public void InternetSampleDownload()
{
FrameTable table = DownloadFrameTable(new Uri("https://raw.githubusercontent.com/Dataweekends/zero_to_deep_learning_udemy/master/data/weight-height.csv"));
FrameView view = table.WhereNotNull();
view.AddComputedColumn("Bmi", (FrameRow r) => {
double h = (double)r["Height"];
double w = (double)r["Weight"];
return(w / (h * h));
});
FrameView males = view.Where("Gender", (string s) => (s == "Male"));
FrameView females = view.Where("Gender", (string s) => (s == "Female"));
SummaryStatistics maleSummary = new SummaryStatistics(males["Height"].As <double>());
SummaryStatistics femaleSummary = new SummaryStatistics(females["Height"].As <double>());
TestResult allNormal = view["Height"].As <double>().ShapiroFranciaTest();
TestResult maleNormal = males["Height"].As <double>().ShapiroFranciaTest();
TestResult femaleNormal = females["Height"].As <double>().ShapiroFranciaTest();
TestResult tTest = Univariate.StudentTTest(males["Height"].As <double>(), females["Height"].As <double>());
TestResult mwTest = Univariate.MannWhitneyTest(males["Height"].As <double>(), females["Height"].As <double>());
LinearRegressionResult result0 = males["Weight"].As <double>().LinearRegression(males["Height"].As <double>());
PolynomialRegressionResult result1 = males["Height"].As <double>().PolynomialRegression(males["Weight"].As <double>(), 1);
PolynomialRegressionResult result2 = males["Height"].As <double>().PolynomialRegression(males["Weight"].As <double>(), 2);
PolynomialRegressionResult result3 = males["Height"].As <double>().PolynomialRegression(males["Weight"].As <double>(), 3);
//MultiLinearRegressionResult multi = view["Weight"].As<double>().MultiLinearRegression(view["Height"].As<double>(), view["Gender"].As<string>().Select(s => (s == "Male") ? 1.0 : 0.0).ToList());
}
public void FrameViewGroupBy()
{
FrameView original = GetTestFrame();
HashSet <bool?> values = new HashSet <bool?>(original["male"].As <bool?>().Distinct());
FrameTable grouped = original.GroupBy("male", v => {
SummaryStatistics summary = new SummaryStatistics(v["height"].As <double>());
return(new Dictionary <string, object>()
{
{ "count", summary.Count },
{ "heightMean", summary.Mean },
{ "heightStandardDeviation", summary.StandardDeviation }
});
});
Assert.IsTrue(grouped.Rows.Count == values.Count);
Assert.IsTrue(grouped.Columns.Count == 4);
for (int i = 0; i < grouped.Rows.Count; i++)
{
bool?value = grouped["male"].As <bool?>()[i];
Assert.IsTrue(values.Contains(value));
FrameView selected = original.Where(r => (bool?)r["male"] == value);
Assert.IsTrue(selected.Rows.Count > 0);
double mean = selected["height"].As <double>().Mean();
Assert.IsTrue(TestUtilities.IsNearlyEqual(grouped["heightMean"].As <double>()[i], mean));
double standardDeviation = selected["height"].As <double>().StandardDeviation();
Assert.IsTrue(TestUtilities.IsNearlyEqual(grouped["heightStandardDeviation"].As <double>()[i], standardDeviation));
}
}
public static void ManipulatingData()
{
FrameTable table;
Uri url = new Uri("https://raw.githubusercontent.com/dcwuser/metanumerics/master/Examples/Data/example.csv");
WebRequest request = WebRequest.Create(url);
using (WebResponse response = request.GetResponse()) {
using (StreamReader reader = new StreamReader(response.GetResponseStream())) {
table = FrameTable.FromCsv(reader);
}
}
FrameView selected = table.Select("Height", "Weight", "Sex");
FrameView discarded = table.Discard("Name");
table.AddComputedColumn("Bmi", r => ((double)r["Weight"]) / MoreMath.Sqr((double)r["Height"] / 100.0));
Console.WriteLine($"Bmi of first subject is {table["Bmi"][0]}.");
FrameView noNulls = table.WhereNotNull();
FrameView noNullWeights = table.WhereNotNull("Weight");
FrameView noNullWeightsOrHeights = table.WhereNotNull("Weight", "Height");
double meanWeight = table.WhereNotNull("Weight").Columns["Weight"].As <double>().Mean();
FrameView men = table.Where <string>("Sex", s => s == "M");
FrameView shortMen = table.Where(
r => ((string)r["Sex"]) == "M" && ((double)r["Height"] < 175.0)
);
FrameView ordered = table.OrderBy("Height");
FrameView reversed = table.OrderBy("Height", SortOrder.Descending);
FrameView alsoOrdered = table.OrderBy <double>("Height", (h1, h2) => h1.CompareTo(h2));
FrameView sorted = table.OrderBy((r1, r2) => {
int first = ((string)r1["Sex"]).CompareTo((string )r2["Sex"]);
int second = ((double)r1["Height"]).CompareTo((double)r2["Height"]);
return(first != 0 ? first : second);
});
List <string> sexes = table["Sex"].As <string>().Distinct().ToList();
FrameTable counts = table.GroupBy("Sex", v => v.Rows.Count, "Count");
FrameTable summarize = table.GroupBy("Sex", v => {
SummaryStatistics summary = new SummaryStatistics(v["Height"].As <double>());
return(new Dictionary <string, object>()
{
{ "Count", summary.Count },
{ "Mean", summary.Mean },
{ "StdDev", summary.StandardDeviation }
});
});
}
public void StreamSampleSummaryAgreement()
{
// Streaming properties should give same answers as list methods.
Random rng = new Random(2);
List <double> sample = new List <double>(TestUtilities.CreateDataSample(rng, new UniformDistribution(Interval.FromEndpoints(-4.0, 3.0)), 32));
SummaryStatistics summary = new SummaryStatistics(sample);
Assert.IsTrue(summary.Count == sample.Count);
Assert.IsTrue(TestUtilities.IsNearlyEqual(sample.Mean(), summary.Mean));
Assert.IsTrue(TestUtilities.IsNearlyEqual(sample.Variance(), summary.Variance));
Assert.IsTrue(TestUtilities.IsNearlyEqual(sample.PopulationMean(), summary.PopulationMean));
Assert.IsTrue(TestUtilities.IsNearlyEqual(sample.PopulationVariance(), summary.PopulationVariance));
Assert.IsTrue(sample.Minimum() == summary.Minimum);
Assert.IsTrue(sample.Maximum() == summary.Maximum);
}
public override SummaryStatistics[] GetSummaryStatistics(IState[] states, params object[] parameters)
{
List <double>[] preds = new List <double> [states.Length];
SummaryStatistics[] summaryStatistics = new SummaryStatistics[states.Length];
List <Tuple <int, int, IState[]> > batches = GetBatches(states, Global.TFMAXBATCHSIZE);
foreach (var batch in batches)
{
List <TrainingInstance> trainingInstances = new List <TrainingInstance>();
foreach (IState state in batch.Item3)
{
trainingInstances.Add(new TrainingInstance(state, 0));
}
var X = representationUncert.BuildData(trainingInstances).Item1;
List <double>[] batchPreds = nnUncert.Predict(X, null, Global.UNCERTMINSAMPLE).Preds;
int count = 0;
for (int i = batch.Item1; i < batch.Item2; i++)
{
preds[i] = batchPreds[count];
count++;
}
}
for (int i = 0; i < preds.Length; i++)
{
double mean = preds[i].Average();
double sdModel = Math.Sqrt(Math.Max(0, preds[i].Select(x => Math.Pow(x, 2)).Average() - Math.Pow(mean, 2)));
summaryStatistics[i] = new SummaryStatistics(mean, sdModel, 0);
}
return(summaryStatistics);
}
public void AccuracyTest()
{
SummaryStatistics s1 = new SummaryStatistics();
SummaryStatistics s2 = new SummaryStatistics();
foreach (double omx in TestUtilities.GenerateRealValues(1.0E-24, 1.0, 1000000))
{
double x = 1.0 - omx;
double f1 = Math.Sqrt((1.0 - x) * (1.0 + x));
double f2 = Math.Sqrt(1.0 - x * x);
DoubleDouble xe = (DoubleDouble)x;
DoubleDouble fc = DoubleDouble.Sqrt(DoubleDouble.One - xe * xe);
double e1 = Math.Abs((double)(f1 - fc));
double e2 = Math.Abs((double)(f2 - fc));
s1.Add(e1);
s2.Add(e2);
}
}
public void StreamingSampleSummaryCombination()
{
// Combining partial summaries should give same answer as full summary
Random rng = new Random(1);
List <double> sample = new List <double>(TestUtilities.CreateDataSample(rng, new UniformDistribution(Interval.FromEndpoints(-4.0, 3.0)), 64));
SummaryStatistics summary = new SummaryStatistics(sample);
Assert.IsTrue(summary.Count == sample.Count);
for (int i = 0; i < 4; i++)
{
// Pick a split point in the data
int m = rng.Next(0, sample.Count);
// Create a summary of the first part.
SummaryStatistics summary1 = new SummaryStatistics(sample.Take(m));
Assert.IsTrue(summary1.Count == m);
// Create a summary of the second part.
SummaryStatistics summary2 = new SummaryStatistics(sample.Skip(m));
Assert.IsTrue(summary2.Count == sample.Count - m);
// Combine them. Their summary statistics should agree with the original summary.
SummaryStatistics combined = SummaryStatistics.Combine(summary1, summary2);
Assert.IsTrue(combined.Count == summary.Count);
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.Mean, summary.Mean));
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.Variance, summary.Variance));
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.StandardDeviation, summary.StandardDeviation));
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.Skewness, summary.Skewness));
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.PopulationMean, summary.PopulationMean));
Assert.IsTrue(TestUtilities.IsNearlyEqual(combined.PopulationVariance, summary.PopulationVariance));
Assert.IsTrue(combined.Minimum == summary.Minimum);
Assert.IsTrue(combined.Maximum == summary.Maximum);
}
}
internal MetricStatistics()
{
_statistic = new SummaryStatistics();
}
public Stats()
{
_statistics = new SummaryStatistics();
}
public static void AnalyzingData()
{
FrameTable table;
Uri url = new Uri("https://raw.githubusercontent.com/dcwuser/metanumerics/master/Examples/Data/example.csv");
WebRequest request = WebRequest.Create(url);
using (WebResponse response = request.GetResponse()) {
using (StreamReader reader = new StreamReader(response.GetResponseStream())) {
table = FrameTable.FromCsv(reader);
}
}
FrameView view = table.WhereNotNull();
// Get the column with (zero-based) index 4.
FrameColumn column4 = view.Columns[4];
// Get the column named "Height".
FrameColumn heightsColumn = view.Columns["Height"];
// Even easier way to get the column named "Height".
FrameColumn alsoHeightsColumn = view["Height"];
IReadOnlyList <double> heights = view["Height"].As <double>();
SummaryStatistics summary = new SummaryStatistics(view["Height"].As <double>());
Console.WriteLine($"Count = {summary.Count}");
Console.WriteLine($"Mean = {summary.Mean}");
Console.WriteLine($"Standard Deviation = {summary.StandardDeviation}");
Console.WriteLine($"Skewness = {summary.Skewness}");
Console.WriteLine($"Estimated population mean = {summary.PopulationMean}");
Console.WriteLine($"Estimated population standard deviation = {summary.PopulationStandardDeviation}");
IReadOnlyList <double> maleHeights =
view.Where <string>("Sex", s => s == "M").Columns["Height"].As <double>();
IReadOnlyList <double> femaleHeights =
view.Where <string>("Sex", s => s == "F").Columns["Height"].As <double>();
TestResult test = Univariate.StudentTTest(maleHeights, femaleHeights);
Console.WriteLine($"{test.Statistic.Name} = {test.Statistic.Value}");
Console.WriteLine($"P = {test.Probability}");
TestResult maleHeightNormality = maleHeights.ShapiroFranciaTest();
TestResult totalHeightNormality = view["Height"].As <double>().ShapiroFranciaTest();
TestResult heightCompatibility = Univariate.KolmogorovSmirnovTest(maleHeights, femaleHeights);
LinearRegressionResult fit =
view["Weight"].As <double>().LinearRegression(view["Height"].As <double>());
Console.WriteLine($"Model weight = ({fit.Slope}) * height + ({fit.Intercept}).");
Console.WriteLine($"Model explains {fit.RSquared * 100.0}% of variation.");
ContingencyTable <string, bool> contingency =
Bivariate.Crosstabs(view["Sex"].As <string>(), view["Result"].As <bool>());
Console.WriteLine($"Male incidence: {contingency.ProbabilityOfColumnConditionalOnRow(true, "M")}");
Console.WriteLine($"Female incidence: {contingency.ProbabilityOfColumnConditionalOnRow(true, "F")}");
Console.WriteLine($"Log odds ratio = {contingency.Binary.LogOddsRatio}");
view.AddComputedColumn("Bmi", r => ((double)r["Weight"]) / MoreMath.Sqr((double)r["Height"] / 100.0));
view.AddComputedColumn("Age", r => (DateTime.Now - (DateTime)r["Birthdate"]).TotalDays / 365.24);
MultiLinearLogisticRegressionResult result =
view["Result"].As <bool>().MultiLinearLogisticRegression(
view["Bmi"].As <double>(),
view["Sex"].As <string, double>(s => s == "M" ? 1.0 : 0.0)
);
foreach (Parameter parameter in result.Parameters)
{
Console.WriteLine($"{parameter.Name} = {parameter.Estimate}");
}
TestResult spearman = Bivariate.SpearmanRhoTest(view["Age"].As <double>(), view["Result"].As <double>());
Console.WriteLine($"{spearman.Statistic.Name} = {spearman.Statistic.Value} P = {spearman.Probability}");
}
/// <summary>
/// Print the values to the <see cref="_Worksheet"/>.
/// </summary>
/// <param name="data">The <see cref="Models.Data"/></param>
/// <param name="meanConfidenceLevel">(Optional) The confidence level for the <see cref="SummaryStatistics.Mean"/>. Default is 0.</param>
/// <param name="standardDeviationConfidenceLevel">(Optional) The confidence level for the <see cref="SummaryStatistics.StandardDeviation"/>. Default is 0.</param>
private void PrintValues(Models.Data data, int meanConfidenceLevel, int standardDeviationConfidenceLevel)
{
// Increment the column by 1.
_column++;
// Calculate the summary of the data.
var summary = new SummaryStatistics(data.Range, _doCalculate, meanConfidenceLevel, standardDeviationConfidenceLevel);
// Write the categories to she sheet.
Sheet.Cells[_row++, _column] = data.Name;
// Base
WriteFunction(_doCalculate.Mean || _doCalculate.BoxWhiskerPlot, summary.Mean);
WriteFunction(_doCalculate.Variance, summary.Variance);
WriteFunction(_doCalculate.StandardDeviation, summary.StandardDeviation);
WriteFunction(_doCalculate.Minimum, summary.Minimum);
WriteFunction(_doCalculate.Quartile1 || _doCalculate.BoxWhiskerPlot, summary.Quartile1);
WriteFunction(_doCalculate.Median, summary.Median);
WriteFunction(_doCalculate.Quartile3, summary.Quartile3);
WriteFunction(_doCalculate.Maximum, summary.Maximum);
WriteFunction(_doCalculate.InterquartileRange, summary.InterquartileRange);
WriteFunction(_doCalculate.Skewness, summary.Skewness);
WriteFunction(_doCalculate.Kurtosis, summary.Kurtosis);
WriteFunction(_doCalculate.MeanAbsoluteDeviation, summary.MeanAbsoluteDeviation);
WriteFunction(_doCalculate.Mode, summary.Mode);
HasMode.Add(summary.HasMode);
WriteFunction(_doCalculate.Range, summary.Range);
WriteFunction(_doCalculate.Count, summary.Count);
WriteFunction(_doCalculate.Sum, summary.Sum);
// Box-Whisker Plot
WriteFunction(_doCalculate.BoxWhiskerPlot, summary.Quartile1Median);
WriteFunction(_doCalculate.BoxWhiskerPlot, summary.MedianQuartile3);
WriteFunction(_doCalculate.BoxWhiskerPlot, summary.MinusWhisker);
WriteFunction(_doCalculate.BoxWhiskerPlot, summary.PlusWhisker);
// Base (but printed after the Box-Whisker Plot if required)
if (_doCalculate.Outliers || _doCalculate.BoxWhiskerPlot)
{
foreach (var outlier in summary.Outliers)
{
Sheet.Cells[_row++, _column] = "=" + outlier;
if (OutliersRow.Count < summary.Outliers.Count)
{
OutliersRow.Add(_row - 1);
}
}
}
// Confidence Interval
WriteFunction(_doCalculate.MeanConfidenceInterval || _doCalculate.StandardDeviationConfidenceInterval, summary.Count);
WriteFunction(_doCalculate.MeanConfidenceInterval || _doCalculate.StandardDeviationConfidenceInterval, summary.Mean);
WriteFunction(_doCalculate.MeanConfidenceInterval || _doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviation);
if (_doCalculate.MeanConfidenceInterval)
{
Sheet.Cells[_row, _column] = summary.MeanConfidenceLevel;
MeanConfidenceLevelRow = _row;
((Range)Sheet.Cells[_row++, _column]).NumberFormat = "0.00%";
summary.SetMeanAlpha(MeanConfidenceLevelRow, _column);
}
WriteFunction(_doCalculate.MeanConfidenceInterval, summary.MeanAlpha);
WriteFunction(_doCalculate.MeanConfidenceInterval, summary.DegreesOfFreedom);
WriteFunction(_doCalculate.MeanConfidenceInterval, summary.MeanConfidenceInterval);
WriteFunction(_doCalculate.MeanConfidenceInterval, summary.MeanLowerLimit);
WriteFunction(_doCalculate.MeanConfidenceInterval, summary.MeanUpperLimit);
if (_doCalculate.StandardDeviationConfidenceInterval)
{
Sheet.Cells[_row, _column] = summary.StandardDeviationConfidenceLevel;
StandardDeviationConfidenceLevelRow = _row;
((Range)Sheet.Cells[_row++, _column]).NumberFormat = "0.00%";
summary.SetStandardDeviationAlpha(StandardDeviationConfidenceLevelRow, _column);
}
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviationAlpha);
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.DegreesOfFreedom);
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviationConfidenceIntervalLowerLimit);
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviationConfidenceIntervalUpperLimit);
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviationLowerLimit);
WriteFunction(_doCalculate.StandardDeviationConfidenceInterval, summary.StandardDeviationUpperLimit);
}
