Updated examples, split into standalone directories, fixed pylint issues

CHANGELOG.md

@@ -5,6 +5,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
 ## Unreleased
+- Breaking API changes in RequestMetadata for column metadata access
+- Updates examples, split into separate standalone directories
 
 ## 0.1.22 - 2024-08-05
 

README.md

@@ -17,9 +17,9 @@ Find the docs at https://disyinformationssysteme.github.io/cadenza-analytics-pyt
 
 
 ## Example:
-An example extension can be found in [examples/extension/example_extensions.py](examples/extension/example_extensions.py).
+Example extension can be found in [examples](examples).
 
-To test the example extension, clone this repository, install the dependencies, navigate to the folder `examples/extension`. Run the example file in your python environment e.g.:
+To test a example extension, clone this repository, install the dependencies, navigate to the folder, e.g. `examples/calculation/extension`. Run the example file in your python environment e.g.:
 ```
 python example_extensions.py
 ```
@@ -56,7 +56,7 @@ To run the example (and your production application) in a docker container you w
 The provided Dockerfile in the examples uses gunicorn with some example options, for more details consult the [documentation](https://docs.gunicorn.org/en/latest/settings.html). Important is that gunicorn has access to a function creating or providing the flask app object, which for `cadenzanalytics` is the `CadenzaAnalyticsExtensionService`.
 The requirements file can use test releases when adding `--extra-index-url https://test.pypi.org/simple` in the first line. It can (re)define versions of its own or transient dependencies, but most importantly needs the `cadenzaanalytics` dependency.
 ```commandline
-cd /examples
+cd /examples/calculation
 docker build . -t cadenza-analytics-example
 docker image list
 docker run -p 8080:8080 YOUR_CREATED_IMAGE_ID 

examples/Dockerfile → examples/calculation/Dockerfile

@@ -1,12 +1,18 @@
-FROM registry.disy.net/docker-hub-proxy/library/python:3.11.0-slim 
+FROM python:3.11-slim
 
 RUN mkdir /service
 RUN mkdir /service/logs
 COPY ./requirements.txt /service/requirements.txt
 COPY ./extension /service/extension
 WORKDIR /service
 
-RUN apt-get update && apt-get -y upgrade
-RUN pip install -r requirements.txt
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        gcc \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir -r requirements.txt
 
 CMD ["gunicorn", "-w", "4", "-b", ":8080", "--chdir", "extension", "example_extensions:analytics_service()", "--access-logfile", "../logs/access.log"]

examples/calculation/extension/example_extensions.py

@@ -0,0 +1,33 @@
+"""Example module for running a disy Cadenza analytics extension that
+ will show a (static) image in disy Cadenza"""
+import pandas as pd
+
+import cadenzaanalytics as ca
+
+
+def calculation_echo_analytics_function(metadata: ca.RequestMetadata, data: pd.DataFrame):
+    return ca.CsvResponse(data, metadata.get_columns_by_attribute_group()['any_data'])
+
+
+any_attribute_group = ca.AttributeGroup(
+    name="any_data",
+    print_name="Any attribute",
+    # any except geometry, these cannot be mixed to make it clear when a geometry or a related
+    # non-geometry attribute is wanted from the user
+    data_types=[ca.DataType.STRING, ca.DataType.INT64, ca.DataType.FLOAT64, ca.DataType.ZONEDDATETIME],
+    min_attributes=1
+)
+
+calculation_echo_extension = ca.CadenzaAnalyticsExtension(
+    relative_path="calculation-echo-extension",
+    analytics_function=calculation_echo_analytics_function,
+    print_name="Example Echo Calculation Extension",
+    extension_type=ca.ExtensionType.CALCULATION,
+    attribute_groups=[any_attribute_group]
+)
+
+analytics_service = ca.CadenzaAnalyticsExtensionService()
+analytics_service.add_analytics_extension(calculation_echo_extension)
+
+if __name__ == '__main__':
+    analytics_service.run_development_server(5005)

examples/calculation/requirements.txt

@@ -0,0 +1,7 @@
+# --extra-index-url https://test.pypi.org/simple
+Flask>=2.2.5
+Flask-Cors>=3.0.10
+gunicorn>=20.1.0
+requests-toolbelt>=1.0.0
+pandas>=2.0.2
+cadenzaanalytics

examples/enrichment/.dockerignore

@@ -0,0 +1,2 @@
+**/__pycache__
+*.py[cod]

examples/enrichment/Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.11-slim
+
+RUN mkdir /service
+RUN mkdir /service/logs
+COPY ./requirements.txt /service/requirements.txt
+COPY ./extension /service/extension
+WORKDIR /service
+
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        gcc \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+CMD ["gunicorn", "-w", "4", "-b", ":8080", "--chdir", "extension", "example_extensions:analytics_service()", "--access-logfile", "../logs/access.log"]

examples/extension/example_extensions.py → examples/enrichment/extension/example_extensions.py

@@ -5,33 +5,15 @@
 import cadenzaanalytics as ca
 
 
-def image_analytics_function(metadata: ca.RequestMetadata, data: pd.DataFrame):
-    # pylint: disable=unused-argument
-    with open("example_image.png", "rb") as image_file:
-        image = image_file.read()
-
-    return ca.ImageResponse(image)
-
-
-def calculation_echo_analytics_function(metadata: ca.RequestMetadata, data: pd.DataFrame):
-    return ca.CsvResponse(data, metadata.get_all_columns_by_attribute_group()['any_data'])
-
-
 def enrichment_echo_analytics_function(metadata: ca.RequestMetadata, data: pd.DataFrame):
     # pylint: disable=unused-argument
-    response_columns = metadata.get_all_columns_by_attribute_group()['any_data']
+    response_columns = metadata.get_columns_by_attribute_group()['any_data']
     response_column_names = [c.name for c in response_columns]
     return ca.RowWiseMappingCsvResponse(
         response_columns,
         lambda row: row[response_column_names])
 
 
-image_attribute_group = ca.AttributeGroup(
-    name="data",
-    print_name="Data",
-    data_types=[ca.DataType.STRING]
-)
-
 any_attribute_group = ca.AttributeGroup(
     name="any_data",
     print_name="Any attribute",
@@ -41,22 +23,6 @@ def enrichment_echo_analytics_function(metadata: ca.RequestMetadata, data: pd.Da
     min_attributes=1
 )
 
-image_extension = ca.CadenzaAnalyticsExtension(
-    relative_path="image-extension",
-    analytics_function=image_analytics_function,
-    print_name="Example Image Extension",
-    extension_type=ca.ExtensionType.VISUALIZATION,
-    attribute_groups=[image_attribute_group]
-)
-
-calculation_echo_extension = ca.CadenzaAnalyticsExtension(
-    relative_path="calculation-echo-extension",
-    analytics_function=calculation_echo_analytics_function,
-    print_name="Example Echo Calculation Extension",
-    extension_type=ca.ExtensionType.CALCULATION,
-    attribute_groups=[any_attribute_group]
-)
-
 enrichment_echo_extension = ca.CadenzaAnalyticsExtension(
     relative_path="echo-extension",
     analytics_function=enrichment_echo_analytics_function,
@@ -66,8 +32,6 @@ def enrichment_echo_analytics_function(metadata: ca.RequestMetadata, data: pd.Da
 )
 
 analytics_service = ca.CadenzaAnalyticsExtensionService()
-analytics_service.add_analytics_extension(image_extension)
-analytics_service.add_analytics_extension(calculation_echo_extension)
 analytics_service.add_analytics_extension(enrichment_echo_extension)
 
 if __name__ == '__main__':

examples/enrichment/requirements.txt

@@ -0,0 +1,7 @@
+# --extra-index-url https://test.pypi.org/simple
+Flask>=2.2.5
+Flask-Cors>=3.0.10
+gunicorn>=20.1.0
+requests-toolbelt>=1.0.0
+pandas>=2.0.2
+cadenzaanalytics

examples/visualization/.dockerignore

@@ -0,0 +1,2 @@
+**/__pycache__
+*.py[cod]

examples/visualization/Dockerfile

@@ -0,0 +1,18 @@
+FROM python:3.11-slim
+
+RUN mkdir /service
+RUN mkdir /service/logs
+COPY ./requirements.txt /service/requirements.txt
+COPY ./extension /service/extension
+WORKDIR /service
+
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y --no-install-recommends \
+        build-essential \
+        gcc \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+CMD ["gunicorn", "-w", "4", "-b", ":8080", "--chdir", "extension", "example_extensions:analytics_service()", "--access-logfile", "../logs/access.log"]

examples/visualization/extension/example_extensions.py

@@ -0,0 +1,34 @@
+"""Example module for running a disy Cadenza analytics extension that
+ will show a (static) image in disy Cadenza"""
+import pandas as pd
+
+import cadenzaanalytics as ca
+
+
+def image_analytics_function(metadata: ca.RequestMetadata, data: pd.DataFrame):
+    # pylint: disable=unused-argument
+    with open("resources/example_image.png", "rb") as image_file:
+        image = image_file.read()
+
+    return ca.ImageResponse(image)
+
+
+image_attribute_group = ca.AttributeGroup(
+    name="data",
+    print_name="Data",
+    data_types=[ca.DataType.STRING]
+)
+
+image_extension = ca.CadenzaAnalyticsExtension(
+    relative_path="image-extension",
+    analytics_function=image_analytics_function,
+    print_name="Example Image Extension",
+    extension_type=ca.ExtensionType.VISUALIZATION,
+    attribute_groups=[image_attribute_group]
+)
+
+analytics_service = ca.CadenzaAnalyticsExtensionService()
+analytics_service.add_analytics_extension(image_extension)
+
+if __name__ == '__main__':
+    analytics_service.run_development_server(5005)

examples/visualization/requirements.txt

@@ -0,0 +1,7 @@
+# --extra-index-url https://test.pypi.org/simple
+Flask>=2.2.5
+Flask-Cors>=3.0.10
+gunicorn>=20.1.0
+requests-toolbelt>=1.0.0
+pandas>=2.0.2
+cadenzaanalytics

src/cadenzaanalytics/cadenza_analytics_extension_service.py

@@ -1,5 +1,6 @@
-"""Provides a service which encapsulates the configuration and execution of individual analytics extensions. Runs a http server which
-executes the individual extensions analytics function and serves an extension discovery endpoint."""
+"""Provides a service which encapsulates the configuration and execution of individual analytics extensions.
+Runs a http server which executes the individual extensions analytics function and serves an extension
+discovery endpoint."""
 import json
 
 from flask import Flask, Response
@@ -39,7 +40,7 @@ def add_analytics_extension(self, analytics_extension: CadenzaAnalyticsExtension
                                methods=['POST'])
 
     def run_development_server(self, port: int = 5000):
-        """Start a development server wich runs the service.
+        """Start a development server which runs the service.
 
         Parameters:
         ----------

src/cadenzaanalytics/data/analytics_extension.py

@@ -7,7 +7,8 @@
 
 
 class AnalyticsExtension(DataObject):
-    """A class representing an analytics extension containing print_name, extension_type, attribute_groups and parameters.
+    """A class representing an analytics extension containing print_name, extension_type, attribute_groups
+     and parameters.
 
     Parameters
     ----------

src/cadenzaanalytics/data/attribute_group.py

@@ -8,7 +8,8 @@
 
 
 class AttributeGroup(DataObject):
-    """A class representing a group of attributes such as name, print_name, data_types, geometry_types, min_attributes and max_attributes.
+    """A class representing a group of attributes such as name, print_name, data_types, geometry_types,
+     min_attributes and max_attributes.
 
     Parameters
     ----------

src/cadenzaanalytics/data/column_metadata.py

@@ -9,7 +9,8 @@
 
 # pylint: disable=too-many-instance-attributes
 class ColumnMetadata(DataObject):
-    """A class representing metadata for columns such as the name, print_name, attribute_group_name, data_type, role, measure_aggregation, format and gemetry_type.
+    """A class representing metadata for columns such as the name, print_name, attribute_group_name, data_type, role,
+     measure_aggregation, format and geometry_type.
 
     Parameters
     ----------

src/cadenzaanalytics/data/geometry_type.py

@@ -2,7 +2,8 @@
 
 
 class GeometryType(Enum):
-    """A class representing different types of geometries such as point, linestring, polygon, multipoint, multilinestring, multipolygon.
+    """A class representing different types of geometries such as point, linestring, polygon, multipoint,
+     multilinestring, multipolygon.
     """
     POINT = "point"
     LINESTRING = "linestring"

src/cadenzaanalytics/data/measure_aggregation.py

@@ -2,7 +2,8 @@
 
 
 class MeasureAggregation(Enum):
-    """A class representing various aggregation functions for measures such as count, countDistinct, sum, average, min and max.
+    """A class representing various aggregation functions for measures such as count, countDistinct,
+    sum, average, min and max.
     """
     COUNT = "count"
     COUNT_DISTINCT = "countDistinct"

src/cadenzaanalytics/data/parameter.py

@@ -5,7 +5,8 @@
 
 
 class Parameter(DataObject):
-    """A class representing parameters such as name, print_name, parameter_type, options, required and default_value used in data objects.
+    """A class representing parameters such as name, print_name, parameter_type, options, required
+    and default_value used in data objects.
 
     Parameters
     ----------