mirror of
https://github.com/Azure/MachineLearningNotebooks.git
synced 2025-12-23 11:02:39 -05:00
update samples from Release-42 as a part of SDK release
This commit is contained in:
vizhur
@@ -39,11 +39,7 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"register model from file"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# If you did NOT complete the tutorial, you can instead run this cell \n",
|
||||
@@ -62,7 +58,19 @@
|
||||
" model_name=model_name,\n",
|
||||
" tags={\"data\": \"mnist\", \"model\": \"classification\"},\n",
|
||||
" description=\"Mnist handwriting recognition\",\n",
|
||||
" workspace=ws)"
|
||||
" workspace=ws)\n",
|
||||
"\n",
|
||||
"from azureml.core.environment import Environment\n",
|
||||
"from azureml.core.conda_dependencies import CondaDependencies\n",
|
||||
"\n",
|
||||
"# to install required packages\n",
|
||||
"env = Environment('tutorial-env')\n",
|
||||
"cd = CondaDependencies.create(pip_packages=['azureml-dataprep[pandas,fuse]>=1.1.14', 'azureml-defaults'], conda_packages = ['scikit-learn==0.22.1'])\n",
|
||||
"\n",
|
||||
"env.python.conda_dependencies = cd\n",
|
||||
"\n",
|
||||
"# Register environment to re-use later\n",
|
||||
"env.register(workspace = ws)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -102,9 +110,61 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Retrieve the model\n",
|
||||
"## Deploy as web service\n",
|
||||
"\n",
|
||||
"You registered a model in your workspace in the previous tutorial. Now, load this workspace and download the model to your local directory."
|
||||
"Deploy the model as a web service hosted in ACI. \n",
|
||||
"\n",
|
||||
"To build the correct environment for ACI, provide the following:\n",
|
||||
"* A scoring script to show how to use the model\n",
|
||||
"* A configuration file to build the ACI\n",
|
||||
"* The model you trained before\n",
|
||||
"\n",
|
||||
"### Create scoring script\n",
|
||||
"\n",
|
||||
"Create the scoring script, called score.py, used by the web service call to show how to use the model.\n",
|
||||
"\n",
|
||||
"You must include two required functions into the scoring script:\n",
|
||||
"* The `init()` function, which typically loads the model into a global object. This function is run only once when the Docker container is started. \n",
|
||||
"\n",
|
||||
"* The `run(input_data)` function uses the model to predict a value based on the input data. Inputs and outputs to the run typically use JSON for serialization and de-serialization, but other formats are supported.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import numpy as np\n",
|
||||
"import os\n",
|
||||
"import pickle\n",
|
||||
"import joblib\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # AZUREML_MODEL_DIR is an environment variable created during deployment.\n",
|
||||
" # It is the path to the model folder (./azureml-models/$MODEL_NAME/$VERSION)\n",
|
||||
" # For multiple models, it points to the folder containing all deployed models (./azureml-models)\n",
|
||||
" model_path = os.path.join(os.getenv('AZUREML_MODEL_DIR'), 'sklearn_mnist_model.pkl')\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(raw_data):\n",
|
||||
" data = np.array(json.loads(raw_data)['data'])\n",
|
||||
" # make prediction\n",
|
||||
" y_hat = model.predict(data)\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return y_hat.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create configuration file\n",
|
||||
"\n",
|
||||
"Create a deployment configuration file and specify the number of CPUs and gigabyte of RAM needed for your ACI container. While it depends on your model, the default of 1 core and 1 gigabyte of RAM is usually sufficient for many models. If you feel you need more later, you would have to recreate the image and redeploy the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -112,37 +172,98 @@
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"load workspace",
|
||||
"download model"
|
||||
"configure web service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"import os \n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"model=Model(ws, 'sklearn_mnist')\n",
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"model.download(target_dir=os.getcwd(), exist_ok=True)\n",
|
||||
"\n",
|
||||
"# verify the downloaded model file\n",
|
||||
"file_path = os.path.join(os.getcwd(), \"sklearn_mnist_model.pkl\")\n",
|
||||
"\n",
|
||||
"os.stat(file_path)"
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores=1, \n",
|
||||
" memory_gb=1, \n",
|
||||
" tags={\"data\": \"MNIST\", \"method\" : \"sklearn\"}, \n",
|
||||
" description='Predict MNIST with sklearn')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test model locally\n",
|
||||
"### Deploy in ACI\n",
|
||||
"Estimated time to complete: **about 2-5 minutes**\n",
|
||||
"\n",
|
||||
"Before deploying, make sure your model is working locally by:\n",
|
||||
"* Downloading the test data if you haven't already\n",
|
||||
"* Loading test data\n",
|
||||
"* Predicting test data\n",
|
||||
"* Examining the confusion matrix"
|
||||
"Configure the image and deploy. The following code goes through these steps:\n",
|
||||
"\n",
|
||||
"1. Create environment object containing dependencies needed by the model using the environment file (`myenv.yml`)\n",
|
||||
"1. Create inference configuration necessary to deploy the model as a web service using:\n",
|
||||
" * The scoring file (`score.py`)\n",
|
||||
" * envrionment object created in previous step\n",
|
||||
"1. Deploy the model to the ACI container.\n",
|
||||
"1. Get the web service HTTP endpoint."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"configure image",
|
||||
"create image",
|
||||
"deploy web service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from azureml.core.model import InferenceConfig\n",
|
||||
"from azureml.core.environment import Environment\n",
|
||||
"from azureml.core import Workspace\n",
|
||||
"from azureml.core.model import Model\n",
|
||||
"\n",
|
||||
"ws = Workspace.from_config()\n",
|
||||
"model = Model(ws, 'sklearn_mnist')\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"myenv = Environment.get(workspace=ws, name=\"tutorial-env\", version=\"1\")\n",
|
||||
"inference_config = InferenceConfig(entry_script=\"score.py\", environment=myenv)\n",
|
||||
"\n",
|
||||
"service = Model.deploy(workspace=ws, \n",
|
||||
" name='sklearn-mnist-svc', \n",
|
||||
" models=[model], \n",
|
||||
" inference_config=inference_config, \n",
|
||||
" deployment_config=aciconfig)\n",
|
||||
"\n",
|
||||
"service.wait_for_deployment(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Get the scoring web service's HTTP endpoint, which accepts REST client calls. This endpoint can be shared with anyone who wants to test the web service or integrate it into an application."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"get scoring uri"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test the model\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -150,7 +271,7 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Download test data\n",
|
||||
"If you haven't already, download the test data to the **./data/** directory"
|
||||
"Download the test data to the **./data/** directory"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -159,16 +280,15 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# download test data\n",
|
||||
"import os\n",
|
||||
"import urllib.request\n",
|
||||
"from azureml.core import Dataset\n",
|
||||
"from azureml.opendatasets import MNIST\n",
|
||||
"\n",
|
||||
"data_folder = os.path.join(os.getcwd(), 'data')\n",
|
||||
"os.makedirs(data_folder, exist_ok = True)\n",
|
||||
"os.makedirs(data_folder, exist_ok=True)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz', filename=os.path.join(data_folder, 'test-images.gz'))\n",
|
||||
"urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz', filename=os.path.join(data_folder, 'test-labels.gz'))"
|
||||
"mnist_file_dataset = MNIST.get_file_dataset()\n",
|
||||
"mnist_file_dataset.download(data_folder, overwrite=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -191,8 +311,8 @@
|
||||
"\n",
|
||||
"data_folder = os.path.join(os.getcwd(), 'data')\n",
|
||||
"# note we also shrink the intensity values (X) from 0-255 to 0-1. This helps the neural network converge faster\n",
|
||||
"X_test = load_data(os.path.join(data_folder, 'test-images.gz'), False) / 255.0\n",
|
||||
"y_test = load_data(os.path.join(data_folder, 'test-labels.gz'), True).reshape(-1)"
|
||||
"X_test = load_data(os.path.join(data_folder, 't10k-images-idx3-ubyte.gz'), False) / 255.0\n",
|
||||
"y_test = load_data(os.path.join(data_folder, 't10k-labels-idx1-ubyte.gz'), True).reshape(-1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -201,7 +321,13 @@
|
||||
"source": [
|
||||
"### Predict test data\n",
|
||||
"\n",
|
||||
"Feed the test dataset to the model to get predictions."
|
||||
"Feed the test dataset to the model to get predictions.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"The following code goes through these steps:\n",
|
||||
"1. Send the data as a JSON array to the web service hosted in ACI. \n",
|
||||
"\n",
|
||||
"1. Use the SDK's `run` API to invoke the service. You can also make raw calls using any HTTP tool such as curl."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -210,12 +336,10 @@
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pickle\n",
|
||||
"import joblib\n",
|
||||
"\n",
|
||||
"clf = joblib.load( os.path.join(os.getcwd(), 'sklearn_mnist_model.pkl'))\n",
|
||||
"y_hat = clf.predict(X_test)\n",
|
||||
"print(y_hat)"
|
||||
"import json\n",
|
||||
"test = json.dumps({\"data\": X_test.tolist()})\n",
|
||||
"test = bytes(test, encoding='utf8')\n",
|
||||
"y_hat = service.run(input_data=test)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -277,209 +401,10 @@
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Deploy as web service\n",
|
||||
"## Show predictions\n",
|
||||
"\n",
|
||||
"Once you've tested the model and are satisfied with the results, deploy the model as a web service hosted in ACI. \n",
|
||||
"Test the deployed model with a random sample of 30 images from the test data. \n",
|
||||
"\n",
|
||||
"To build the correct environment for ACI, provide the following:\n",
|
||||
"* A scoring script to show how to use the model\n",
|
||||
"* An environment file to show what packages need to be installed\n",
|
||||
"* A configuration file to build the ACI\n",
|
||||
"* The model you trained before\n",
|
||||
"\n",
|
||||
"### Create scoring script\n",
|
||||
"\n",
|
||||
"Create the scoring script, called score.py, used by the web service call to show how to use the model.\n",
|
||||
"\n",
|
||||
"You must include two required functions into the scoring script:\n",
|
||||
"* The `init()` function, which typically loads the model into a global object. This function is run only once when the Docker container is started. \n",
|
||||
"\n",
|
||||
"* The `run(input_data)` function uses the model to predict a value based on the input data. Inputs and outputs to the run typically use JSON for serialization and de-serialization, but other formats are supported.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%writefile score.py\n",
|
||||
"import json\n",
|
||||
"import numpy as np\n",
|
||||
"import os\n",
|
||||
"import pickle\n",
|
||||
"import joblib\n",
|
||||
"\n",
|
||||
"def init():\n",
|
||||
" global model\n",
|
||||
" # AZUREML_MODEL_DIR is an environment variable created during deployment.\n",
|
||||
" # It is the path to the model folder (./azureml-models/$MODEL_NAME/$VERSION)\n",
|
||||
" # For multiple models, it points to the folder containing all deployed models (./azureml-models)\n",
|
||||
" model_path = os.path.join(os.getenv('AZUREML_MODEL_DIR'), 'sklearn_mnist_model.pkl')\n",
|
||||
" model = joblib.load(model_path)\n",
|
||||
"\n",
|
||||
"def run(raw_data):\n",
|
||||
" data = np.array(json.loads(raw_data)['data'])\n",
|
||||
" # make prediction\n",
|
||||
" y_hat = model.predict(data)\n",
|
||||
" # you can return any data type as long as it is JSON-serializable\n",
|
||||
" return y_hat.tolist()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create environment file\n",
|
||||
"\n",
|
||||
"Next, create an environment file, called myenv.yml, that specifies all of the script's package dependencies. This file is used to ensure that all of those dependencies are installed in the Docker image. This model needs `scikit-learn` and `azureml-sdk`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"set conda dependencies"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.conda_dependencies import CondaDependencies \n",
|
||||
"\n",
|
||||
"myenv = CondaDependencies()\n",
|
||||
"myenv.add_pip_package(\"scikit-learn==0.22.1\")\n",
|
||||
"myenv.add_pip_package(\"azureml-defaults\")\n",
|
||||
"\n",
|
||||
"with open(\"myenv.yml\",\"w\") as f:\n",
|
||||
" f.write(myenv.serialize_to_string())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Review the content of the `myenv.yml` file."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"with open(\"myenv.yml\",\"r\") as f:\n",
|
||||
" print(f.read())"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Create configuration file\n",
|
||||
"\n",
|
||||
"Create a deployment configuration file and specify the number of CPUs and gigabyte of RAM needed for your ACI container. While it depends on your model, the default of 1 core and 1 gigabyte of RAM is usually sufficient for many models. If you feel you need more later, you would have to recreate the image and redeploy the service."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"configure web service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from azureml.core.webservice import AciWebservice\n",
|
||||
"\n",
|
||||
"aciconfig = AciWebservice.deploy_configuration(cpu_cores=1, \n",
|
||||
" memory_gb=1, \n",
|
||||
" tags={\"data\": \"MNIST\", \"method\" : \"sklearn\"}, \n",
|
||||
" description='Predict MNIST with sklearn')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Deploy in ACI\n",
|
||||
"Estimated time to complete: **about 7-8 minutes**\n",
|
||||
"\n",
|
||||
"Configure the image and deploy. The following code goes through these steps:\n",
|
||||
"\n",
|
||||
"1. Create environment object containing dependencies needed by the model using the environment file (`myenv.yml`)\n",
|
||||
"1. Create inference configuration necessary to deploy the model as a web service using:\n",
|
||||
" * The scoring file (`score.py`)\n",
|
||||
" * envrionment object created in previous step\n",
|
||||
"1. Deploy the model to the ACI container.\n",
|
||||
"1. Get the web service HTTP endpoint."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"configure image",
|
||||
"create image",
|
||||
"deploy web service",
|
||||
"aci"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%%time\n",
|
||||
"from azureml.core.webservice import Webservice\n",
|
||||
"from azureml.core.model import InferenceConfig\n",
|
||||
"from azureml.core.environment import Environment\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"myenv = Environment.from_conda_specification(name=\"myenv\", file_path=\"myenv.yml\")\n",
|
||||
"inference_config = InferenceConfig(entry_script=\"score.py\", environment=myenv)\n",
|
||||
"\n",
|
||||
"service = Model.deploy(workspace=ws, \n",
|
||||
" name='sklearn-mnist-svc', \n",
|
||||
" models=[model], \n",
|
||||
" inference_config=inference_config, \n",
|
||||
" deployment_config=aciconfig)\n",
|
||||
"\n",
|
||||
"service.wait_for_deployment(show_output=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Get the scoring web service's HTTP endpoint, which accepts REST client calls. This endpoint can be shared with anyone who wants to test the web service or integrate it into an application."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {
|
||||
"tags": [
|
||||
"get scoring uri"
|
||||
]
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"print(service.scoring_uri)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Test deployed service\n",
|
||||
"\n",
|
||||
"Earlier you scored all the test data with the local version of the model. Now, you can test the deployed model with a random sample of 30 images from the test data. \n",
|
||||
"\n",
|
||||
"The following code goes through these steps:\n",
|
||||
"1. Send the data as a JSON array to the web service hosted in ACI. \n",
|
||||
"\n",
|
||||
"1. Use the SDK's `run` API to invoke the service. You can also make raw calls using any HTTP tool such as curl.\n",
|
||||
"\n",
|
||||
"1. Print the returned predictions and plot them along with the input images. Red font and inverse image (white on black) is used to highlight the misclassified samples. \n",
|
||||
"\n",
|
||||
|
||||
Reference in New Issue
Block a user