randallwhitman

diff --git a/README.md b/README.md
index e0381ae..ad8b512 100644
--- a/README.md
+++ b/README.md
@@ -71,7 +71,7 @@ Find a bug or want to request a new feature?  Please let us know by submitting a
 Esri welcomes contributions from anyone and everyone. Please see our [guidelines for contributing](https://github.com/esri/contributing)
 
 ## Licensing
-Copyright 2013-2019 Esri
+Copyright 2013-2020 Esri

randallwhitman

create external table trips_by_origin_cell(leftlon double, botlat double, rightlon double, toplat double, totnum int, samedest int, pct double, destlhs double, destbot double, destrhs double, desttop double)
row format delimited fields terminated by '\t'
location '/user/rwhitman/out-trips-by-origin-cell';

create external table trip_origin_json  (totnum int, samedest int, pct double, destlhs double, destbot double, destrhs double, desttop double, shape binary)
row format serde 'com.esri.hadoop.hive.serde.JsonSerde'
stored as inputformat 'com.esri.json.hadoop.UnenclosedJsonInputFormat'
outputformat 'org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
location '/user/rwhitman/trip-origin-json';

randallwhitman

env HADOOP_CLASSPATH=../lib/esri-geometry-api.jar:../lib/spatial-sdk-hadoop.jar \
  hadoop jar trip-discovery.jar com.esri.hadoop.examples.trip.TripCellDrv \
  -libjars ../lib/esri-geometry-api.jar,../lib/spatial-sdk-hadoop.jar \
  15 500 trips/japan-tokyo-gcs.json trips/vehicle-positions.csv out-trips-inferred

env HADOOP_CLASSPATH=../lib/esri-geometry-api.jar \
  hadoop jar trip-discovery.jar com.esri.hadoop.examples.trip.TripCorrDrv \
  -libjars ../lib/esri-geometry-api.jar \
  1 'out-trips-inferred/part-r-*' out-trips-by-origin-cell

randallwhitman

public class TripCellMap extends Mapper<LongWritable, Text, Text, CarSortWritable> {

    // column indices for values in the vehicle CSV
    static final int COL_CAR = 0;  // vehicle ID
    static final int COL_DAT = 1;  // date in YYMMDD
    static final int COL_TIM = 2;  // time in HHMMSS
    static final int COL_LON = 3;  // longitude in DMS
    static final int COL_LAT = 4;  // latitude in DMS
    static final int COL_DIR = 5;  // compass orientation in degrees
    static final int COL_SPD = 6;  // speed in km/h

randallwhitman

    public void reduce(Text key, Iterable<TripCorrWrit> values, Context ctx)
        throws IOException, InterruptedException {

        final int INIT_SIZE = 8000;
        HashMap<String,Long> records = new HashMap<String,Long>(INIT_SIZE);

        String sval, maxDest = null;
        long totCount = 0, maxCount = 0;
        for (TripCorrWrit entry : values) {
            sval = entry.toString();  // bounds of destination cell - value of iterator, key of hashmap

randallwhitman

    public void reduce(Text key, Iterable<CarSortWritable> values, Context ctx)
        throws IOException, InterruptedException {

        String[] kys = key.toString().split(",");  // carID & date
        Text outKy = new Text(kys[0]);

        // Expect at most tens of thousands of positions per car per day - expect up to thousands.
        // (per year, up to 2-3 hundreds of thousands)
        final int MAX_BUFFER_SIZE = 8000;  // would fit a record every 11s all day
        ArrayList<CarSortWritable> records = new ArrayList<CarSortWritable>(MAX_BUFFER_SIZE);

randallwhitman

    private int queryGrid(double longitude, double latitude) {
        int cellIndex; // xIdx + xCount * yIdx
        if (longitude >= lonMin && longitude <= lonMax  &&
            latitude >= latMin  && latitude <= latMax)  {   // avoid outliers
            int xIdx = (int)((longitude-lonMin)/arcLon);
            if (xIdx >= 0 && xIdx < xCount) {
                int yIdx = (int)(yCount*(latitude-latMin)/latExtent);  // approximate, to refine
                yIdx = yIdx < yCount ? yIdx : yCount - 1;
                cellIndex = xIdx + xCount * yIdx;
                // Expect either correct, or one of either too high or too low, not both

randallwhitman

    @Override
    public void setup(Context context)
    {
        // first pull values from the configuration     
        Configuration config = context.getConfiguration();

        int minutes = config.getInt("com.esri.trip.threshold", 15);  //minutes stoppage delineating trips
        threshold = minutes * 60;  // minutes -> seconds

        double gridSide = 1000.;   // Nominal/average/target length of side of grid cell (meters)