Add Copyright Disclaimer

.github/workflows/mlrun.yml

@@ -1,3 +1,17 @@
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
 name: mlrun-project-workflow
 on: [issue_comment]
 

gen_iris.py

@@ -1,3 +1,17 @@
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
 import pandas as pd
 from sklearn.datasets import load_iris
 

kflow.py

@@ -1,35 +1,49 @@
-import mlrun
-from kfp import dsl
-
-funcs = {}
-project = mlrun.projects.pipeline_context.project
-iris_data = 'https://s3.wasabisys.com/iguazio/data/iris/iris.data.raw.csv'
-default_pkg_class = "sklearn.linear_model.LogisticRegression"
-
-@dsl.pipeline(
-    name="Demo training pipeline",
-    description="Shows how to use mlrun."
-)
-def kfpipeline(model_pkg_class=default_pkg_class, build=0):
-
-    # if build=True, build the function image before the run
-    with dsl.Condition(build==1) as build_cond:
-        funcs["prep-data"].deploy_step(skip_deployed=True)
-
-    # run a local data prep function
-    prep_data = funcs["prep-data"].as_step(name='prep_data',
-                                           inputs={'source_url': project.get_artifact_uri("data")},
-                                           outputs=["cleaned_data"]).after(build_cond)
-
-    # train the model using a library (hub://) function and the generated data
-    train = funcs["train"].as_step(name='train',
-                                   inputs={'dataset': prep_data.outputs['cleaned_data']},
-                                   params={'model_pkg_class': model_pkg_class,
-                                           'label_column': project.get_param('label', 'label')},
-                                   outputs=["model", "test_set"])
-
-    # test the model using a library (hub://) function and the generated model
-    test = funcs["test"].as_step(name="test",
-                                 params={"label_column": "label"},
-                                 inputs={"models_path": train.outputs['model'],
-                                         "test_set": train.outputs['test_set']})
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
+import mlrun
+from kfp import dsl
+
+funcs = {}
+project = mlrun.projects.pipeline_context.project
+iris_data = 'https://s3.wasabisys.com/iguazio/data/iris/iris.data.raw.csv'
+default_pkg_class = "sklearn.linear_model.LogisticRegression"
+
+@dsl.pipeline(
+    name="Demo training pipeline",
+    description="Shows how to use mlrun."
+)
+def kfpipeline(model_pkg_class=default_pkg_class, build=0):
+
+    # if build=True, build the function image before the run
+    with dsl.Condition(build==1) as build_cond:
+        funcs["prep-data"].deploy_step(skip_deployed=True)
+
+    # run a local data prep function
+    prep_data = funcs["prep-data"].as_step(name='prep_data',
+                                           inputs={'source_url': project.get_artifact_uri("data")},
+                                           outputs=["cleaned_data"]).after(build_cond)
+
+    # train the model using a library (hub://) function and the generated data
+    train = funcs["train"].as_step(name='train',
+                                   inputs={'dataset': prep_data.outputs['cleaned_data']},
+                                   params={'model_pkg_class': model_pkg_class,
+                                           'label_column': project.get_param('label', 'label')},
+                                   outputs=["model", "test_set"])
+
+    # test the model using a library (hub://) function and the generated model
+    test = funcs["test"].as_step(name="test",
+                                 params={"label_column": "label"},
+                                 inputs={"models_path": train.outputs['model'],
+                                         "test_set": train.outputs['test_set']})

newflow.py

@@ -1,3 +1,17 @@
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
 from kfp import dsl
 
 from mlrun import build_function, deploy_function, get_current_project, run_function

prep_data.py

@@ -1,13 +1,27 @@
-import mlrun
-
-def prep_data(context, source_url: mlrun.DataItem, label_column='label'):
-    # Convert the DataItem to a pandas DataFrame
-    df = source_url.as_df()
-    print("data url:", source_url.url)
-    df[label_column] = df[label_column].astype('category').cat.codes
-
-    # Record the DataFrane length after the run
-    context.log_result('num_rows', df.shape[0])
-
-    # Store the data set in your artifacts database
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
+import mlrun
+
+def prep_data(context, source_url: mlrun.DataItem, label_column='label'):
+    # Convert the DataItem to a pandas DataFrame
+    df = source_url.as_df()
+    print("data url:", source_url.url)
+    df[label_column] = df[label_column].astype('category').cat.codes
+
+    # Record the DataFrane length after the run
+    context.log_result('num_rows', df.shape[0])
+
+    # Store the data set in your artifacts database
     context.log_dataset('cleaned_data', df=df, index=False, format='csv')

project.yaml

@@ -1,41 +1,55 @@
-kind: project
-metadata:
-  name: pipe
-spec:
-  description: test
-  params:
-    label_column: label
-  functions:
-  - url: prep_data.py
-    name: prep-data
-    image: mlrun/mlrun
-    handler: prep_data
-    with_repo: true
-  - url: hub://sklearn_classifier
-    name: train
-  - url: hub://test_classifier
-    name: test
-  - url: hub://v2_model_server
-    name: serve
-  - url: gen_iris.py
-    name: gen-iris
-    image: mlrun/mlrun
-    handler: iris_generator
-    requirements:
-    - requests
-  workflows:
-  - name: main
-    path: ./kflow.py
-    engine: kfp
-  - name: newflow
-    path: ./newflow.py
-    handler: newpipe
-  artifacts:
-  - kind: ''
-    target_path: https://s3.wasabisys.com/iguazio/data/iris/iris.data.raw.csv
-    key: data
-  source: ./
-  subpath: ''
-  origin_url: ''
-  load_source_on_run: true
-  desired_state: online
+# Copyright 2021 Iguazio
+#
+# Licensed 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.
+#
+kind: project
+metadata:
+  name: pipe
+spec:
+  description: test
+  params:
+    label_column: label
+  functions:
+  - url: prep_data.py
+    name: prep-data
+    image: mlrun/mlrun
+    handler: prep_data
+    with_repo: true
+  - url: hub://sklearn_classifier
+    name: train
+  - url: hub://test_classifier
+    name: test
+  - url: hub://v2_model_server
+    name: serve
+  - url: gen_iris.py
+    name: gen-iris
+    image: mlrun/mlrun
+    handler: iris_generator
+    requirements:
+    - requests
+  workflows:
+  - name: main
+    path: ./kflow.py
+    engine: kfp
+  - name: newflow
+    path: ./newflow.py
+    handler: newpipe
+  artifacts:
+  - kind: ''
+    target_path: https://s3.wasabisys.com/iguazio/data/iris/iris.data.raw.csv
+    key: data
+  source: ./
+  subpath: ''
+  origin_url: ''
+  load_source_on_run: true
+  desired_state: online