n", "import pandas as pd\n", "import tensorflow as tf\n", "\n", "from tensorflow.keras import layers" ] }, { "cell_type": "code", "execution_count": 3, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:51.923571Z", "iopub.status.busy": "2024-01-12T02:20:51.923175Z", "iopub.status.idle": "2024-01-12T02:20:51.929625Z", "shell.execute_reply": "2024-01-12T02:20:51.929022Z" }, "id": "TKU7RyoQGVKB" }, "outputs": [ { "data": { "text/plain": [ "'2.15.0'" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "tf.__version__" ] }, { "cell_type": "markdown", "metadata": { "id": "UXvBvobayEqi" }, "source": [ "## Load the dataset and read it into a pandas DataFrame\n", "\n", "pandas is a Python library with many helpful utilities for loading and working with structured data. Use `tf.keras.utils.get_file` to download and extract the CSV file with the PetFinder.my mini dataset, and load it into a DataFrame with `pandas.read_csv`:" ] }, { "cell_type": "code", "execution_count": 4, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:51.932844Z", "iopub.status.busy": "2024-01-12T02:20:51.932378Z", "iopub.status.idle": "2024-01-12T02:20:52.195068Z", "shell.execute_reply": "2024-01-12T02:20:52.194431Z" }, "id": "qJ4Ajn-YyEqj" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Downloading data from http://storage.googleapis.com/download.tensorflow.org/data/petfinder-mini.zip\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 8192/1668792 [..............................] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1668792/1668792 [==============================] - 0s 0us/step\n" ] } ], "source": [ "dataset_url = 'http://storage.googleapis.com/download.tensorflow.org/data/petfinder-mini.zip'\n", "csv_file = 'datasets/petfinder-mini/petfinder-mini.csv'\n", "\n", "tf.keras.utils.get_file('petfinder_mini.zip', dataset_url,\n", " extract=True, cache_dir='.')\n", "dataframe = pd.read_csv(csv_file)" ] }, { "cell_type": "markdown", "metadata": { "id": "efa6910dfa5f" }, "source": [ "Inspect the dataset by checking the first five rows of the DataFrame:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.198562Z", "iopub.status.busy": "2024-01-12T02:20:52.198320Z", "iopub.status.idle": "2024-01-12T02:20:52.210833Z", "shell.execute_reply": "2024-01-12T02:20:52.210286Z" }, "id": "3uiq4hoIGyXI" }, "outputs": [ { "data": { "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
TypeAgeBreed1GenderColor1Color2MaturitySizeFurLengthVaccinatedSterilizedHealthFeeDescriptionPhotoAmtAdoptionSpeed
0Cat3TabbyMaleBlackWhiteSmallShortNoNoHealthy100Nibble is a 3+ month old ball of cuteness. He ...12
1Cat1Domestic Medium HairMaleBlackBrownMediumMediumNot SureNot SureHealthy0I just found it alone yesterday near my apartm...20
2Dog1Mixed BreedMaleBrownWhiteMediumMediumYesNoHealthy0Their pregnant mother was dumped by her irresp...73
3Dog4Mixed BreedFemaleBlackBrownMediumShortYesNoHealthy150Good guard dog, very alert, active, obedience ...82
4Dog1Mixed BreedMaleBlackNo ColorMediumShortNoNoHealthy0This handsome yet cute boy is up for adoption....32
\n", "
" ], "text/plain": [ " Type Age Breed1 Gender Color1 Color2 MaturitySize \\\n", "0 Cat 3 Tabby Male Black White Small \n", "1 Cat 1 Domestic Medium Hair Male Black Brown Medium \n", "2 Dog 1 Mixed Breed Male Brown White Medium \n", "3 Dog 4 Mixed Breed Female Black Brown Medium \n", "4 Dog 1 Mixed Breed Male Black No Color Medium \n", "\n", " FurLength Vaccinated Sterilized Health Fee \\\n", "0 Short No No Healthy 100 \n", "1 Medium Not Sure Not Sure Healthy 0 \n", "2 Medium Yes No Healthy 0 \n", "3 Short Yes No Healthy 150 \n", "4 Short No No Healthy 0 \n", "\n", " Description PhotoAmt AdoptionSpeed \n", "0 Nibble is a 3+ month old ball of cuteness. He ... 1 2 \n", "1 I just found it alone yesterday near my apartm... 2 0 \n", "2 Their pregnant mother was dumped by her irresp... 7 3 \n", "3 Good guard dog, very alert, active, obedience ... 8 2 \n", "4 This handsome yet cute boy is up for adoption.... 3 2 " ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "dataframe.head()" ] }, { "cell_type": "markdown", "metadata": { "id": "C3zDbrozyEqq" }, "source": [ "## Create a target variable\n", "\n", "The original task in Kaggle's PetFinder.my Adoption Prediction competition was to predict the speed at which a pet will be adopted (e.g. in the first week, the first month, the first three months, and so on).\n", "\n", "In this tutorial, you will simplify the task by transforming it into a binary classification problem, where you simply have to predict whether a pet was adopted or not.\n", "\n", "After modifying the `AdoptionSpeed` column, `0` will indicate the pet was not adopted, and `1` will indicate it was." ] }, { "cell_type": "code", "execution_count": 6, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.213792Z", "iopub.status.busy": "2024-01-12T02:20:52.213565Z", "iopub.status.idle": "2024-01-12T02:20:52.219031Z", "shell.execute_reply": "2024-01-12T02:20:52.218446Z" }, "id": "wmMDc46-yEqq" }, "outputs": [], "source": [ "# In the original dataset, `'AdoptionSpeed'` of `4` indicates\n", "# a pet was not adopted.\n", "dataframe['target'] = np.where(dataframe['AdoptionSpeed']==4, 0, 1)\n", "\n", "# Drop unused features.\n", "dataframe = dataframe.drop(columns=['AdoptionSpeed', 'Description'])" ] }, { "cell_type": "markdown", "metadata": { "id": "sp0NCbswyEqs" }, "source": [ "## Split the DataFrame into training, validation, and test sets\n", "\n", "The dataset is in a single pandas DataFrame. Split it into training, validation, and test sets using a, for example, 80:10:10 ratio, respectively:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.221854Z", "iopub.status.busy": "2024-01-12T02:20:52.221634Z", "iopub.status.idle": "2024-01-12T02:20:52.229868Z", "shell.execute_reply": "2024-01-12T02:20:52.229227Z" }, "id": "XvSinthO8oMj" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/numpy/core/fromnumeric.py:59: FutureWarning: 'DataFrame.swapaxes' is deprecated and will be removed in a future version. Please use 'DataFrame.transpose' instead.\n", " return bound(*args, **kwds)\n" ] } ], "source": [ "train, val, test = np.split(dataframe.sample(frac=1), [int(0.8*len(dataframe)), int(0.9*len(dataframe))])" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.232666Z", "iopub.status.busy": "2024-01-12T02:20:52.232414Z", "iopub.status.idle": "2024-01-12T02:20:52.236111Z", "shell.execute_reply": "2024-01-12T02:20:52.235587Z" }, "id": "U02Q1moWoPwQ" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "9229 training examples\n", "1154 validation examples\n", "1154 test examples\n" ] } ], "source": [ "print(len(train), 'training examples')\n", "print(len(val), 'validation examples')\n", "print(len(test), 'test examples')" ] }, { "cell_type": "markdown", "metadata": { "id": "C_7uVu-xyEqv" }, "source": [ "## Create an input pipeline using tf.data\n", "\n", "Next, create a utility function that converts each training, validation, and test set DataFrame into a `tf.data.Dataset`, then shuffles and batches the data.\n", "\n", "Note: If you were working with a very large CSV file (so large that it does not fit into memory), you would use the `tf.data` API to read it from disk directly. That is not covered in this tutorial." ] }, { "cell_type": "code", "execution_count": 9, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.239104Z", "iopub.status.busy": "2024-01-12T02:20:52.238885Z", "iopub.status.idle": "2024-01-12T02:20:52.243384Z", "shell.execute_reply": "2024-01-12T02:20:52.242748Z" }, "id": "7r4j-1lRyEqw" }, "outputs": [], "source": [ "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", " ds = tf.data.Dataset.from_tensor_slices((dict(df), labels))\n", " if shuffle:\n", " ds = ds.shuffle(buffer_size=len(dataframe))\n", " ds = ds.batch(batch_size)\n", " ds = ds.prefetch(batch_size)\n", " return ds" ] }, { "cell_type": "markdown", "metadata": { "id": "PYxIXH579uS9" }, "source": [ "Now, use the newly created function (`df_to_dataset`) to check the format of the data the input pipeline helper function returns by calling it on the training data, and use a small batch size to keep the output readable:" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:52.246121Z", "iopub.status.busy": "2024-01-12T02:20:52.245903Z", "iopub.status.idle": "2024-01-12T02:20:54.578343Z", "shell.execute_reply": "2024-01-12T02:20:54.577640Z" }, "id": "tYiNH-QI96Jo" }, "outputs": [], "source": [ "batch_size = 5\n", "train_ds = df_to_dataset(train, batch_size=batch_size)" ] }, { "cell_type": "code", "execution_count": 11, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:54.582412Z", "iopub.status.busy": "2024-01-12T02:20:54.582110Z", "iopub.status.idle": "2024-01-12T02:20:54.668124Z", "shell.execute_reply": "2024-01-12T02:20:54.667499Z" }, "id": "nFYir6S8HgIJ" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Every feature: ['Type', 'Age', 'Breed1', 'Gender', 'Color1', 'Color2', 'MaturitySize', 'FurLength', 'Vaccinated', 'Sterilized', 'Health', 'Fee', 'PhotoAmt', 'target']\n", "A batch of ages: tf.Tensor(\n", "[[18]\n", " [48]\n", " [ 1]\n", " [38]\n", " [12]], shape=(5, 1), dtype=int64)\n", "A batch of targets: tf.Tensor([1 1 1 1 0], shape=(5,), dtype=int64)\n" ] } ], "source": [ "[(train_features, label_batch)] = train_ds.take(1)\n", "print('Every feature:', list(train_features.keys()))\n", "print('A batch of ages:', train_features['Age'])\n", "print('A batch of targets:', label_batch )" ] }, { "cell_type": "markdown", "metadata": { "id": "geqHWW54Hmte" }, "source": [ "As the output demonstrates, the training set returns a dictionary of column names (from the DataFrame) that map to column values from rows." ] }, { "cell_type": "markdown", "metadata": { "id": "-v50jBIuj4gb" }, "source": [ "## Apply the Keras preprocessing layers\n", "\n", "The Keras preprocessing layers allow you to build Keras-native input processing pipelines, which can be used as independent preprocessing code in non-Keras workflows, combined directly with Keras models, and exported as part of a Keras SavedModel.\n", "\n", "In this tutorial, you will use the following four preprocessing layers to demonstrate how to perform preprocessing, structured data encoding, and feature engineering:\n", "\n", "- `tf.keras.layers.Normalization`: Performs feature-wise normalization of input features.\n", "- `tf.keras.layers.CategoryEncoding`: Turns integer categorical features into one-hot, multi-hot, or tf-idf\n", "dense representations.\n", "- `tf.keras.layers.StringLookup`: Turns string categorical values into integer indices.\n", "- `tf.keras.layers.IntegerLookup`: Turns integer categorical values into integer indices.\n", "\n", "You can learn more about the available layers in the [Working with preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers) guide.\n", "\n", "- For _numerical features_ of the PetFinder.my mini dataset, you will use a `tf.keras.layers.Normalization` layer to standardize the distribution of the data.\n", "- For _categorical features_, such as pet `Type`s (`Dog` and `Cat` strings), you will transform them to multi-hot encoded tensors with `tf.keras.layers.CategoryEncoding`." ] }, { "cell_type": "markdown", "metadata": { "id": "twXBSxnT66o8" }, "source": [ "### Numerical columns\n", "\n", "For each numeric feature in the PetFinder.my mini dataset, you will use a `tf.keras.layers.Normalization` layer to standardize the distribution of the data.\n", "\n", "Define a new utility function that returns a layer which applies feature-wise normalization to numerical features using that Keras preprocessing layer:" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:54.671903Z", "iopub.status.busy": "2024-01-12T02:20:54.671648Z", "iopub.status.idle": "2024-01-12T02:20:54.675886Z", "shell.execute_reply": "2024-01-12T02:20:54.675202Z" }, "id": "D6OuEKMMyEq1" }, "outputs": [], "source": [ "def get_normalization_layer(name, dataset):\n", " # Create a Normalization layer for the feature.\n", " normalizer = layers.Normalization(axis=None)\n", "\n", " # Prepare a Dataset that only yields the feature.\n", " feature_ds = dataset.map(lambda x, y: x[name])\n", "\n", " # Learn the statistics of the data.\n", " normalizer.adapt(feature_ds)\n", "\n", " return normalizer" ] }, { "cell_type": "markdown", "metadata": { "id": "lL4TRreQCPjV" }, "source": [ "Next, test the new function by calling it on the total uploaded pet photo features to normalize `'PhotoAmt'`:" ] }, { "cell_type": "code", "execution_count": 13, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:54.679376Z", "iopub.status.busy": "2024-01-12T02:20:54.678979Z", "iopub.status.idle": "2024-01-12T02:20:57.983526Z", "shell.execute_reply": "2024-01-12T02:20:57.982767Z" }, "id": "MpKgUDyk69bM" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" } ], "source": [ "photo_count_col = train_features['PhotoAmt']\n", "layer = get_normalization_layer('PhotoAmt', train_ds)\n", "layer(photo_count_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "foWY00YBUx9N" }, "source": [ "Note: If you have many numeric features (hundreds, or more), it is more efficient to concatenate them first and use a single `tf.keras.layers.Normalization` layer." ] }, { "cell_type": "markdown", "metadata": { "id": "yVD--2WZ7vmh" }, "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", "\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:" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:57.987104Z", "iopub.status.busy": "2024-01-12T02:20:57.986832Z", "iopub.status.idle": "2024-01-12T02:20:57.992156Z", "shell.execute_reply": "2024-01-12T02:20:57.991544Z" }, "id": "GmgaeRjlDoUO" }, "outputs": [], "source": [ "def get_category_encoding_layer(name, dataset, dtype, max_tokens=None):\n", " # Create a layer that turns strings into integer indices.\n", " if dtype == 'string':\n", " index = layers.StringLookup(max_tokens=max_tokens)\n", " # Otherwise, create a layer that turns integer values into integer indices.\n", " else:\n", " index = layers.IntegerLookup(max_tokens=max_tokens)\n", "\n", " # Prepare a `tf.data.Dataset` that only yields the feature.\n", " feature_ds = dataset.map(lambda x, y: x[name])\n", "\n", " # Learn the set of possible values and assign them a fixed integer index.\n", " index.adapt(feature_ds)\n", "\n", " # Encode the integer indices.\n", " encoder = layers.CategoryEncoding(num_tokens=index.vocabulary_size())\n", "\n", " # Apply multi-hot encoding to the indices. The lambda function captures the\n", " # layer, so you can use them, or include them in the Keras Functional model later.\n", " return lambda feature: encoder(index(feature))" ] }, { "cell_type": "markdown", "metadata": { "id": "7b3DwtTeCPjX" }, "source": [ "Test the `get_category_encoding_layer` function by calling it on pet `'Type'` features to turn them into multi-hot encoded tensors:" ] }, { "cell_type": "code", "execution_count": 15, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:20:57.995466Z", "iopub.status.busy": "2024-01-12T02:20:57.995211Z", "iopub.status.idle": "2024-01-12T02:21:00.968807Z", "shell.execute_reply": "2024-01-12T02:21:00.967922Z" }, "id": "X2t2ff9K8PcT" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_type_col = train_features['Type']\n", "test_type_layer = get_category_encoding_layer(name='Type',\n", " dataset=train_ds,\n", " dtype='string')\n", "test_type_layer(test_type_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "j6eDongw8knz" }, "source": [ "Repeat the process on the pet `'Age'` features:" ] }, { "cell_type": "code", "execution_count": 16, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:00.972626Z", "iopub.status.busy": "2024-01-12T02:21:00.972352Z", "iopub.status.idle": "2024-01-12T02:21:03.623171Z", "shell.execute_reply": "2024-01-12T02:21:03.622426Z" }, "id": "7FjBioQ38oNE" }, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 16, "metadata": {}, "output_type": "execute_result" } ], "source": [ "test_age_col = train_features['Age']\n", "test_age_layer = get_category_encoding_layer(name='Age',\n", " dataset=train_ds,\n", " dtype='int64',\n", " max_tokens=5)\n", "test_age_layer(test_age_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "SiE0glOPkMyh" }, "source": [ "## Preprocess selected features to train the model on\n", "\n", "You have learned how to use several types of Keras preprocessing layers. Next, you will:\n", "\n", "- Apply the preprocessing utility functions defined earlier on 13 numerical and categorical features from the PetFinder.my mini dataset.\n", "- Add all the feature inputs to a list.\n", "\n", "As mentioned in the beginning, to train the model, you will use the PetFinder.my mini dataset's numerical (`'PhotoAmt'`, `'Fee'`) and categorical (`'Age'`, `'Type'`, `'Color1'`, `'Color2'`, `'Gender'`, `'MaturitySize'`, `'FurLength'`, `'Vaccinated'`, `'Sterilized'`, `'Health'`, `'Breed1'`) features.\n", "\n", "Note: If your aim is to build an accurate model, try a larger dataset of your own, and think carefully about which features are the most meaningful to include, and how they should be represented." ] }, { "cell_type": "markdown", "metadata": { "id": "Uj1GoHSZ9R3H" }, "source": [ "Earlier, you used a small batch size to demonstrate the input pipeline. Let's now create a new input pipeline with a larger batch size of 256:" ] }, { "cell_type": "code", "execution_count": 17, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:03.627110Z", "iopub.status.busy": "2024-01-12T02:21:03.626847Z", "iopub.status.idle": "2024-01-12T02:21:03.664263Z", "shell.execute_reply": "2024-01-12T02:21:03.663552Z" }, "id": "Rcv2kQTTo23h" }, "outputs": [], "source": [ "batch_size = 256\n", "train_ds = df_to_dataset(train, batch_size=batch_size)\n", "val_ds = df_to_dataset(val, shuffle=False, batch_size=batch_size)\n", "test_ds = df_to_dataset(test, shuffle=False, batch_size=batch_size)" ] }, { "cell_type": "markdown", "metadata": { "id": "5bIGNYN2V7iR" }, "source": [ "Normalize the numerical features (the number of pet photos and the adoption fee), and add them to one list of inputs called `encoded_features`:" ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:03.667715Z", "iopub.status.busy": "2024-01-12T02:21:03.667456Z", "iopub.status.idle": "2024-01-12T02:21:04.278615Z", "shell.execute_reply": "2024-01-12T02:21:04.277878Z" }, "id": "Q3RBa51VkaAn" }, "outputs": [], "source": [ "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", " encoded_features.append(encoded_numeric_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "qVcUAFd6bvlT" }, "source": [ "Turn the integer categorical values from the dataset (the pet age) into integer indices, perform multi-hot encoding, and add the resulting feature inputs to `encoded_features`:" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:04.282496Z", "iopub.status.busy": "2024-01-12T02:21:04.282252Z", "iopub.status.idle": "2024-01-12T02:21:04.505645Z", "shell.execute_reply": "2024-01-12T02:21:04.504853Z" }, "id": "1FOMGfZflhoA" }, "outputs": [], "source": [ "age_col = tf.keras.Input(shape=(1,), name='Age', dtype='int64')\n", "\n", "encoding_layer = get_category_encoding_layer(name='Age',\n", " dataset=train_ds,\n", " dtype='int64',\n", " max_tokens=5)\n", "encoded_age_col = encoding_layer(age_col)\n", "all_inputs.append(age_col)\n", "encoded_features.append(encoded_age_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "QYzynk6wdqKe" }, "source": [ "Repeat the same step for the string categorical values:" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:04.509726Z", "iopub.status.busy": "2024-01-12T02:21:04.509464Z", "iopub.status.idle": "2024-01-12T02:21:06.604175Z", "shell.execute_reply": "2024-01-12T02:21:06.603371Z" }, "id": "K8C8xyiXm-Ie" }, "outputs": [], "source": [ "categorical_cols = ['Type', 'Color1', 'Color2', 'Gender', 'MaturitySize',\n", " 'FurLength', 'Vaccinated', 'Sterilized', 'Health', 'Breed1']\n", "\n", "for header in categorical_cols:\n", " categorical_col = tf.keras.Input(shape=(1,), name=header, dtype='string')\n", " encoding_layer = get_category_encoding_layer(name=header,\n", " dataset=train_ds,\n", " dtype='string',\n", " max_tokens=5)\n", " encoded_categorical_col = encoding_layer(categorical_col)\n", " all_inputs.append(categorical_col)\n", " encoded_features.append(encoded_categorical_col)" ] }, { "cell_type": "markdown", "metadata": { "id": "YHSnhz2fyEq3" }, "source": [ "## Create, compile, and train the model\n" ] }, { "cell_type": "markdown", "metadata": { "id": "IDGyN_wpo0XS" }, "source": [ "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": 21, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:06.608404Z", "iopub.status.busy": "2024-01-12T02:21:06.608151Z", "iopub.status.idle": "2024-01-12T02:21:06.662410Z", "shell.execute_reply": "2024-01-12T02:21:06.661753Z" }, "id": "6Yrj-_pr6jyL" }, "outputs": [], "source": [ "all_features = tf.keras.layers.concatenate(encoded_features)\n", "x = tf.keras.layers.Dense(32, activation=\"relu\")(all_features)\n", "x = tf.keras.layers.Dropout(0.5)(x)\n", "output = tf.keras.layers.Dense(1)(x)\n", "\n", "model = tf.keras.Model(all_inputs, output)" ] }, { "cell_type": "markdown", "metadata": { "id": "NRLDRcYAefTA" }, "source": [ "Configure the model with Keras `Model.compile`:" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:06.665798Z", "iopub.status.busy": "2024-01-12T02:21:06.665555Z", "iopub.status.idle": "2024-01-12T02:21:06.679992Z", "shell.execute_reply": "2024-01-12T02:21:06.679407Z" }, "id": "GZDb_lJdelSg" }, "outputs": [], "source": [ "model.compile(optimizer='adam',\n", " loss=tf.keras.losses.BinaryCrossentropy(from_logits=True),\n", " metrics=[\"accuracy\"])" ] }, { "cell_type": "markdown", "metadata": { "id": "f6mNMfG6yEq5" }, "source": [ "Let's visualize the connectivity graph:\n" ] }, { "cell_type": "code", "execution_count": 23, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:06.682998Z", "iopub.status.busy": "2024-01-12T02:21:06.682760Z", "iopub.status.idle": "2024-01-12T02:21:07.050488Z", "shell.execute_reply": "2024-01-12T02:21:07.049648Z" }, "id": "Y7Bkx4c7yEq5" }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Use `rankdir='LR'` to make the graph horizontal.\n", "tf.keras.utils.plot_model(model, show_shapes=True, rankdir=\"LR\")" ] }, { "cell_type": "markdown", "metadata": { "id": "CED6OStLyEq7" }, "source": [ "Next, train and test the model:" ] }, { "cell_type": "code", "execution_count": 24, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:07.056880Z", "iopub.status.busy": "2024-01-12T02:21:07.056593Z", "iopub.status.idle": "2024-01-12T02:21:13.247231Z", "shell.execute_reply": "2024-01-12T02:21:13.246557Z" }, "id": "OQfE3PC6yEq8" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Epoch 1/10\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/tmpfs/src/tf_docs_env/lib/python3.9/site-packages/keras/src/engine/functional.py:642: UserWarning: Input dict contained keys ['target'] which did not match any model input. They will be ignored by the model.\n", " inputs = self._flatten_to_reference_inputs(inputs)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n", "I0000 00:00:1705026069.800827 9903 device_compiler.h:186] Compiled cluster using XLA! This line is logged at most once for the lifetime of the process.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1:49 - loss: 0.6922 - accuracy: 0.4336" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.6908 - accuracy: 0.4734 " ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.6612 - accuracy: 0.5391" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.6469 - accuracy: 0.5736" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 4s 18ms/step - loss: 0.6416 - accuracy: 0.5808 - val_loss: 0.5700 - val_accuracy: 0.7253\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 2/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 2s - loss: 0.6095 - accuracy: 0.6523" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5938 - accuracy: 0.6673" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5964 - accuracy: 0.6628" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.5878 - accuracy: 0.6652" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5878 - accuracy: 0.6641 - val_loss: 0.5470 - val_accuracy: 0.7314\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 3/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1s - loss: 0.6191 - accuracy: 0.6562" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5873 - accuracy: 0.6690" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5788 - accuracy: 0.6811" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.5715 - accuracy: 0.6854" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5700 - accuracy: 0.6863 - val_loss: 0.5353 - val_accuracy: 0.7409\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 4/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1s - loss: 0.5549 - accuracy: 0.7227" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5481 - accuracy: 0.7003" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5469 - accuracy: 0.7063" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.5480 - accuracy: 0.7045" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5525 - accuracy: 0.7009 - val_loss: 0.5267 - val_accuracy: 0.7392\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 5/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1s - loss: 0.5850 - accuracy: 0.6992" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/37 [========>.....................] - ETA: 0s - loss: 0.5457 - accuracy: 0.6963" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "23/37 [=================>............] - ETA: 0s - loss: 0.5433 - accuracy: 0.7002" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "34/37 [==========================>...] - ETA: 0s - loss: 0.5426 - accuracy: 0.7074" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5438 - accuracy: 0.7070 - val_loss: 0.5219 - val_accuracy: 0.7400\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 6/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1s - loss: 0.5302 - accuracy: 0.6992" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/37 [========>.....................] - ETA: 0s - loss: 0.5331 - accuracy: 0.7096" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "23/37 [=================>............] - ETA: 0s - loss: 0.5394 - accuracy: 0.7113" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "34/37 [==========================>...] - ETA: 0s - loss: 0.5375 - accuracy: 0.7124" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5379 - accuracy: 0.7120 - val_loss: 0.5179 - val_accuracy: 0.7374\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 7/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 2s - loss: 0.5118 - accuracy: 0.7578" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "12/37 [========>.....................] - ETA: 0s - loss: 0.5381 - accuracy: 0.7171" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "23/37 [=================>............] - ETA: 0s - loss: 0.5388 - accuracy: 0.7188" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.5396 - accuracy: 0.7145" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5381 - accuracy: 0.7150 - val_loss: 0.5157 - val_accuracy: 0.7392\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 8/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 2s - loss: 0.5215 - accuracy: 0.7344" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5410 - accuracy: 0.7188" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5353 - accuracy: 0.7255" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "32/37 [========================>.....] - ETA: 0s - loss: 0.5344 - accuracy: 0.7230" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5352 - accuracy: 0.7216 - val_loss: 0.5140 - val_accuracy: 0.7383\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 9/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 2s - loss: 0.5534 - accuracy: 0.7266" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5253 - accuracy: 0.7248" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5271 - accuracy: 0.7276" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "33/37 [=========================>....] - ETA: 0s - loss: 0.5285 - accuracy: 0.7246" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5299 - accuracy: 0.7230 - val_loss: 0.5120 - val_accuracy: 0.7418\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Epoch 10/10\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\r", " 1/37 [..............................] - ETA: 1s - loss: 0.5302 - accuracy: 0.7266" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "11/37 [=======>......................] - ETA: 0s - loss: 0.5203 - accuracy: 0.7365" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "22/37 [================>.............] - ETA: 0s - loss: 0.5294 - accuracy: 0.7298" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "32/37 [========================>.....] - ETA: 0s - loss: 0.5288 - accuracy: 0.7303" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "37/37 [==============================] - 0s 6ms/step - loss: 0.5283 - accuracy: 0.7293 - val_loss: 0.5112 - val_accuracy: 0.7435\n" ] }, { "data": { "text/plain": [ "" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.fit(train_ds, epochs=10, validation_data=val_ds)" ] }, { "cell_type": "code", "execution_count": 25, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:13.250754Z", "iopub.status.busy": "2024-01-12T02:21:13.250172Z", "iopub.status.idle": "2024-01-12T02:21:13.295796Z", "shell.execute_reply": "2024-01-12T02:21:13.295168Z" }, "id": "T8N2uAdU2Cni" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r", "1/5 [=====>........................] - ETA: 0s - loss: 0.4924 - accuracy: 0.7773" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "5/5 [==============================] - 0s 5ms/step - loss: 0.4979 - accuracy: 0.7591\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Accuracy 0.7590987682342529\n" ] } ], "source": [ "loss, accuracy = model.evaluate(test_ds)\n", "print(\"Accuracy\", accuracy)" ] }, { "cell_type": "markdown", "metadata": { "id": "LmZMnTKaCZda" }, "source": [ "## Perform inference\n", "\n", "The model you have developed can now classify a row from a CSV file directly after you've included the preprocessing layers inside the model itself.\n", "\n", "You can now [save and reload the Keras model](../keras/save_and_load.ipynb) with `Model.save` and `Model.load_model` before performing inference on new data:" ] }, { "cell_type": "code", "execution_count": 26, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:13.299094Z", "iopub.status.busy": "2024-01-12T02:21:13.298865Z", "iopub.status.idle": "2024-01-12T02:21:13.783753Z", "shell.execute_reply": "2024-01-12T02:21:13.783086Z" }, "id": "QH9Zy1sBvwOH" }, "outputs": [], "source": [ "model.save('my_pet_classifier.keras')\n", "reloaded_model = tf.keras.models.load_model('my_pet_classifier.keras')" ] }, { "cell_type": "markdown", "metadata": { "id": "D973plJrdwQ9" }, "source": [ "To get a prediction for a new sample, you can simply call the Keras `Model.predict` method. There are just two things you need to do:\n", "\n", "1. Wrap scalars into a list so as to have a batch dimension (`Model`s only process batches of data, not single samples).\n", "2. Call `tf.convert_to_tensor` on each feature." ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "execution": { "iopub.execute_input": "2024-01-12T02:21:13.787713Z", "iopub.status.busy": "2024-01-12T02:21:13.787478Z", "iopub.status.idle": "2024-01-12T02:21:14.354934Z", "shell.execute_reply": "2024-01-12T02:21:14.354163Z" }, "id": "rKq4pxtdDa7i" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\r", "1/1 [==============================] - ETA: 0s" ] }, { "name": "stdout", "output_type": "stream", "text": [ "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r", "1/1 [==============================] - 0s 412ms/step\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "This particular pet had a 79.3 percent probability of getting adopted.\n" ] } ], "source": [ "sample = {\n", " 'Type': 'Cat',\n", " 'Age': 3,\n", " 'Breed1': 'Tabby',\n", " 'Gender': 'Male',\n", " 'Color1': 'Black',\n", " 'Color2': 'White',\n", " 'MaturitySize': 'Small',\n", " 'FurLength': 'Short',\n", " 'Vaccinated': 'No',\n", " 'Sterilized': 'No',\n", " 'Health': 'Healthy',\n", " 'Fee': 100,\n", " 'PhotoAmt': 2,\n", "}\n", "\n", "input_dict = {name: tf.convert_to_tensor([value]) for name, value in sample.items()}\n", "predictions = reloaded_model.predict(input_dict)\n", "prob = tf.nn.sigmoid(predictions[0])\n", "\n", "print(\n", " \"This particular pet had a %.1f percent probability \"\n", " \"of getting adopted.\" % (100 * prob)\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "XJQQZEiH2FaB" }, "source": [ "Note: You will typically have better results with deep learning with larger and more complex datasets. When working with a small dataset, such as the simplified PetFinder.my one, you can use a decision tree or a random forest as a strong baseline. The goal of this tutorial is to demonstrate the mechanics of working with structured data, so you have a starting point when working with your own datasets in the future.\n" ] }, { "cell_type": "markdown", "metadata": { "id": "k0QAY2Tb2HYG" }, "source": [ "## Next steps\n", "\n", "To learn more about classifying structured data, try working with other datasets. To improve accuracy during training and testing your models, think carefully about which features to include in your model and how they should be represented.\n", "\n", "Below are some suggestions for datasets:\n", "\n", "- [TensorFlow Datasets: MovieLens](https://www.tensorflow.org/datasets/catalog/movie_lens): A set of movie ratings from a movie recommendation service.\n", "- [TensorFlow Datasets: Wine Quality](https://www.tensorflow.org/datasets/catalog/wine_quality): Two datasets related to red and white variants of the Portuguese \"Vinho Verde\" wine. You can also find the Red Wine Quality dataset on Kaggle.\n", "- Kaggle: arXiv Dataset: A corpus of 1.7 million scholarly articles from arXiv, covering physics, computer science, math, statistics, electrical engineering, quantitative biology, and economics.\n" ] } ], "metadata": { "colab": { "collapsed_sections": [], "name": "preprocessing_layers.ipynb", "toc_visible": true }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.9.18" } }, "nbformat": 4, "nbformat_minor": 0 }