private void Graph(string[] args,
double[] x1, double[] y1,
double[] x2, double[] y2,
double[] x3, double[] y3)
{
string chartFileName = string.Empty;
var pl = new PLStream();
if (args.Length == 1 && args[0] == "svg")
{
chartFileName = @"Logistic.svg";
pl.sdev("svg");
pl.sfnam("Logistic.svg");
}
else
{
chartFileName = @"Logistic.png";
pl.sdev("pngcairo");
pl.sfnam("Logistic.png");
}
pl.spal0("cmap0_alternate.pal");
pl.init();
const int xMin = -4;
const int xMax = 4;
const int yMin = -5;
const int yMax = 20;
pl.env(xMin, xMax, yMin, yMax, AxesScale.Independent, AxisBox.BoxTicksLabels);
// Set scaling for mail title text 125% size of default
pl.lab("X1", "X2", "Title");
pl.col0(3);
pl.sym(x1, y1, (char)228);
pl.col0(9);
pl.sym(x2, y2, (char)228);
pl.col0(2);
pl.line(x3, y3);
pl.eop();
pl.gver(out var verText);
var p = new Process();
string chartFileNamePath = @".\" + chartFileName;
p.StartInfo = new ProcessStartInfo(chartFileNamePath)
{
UseShellExecute = true
};
p.Start();
}
static void ProcessData(MLContext context, IDataView data)
{
var houses = context.Data.CreateEnumerable <HouseBlockData>(data, reuseRowObject: false).ToArray();
// plot median house value by longitude
var pl = new PLStream();
pl.sdev("pngcairo"); // png rendering
pl.sfnam("data.png"); // output filename
pl.spal0("cmap0_alternate.pal"); // alternate color palette
pl.init();
pl.env(
0, 10, // x-axis range
0, 600000, // y-axis range
AxesScale.Independent, // scale x and y independently
AxisBox.BoxTicksLabelsAxes); // draw box, ticks, and num ticks
pl.lab(
"Median Income", // x-axis label
"Median House Value", // y-axis label
"House value by longitude"); // plot title
pl.sym(
houses.Select(h => (double)h.MedianIncome).ToArray(),
houses.Select(h => (double)h.MedianHouseValue).ToArray(),
(char)218
);
pl.eop();
}
static void PlotData(MLContext context, IDataView data)
{
var transactions = context.Data.CreateEnumerable <CreditCardData>(data, reuseRowObject: false).ToArray();
// plot median house value by longitude
var pl = new PLStream();
pl.sdev("pngcairo"); // png rendering
pl.sfnam("data.png"); // output filename
pl.spal0("cmap0_alternate.pal"); // alternate color palette
pl.init();
pl.env(
0, 5000, // x-axis range
0, 2500, // y-axis range
AxesScale.Independent, // scale x and y independently
AxisBox.BoxTicksLabelsAxes); // draw box, ticks, and num ticks
pl.lab(
"Time", // x-axis label
"Amount", // y-axis label
"Transactions by Time"); // plot title
pl.sym(
transactions.Select(txn => (double)txn.Time).ToArray(),
transactions.Select(txn => (double)txn.Amount).ToArray(),
(char)218
);
pl.eop();
}
private static void Graph(string[] args, double[] x, double[] y)
{
string chartFileName = string.Empty;
var pl = new PLStream();
if (args.Length == 1 && args[0] == "svg")
{
chartFileName = @"KNN.svg";
pl.sdev("svg");
pl.sfnam("KNN.svg");
}
else
{
chartFileName = @"KNN.png";
pl.sdev("pngcairo");
pl.sfnam("KNN.png");
}
pl.spal0("cmap0_alternate.pal");
pl.init();
const int xMin = 0;
const int xMax = 1;
const int yMin = 0;
const int yMax = 1;
pl.env(xMin, xMax, yMin, yMax, AxesScale.Independent, AxisBox.BoxTicksLabelsAxes);
pl.schr(0, 0.75);
pl.lab("X-axis", "Y-axis", "Title");
pl.col0(3);
pl.sym(x, y, (char)210);
pl.eop();
pl.gver(out var verText);
var p = new Process();
string chartFileNamePath = @".\" + chartFileName;
p.StartInfo = new ProcessStartInfo(chartFileNamePath)
{
UseShellExecute = true
};
p.Start();
}
/// <summary>
/// The main program entry point.
/// </summary>
/// <param name="args">The command line arguments</param>
static void Main(string[] args)
{
// create the machine learning context
var context = new MLContext();
// load the dataset
Console.WriteLine("Loading data...");
var data = context.Data.LoadFromTextFile <HouseBlockData>(
path: dataPath,
hasHeader: true,
separatorChar: ',');
// keep only records with a median house value < 500,000
data = context.Data.FilterRowsByColumn(
data,
"MedianHouseValue",
upperBound: 499_999
);
// get an array of housing data
var houses = context.Data.CreateEnumerable <HouseBlockData>(data, reuseRowObject: false).ToArray();
// plot median house value by longitude
var pl = new PLStream();
pl.sdev("pngcairo"); // png rendering
pl.sfnam("data.png"); // output filename
pl.spal0("cmap0_alternate.pal"); // alternate color palette
pl.init();
pl.env(
0, 10, // x-axis range
0, 600000, // y-axis range
AxesScale.Independent, // scale x and y independently
AxisBox.BoxTicksLabelsAxes); // draw box, ticks, and num ticks
pl.lab(
"Median Income", // x-axis label
"Median House Value", // y-axis label
"House value by longitude"); // plot title
pl.sym(
houses.Select(h => (double)h.MedianIncome).ToArray(),
houses.Select(h => (double)h.MedianHouseValue).ToArray(),
(char)218
);
pl.eop();
// build a data loading pipeline
// step 1: divide the median house value by 1000
var pipeline = context.Transforms.CustomMapping <HouseBlockData, ToMedianHouseValue>(
(input, output) => { output.NormalizedMedianHouseValue = input.MedianHouseValue / 1000; },
contractName: "MedianHouseValue"
);
// get a 10-record preview of the transformed data
// var model = pipeline.Fit(data);
// var transformedData = model.Transform(data);
// var preview = transformedData.Preview(maxRows: 10);
// show the preview
// WritePreview(preview);
// step 2: bin the longitude
var pipeline2 = pipeline.Append(context.Transforms.NormalizeBinning(
inputColumnName: "Longitude",
outputColumnName: "BinnedLongitude",
maximumBinCount: 10
))
// step 3: bin the latitude
.Append(context.Transforms.NormalizeBinning(
inputColumnName: "Latitude",
outputColumnName: "BinnedLatitude",
maximumBinCount: 10
))
// step 4: one-hot encode the longitude
.Append(context.Transforms.Categorical.OneHotEncoding(
inputColumnName: "BinnedLongitude",
outputColumnName: "EncodedLongitude"
))
// step 5: one-hot encode the latitude
.Append(context.Transforms.Categorical.OneHotEncoding(
inputColumnName: "BinnedLatitude",
outputColumnName: "EncodedLatitude"
));
// step 6: cross the two one-hot encoded columns
var pipeline3 = pipeline2.Append(context.Transforms.CustomMapping <FromLocation, ToLocation>(
(input, output) =>
{
output.Location = new float[input.EncodedLongitude.Length * input.EncodedLatitude.Length];
var index = 0;
for (var i = 0; i < input.EncodedLongitude.Length; i++)
{
for (var j = 0; j < input.EncodedLatitude.Length; j++)
{
output.Location[index++] = input.EncodedLongitude[i] * input.EncodedLatitude[j];
}
}
},
contractName: "Location"
))
// step 7: remove all the columns we don't need anymore
.Append(context.Transforms.DropColumns(
"MedianHouseValue",
"Longitude",
"Latitude",
"BinnedLongitude",
"BinnedLatitude",
"EncodedLongitude",
"EncodedLatitude"
));
// get a 10-record preview of the transformed data
var model = pipeline3.Fit(data);
var transformedData = model.Transform(data);
var preview = transformedData.Preview(maxRows: 10);
// show the location vector
//WritePreview(preview);
WritePreviewColumn(preview, "Location");
}
