public static final void main(String args[]) throws IOException {
String outdir = "/home/johannes/gsv/miv-matrix/qs2013/";
String matrixFile = "/home/johannes/gsv/miv-matrix/qs2013/matrix.txt";
String zoneFile = "/home/johannes/gsv/gis/zones/geojson/nuts3.psm.gk3.geojson";
String inhabFile = "/home/johannes/gsv/miv-matrix/qs2013/inhabitants.csv";
final NumericMatrix carVol = new NumericMatrix();
final NumericMatrix railVol = new NumericMatrix();
final NumericMatrix airVol = new NumericMatrix();
logger.info("Loading zones...");
ZoneCollection zones = ZoneGeoJsonIO.readFromGeoJSON(zoneFile, "NO");
TObjectDoubleHashMap<String> zoneRho = calcDensity(inhabFile, zones);
logger.info("Reading matrix...");
MatrixReader mReader = new MatrixReader();
mReader.read(
matrixFile,
new MatrixReader.RowHandler() {
@Override
public void handleRow(
String from,
String to,
String purpose,
String year,
String mode,
String direction,
String day,
String season,
double volume) {
if (mode.equalsIgnoreCase("M")) {
carVol.add(from, to, volume);
} else if (mode.equalsIgnoreCase("B")) {
railVol.add(from, to, volume);
} else if (mode.equalsIgnoreCase("F")) {
airVol.add(from, to, volume);
}
}
});
logger.info("Calculating shares per od-pair...");
NumericMatrix carShare = new NumericMatrix();
NumericMatrix railShare = new NumericMatrix();
NumericMatrix airShare = new NumericMatrix();
NumericMatrix odCounts = new NumericMatrix();
Discretizer discr = FixedSampleSizeDiscretizer.create(zoneRho.values(), 1, 20);
// Discretizer discr = new DummyDiscretizer();
Set<String> keys = carVol.keys();
keys.addAll(railVol.keys());
keys.addAll(airVol.keys());
ProgressLogger.init(keys.size(), 2, 10);
for (String from : keys) {
for (String to : keys) {
Double car = carVol.get(from, to);
if (car == null) car = 0.0;
Double rail = railVol.get(from, to);
if (rail == null) rail = 0.0;
Double air = airVol.get(from, to);
if (air == null) air = 0.0;
if (car > 0 && rail > 0 && air > 0) {
double total = car + rail + air;
double fromRho = zoneRho.get(from);
double toRho = zoneRho.get(to);
fromRho = discr.discretize(fromRho);
toRho = discr.discretize(toRho);
String fromRhoStr = String.valueOf(fromRho);
String toRhoStr = String.valueOf(toRho);
odCounts.add(fromRhoStr, toRhoStr, 1);
// odCounts.add(fromRhoStr, toRhoStr, total);
carShare.add(fromRhoStr, toRhoStr, car / total);
railShare.add(fromRhoStr, toRhoStr, rail / total);
airShare.add(fromRhoStr, toRhoStr, air / total);
}
}
ProgressLogger.step();
}
ProgressLogger.terminate();
logger.info("Calculating averages...");
keys = odCounts.keys();
for (String from : keys) {
for (String to : keys) {
Double count = odCounts.get(from, to);
if (count != null) {
carShare.multiply(from, to, 1 / count);
railShare.multiply(from, to, 1 / count);
airShare.multiply(from, to, 1 / count);
}
}
}
logger.info("Writing matrices...");
NumericMatrixTxtIO.write(carShare, String.format("%s/carShare.txt", outdir));
NumericMatrixTxtIO.write(railShare, String.format("%s/railShare.txt", outdir));
NumericMatrixTxtIO.write(airShare, String.format("%s/airShare.txt", outdir));
logger.info("Done.");
}
private void loadSociogramData(Collection<VertexRecord> records, SQLDumpReader sqlData) {
logger.info("Loading sociogram data...");
Map<String, VertexRecord> map = sqlData.getFullAlterKeyMappping(records);
TObjectIntHashMap<Vertex> rawDegrees = new TObjectIntHashMap<Vertex>();
for (Vertex v : proj.getVertices()) {
rawDegrees.put(v, v.getNeighbours().size());
}
int edgecnt = 0;
int doublecnt = 0;
int egoEdge = 0;
Set<Vertex> notOkVertices = new HashSet<Vertex>();
Set<Vertex> okVertices = new HashSet<Vertex>();
DescriptiveStatistics notOkStats = new DescriptiveStatistics();
DescriptiveStatistics okStats = new DescriptiveStatistics();
DescriptiveStatistics numDistr = new DescriptiveStatistics();
DescriptiveStatistics numDistrNoZero = new DescriptiveStatistics();
DescriptiveStatistics sizeDistr = new DescriptiveStatistics();
TDoubleArrayList sizeValues = new TDoubleArrayList();
TDoubleArrayList kSizeValues = new TDoubleArrayList();
TDoubleArrayList numValues = new TDoubleArrayList();
TDoubleArrayList numValues2 = new TDoubleArrayList();
TDoubleArrayList kNumValues = new TDoubleArrayList();
for (VertexRecord record : records) {
if (record.isEgo) {
List<Set<String>> cliques = sqlData.getCliques(record);
numDistr.addValue(cliques.size());
Vertex v = idMap.get(record.id);
numValues.add(cliques.size());
kNumValues.add(v.getNeighbours().size());
if (!cliques.isEmpty()) numDistrNoZero.addValue(cliques.size());
for (Set<String> clique : cliques) {
sizeDistr.addValue(clique.size());
sizeValues.add(clique.size());
kSizeValues.add(rawDegrees.get(projMap.get(v)));
numValues2.add(cliques.size());
List<SocialSparseVertex> vertices = new ArrayList<SocialSparseVertex>(clique.size());
for (String alter : clique) {
VertexRecord r = map.get(record.egoSQLId + alter);
if (r != null) {
SocialSparseVertex vertex = idMap.get(r.id);
if (vertex != null) {
vertices.add(vertex);
} else {
logger.warn("Vertex not found.");
}
} else {
logger.warn("Record not found.");
}
}
for (int i = 0; i < vertices.size(); i++) {
for (int j = i + 1; j < vertices.size(); j++) {
SampledVertexDecorator<SocialSparseVertex> vProj1 = projMap.get(vertices.get(i));
SampledVertexDecorator<SocialSparseVertex> vProj2 = projMap.get(vertices.get(j));
if (!vProj1.isSampled() && !vProj2.isSampled()) {
if (Math.random() < 0.62) {
SocialSparseEdge socialEdge =
builder.addEdge(graph, vertices.get(i), vertices.get(j));
if (socialEdge != null) {
projBuilder.addEdge(proj, vProj1, vProj2, socialEdge);
edgecnt++;
if (vProj1.isSampled() || vProj2.isSampled()) {
egoEdge++;
if (vProj1.isSampled()) notOkVertices.add(vProj1);
else notOkVertices.add(vProj2);
}
} else {
doublecnt++;
if (vProj1.isSampled()) okVertices.add(vProj1);
else if (vProj2.isSampled()) okVertices.add(vProj2);
}
}
}
}
}
}
}
}
for (Vertex v : okVertices) okStats.addValue(rawDegrees.get(v));
for (Vertex v : notOkVertices) notOkStats.addValue(rawDegrees.get(v));
try {
TDoubleDoubleHashMap hist =
Histogram.createHistogram(okStats, new LinearDiscretizer(1), false);
StatsWriter.writeHistogram(
hist,
"k",
"n",
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/k_ok.txt");
TDoubleDoubleHashMap hist2 =
Histogram.createHistogram(notOkStats, new LinearDiscretizer(1), false);
StatsWriter.writeHistogram(
hist2,
"k",
"n",
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/k_notok.txt");
TDoubleDoubleHashMap ratio = new TDoubleDoubleHashMap();
double[] keys = hist.keys();
for (double k : keys) {
double val1 = hist2.get(k);
double val2 = hist.get(k);
ratio.put(k, val1 / (val2 + val1));
}
StatsWriter.writeHistogram(
ratio,
"k",
"p",
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/k_ratio.txt");
logger.info("Mean num of cliques: " + numDistrNoZero.getMean());
logger.info("Mean size: " + sizeDistr.getMean());
logger.info("Median num of cliques: " + StatUtils.percentile(numDistrNoZero.getValues(), 50));
logger.info("Median size: " + StatUtils.percentile(sizeDistr.getValues(), 50));
TDoubleDoubleHashMap histNum =
Histogram.createHistogram(
numDistrNoZero,
FixedSampleSizeDiscretizer.create(numDistrNoZero.getValues(), 2, 20),
true);
Histogram.normalize(histNum);
StatsWriter.writeHistogram(
histNum,
"num",
"freq",
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/numCliques.txt");
TDoubleDoubleHashMap histSize =
Histogram.createHistogram(
sizeDistr, FixedSampleSizeDiscretizer.create(sizeDistr.getValues(), 2, 20), true);
Histogram.normalize(histSize);
StatsWriter.writeHistogram(
histSize,
"size",
"freq",
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/numPersons.txt");
Discretizer discretizer =
FixedSampleSizeDiscretizer.create(kSizeValues.toNativeArray(), 20, 20);
TDoubleArrayList valuesX = new TDoubleArrayList();
for (int i = 0; i < kSizeValues.size(); i++) {
valuesX.add(discretizer.discretize(kSizeValues.get(i)));
}
Correlations.writeToFile(
Correlations.mean(valuesX.toNativeArray(), sizeValues.toNativeArray()),
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/size_k.txt",
"k",
"size");
discretizer = FixedSampleSizeDiscretizer.create(kNumValues.toNativeArray(), 20, 20);
valuesX = new TDoubleArrayList();
for (int i = 0; i < kNumValues.size(); i++) {
valuesX.add(discretizer.discretize(kNumValues.get(i)));
}
Correlations.writeToFile(
Correlations.mean(valuesX.toNativeArray(), numValues.toNativeArray()),
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/num_k.txt",
"k",
"n");
Correlations.writeToFile(
Correlations.mean(numValues2.toNativeArray(), sizeValues.toNativeArray()),
"/Users/jillenberger/Work/socialnets/data/ivt2009/11-2011/augmented/size_num.txt",
"num",
"size");
} catch (FileNotFoundException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
logger.info(
String.format("Inserted %1$s edges, %2$s edges already present.", edgecnt, doublecnt));
logger.info(String.format("Inserted %1$s edges between at least one ego.", egoEdge));
}
