From 13dedec4a4e5fc863ffcf51173c9b597d3133c74 Mon Sep 17 00:00:00 2001
From: James Gan <ganzhi@gmail.com>
Date: Mon, 17 Jun 2019 13:38:27 -0700
Subject: [PATCH] Make it in same folder as internal repo

---
 .../azure-ml-datadrift.ipynb                  |  0
 how-to-use-azureml/data-drift/readme.md       |  2 +-
 how-to-use-azureml/data-drift/score.py        | 58 +++++++++++++++++++
 3 files changed, 59 insertions(+), 1 deletion(-)
 rename how-to-use-azureml/data-drift/{data-drift-model => }/azure-ml-datadrift.ipynb (100%)
 create mode 100644 how-to-use-azureml/data-drift/score.py

diff --git a/how-to-use-azureml/data-drift/data-drift-model/azure-ml-datadrift.ipynb b/how-to-use-azureml/data-drift/azure-ml-datadrift.ipynb
similarity index 100%
rename from how-to-use-azureml/data-drift/data-drift-model/azure-ml-datadrift.ipynb
rename to how-to-use-azureml/data-drift/azure-ml-datadrift.ipynb
diff --git a/how-to-use-azureml/data-drift/readme.md b/how-to-use-azureml/data-drift/readme.md
index ad6f9d96..9eb416c2 100644
--- a/how-to-use-azureml/data-drift/readme.md
+++ b/how-to-use-azureml/data-drift/readme.md
@@ -1,3 +1,3 @@
 ## Using data drift APIs
 
-1. [Detect data drift for a model](data-drift-model): Detect data drift for a deployed model.
\ No newline at end of file
+1. [Detect data drift for a model](azure-ml-datadrift.ipynb): Detect data drift for a deployed model.
\ No newline at end of file
diff --git a/how-to-use-azureml/data-drift/score.py b/how-to-use-azureml/data-drift/score.py
new file mode 100644
index 00000000..cda62f8b
--- /dev/null
+++ b/how-to-use-azureml/data-drift/score.py
@@ -0,0 +1,58 @@
+import pickle
+import json
+import numpy
+import azureml.train.automl
+from sklearn.externals import joblib
+from sklearn.linear_model import Ridge
+from azureml.core.model import Model
+from azureml.core.run import Run
+from azureml.monitoring import ModelDataCollector
+import time
+import pandas as pd
+
+
+def init():
+    global model, inputs_dc, prediction_dc, feature_names, categorical_features
+
+    print("Model is initialized" + time.strftime("%H:%M:%S"))
+    model_path = Model.get_model_path(model_name="driftmodel")
+    model = joblib.load(model_path)
+
+    feature_names = ["usaf", "wban", "latitude", "longitude", "station_name", "p_k",
+                     "sine_weekofyear", "cosine_weekofyear", "sine_hourofday", "cosine_hourofday",
+                     "temperature-7"]
+
+    categorical_features = ["usaf", "wban", "p_k", "station_name"]
+
+    inputs_dc = ModelDataCollector(model_name="driftmodel",
+                                   identifier="inputs",
+                                   feature_names=feature_names)
+
+    prediction_dc = ModelDataCollector("driftmodel",
+                                       identifier="predictions",
+                                       feature_names=["temperature"])
+
+
+def run(raw_data):
+    global inputs_dc, prediction_dc
+
+    try:
+        data = json.loads(raw_data)["data"]
+        data = pd.DataFrame(data)
+
+        # Remove the categorical features as the model expects OHE values
+        input_data = data.drop(categorical_features, axis=1)
+
+        result = model.predict(input_data)
+
+        # Collect the non-OHE dataframe
+        collected_df = data[feature_names]
+
+        inputs_dc.collect(collected_df.values)
+        prediction_dc.collect(result)
+        return result.tolist()
+    except Exception as e:
+        error = str(e)
+
+        print(error + time.strftime("%H:%M:%S"))
+        return error