%%classpath add mvn
tech.tablesaw tablesaw-beakerx 0.30.3
com.jimmoores quandl-tablesaw 2.0.0
com.github.haifengl smile-core 1.5.2

%import static tech.tablesaw.aggregate.AggregateFunctions.*
%import tech.tablesaw.api.*
%import tech.tablesaw.columns.*
%import smile.clustering.*
%import smile.regression.*

// display Tablesaw tables with BeakerX table display widget
tech.tablesaw.beakerx.TablesawDisplayer.register()

tornadoes = Table.read().csv("../resources/data/tornadoes_2014.csv")

//print dataset structure
tornadoes.structure()

//get header names
tornadoes.columnNames()

//displays the row and column counts
tornadoes.shape()

//displays the first n rows
tornadoes.first(10)

tornadoes.structure()

//summarize the data in each column
tornadoes.summary()

//Mapping operations
def month = tornadoes.dateColumn("Date").month()
tornadoes.addColumns(month);
tornadoes.columnNames()

//Sorting by column
tornadoes.sortOn("-Fatalities")

//Descriptive statistics
tornadoes.column("Fatalities").summary()

//Performing totals and sub-totals
def injuriesByScale = tornadoes.summarize("Injuries", median).by("Scale")
injuriesByScale.setName("Median injuries by Tornado Scale")
injuriesByScale

//Cross Tabs
tornadoes.xTabCounts("State", "Scale")

whiskeyData = Table.read().csv("../resources/data/whiskey.csv")
whiskeyData.structure()

kMeans = new KMeans(whiskeyData.as().doubleMatrix("Body", "Sweetness", "Smoky", "Medicinal", "Tobacco", "Honey", "Spicy", "Winey", "Nutty", "Malty", "Fruity", "Floral"), 5)

Table whiskeyClusters = Table.create("Clusters", whiskeyData.stringColumn("Distillery"), DoubleColumn.create("Cluster", kMeans.getClusterLabel()));
whiskeyClusters = whiskeyClusters.sortAscendingOn("Cluster", "Distillery");

baseball = Table.read().csv("../resources/data/baseball.csv");

// filter to the data available at the start of the 2002 season
moneyball = baseball.where(baseball.numberColumn("year").isLessThan(2002));
wins = moneyball.nCol("W");
year = moneyball.nCol("Year");
playoffs = moneyball.column("Playoffs");
runDifference = moneyball.numberColumn("RS").subtract(moneyball.numberColumn("RA")).setName("RD");
moneyball.addColumns(runDifference);

def Plot = new Plot(title: "RD x Wins", xLabel:"RD", yLabel: "W")
Plot << new Points(x: moneyball.numberColumn("RD").asDoubleArray(), y: moneyball.numberColumn("W").asDoubleArray())

winsModel = new OLS(moneyball.select("W", "RD").smile().numericDataset("RD"));

runsScored = new OLS(moneyball.select("OBP", "SLG", "RS").smile().numericDataset("RS"));

new Histogram(xLabel:"X",
              yLabel:"Proportion",
              data: Arrays.asList(runsScored.residuals()),
              binCount: 25);

%import com.jimmoores.quandl.*
%import com.jimmoores.quandl.tablesaw.*

TableSawQuandlSession session = TableSawQuandlSession.create();
Table table = session.getDataSet(DataSetRequest.Builder.of("WIKI/AAPL").build());
// Create a new column containing the year
NumberColumn yearColumn = table.dateColumn("Date").year();
yearColumn.setName("Year");
table.addColumns(yearColumn);
// Create max, min and total volume tables aggregated by year
Table summaryMax = table.summarize("Adj. Close", max).by("year");
Table summaryMin = table.summarize("Adj. Close", min).by("year");
Table summaryVolume = table.summarize("Volume", sum).by("year");
// Create a new table from each of these
summary = Table.create("Summary", summaryMax.column(0), summaryMax.column(1), 
                       summaryMin.column(1), summaryVolume.column(1));
// Add back a DateColumn to the summary...will be used for plotting
DateColumn yearDates = DateColumn.create("YearDate");
for (year in summary.column('Year')) {
    yearDates.append(java.time.LocalDate.of((int) year, 1, 1));
}
summary.addColumns(yearDates)

summary

years = summary.column('YearDate').collect()

plot = new TimePlot(title: 'Price Chart for AAPL', xLabel: 'Time', yLabel: 'Max [Adj. Close]')
plot << new YAxis(label: 'Volume')
plot << new Points(x: years, y: summary.column('Max [Adj. Close]').collect())
plot << new Line(x: years, y: summary.column('Max [Adj. Close]').collect(), color: Color.blue)
plot << new Stems(x: years, y: summary.column('Sum [Volume]').collect(), yAxis: 'Volume')