migrate gh artifact actions to v4 (#20)

* migrate gh artifact actions to v4

from migration guide no breaking changes apply here.

* updates pipfile.lock dependency versions

* updates CI due to pytest issue see https://github.com/scipy/scipy/issues/22236

* bump to python 3.12

* revert to py3.10

.github/workflows/main.yml

@@ -36,17 +36,19 @@ jobs:
               run: |
                 python setup.py check
                 python setup.py bdist_wheel sdist
-
           - python: "3.10"
             task:
-              name: "Style"
+              name: "Lint"
               run: |
                 black --check .
           - python: "3.10"
             task:
               name: "Test"
-              run: pytest --exitfirst --failed-first
-
+              run: pytest --exitfirst --failed-first --assert=plain
+          - python: "3.8"
+            task:
+              name: "Test (3.8)"
+              run: pytest --exitfirst --failed-first --assert=plain
     steps:
       - uses: actions/checkout@v3
 
@@ -63,7 +65,7 @@ jobs:
 
       - name: Upload package distribution files
         if: matrix.task.name == 'Build'
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: package
           path: dist
@@ -97,7 +99,7 @@ jobs:
           echo "TAG=${GITHUB_REF#refs/tags/}" >> $GITHUB_ENV
 
       - name: Download package distribution files
-        uses: actions/download-artifact@v3
+        uses: actions/download-artifact@v4
         with:
           name: package
           path: dist

Pipfile

@@ -16,6 +16,7 @@ black = "*"
 pre-commit = "*"
 pytest = "*"
 wheel = "*"
+geoclustering = {editable = true, path = "."}
 
 [requires]
 python_version = "3.9"

README.md

@@ -72,7 +72,7 @@ id,name,lat,lon
 
 ## Output
 
-If at least one cluster was found, the tool outputs a folder with output as `json`, `geojson`, `txt` files. A kepler.gl `html` file is generated as well.
+If at least one cluster was found, the tool outputs a folder with output as `json`, `geojson`, `txt`, `csv` files. A kepler.gl `html` file is generated as well.
 
 ### JSON
 
@@ -132,6 +132,16 @@ id 9, name Rosanna Foggo, lat -6.2074293, lon 106.8915948
 // ...
 ```
 
+### CSV
+
+Encodes each event in one line with `cluster_id` information associated.
+
+```csv
+cluster_id,name,lat,lon
+9,Rosanna Foggo,-6.2074293,106.8915948
+...
+```
+
 ### kepler.gl
 
 ![kepler.gl instance](https://user-images.githubusercontent.com/1682504/176478177-c0446b51-4060-495c-803d-79e2bbd3e966.png)
@@ -142,10 +152,19 @@ It is assumed that you are using **Python3.9+**. It is encouraged to [setup a vi
 
 ```sh
     # install dependencies & dev-dependencies
+    # PIP
     pip install -e .[dev,full]
+    # PIPENV
+    pipenv install --dev -e .
 
     # install a git hook that runs the code formatter before each commit.
     pre-commit install
 ```
 
 We use [Black](https://github.com/psf/black) as our code formatter. If you don't want to use the `pre-commit` hook, you can run the formatter manually or via an editor plugin.
+
+## Release
+
+1. Update [version.py](geoclustering/version.py)
+2. Run `scripts/release.sh` 
+3. Confirm GH action completed successfully

geoclustering/__main__.py

@@ -1,6 +1,5 @@
 from pathlib import Path
 import click
-import os
 import webbrowser
 
 import geoclustering.clustering as clustering
@@ -44,12 +43,13 @@ import geoclustering.io as io
 )
 @click.option(
     "--open",
+    "_open",
     is_flag=True,
     help="Open the generated visualization in the default browser automatically.",
 )
 @click.option("--debug", is_flag=True, help="Print debug output.")
 @click.argument("filename", type=click.Path(exists=True))
-def main(distance, size, output, filename, algorithm, open, debug):
+def main(distance, size, output, filename, algorithm, _open, debug):
     def print_debug(s):
         if debug:
             click.secho(s, fg="bright_black")
@@ -68,21 +68,21 @@ def main(distance, size, output, filename, algorithm, open, debug):
     print_debug(f"Found {len(clusters)} valid clusters using {algorithm}")
 
     encoded = encoding.encode_clusters(clusters)
-
     io.write_output_file(output, "result.txt", encoded["string"])
     io.write_output_file(output, "result.json", encoded["json"])
     io.write_output_file(output, "result.geojson", encoded["geojson"])
+    io.write_output_file(output, "result.csv", encoded["csv"])
 
     vis = io.write_visualization(output, "result.html", encoded["geojson"])
     if vis is None:
-        print_debug(f"Skipped generating visualization: kepler is not installed.")
+        print_debug("Skipped generating visualization: kepler is not installed.")
 
     click.echo(f"Output files saved to {Path(output).absolute()}")
 
-    if open:
+    if _open:
         if vis:
             webbrowser.open_new_tab("file://" + str(vis.absolute()))
-            print_debug(f"Opened visualization in default browser.")
+            print_debug("Opened visualization in default browser.")
         else:
             click.secho(
                 "Can't open kepler.gl: package not installed. Please re-install geoclustering with `pip install geoclustering[full]`.",

geoclustering/encoding.py

@@ -1,6 +1,8 @@
 import json
 import numpy as np
 import geojson
+import csv
+import io  # not io.py
 
 
 class NpEncoder(json.JSONEncoder):
@@ -47,7 +49,7 @@ class JSONEncoder:
 
         for record in cluster:
             cluster_data["points"].append(record)
-            self.state.append(cluster_data)
+        self.state.append(cluster_data)
 
     def get(self):
         return json.dumps(self.state, cls=NpEncoder)
@@ -74,13 +76,37 @@ class GeoJSONEncoder:
         return json.dumps(geojson.FeatureCollection(self.state), cls=NpEncoder)
 
 
+class CSVEncoder:
+    """Encodes clustering result as a CSV"""
+
+    def __init__(self):
+        self.state = io.StringIO()
+        self.writer = False
+
+    def visitor(self, cluster_id, cluster):
+        if not self.writer:
+            self.writer = csv.DictWriter(
+                self.state,
+                fieldnames=["cluster_id"] + list(cluster[0].keys()),
+                quoting=csv.QUOTE_NONNUMERIC,
+                lineterminator="\n",
+            )
+            self.writer.writeheader()
+
+        for record in cluster:
+            self.writer.writerow({**record, "cluster_id": cluster_id})
+
+    def get(self):
+        return self.state.getvalue()
+
+
 def encode_clusters(clusters):
     json_encoder = JSONEncoder()
     geojson_encoder = GeoJSONEncoder()
     string_encoder = StringEncoder()
+    csv_encoder = CSVEncoder()
 
-    encoders = [json_encoder, geojson_encoder, string_encoder]
-
+    encoders = [json_encoder, geojson_encoder, string_encoder, csv_encoder]
     for cluster_id, cluster in clusters.items():
         for encoder in encoders:
             encoder.visitor(cluster_id, cluster)
@@ -89,4 +115,5 @@ def encode_clusters(clusters):
         "json": json_encoder.get(),
         "geojson": geojson_encoder.get(),
         "string": string_encoder.get(),
+        "csv": csv_encoder.get(),
     }

geoclustering/io.py

@@ -58,13 +58,16 @@ def read_csv_file(filename):
     valid_index = df.lat.apply(is_valid_lat) & df.lon.apply(is_valid_lon)
     df_invalid = df[~valid_index]
 
-    if count_invalid := len(df_invalid):
+    count_invalid = len(df_invalid)
+    if count_invalid:
         df_not_empty = df_invalid[
             (df_invalid.lat.apply(is_not_none) | df_invalid.lon.apply(is_not_none))
         ]
-        count_not_empty = len(df_not_empty)
 
-        if count_empty := count_invalid - count_not_empty:
+        count_not_empty = len(df_not_empty)
+        count_empty = count_invalid - count_not_empty
+
+        if count_empty:
             print(f"Removed {count_empty} empty coordinate pairs.")
 
         if count_not_empty:

geoclustering/version.py

@@ -1,8 +1,8 @@
 _MAJOR = "0"
-_MINOR = "3"
+_MINOR = "4"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "0"
+_PATCH = "1"
 # This is mainly for nightly builds which have the suffix ".dev$DATE". See
 # https://semver.org/#is-v123-a-semantic-version for the semantics.
 _SUFFIX = ""

tests/clustering.py

@@ -1,6 +1,5 @@
 from geoclustering.clustering import cluster_locations
-from geoclustering.io import read_csv_file
-from tests.helpers import get_fixture_path, read_fixture_csv
+from tests.helpers import read_fixture_csv
 
 
 df = read_fixture_csv("clustering.csv")

tests/encoding.py

@@ -1,4 +1,3 @@
-from geoclustering.clustering import cluster_locations
 from geoclustering.encoding import encode_clusters
 from tests.helpers import read_fixture_csv, read_fixture_content
 
@@ -28,3 +27,4 @@ def test_encoders():
     assert res["string"] == read_fixture_content("snapshots/result.txt")
     assert res["json"] == read_fixture_content("snapshots/result.json")
     assert res["geojson"] == read_fixture_content("snapshots/result.geojson")
+    assert res["csv"] == read_fixture_content("snapshots/result.csv")

tests/fixtures/snapshots/result.csv

@@ -0,0 +1,5 @@
+"cluster_id","id","name","lat","lon"
+0,1,"Alice",52.523955,13.442362
+0,2,"Bob",52.526659,13.448097
+1,3,"Carol",52.525626,13.419246
+1,4,"Dan",52.52443559865125,13.41261723049818

tests/fixtures/snapshots/result.json

@@ -1 +1 @@
-[{"cluster_id": 0, "points": [{"id": 1, "name": "Alice", "lat": 52.523955, "lon": 13.442362}, {"id": 2, "name": "Bob", "lat": 52.526659, "lon": 13.448097}]}, {"cluster_id": 0, "points": [{"id": 1, "name": "Alice", "lat": 52.523955, "lon": 13.442362}, {"id": 2, "name": "Bob", "lat": 52.526659, "lon": 13.448097}]}, {"cluster_id": 1, "points": [{"id": 3, "name": "Carol", "lat": 52.525626, "lon": 13.419246}, {"id": 4, "name": "Dan", "lat": 52.52443559865125, "lon": 13.41261723049818}]}, {"cluster_id": 1, "points": [{"id": 3, "name": "Carol", "lat": 52.525626, "lon": 13.419246}, {"id": 4, "name": "Dan", "lat": 52.52443559865125, "lon": 13.41261723049818}]}]
+[{"cluster_id": 0, "points": [{"id": 1, "name": "Alice", "lat": 52.523955, "lon": 13.442362}, {"id": 2, "name": "Bob", "lat": 52.526659, "lon": 13.448097}]}, {"cluster_id": 1, "points": [{"id": 3, "name": "Carol", "lat": 52.525626, "lon": 13.419246}, {"id": 4, "name": "Dan", "lat": 52.52443559865125, "lon": 13.41261723049818}]}]