added activity dashboard and activity analysis

contribs/application/src/main/java/org/matsim/application/analysis/activity/ActivityCountAnalysis.java

@@ -0,0 +1,163 @@
+package org.matsim.application.analysis.activity;
+
+import it.unimi.dsi.fastutil.objects.Object2ObjectOpenHashMap;
+import it.unimi.dsi.fastutil.objects.Object2IntMap;
+import it.unimi.dsi.fastutil.objects.Object2IntOpenHashMap;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import org.geotools.api.feature.Feature;
+import org.geotools.api.feature.Property;
+import org.matsim.api.core.v01.Coord;
+import org.matsim.application.CommandSpec;
+import org.matsim.application.MATSimAppCommand;
+import org.matsim.application.options.*;
+import org.matsim.core.utils.io.IOUtils;
+import picocli.CommandLine;
+import tech.tablesaw.api.*;
+import tech.tablesaw.io.csv.CsvReadOptions;
+import tech.tablesaw.selection.Selection;
+
+import java.util.*;
+import java.util.regex.Pattern;
+
+@CommandSpec(
+	requires = {"activities.csv"},
+	produces = {"activities_%s_per_region.csv"}
+)
+public class ActivityCountAnalysis implements MATSimAppCommand {
+
+	private static final Logger log = LogManager.getLogger(ActivityCountAnalysis.class);
+
+	@CommandLine.Mixin
+	private final InputOptions input = InputOptions.ofCommand(ActivityCountAnalysis.class);
+	@CommandLine.Mixin
+	private final OutputOptions output = OutputOptions.ofCommand(ActivityCountAnalysis.class);
+	@CommandLine.Mixin
+	private ShpOptions shp;
+	@CommandLine.Mixin
+	private SampleOptions sample;
+	@CommandLine.Option(names = "--id-column", description = "Column to use as ID for the shapefile", required = true)
+	private String idColumn;
+
+	@CommandLine.Option(names = "--activity-mapping", description = "Map of patterns to merge activity types", split = ";")
+	private Map<String, String> activityMapping;
+
+	public static void main(String[] args) {
+		new ActivityCountAnalysis().execute(args);
+	}
+
+	@Override
+	public Integer call() throws Exception {
+
+		HashMap<String, Set<String>> formattedActivityMapping = new HashMap<>();
+
+		if (this.activityMapping == null) this.activityMapping = new HashMap<>();
+
+		for (Map.Entry<String, String> entry : this.activityMapping.entrySet()) {
+			String pattern = entry.getKey();
+			String activity = entry.getValue();
+			Set<String> activities = new HashSet<>(Arrays.asList(activity.split(",")));
+			formattedActivityMapping.put(pattern, activities);
+		}
+
+		// Reading the input csv
+		Table activities = Table.read().csv(CsvReadOptions.builder(IOUtils.getBufferedReader(input.getPath("activities.csv")))
+			.columnTypesPartial(Map.of("person", ColumnType.TEXT, "activity_type", ColumnType.TEXT))
+			.sample(false)
+			.separator(CsvOptions.detectDelimiter(input.getPath("activities.csv"))).build());
+
+		// remove the underscore and the number from the activity_type column
+		TextColumn activityType = activities.textColumn("activity_type");
+		activityType.set(Selection.withRange(0, activityType.size()), activityType.replaceAll("_[0-9]{2,}$", ""));
+
+		ShpOptions.Index index = shp.createIndex(idColumn);
+
+
+		// stores the counts of activities per region
+		Object2ObjectOpenHashMap<Object, Object2IntMap<String>> regionActivityCounts = new Object2ObjectOpenHashMap<>();
+		// stores the activities that have been counted for each person in each region
+		Object2ObjectOpenHashMap<Object, Set<String>> personActivityTracker = new Object2ObjectOpenHashMap<>();
+
+		// iterate over the csv rows
+		for (Row row : activities) {
+			String person = row.getString("person");
+			String activity = row.getText("activity_type");
+
+			for (Map.Entry<String, Set<String>> entry : formattedActivityMapping.entrySet()) {
+				String pattern = entry.getKey();
+				Set<String> activities2 = entry.getValue();
+				for (String act : activities2) {
+					if (Pattern.matches(act, activity)) {
+						activity = pattern;
+						break;
+					}
+				}
+			}
+
+			Coord coord = new Coord(row.getDouble("coord_x"), row.getDouble("coord_y"));
+
+			// get the region for the current coordinate
+			Feature feature = index.queryFeature(coord);
+
+			if (feature == null) {
+				continue;
+			}
+
+			Property prop = feature.getProperty(idColumn);
+			if (prop == null)
+				throw new IllegalArgumentException("No property found for column %s".formatted(idColumn));
+
+			Object region = prop.getValue();
+			if (region != null && region.toString().length() > 0) {
+
+				// Add region to the activity counts and person activity tracker if not already present
+				regionActivityCounts.computeIfAbsent(region, k -> new Object2IntOpenHashMap<>());
+				personActivityTracker.computeIfAbsent(region, k -> new HashSet<>());
+
+				Set<String> trackedActivities = personActivityTracker.get(region);
+				String personActivityKey = person + "_" + activity;
+
+				// adding activity only if it has not been counted for the person in the region
+				if (!trackedActivities.contains(personActivityKey)) {
+					Object2IntMap<String> activityCounts = regionActivityCounts.get(region);
+					activityCounts.mergeInt(activity, 1, Integer::sum);
+
+					// mark the activity as counted for the person in the region
+					trackedActivities.add(personActivityKey);
+				}
+			}
+		}
+
+		Set<String> uniqueActivities = new HashSet<>();
+
+		for (Object2IntMap<String> map : regionActivityCounts.values()) {
+			uniqueActivities.addAll(map.keySet());
+		}
+
+		for (String activity : uniqueActivities) {
+			Table resultTable = Table.create();
+			TextColumn regionColumn = TextColumn.create("region");
+			DoubleColumn activityColumn = DoubleColumn.create("count");
+			resultTable.addColumns(regionColumn, activityColumn);
+			for (Map.Entry<Object, Object2IntMap<String>> entry : regionActivityCounts.entrySet()) {
+				Object region = entry.getKey();
+				double value = 0;
+				for (Map.Entry<String, Integer> entry2 : entry.getValue().object2IntEntrySet()) {
+					String ect = entry2.getKey();
+					if (Pattern.matches(ect, activity)) {
+						value = entry2.getValue() * sample.getUpscaleFactor();
+						break;
+					}
+				}
+				Row row = resultTable.appendRow();
+				row.setString("region", region.toString());
+				row.setDouble("count", value);
+			}
+			resultTable.addColumns(activityColumn.divide(activityColumn.sum()).setName("count_normalized"));
+			resultTable.write().csv(output.getPath("activities_%s_per_region.csv", activity).toFile());
+			log.info("Wrote activity counts for {} to {}", activity, output.getPath("activities_%s_per_region.csv", activity));
+		}
+
+		return 0;
+	}
+}

contribs/application/src/main/java/org/matsim/application/options/ShpOptions.java

@@ -230,6 +230,7 @@ public Geometry getGeometry() {
 
 	/**
 	 * Return the union of all geometries in the shape file and project it to the target crs.
+	 *
 	 * @param toCRS target coordinate system
 	 */
 	public Geometry getGeometry(String toCRS) {

contribs/simwrapper/src/main/java/org/matsim/simwrapper/Data.java

@@ -1,5 +1,6 @@
 package org.matsim.simwrapper;
 
+import com.google.common.io.Resources;
 import org.apache.commons.io.FilenameUtils;
 import org.matsim.application.CommandRunner;
 import org.matsim.application.MATSimAppCommand;
@@ -186,6 +187,17 @@ public String resource(String name) {
 		return this.getUnixPath(this.path.getParent().relativize(resolved));
 	}
 
+	public String resources(String... names) {
+		String first = null;
+		for (String name : names) {
+			String resource = resource(name);
+			if (first == null)
+				first = resource;
+		}
+
+		return first;
+	}
+
 	/**
 	 * Copies an input file (which can be local or an url) to the output directory. This method is intended to copy input for analysis classes.
 	 */

contribs/simwrapper/src/main/java/org/matsim/simwrapper/dashboard/ActivityDashboard.java

@@ -0,0 +1,36 @@
+package org.matsim.simwrapper.dashboard;
+
+import org.matsim.application.analysis.activity.ActivityCountAnalysis;
+import org.matsim.simwrapper.Dashboard;
+import org.matsim.simwrapper.Header;
+import org.matsim.simwrapper.Layout;
+import org.matsim.simwrapper.viz.MapPlot;
+
+public class ActivityDashboard implements Dashboard {
+	@Override
+	public void configure(Header header, Layout layout) {
+
+		header.title = "Activity Analysis";
+		header.description = "Displays the activities by type and location.";
+
+		layout.row("activites")
+			.el(MapPlot.class, (viz, data) -> {
+				viz.title = "Activity Map";
+				viz.description = "Activities per region";
+				viz.height = 12.0;
+				viz.center = data.context().getCenter();
+				viz.zoom = data.context().mapZoomLevel;
+				viz.display.fill.dataset = "activities_home";
+
+				// --shp= + data.resource(fff.shp)
+
+				viz.display.fill.columnName = "count";
+				String shp = data.resources("kehlheim_test.shp", "kehlheim_test.shx", "kehlheim_test.dbf", "kehlheim_test.prj");
+				viz.setShape(shp);
+
+
+				viz.addDataset("activities_home", data.computeWithPlaceholder(ActivityCountAnalysis.class, "activities_%s_per_region.csv", "home", "--id-column=id", "--shp=" + shp));
+				viz.addDataset("activities_other", data.computeWithPlaceholder(ActivityCountAnalysis.class, "activities_%s_per_region.csv", "other", "--id-column=id", "--shp=" + shp));
+			});
+	}
+}

contribs/simwrapper/src/test/java/org/matsim/simwrapper/dashboard/DashboardTests.java

@@ -179,4 +179,11 @@ void ptCustom() {
 
 		run(pt);
 	}
+
+	@Test
+	void activity() {
+		ActivityDashboard ad = new ActivityDashboard();
+
+		run(ad);
+	}
 }

contribs/simwrapper/src/test/resources/kehlheim_test.cpg

@@ -0,0 +1 @@
+UTF-8

contribs/simwrapper/src/test/resources/kehlheim_test.prj

@@ -0,0 +1 @@
+PROJCS["ETRS_1989_UTM_Zone_32N",GEOGCS["GCS_ETRS_1989",DATUM["D_ETRS_1989",SPHEROID["GRS_1980",6378137.0,298.257222101]],PRIMEM["Greenwich",0.0],UNIT["Degree",0.0174532925199433]],PROJECTION["Transverse_Mercator"],PARAMETER["False_Easting",500000.0],PARAMETER["False_Northing",0.0],PARAMETER["Central_Meridian",9.0],PARAMETER["Scale_Factor",0.9996],PARAMETER["Latitude_Of_Origin",0.0],UNIT["Meter",1.0]]

contribs/simwrapper/src/test/resources/kehlheim_test.qmd

@@ -0,0 +1,27 @@
+<!DOCTYPE qgis PUBLIC 'http://mrcc.com/qgis.dtd' 'SYSTEM'>
+<qgis version="3.38.3-Grenoble">
+  <identifier></identifier>
+  <parentidentifier></parentidentifier>
+  <language></language>
+  <type>dataset</type>
+  <title></title>
+  <abstract></abstract>
+  <links/>
+  <dates/>
+  <fees></fees>
+  <encoding></encoding>
+  <crs>
+    <spatialrefsys nativeFormat="Wkt">
+      <wkt>PROJCRS["ETRS89 / UTM zone 32N",BASEGEOGCRS["ETRS89",ENSEMBLE["European Terrestrial Reference System 1989 ensemble",MEMBER["European Terrestrial Reference Frame 1989"],MEMBER["European Terrestrial Reference Frame 1990"],MEMBER["European Terrestrial Reference Frame 1991"],MEMBER["European Terrestrial Reference Frame 1992"],MEMBER["European Terrestrial Reference Frame 1993"],MEMBER["European Terrestrial Reference Frame 1994"],MEMBER["European Terrestrial Reference Frame 1996"],MEMBER["European Terrestrial Reference Frame 1997"],MEMBER["European Terrestrial Reference Frame 2000"],MEMBER["European Terrestrial Reference Frame 2005"],MEMBER["European Terrestrial Reference Frame 2014"],ELLIPSOID["GRS 1980",6378137,298.257222101,LENGTHUNIT["metre",1]],ENSEMBLEACCURACY[0.1]],PRIMEM["Greenwich",0,ANGLEUNIT["degree",0.0174532925199433]],ID["EPSG",4258]],CONVERSION["UTM zone 32N",METHOD["Transverse Mercator",ID["EPSG",9807]],PARAMETER["Latitude of natural origin",0,ANGLEUNIT["degree",0.0174532925199433],ID["EPSG",8801]],PARAMETER["Longitude of natural origin",9,ANGLEUNIT["degree",0.0174532925199433],ID["EPSG",8802]],PARAMETER["Scale factor at natural origin",0.9996,SCALEUNIT["unity",1],ID["EPSG",8805]],PARAMETER["False easting",500000,LENGTHUNIT["metre",1],ID["EPSG",8806]],PARAMETER["False northing",0,LENGTHUNIT["metre",1],ID["EPSG",8807]]],CS[Cartesian,2],AXIS["(E)",east,ORDER[1],LENGTHUNIT["metre",1]],AXIS["(N)",north,ORDER[2],LENGTHUNIT["metre",1]],USAGE[SCOPE["Engineering survey, topographic mapping."],AREA["Europe between 6°E and 12°E: Austria; Belgium; Denmark - onshore and offshore; Germany - onshore and offshore; Norway including - onshore and offshore; Spain - offshore."],BBOX[38.76,6,84.33,12]],ID["EPSG",25832]]</wkt>
+      <proj4>+proj=utm +zone=32 +ellps=GRS80 +towgs84=0,0,0,0,0,0,0 +units=m +no_defs</proj4>
+      <srsid>2105</srsid>
+      <srid>25832</srid>
+      <authid>EPSG:25832</authid>
+      <description>ETRS89 / UTM zone 32N</description>
+      <projectionacronym>utm</projectionacronym>
+      <ellipsoidacronym>EPSG:7019</ellipsoidacronym>
+      <geographicflag>false</geographicflag>
+    </spatialrefsys>
+  </crs>
+  <extent/>
+</qgis>