Java Table.selectWhere方法代码示例

import tech.tablesaw.api.Table; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
    Table table = Table.read().csv("../data/tornadoes_1950-2014.csv");
    Table t2 = table.countBy(table.categoryColumn("State"));
    t2 = t2.selectWhere(column("Count").isGreaterThan(100));
    show("tornadoes by state", t2.categoryColumn("Category"), t2.nCol("Count"));
    show("T", table.summarize("fatalities", sum).by("Scale"));
}
 

import tech.tablesaw.api.Table; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        Table ops = Table.create("../data/operations.csv");

        out(ops.structure());

        out(ops);

        DateTimeColumn start = ops.dateColumn("Date").atTime(ops.timeColumn("Start"));
        DateTimeColumn end = ops.dateColumn("Date").atTime(ops.timeColumn("End"));

        for (int row : ops) {
            if (ops.timeColumn("End").get(row).isBefore(ops.timeColumn("Start").get(row))) {
                end.get(row).plusDays(1);
            }
        }

        // Calc duration
        LongColumn duration = start.differenceInSeconds(end);
        ops.addColumn(duration);
        duration.setName("Duration");

        out(ops);

        Table q2_429_assembly = ops.selectWhere(
                allOf
                        (column("date").isInQ2(),
                                (column("SKU").startsWith("429")),
                                (column("Operation").isEqualTo("Assembly"))));

        Table durationByFacilityAndShift = q2_429_assembly.median("Duration").by("Facility", "Shift");

        out(durationByFacilityAndShift);

        durationByFacilityAndShift.write().csv("/tmp/durationByFacilityAndShift.csv");
    }
 

import tech.tablesaw.api.Table; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        // Get the data
        Table baseball = Table.read().csv("../data/baseball.csv");
        out(baseball.structure());

        // filter to the data available in the 2002 season
        Table moneyball = baseball.selectWhere(column("year").isLessThan(2002));

        // plot regular season wins against year, segregating on whether the team made the plays
        NumericColumn wins = moneyball.numericColumn("W");
        NumericColumn year = moneyball.numericColumn("Year");
        Column playoffs = moneyball.column("Playoffs");
        Scatter.show("Regular season wins by year", wins, year, moneyball.splitOn(playoffs));

        // Calculate the run difference for use in the regression model
        IntColumn runDifference = moneyball.shortColumn("RS").subtract(moneyball.shortColumn("RA"));
        moneyball.addColumn(runDifference);
        runDifference.setName("RD");

        // Plot RD vs Wins to see if the relationship looks linear
        Scatter.show("RD x Wins", moneyball.numericColumn("RD"), moneyball.numericColumn("W"));

        // Create the regression model
        //ShortColumn wins = moneyball.shortColumn("W");
        LeastSquares winsModel = LeastSquares.train(wins, runDifference);
        out(winsModel);

        // Make a prediction of how many games we win if we score 135 more runs than our opponents
        double[] testValue = new double[1];
        testValue[0] = 135;
        double prediction = winsModel.predict(testValue);
        out("Predicted wins with RD = 135: " + prediction);

        // Predict runsScored based on On-base percentage, batting average and slugging percentage

        LeastSquares runsScored = LeastSquares.train(moneyball.nCol("RS"),
                moneyball.nCol("OBP"), moneyball.nCol("BA"), moneyball.nCol("SLG"));
        out(runsScored);

        LeastSquares runsScored2 = LeastSquares.train(moneyball.nCol("RS"),
                moneyball.nCol("OBP"), moneyball.nCol("SLG"));
        out(runsScored2);

        Histogram.show(runsScored2.residuals());

        Scatter.fittedVsResidual(runsScored2);
        Scatter.actualVsFitted(runsScored2);

        // We use opponent OBP and opponent SLG to model the efficacy of our pitching and defence

        Table moneyball2 = moneyball.selectWhere(column("year").isGreaterThan(1998));
        LeastSquares runsAllowed = LeastSquares.train(moneyball2.nCol("RA"),
                moneyball2.nCol("OOBP"), moneyball2.nCol("OSLG"));
        out(runsAllowed);

    }
 

import tech.tablesaw.api.Table; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {
    Table table = Table.read().csv("../data/tornadoes_1950-2014.csv");
    table = table.selectWhere(column("Fatalities").isGreaterThan(3));
    Pareto.show("Tornado Fatalities by State", table.summarize("fatalities", sum).by("State"));
}
 

import tech.tablesaw.api.Table; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception {

        out("");
        out("Some Examples: ");

        // Read the CSV file
        ColumnType[] types = {INTEGER, CATEGORY, CATEGORY, FLOAT, FLOAT};
        Table table = Table.read().csv(CsvReadOptions.builder("../data/bus_stop_test.csv").columnTypes(types));

        // Look at the column names
        out(table.columnNames());

        // Peak at the data
        out(table.first(5));

        // Remove the description column
        table.removeColumns("stop_desc");

        // Check the column names to see that it's gone
        out(table.columnNames());

        // Take a look at some data
        out("In 'examples. Printing first(5)");
        out(table.first(5));

        // Lets take a look at the latitude and longitude columns
        // out(table.realColumn("stop_lat").rowSummary().out());
        out(table.floatColumn("stop_lat").summary());

        // Now lets fill a column based on data in the existing columns

        // Apply the map function and fill the resulting column to the original table

        // Lets filtering out some of the rows. We're only interested in records with IDs between 524-624

        Table filtered = table.selectWhere(QueryHelper.column("stop_id").isBetweenIncluding(524, 624));
        out(filtered.first(5));

        // Write out the new CSV file
        CsvWriter.write(filtered, "../data/filtered_bus_stops.csv");
    }