Add example of using scalars

Author: deliahu

examples/iris/handlers/sklearn.py

@@ -1,15 +1,28 @@
+from cortex.lib.log import get_logger
 import numpy as np
+import boto3
+import json
+
+logger = get_logger()
+s3 = boto3.client("s3")
 
 iris_labels = ["Iris-setosa", "Iris-versicolor", "Iris-virginica"]
 
+scalars_obj = s3.get_object(Bucket="cortex-examples", Key="iris/scalars.json")
+scalars = json.loads(scalars_obj["Body"].read().decode("utf-8"))
+logger.info("downloaded scalars: {}".format(scalars))
+
 
 def pre_inference(sample, metadata):
-    return [
-        sample["sepal_length"],
-        sample["sepal_width"],
-        sample["petal_length"],
-        sample["petal_width"],
-    ]
+    x = np.array(
+        [
+            sample["sepal_length"],
+            sample["sepal_width"],
+            sample["petal_length"],
+            sample["petal_width"],
+        ]
+    )
+    return ((x - scalars["mean"]) / scalars["stddev"]).astype(np.float32)
 
 
 def post_inference(prediction, metadata):

examples/iris/models/sklearn_model.py

@@ -1,11 +1,20 @@
+import numpy as np
 from sklearn.datasets import load_iris
 from sklearn.model_selection import train_test_split
 from sklearn.linear_model import LogisticRegression
+from sklearn.preprocessing import StandardScaler
 from onnxmltools import convert_sklearn
 from onnxconverter_common.data_types import FloatTensorType
 
 iris = load_iris()
 X, y = iris.data, iris.target
+
+scaler = StandardScaler()
+X = scaler.fit_transform(X)
+print("mean:", scaler.mean_)
+print("standard deviation:", np.sqrt(scaler.var_))
+
+
 X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.8, random_state=42)
 
 logreg_model = LogisticRegression(solver="lbfgs", multi_class="multinomial")