Bump version to v0.2.0 for release

closes #9

.github/actions/setup-venv/action.yml

@@ -30,8 +30,7 @@ runs:
       id: virtualenv-cache
       with:
         path: .venv
-        key: ${{ inputs.cache-prefix }}-${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('requirements.txt', 'dev-requirements.txt') }}
-
+        key: ${{ inputs.cache-prefix }}-${{ runner.os }}-${{ env.PYTHON_VERSION }}-${{ hashFiles('Pipfile.lock') }}
     - if: steps.virtualenv-cache.outputs.cache-hit != 'true'
       shell: bash
       run: |

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2022, Felix Spöttel
+Copyright (c) 2022, Stichting Bellingcat
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -39,6 +39,12 @@ pip install .
 ```
 Usage: geoclustering [OPTIONS] FILENAME
 
+  Tool to cluster geolocations. A cluster is created when a certain number of
+  points (--size) each are within a given distance (--distance) of at least
+  one other point in the cluster. Input is supplied as a csv file. At a
+  minimum, each row needs to have a 'lat' and a 'lon' column. Other rows are
+  reflected to the output.
+
 Options:
   -d, --distance FLOAT            (in km) Max. distance between two points in
                                   a cluster.  [required]
@@ -50,6 +56,9 @@ Options:
                                   Clustering algorithm to be used. `optics`
                                   produces tighter clusters but is slower.
                                   Default: dbscan
+  --open                          Open the generated visualization in the
+                                  default browser automatically.
+  --debug                         Print debug output.
   --help                          Show this message and exit.
 ```
 

geoclustering/__main__.py

@@ -1,4 +1,6 @@
+from pathlib import Path
 import click
+import os
 import webbrowser
 
 import geoclustering.clustering as clustering
@@ -6,7 +8,13 @@ import geoclustering.encoding as encoding
 import geoclustering.io as io
 
 
-@click.command()
+def print_debug(s):
+    click.secho(s, fg="bright_black")
+
+
+@click.command(
+    help="Tool to cluster geolocations. A cluster is created when a certain number of points (--size) each are within a given distance (--distance) of at least one other point in the cluster. Input is supplied as a csv file. At a minimum, each row needs to have a 'lat' and a 'lon' column. Other rows are reflected to the output."
+)
 @click.option(
     "--distance",
     "-d",
@@ -38,9 +46,20 @@ import geoclustering.io as io
     default="dbscan",
     help="Clustering algorithm to be used. `optics` produces tighter clusters but is slower. Default: dbscan",
 )
+@click.option(
+    "--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):
+def main(distance, size, output, filename, algorithm, open, debug):
+    if debug:
+        print_debug(f"Reading input from {Path(filename).absolute()}")
+
     df = io.read_csv_file(filename)
+    if debug:
+        print_debug(f"Read {len(df)} valid coordinates")
 
     clusters = clustering.cluster_locations(
         df=df, algorithm=algorithm, radius_km=distance, min_cluster_size=size
@@ -50,14 +69,19 @@ def main(distance, size, output, filename, algorithm):
         click.echo("Did not find clusters matching input parameters.")
         return
 
+    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"])
     vis = io.write_visualization(output, "result.html", encoded["geojson"])
+    click.echo(f"Output files saved to {Path(output).absolute()}")
 
-    webbrowser.open_new_tab("file://" + str(vis.absolute()))
+    if open:
+        print_debug(f"Opening visualization in default browser")
+        webbrowser.open_new_tab("file://" + str(vis.absolute()))
 
 
 if __name__ == "__main__":

geoclustering/clustering.py

@@ -14,8 +14,6 @@ def to_cluster_dict(df, clustering):
     """
     clusters_by_id = {}
 
-    print(clustering.labels_)
-
     for idx, cluster_id in enumerate(clustering.labels_):
         # ignore "noise" locations that don't belong to any cluster.
         if cluster_id > -1:

geoclustering/io.py

@@ -2,9 +2,22 @@ from keplergl import KeplerGl
 from pathlib import Path
 from pkg_resources import resource_filename
 import json
-import json
 import pandas as pd
 import numpy as np
+import os
+import sys
+
+
+class HiddenPrints:
+    """Disables stdout prints for a block of code."""
+
+    def __enter__(self):
+        self._original_stdout = sys.stdout
+        sys.stdout = open(os.devnull, "w")
+
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        sys.stdout.close()
+        sys.stdout = self._original_stdout
 
 
 def is_valid_lat(val: str) -> bool:
@@ -64,7 +77,10 @@ def write_output_file(dirname, filename, data):
 
 def write_visualization(dirname, filename, data):
     """Write a visualization, ensuring parent directories."""
-    map = KeplerGl()
+    # Hide kepler stdout output.
+    with HiddenPrints():
+        map = KeplerGl()
+
     map.add_data(data=data, name="clusters")
 
     # config configures a default color scheme for our clusters layer.
@@ -73,6 +89,9 @@ def write_visualization(dirname, filename, data):
         map.config = json.loads(f.read())
 
     filepath = ensure_file_path(dirname, filename)
-    map.save_to_html(file_name=str(filepath), center_map=True)
+
+    # Hide kepler stdout output.
+    with HiddenPrints():
+        map.save_to_html(file_name=str(filepath), center_map=True)
 
     return filepath

geoclustering/kepler_config.json

@@ -9,7 +9,7 @@
           "config": {
             "dataId": "clusters",
             "label": "clusters",
-            "color": [179, 173, 158],
+            "color": [248, 149, 112],
             "highlightColor": [252, 242, 26, 255],
             "columns": { "geojson": "_geojson" },
             "isVisible": true,
@@ -19,16 +19,30 @@
               "thickness": 0.5,
               "strokeColor": null,
               "colorRange": {
-                "name": "Global Warming",
-                "type": "sequential",
+                "name": "Uber Viz Qualitative 4",
+                "type": "qualitative",
                 "category": "Uber",
                 "colors": [
-                  "#5A1846",
-                  "#900C3F",
-                  "#C70039",
-                  "#E3611C",
-                  "#F1920E",
-                  "#FFC300"
+                  "#12939A",
+                  "#DDB27C",
+                  "#88572C",
+                  "#FF991F",
+                  "#F15C17",
+                  "#223F9A",
+                  "#DA70BF",
+                  "#125C77",
+                  "#4DC19C",
+                  "#776E57",
+                  "#17B8BE",
+                  "#F6D18A",
+                  "#B7885E",
+                  "#FFCB99",
+                  "#F89570",
+                  "#829AE3",
+                  "#E79FD5",
+                  "#1E96BE",
+                  "#89DAC1",
+                  "#B3AD9E"
                 ]
               },
               "strokeColorRange": {

geoclustering/version.py

@@ -1,8 +1,8 @@
 _MAJOR = "0"
-_MINOR = "1"
+_MINOR = "2"
 # On main and in a nightly release the patch should be one ahead of the last
 # released build.
-_PATCH = "3"
+_PATCH = "0"
 # 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 = ""