close davidkhala/BI-collection#6

Author: davidkhala

.github/workflows/data.yaml

@@ -20,4 +20,14 @@ jobs:
         with:
           tests: frame/tests
           test-entry-point: pytest
-          working-directory: frame
+          working-directory: frame
+  dash:
+    runs-on: ubuntu-latest
+    env:
+      container: dash
+    steps:
+      - uses: actions/checkout@main
+      - run: export DOCKER_BUILDKIT=1
+      - run: docker build -t dash:latest visualization/app/dash
+      - run: docker run --name $container -d dash:latest
+      - run: curl https://raw.githubusercontent.com/davidkhala/containers/refs/heads/main/cli/health.sh | bash -s wait-until-healthy $container

visualization/README.md

@@ -0,0 +1,7 @@
+FROM python
+RUN pip install dash
+RUN pip install pandas
+ADD gapminder_unfiltered.py .
+HEALTHCHECK --interval=1s CMD curl --fail http://localhost:8050/health || exit 1
+ENTRYPOINT [ "python", "gapminder_unfiltered.py" ]
+EXPOSE 8050

visualization/app/dash/Dockerfile

@@ -0,0 +1,31 @@
+from dash import Dash, html, dcc, callback, Output, Input
+from plotly import express
+import pandas
+
+df = pandas.read_csv('https://raw.githubusercontent.com/plotly/datasets/master/gapminder_unfiltered.csv')
+
+app = Dash()
+
+app.layout = [
+    html.H1(children='Title of Dash App', style={'textAlign': 'center'}),
+    dcc.Dropdown(df.country.unique(), 'Canada', id='dropdown-selection'),
+    dcc.Graph(id='graph-content')
+]
+
+
+@callback(
+    Output('graph-content', 'figure'),
+    Input('dropdown-selection', 'value')
+)
+def update_graph(value):
+    dff = df[df.country == value]
+    return express.line(dff, x='year', y='pop')
+
+
+@app.server.route('/health')
+def is_health():
+    return 'OK'
+
+
+if __name__ == '__main__':
+    app.run('0.0.0.0', debug=True)

visualization/app/dash/gapminder_unfiltered.py

@@ -0,0 +1,6 @@
+# Matplotlib library
+> The Matplotlib library requires data to be in a Pandas dataframe rather than a Spark dataframe
+- > [**toPandas** method is used to convert it](https://learn.microsoft.com/en-us/training/modules/use-apache-spark-work-files-lakehouse/6-visualize-data)
+
+
+> Python supports a large selection of packages; most of them built on the base **Matplotlib** library.

visualization/davidkhala/data/visualization/dash/__init__.py

@@ -0,0 +1,25 @@
+[project]
+name = "davidkhala.data.visualization"
+version = "0.0.0"
+description = "data visualization tools"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = []
+
+[project.optional-dependencies]
+dash = ["dash"]
+streamlit = ["streamlit"]
+
+
+[dependency-groups]
+dev = ["pytest","pandas"]
+
+[tool.hatch.build.targets.sdist]
+include = ["davidkhala"]
+
+[tool.hatch.build.targets.wheel]
+include = ["davidkhala"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"