From ce3214b7c6af8b114473311bc6b2b481cc479d35 Mon Sep 17 00:00:00 2001
From: Sheri Gilley <sgilley@microsoft.com>
Date: Tue, 16 Oct 2018 17:33:24 -0500
Subject: [PATCH] fix name

---
 .../how-to-deploy-to-aci.py                   |  4 +--
 docs/how-to-deploy-to-aci/utils.py            | 27 +++++++++++++++++++
 2 files changed, 29 insertions(+), 2 deletions(-)
 create mode 100644 docs/how-to-deploy-to-aci/utils.py

diff --git a/docs/how-to-deploy-to-aci/how-to-deploy-to-aci.py b/docs/how-to-deploy-to-aci/how-to-deploy-to-aci.py
index 0ff289d2..13252ddd 100644
--- a/docs/how-to-deploy-to-aci/how-to-deploy-to-aci.py
+++ b/docs/how-to-deploy-to-aci/how-to-deploy-to-aci.py
@@ -6,10 +6,10 @@ print('SDK version' + azureml.core.VERSION)
 
 # PREREQ: load workspace info
 # import azureml.core
-# <load_workspace>
+# <load-workspace>
 from azureml.core import Workspace
 ws = Workspace.from_config()
-# </load_workspace>
+# </load-workspace>
 
 scorepy_content = "import json\nimport numpy as np\nimport os\nimport pickle\nfrom sklearn.externals import joblib\nfrom sklearn.linear_model import LogisticRegression\n\nfrom azureml.core.model import Model\n\ndef init():\n    global model\n    # retreive the path to the model file using the model name\n    model_path = Model.get_model_path('sklearn_mnist')\n    model = joblib.load(model_path)\n\ndef run(raw_data):\n    data = np.array(json.loads(raw_data)['data'])\n    # make prediction\n    y_hat = model.predict(data)\n    return json.dumps(y_hat.tolist())"
 print(scorepy_content)
diff --git a/docs/how-to-deploy-to-aci/utils.py b/docs/how-to-deploy-to-aci/utils.py
new file mode 100644
index 00000000..98170ada
--- /dev/null
+++ b/docs/how-to-deploy-to-aci/utils.py
@@ -0,0 +1,27 @@
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License.
+
+import gzip
+import numpy as np
+import struct
+
+
+# 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
+
+
+# one-hot encode a 1-D array
+def one_hot_encode(array, num_of_classes):
+    return np.eye(num_of_classes)[array.reshape(-1)]