update samples from Release-91 as a part of SDK release

how-to-use-azureml/machine-learning-pipelines/intro-to-pipelines/aml-pipelines-parameter-tuning-with-hyperdrive.ipynb

@@ -121,12 +121,17 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "os.makedirs('./data/mnist', exist_ok=True)\n",
+        "data_folder = os.path.join(os.getcwd(), 'data/mnist')\n",
+        "os.makedirs(data_folder, exist_ok=True)\n",
         "\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/train-images-idx3-ubyte.gz', filename = './data/mnist/train-images.gz')\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/train-labels-idx1-ubyte.gz', filename = './data/mnist/train-labels.gz')\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz', filename = './data/mnist/test-images.gz')\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz', filename = './data/mnist/test-labels.gz')"
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/train-images-idx3-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 'train-images-idx3-ubyte.gz'))\n",
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/train-labels-idx1-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 'train-labels-idx1-ubyte.gz'))\n",
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/t10k-images-idx3-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 't10k-images-idx3-ubyte.gz'))\n",
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/t10k-labels-idx1-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 't10k-labels-idx1-ubyte.gz'))"
       ]
     },
     {
@@ -146,11 +151,11 @@
         "from utils import load_data\n",
         "\n",
         "# note we also shrink the intensity values (X) from 0-255 to 0-1. This helps the neural network converge faster.\n",
-        "X_train = load_data('./data/mnist/train-images.gz', False) / 255.0\n",
-        "y_train = load_data('./data/mnist/train-labels.gz', True).reshape(-1)\n",
+        "X_train = load_data(os.path.join(data_folder, 'train-images-idx3-ubyte.gz'), False) / np.float32(255.0)\n",
+        "X_test = load_data(os.path.join(data_folder, 't10k-images-idx3-ubyte.gz'), False) / np.float32(255.0)\n",
+        "y_train = load_data(os.path.join(data_folder, 'train-labels-idx1-ubyte.gz'), True).reshape(-1)\n",
+        "y_test = load_data(os.path.join(data_folder, 't10k-labels-idx1-ubyte.gz'), True).reshape(-1)\n",
         "\n",
-        "X_test = load_data('./data/mnist/test-images.gz', False) / 255.0\n",
-        "y_test = load_data('./data/mnist/test-labels.gz', True).reshape(-1)\n",
         "\n",
         "count = 0\n",
         "sample_size = 30\n",

how-to-use-azureml/ml-frameworks/chainer/train-hyperparameter-tune-deploy-with-chainer/chainer_mnist.py

@@ -4,6 +4,8 @@ import os
 
 import numpy as np
 
+from utils import download_mnist
+
 import chainer
 from chainer import backend
 from chainer import backends
@@ -17,6 +19,7 @@ from chainer.training import extensions
 from chainer.dataset import concat_examples
 from chainer.backends.cuda import to_cpu
 
+
 from azureml.core.run import Run
 run = Run.get_context()
 
@@ -49,7 +52,7 @@ def main():
     args = parser.parse_args()
 
     # Download the MNIST data if you haven't downloaded it yet
-    train, test = datasets.mnist.get_mnist(withlabel=True, ndim=1)
+    train, test = download_mnist()
 
     gpu_id = args.gpu_id
     batchsize = args.batchsize

how-to-use-azureml/ml-frameworks/chainer/train-hyperparameter-tune-deploy-with-chainer/chainer_score.py

@@ -2,6 +2,8 @@ import numpy as np
 import os
 import json
 
+from utils import download_mnist
+
 from chainer import serializers, using_config, Variable, datasets
 import chainer.functions as F
 import chainer.links as L
@@ -41,7 +43,7 @@ def init():
 def run(input_data):
     i = np.array(json.loads(input_data)['data'])
 
-    _, test = datasets.get_mnist()
+    _, test = download_mnist()
     x = Variable(np.asarray([test[i][0]]))
     y = model(x)
 

how-to-use-azureml/ml-frameworks/chainer/train-hyperparameter-tune-deploy-with-chainer/train-hyperparameter-tune-deploy-with-chainer.ipynb

@@ -217,7 +217,8 @@
         "import shutil\n",
         "\n",
         "shutil.copy('chainer_mnist.py', project_folder)\n",
-        "shutil.copy('chainer_score.py', project_folder)"
+        "shutil.copy('chainer_score.py', project_folder)\n",
+        "shutil.copy('utils.py', project_folder)"
       ]
     },
     {
@@ -263,6 +264,7 @@
         "- python=3.6.2\n",
         "- pip:\n",
         "  - azureml-defaults\n",
+        "  - azureml-opendatasets\n",
         "  - chainer==5.1.0\n",
         "  - cupy-cuda90==5.1.0\n",
         "  - mpi4py==3.0.0\n",
@@ -557,6 +559,7 @@
         "cd.add_conda_package('numpy')\n",
         "cd.add_pip_package('chainer==5.1.0')\n",
         "cd.add_pip_package(\"azureml-defaults\")\n",
+        "cd.add_pip_package(\"azureml-opendatasets\")\n",
         "cd.save_to_file(base_directory='./', conda_file_path='myenv.yml')\n",
         "\n",
         "print(cd.serialize_to_string())"
@@ -584,7 +587,8 @@
         "\n",
         "\n",
         "myenv = Environment.from_conda_specification(name=\"myenv\", file_path=\"myenv.yml\")\n",
-        "inference_config = InferenceConfig(entry_script=\"chainer_score.py\", environment=myenv)\n",
+        "inference_config = InferenceConfig(entry_script=\"chainer_score.py\", environment=myenv,\n",
+        "                                   source_directory=project_folder)\n",
         "\n",
         "aciconfig = AciWebservice.deploy_configuration(cpu_cores=1,\n",
         "                                               auth_enabled=True, # this flag generates API keys to secure access\n",
@@ -592,11 +596,11 @@
         "                                               tags={'name': 'mnist', 'framework': 'Chainer'},\n",
         "                                               description='Chainer DNN with MNIST')\n",
         "\n",
-        "service = Model.deploy(workspace=ws, \n",
-        "                           name='chainer-mnist-1', \n",
-        "                           models=[model], \n",
-        "                           inference_config=inference_config, \n",
-        "                           deployment_config=aciconfig)\n",
+        "service = Model.deploy(workspace=ws,\n",
+        "                       name='chainer-mnist-1',\n",
+        "                       models=[model],\n",
+        "                       inference_config=inference_config,\n",
+        "                       deployment_config=aciconfig)\n",
         "service.wait_for_deployment(True)\n",
         "print(service.state)\n",
         "print(service.scoring_uri)"
@@ -685,13 +689,16 @@
         "            res = res.reshape(n_items[0], 1)\n",
         "    return res\n",
         "\n",
-        "os.makedirs('./data/mnist', exist_ok=True)\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-images-idx3-ubyte.gz', filename = './data/mnist/test-images.gz')\n",
-        "urllib.request.urlretrieve('http://yann.lecun.com/exdb/mnist/t10k-labels-idx1-ubyte.gz', filename = './data/mnist/test-labels.gz')\n",
+        "data_folder = os.path.join(os.getcwd(), 'data/mnist')\n",
+        "os.makedirs(data_folder, exist_ok=True)\n",
         "\n",
-        "X_test = load_data('./data/mnist/test-images.gz', False)\n",
-        "y_test = load_data('./data/mnist/test-labels.gz', True).reshape(-1)\n",
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/t10k-images-idx3-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 't10k-images-idx3-ubyte.gz'))\n",
+        "urllib.request.urlretrieve('https://azureopendatastorage.blob.core.windows.net/mnist/t10k-labels-idx1-ubyte.gz',\n",
+        "                           filename=os.path.join(data_folder, 't10k-labels-idx1-ubyte.gz'))\n",
         "\n",
+        "X_test = load_data(os.path.join(data_folder, 't10k-images-idx3-ubyte.gz'), False) / np.float32(255.0)\n",
+        "y_test = load_data(os.path.join(data_folder, 't10k-labels-idx1-ubyte.gz'), True).reshape(-1)\n",
         "\n",
         "# send a random row from the test set to score\n",
         "random_index = np.random.randint(0, len(X_test)-1)\n",

how-to-use-azureml/ml-frameworks/chainer/train-hyperparameter-tune-deploy-with-chainer/train-hyperparameter-tune-deploy-with-chainer.yml

@@ -10,3 +10,4 @@ dependencies:
   - gzip
   - struct
   - requests
+  - azureml-opendatasets

how-to-use-azureml/ml-frameworks/chainer/train-hyperparameter-tune-deploy-with-chainer/utils.py

@@ -0,0 +1,50 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import glob
+import gzip
+import numpy as np
+import os
+import struct
+
+from azureml.core import Dataset
+from azureml.opendatasets import MNIST
+from chainer.datasets import tuple_dataset
+
+
+# load compressed MNIST gz files and return numpy arrays
+def load_data(filename, label=False):
+    with gzip.open(filename) as gz:
+        struct.unpack('I', gz.read(4))
+        n_items = struct.unpack('>I', gz.read(4))
+        if not label:
+            n_rows = struct.unpack('>I', gz.read(4))[0]
+            n_cols = struct.unpack('>I', gz.read(4))[0]
+            res = np.frombuffer(gz.read(n_items[0] * n_rows * n_cols), dtype=np.uint8)
+            res = res.reshape(n_items[0], n_rows * n_cols)
+        else:
+            res = np.frombuffer(gz.read(n_items[0]), dtype=np.uint8)
+            res = res.reshape(n_items[0], 1)
+    return res
+
+
+def download_mnist():
+    data_folder = os.path.join(os.getcwd(), 'data/mnist')
+    os.makedirs(data_folder, exist_ok=True)
+
+    mnist_file_dataset = MNIST.get_file_dataset()
+    mnist_file_dataset.download(data_folder, overwrite=True)
+
+    X_train = load_data(glob.glob(os.path.join(data_folder, "**/train-images-idx3-ubyte.gz"),
+                        recursive=True)[0], False) / 255.0
+    X_test = load_data(glob.glob(os.path.join(data_folder, "**/t10k-images-idx3-ubyte.gz"),
+                       recursive=True)[0], False) / 255.0
+    y_train = load_data(glob.glob(os.path.join(data_folder, "**/train-labels-idx1-ubyte.gz"),
+                        recursive=True)[0], True).reshape(-1)
+    y_test = load_data(glob.glob(os.path.join(data_folder, "**/t10k-labels-idx1-ubyte.gz"),
+                       recursive=True)[0], True).reshape(-1)
+
+    train = tuple_dataset.TupleDataset(X_train.astype(np.float32), y_train.astype(np.int32))
+    test = tuple_dataset.TupleDataset(X_test.astype(np.float32), y_test.astype(np.int32))
+
+    return train, test

how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.ipynb

@@ -33,7 +33,9 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "## Install required packages"
+        "## Install required packages\n",
+        "\n",
+        "This notebook works with Fairlearn v0.4.6, and not later versions. If needed, please uncomment and run the following cell:"
       ]
     },
     {
@@ -42,9 +44,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "%pip install --upgrade fairlearn\n",
-        "%pip install --upgrade interpret-community\n",
-        "%pip install --upgrade raiwidgets"
+        "# %pip install --upgrade fairlearn==0.4.6"
       ]
     },
     {
@@ -71,8 +71,6 @@
       "source": [
         "from fairlearn.reductions import GridSearch\n",
         "from fairlearn.reductions import DemographicParity, ErrorRate\n",
-        "from fairlearn.datasets import fetch_adult\n",
-        "from fairlearn.metrics import MetricFrame, selection_rate\n",
         "\n",
         "from sklearn import svm, neighbors, tree\n",
         "from sklearn.compose import ColumnTransformer, make_column_selector\n",
@@ -83,6 +81,7 @@
         "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
         "from sklearn.svm import SVC\n",
         "from sklearn.metrics import accuracy_score\n",
+        "from sklearn.datasets import fetch_openml\n",
         "\n",
         "import pandas as pd\n",
         "import numpy as np\n",
@@ -106,7 +105,7 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dataset = fetch_adult(as_frame=True)\n",
+        "dataset = fetch_openml(data_id=1590, as_frame=True)\n",
         "X_raw, y = dataset['data'], dataset['target']\n",
         "X_raw[\"race\"].value_counts().to_dict()"
       ]
@@ -342,13 +341,13 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from raiwidgets import FairnessDashboard\n",
+        "from fairlearn.widget import FairlearnDashboard\n",
         "\n",
         "y_pred = model.predict(X_test)\n",
         "\n",
-        "FairnessDashboard(sensitive_features=sensitive_features_test,\n",
-        "                  y_true=y_test,\n",
-        "                  y_pred=y_pred)"
+        "FairlearnDashboard(sensitive_features=sensitive_features_test,\n",
+        "                   y_true=y_test,\n",
+        "                   y_pred=y_pred)"
       ]
     },
     {
@@ -404,7 +403,7 @@
         "sweep.fit(X_train_prep, y_train,\n",
         "          sensitive_features=sensitive_features_train.sex)\n",
         "\n",
-        "predictors = sweep.predictors_"
+        "predictors = sweep._predictors"
       ]
     },
     {
@@ -420,13 +419,18 @@
       "metadata": {},
       "outputs": [],
       "source": [
+        "from fairlearn.metrics import demographic_parity_difference\n",
+        "\n",
         "accuracies, disparities = [], []\n",
         "\n",
         "for predictor in predictors:\n",
-        "    accuracy_metric_frame = MetricFrame(accuracy_score, y_train, predictor.predict(X_train_prep), sensitive_features=sensitive_features_train.sex)\n",
-        "    selection_rate_metric_frame = MetricFrame(selection_rate, y_train, predictor.predict(X_train_prep), sensitive_features=sensitive_features_train.sex)\n",
-        "    accuracies.append(accuracy_metric_frame.overall)\n",
-        "    disparities.append(selection_rate_metric_frame.difference())\n",
+        "    y_pred = predictor.predict(X_train_prep)\n",
+        "    # accuracy_metric_frame = MetricFrame(accuracy_score, y_train, predictor.predict(X_train_prep), sensitive_features=sensitive_features_train.sex)\n",
+        "    # selection_rate_metric_frame = MetricFrame(selection_rate, y_train, predictor.predict(X_train_prep), sensitive_features=sensitive_features_train.sex)\n",
+        "    accuracies.append(accuracy_score(y_train, y_pred))\n",
+        "    disparities.append(demographic_parity_difference(y_train,\n",
+        "                                                     y_pred,\n",
+        "                                                     sensitive_features=sensitive_features_train.sex))\n",
         "    \n",
         "all_results = pd.DataFrame({\"predictor\": predictors, \"accuracy\": accuracies, \"disparity\": disparities})\n",
         "\n",
@@ -456,8 +460,6 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "from raiwidgets import FairnessDashboard\n",
-        "\n",
         "dashboard_all = {}\n",
         "for name, predictor in all_models_dict.items():\n",
         "    value = predictor.predict(X_test_prep)\n",
@@ -467,7 +469,7 @@
         "for name, predictor in dominant_models_dict.items():\n",
         "    dominant_all[name] = predictor.predict(X_test_prep)\n",
         "\n",
-        "FairnessDashboard(sensitive_features=sensitive_features_test, \n",
+        "FairlearnDashboard(sensitive_features=sensitive_features_test, \n",
         "                  y_true=y_test,\n",
         "                  y_pred=dominant_all)"
       ]
@@ -551,7 +553,7 @@
       "cell_type": "markdown",
       "metadata": {},
       "source": [
-        "Next, we register each of the models in the `dashboard_predicted` dictionary into the workspace. For this, we have to save each model to a file, and then register that file:"
+        "Next, we register each of the models in the `dominant_all` dictionary into the workspace. For this, we have to save each model to a file, and then register that file:"
       ]
     },
     {
@@ -576,7 +578,7 @@
         "    return registered_model.id\n",
         "\n",
         "model_name_id_mapping = dict()\n",
-        "for name, model in dashboard_all.items():\n",
+        "for name, model in dominant_all.items():\n",
         "    m_id = register_model(name, model)\n",
         "    model_name_id_mapping[name] = m_id"
       ]
@@ -594,9 +596,9 @@
       "metadata": {},
       "outputs": [],
       "source": [
-        "dashboard_all_ids = dict()\n",
-        "for name, y_pred in dashboard_all.items():\n",
-        "    dashboard_all_ids[model_name_id_mapping[name]] = y_pred"
+        "dominant_all_ids = dict()\n",
+        "for name, y_pred in dominant_all.items():\n",
+        "    dominant_all_ids[model_name_id_mapping[name]] = y_pred"
       ]
     },
     {
@@ -619,7 +621,7 @@
         "from fairlearn.metrics._group_metric_set import _create_group_metric_set\n",
         "\n",
         "dash_dict_all = _create_group_metric_set(y_true=y_test,\n",
-        "                                         predictions=dashboard_all_ids,\n",
+        "                                         predictions=dominant_all_ids,\n",
         "                                         sensitive_features=sf,\n",
         "                                         prediction_type='binary_classification')"
       ]

how-to-use-azureml/responsible-ai/visualize-upload-loan-decision/rai-loan-decision.yml

@@ -5,7 +5,7 @@ dependencies:
   - azureml-interpret
   - azureml-contrib-fairness
   - interpret-community[visualization]
-  - fairlearn
+  - fairlearn==0.4.6
   - matplotlib
   - azureml-dataset-runtime
   - ipywidgets