%%classpath add mvn
tech.tablesaw tablesaw-plot 0.11.4
tech.tablesaw tablesaw-smile 0.11.4
tech.tablesaw tablesaw-beakerx 0.11.4

%import tech.tablesaw.aggregate.*
%import tech.tablesaw.api.*
%import tech.tablesaw.api.ml.clustering.*
%import tech.tablesaw.api.ml.regression.*
%import tech.tablesaw.columns.*

// 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)

import static tech.tablesaw.api.QueryHelper.column
tornadoes.structure().selectWhere(column("Column Type").isEqualTo("FLOAT"))

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

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

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

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

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

//Cross Tabs
CrossTab.xCount(tornadoes, tornadoes.categoryColumn("State"), tornadoes.shortColumn("Scale"))

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

model = new Kmeans(
    5,
    t.nCol(2), t.nCol(3), t.nCol(4), t.nCol(5), t.nCol(6), t.nCol(7),
    t.nCol(8), t.nCol(9), t.nCol(10), t.nCol(11), t.nCol(12), t.nCol(13)
);

//print claster formation
model.clustered(t.column("Distillery"));

//print centroids for each claster
model.labeledCentroids();

//gets the distortion for our model
model.distortion()

def n = t.rowCount();
def kValues = new double[n - 2];
def distortions = new double[n - 2];

for (int k = 2; k < n; k++) {
  kValues[k - 2] = k;
  def kmeans = new Kmeans(k,
      t.nCol(2), t.nCol(3), t.nCol(4), t.nCol(5), t.nCol(6), t.nCol(7),
      t.nCol(8), t.nCol(9), t.nCol(10), t.nCol(11), t.nCol(12), t.nCol(13)
  );
  distortions[k - 2] = kmeans.distortion();
}
def linearYPlot = new Plot(title: "K-means clustering demo", xLabel:"K", yLabel: "distortion")
linearYPlot << new Line(x: kValues, y: distortions)

import static tech.tablesaw.api.QueryHelper.column

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

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

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

winsModel = LeastSquares.train(wins, runDifference);

def runDiff = new double[1];
runDiff[0] = 135;
def expectedWins = winsModel.predict(runDiff);
runsScored2 = LeastSquares.train(moneyball.nCol("RS"), moneyball.nCol("OBP"), moneyball.nCol("SLG"));

new Histogram(xLabel:"X",
              yLabel:"Proportion",
              data: Arrays.asList(runsScored2.residuals()), 
              binCount: 25);

%classpath add mvn com.jimmoores quandl-tablesaw 2.0.0
%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
ShortColumn yearColumn = table.dateColumn("Date").year();
yearColumn.setName("Year");
table.addColumn(yearColumn);
// Create max, min and total volume tables aggregated by year
Table summaryMax = table.groupBy("year").max("Adj. Close");
Table summaryMin = table.groupBy("year").min("Adj. Close");
Table summaryVolume = table.groupBy("year")sum("Volume");
// 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 = new DateColumn("YearDate");
for(year in summary.column('Year')){
    yearDates.append(java.time.LocalDate.of(year,1,1));
}
summary.addColumn(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')