[GitHub] [beam] AnandInguva commented on a diff in pull request #22088: sklearn runinference regression example

[GitBox <gi...@apache.org>]

AnandInguva commented on code in PR #22088:
URL: https://github.com/apache/beam/pull/22088#discussion_r911226530


##########
sdks/python/apache_beam/examples/inference/sklearn_japanese_housing_regression.py:
##########
@@ -0,0 +1,161 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one or more
+# contributor license agreements.  See the NOTICE file distributed with
+# this work for additional information regarding copyright ownership.
+# The ASF licenses this file to You under the Apache License, Version 2.0
+# (the "License"); you may not use this file except in compliance with
+# the License.  You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+"""A pipeline that uses RunInference API on a regression about housing prices.
+
+This example uses the japanese housing data from kaggle.
+
+Since the data has missing fields, this example illustrates how to split
+data and assign it to appropriate models. The predictions are then recombined.
+
+In order to set this example up, you will need two things.
+1. Build models (or use ours) and reference those via the model directory.
+2. Download the data from kaggle and host it.
+"""
+
+import argparse
+from typing import Iterable
+
+import apache_beam as beam
+from apache_beam.io.filesystems import FileSystems
+from apache_beam.ml.inference.base import RunInference
+from apache_beam.ml.inference.sklearn_inference import ModelFileType
+from apache_beam.ml.inference.sklearn_inference import SklearnModelHandlerPandas
+from apache_beam.options.pipeline_options import PipelineOptions
+from apache_beam.options.pipeline_options import SetupOptions
+import pandas
+
+MODELS = [{
+    'name': 'all_features',
+    'required_features': [
+        'Area',
+        'Year',
+        'MinTimeToNearestStation',
+        'MaxTimeToNearestStation',
+        'TotalFloorArea',
+        'Frontage',
+        'Breadth',
+        'BuildingYear'
+    ]
+},
+          {
+              'name': 'floor_area',
+              'required_features': ['Area', 'Year', 'TotalFloorArea']
+          },
+          {
+              'name': 'stations',
+              'required_features': [
+                  'Area',
+                  'Year',
+                  'MinTimeToNearestStation',
+                  'MaxTimeToNearestStation'
+              ]
+          }, {
+              'name': 'no_features', 'required_features': ['Area', 'Year']
+          }]
+
+
+def sort_by_features(dataframe, max_size):
+  """ Partitions the dataframe by what data it has available."""
+  for i, model in enumerate(MODELS):
+    required_features = dataframe[model['required_features']]
+    if not required_features.isnull().any().any():
+      return i
+  return -1
+
+
+def load_dataframe(file_name: str) -> Iterable[pandas.DataFrame]:

Review Comment:
   Can we change this to a DoFn?



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: github-unsubscribe@beam.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org