/// <summary>
/// This converts the value into a normalized vector (values from -1 to 1 in each dimension)
/// </summary>
/// <remarks>
/// This is useful if you want to convert numbers into vectors
///
/// Say you want to do a SOM against a database. Each column needs to be mapped to a vector. Then all vectors of a row will get
/// stitched together to be one intance of ISOMInput.Weights
///
/// If one of the columns is numeric (maybe dollars or quantities), then you would use this method
///
/// The first step would be to prequery so see what the range of possible values are. Run that maximum expected value through
/// GetConvertBaseProps() to figure out what base to represent the numbers as. This method converts the number to that base,
/// then normalizes each digit to -1 to 1 (sort of like percent of base)
/// </remarks>
private static double[] ConvertToVector_Direct(double value, SOMConvertToVectorProps props)
{
// Convert to a different base
long scaledValue = Convert.ToInt64(value * props.Number_ScaleToLong);
int[] converted = MathND.ConvertToBase(scaledValue, props.Number_BaseConvertTo.Value);
// Too big, return 1s
if (converted.Length > props.Width)
{
double maxValue = value < 0 ? -1d : 1d;
return(Enumerable.Range(0, props.Width).Select(o => maxValue).ToArray());
}
// Normalize (treat each item like a percent)
double baseDbl = props.Number_BaseConvertTo.Value.ToDouble();
double[] normalized = converted.
Select(o => o.ToDouble() / baseDbl).
ToArray();
// Return, make sure the array is the right size
if (normalized.Length < props.Width)
{
return(Enumerable.Range(0, props.Width - normalized.Length).
Select(o => 0d).
Concat(normalized).
ToArray());
}
else
{
return(normalized);
}
}
/// <summary>
/// This overload converts text to a vector
/// </summary>
/// <param name="uniqueNonWhitespace">This is a list of all possible characters that could be encountered (but not any characters that would cause IsWhitespace to return true)</param>
private static double[] ConvertToVector_Text(string text, SOMConvertToVectorProps props, char[] uniqueNonWhitespace)
{
if (uniqueNonWhitespace.Length == 0)
{
// It's all zeros
return(new double[props.Width]);
}
int[] numbers = ConvertToVector_Text_Number(text, uniqueNonWhitespace);
double[] normalized = ConvertToVector_Text_Normalize(numbers, uniqueNonWhitespace.Length);
return(ConvertToVector_Text_Fit(normalized, props.Width, props.Text_Justification.Value));
}
public static double[] ConvertToVector(string text, SOMFieldStats stats, SOMConvertToVectorProps convertProps)
{
switch (stats.FieldType)
{
case SOMFieldType.Integer:
case SOMFieldType.FloatingPoint:
#region numeric
double castDbl1 = string.IsNullOrWhiteSpace(text) ? 0d : double.Parse(text.Trim());
return(ConvertToVector_LeftSignificant(castDbl1, convertProps));
#endregion
case SOMFieldType.DateTime:
#region date
DateTime castDt;
if (!DateTime.TryParse(text, out castDt))
{
castDt = stats.Date_Min.Value;
}
double castDbl2 = (castDt - stats.Date_Min.Value).TotalDays; // convertProps was built from "(stats.Date_Max - stats.Date_Min).TotalDays"
return(ConvertToVector_LeftSignificant(castDbl2, convertProps));
#endregion
case SOMFieldType.AlphaNumeric:
case SOMFieldType.AnyText:
#region text
return(ConvertToVector_Text(text, convertProps, stats.UniqueChars_NonWhitespace));
#endregion
default:
throw new ApplicationException("finish this: " + stats.FieldType.ToString());
}
}
/// <summary>
/// This washes the bits to the right with values approaching one
/// </summary>
/// <remarks>
/// The leftmost bit is most significant, and needs to be returned acurately. The bits to the right don't matter as much, but
/// the self organizing map just groups things together based on the pattern of the bits. So the bits to the right need to approach
/// one (think of them as overidden by the bits to the left)
///
/// I didn't want linear, I wanted something faster. So the bits to the right follow a sqrt curve (x axis scaled between 0 and 1
/// over the remaining bits)
///
/// Example:
/// If this trend toward one isn't there, then these two values would map close to each other (even though the first one represents
/// 1, and the second could represent 201)
/// 0 0 0 0 1
/// 0 .1 0 0 1
/// This method would turn these into something like:
/// 0 0 0 0 1
/// 0 .1 .6 .95 1 --- bits to the right follow a sqrt toward 1
///
/// Instead of sqrt, it's actually between x^POWMIN and x^POWMAX. The value of the bit becomes a percent from min to max
/// </remarks>
private static double[] ConvertToVector_LeftSignificant(double value, SOMConvertToVectorProps props)
{
const double POWMIN = .1;
const double POWMAX = .04;
// Convert to a different base
long scaledValue = Convert.ToInt64(value * props.Number_ScaleToLong);
int[] converted = MathND.ConvertToBase(scaledValue, props.Number_BaseConvertTo.Value);
if (converted.Length == 0)
{
// Zero, return 0s
return(Enumerable.Range(0, props.Width).Select(o => 0d).ToArray());
}
else if (converted.Length > props.Width)
{
// Too big, return 1s
double maxValue = value < 0 ? -1d : 1d;
return(Enumerable.Range(0, props.Width).Select(o => maxValue).ToArray());
}
// Normalize so it's between -1 and 1
double[] normalized = new double[converted.Length];
double baseDbl = props.Number_BaseConvertTo.Value.ToDouble();
// Leftmost bit
normalized[0] = converted[0].ToDouble() / baseDbl;
double absFirst = Math.Abs(normalized[0]);
// Bits to the right of the leftmost (their values are made to approach 1)
if (converted.Length > 1)
{
// The sqrt will be between 0 and 1, so scale the x and y
double yGap = 1d - absFirst;
double xScale = 1d / (normalized.Length - 1);
for (int cntr = 1; cntr < normalized.Length; cntr++)
{
// Y will be between these two curves
double yMin = Math.Pow(cntr * xScale, POWMIN);
double yMax = Math.Pow(cntr * xScale, POWMAX);
// Treat this bit like a percent between the two curves
double y = UtilityCore.GetScaledValue(yMin, yMax, 0, props.Number_BaseConvertTo.Value, Math.Abs(converted[cntr]));
y *= yGap;
y += absFirst;
if (normalized[0] < 0)
{
y = -y;
}
normalized[cntr] = y;
}
}
// Return, make sure the array is the right size
if (normalized.Length < props.Width)
{
return(Enumerable.Range(0, props.Width - normalized.Length).
Select(o => 0d).
Concat(normalized).
ToArray());
}
else
{
return(normalized);
}
}
/// <summary>
/// This overload converts text to a vector
/// </summary>
/// <param name="uniqueNonWhitespace">This is a list of all possible characters that could be encountered (but not any characters that would cause IsWhitespace to return true)</param>
private static double[] ConvertToVector_Text(string text, SOMConvertToVectorProps props, char[] uniqueNonWhitespace)
{
if (uniqueNonWhitespace.Length == 0)
{
// It's all zeros
return new double[props.Width];
}
int[] numbers = ConvertToVector_Text_Number(text, uniqueNonWhitespace);
double[] normalized = ConvertToVector_Text_Normalize(numbers, uniqueNonWhitespace.Length);
return ConvertToVector_Text_Fit(normalized, props.Width, props.Text_Justification.Value);
}
/// <summary>
/// This washes the bits to the right with values approaching one
/// </summary>
/// <remarks>
/// The leftmost bit is most significant, and needs to be returned acurately. The bits to the right don't matter as much, but
/// the self organizing map just groups things together based on the pattern of the bits. So the bits to the right need to approach
/// one (think of them as overidden by the bits to the left)
///
/// I didn't want linear, I wanted something faster. So the bits to the right follow a sqrt curve (x axis scaled between 0 and 1
/// over the remaining bits)
///
/// Example:
/// If this trend toward one isn't there, then these two values would map close to each other (even though the first one represents
/// 1, and the second could represent 201)
/// 0 0 0 0 1
/// 0 .1 0 0 1
/// This method would turn these into something like:
/// 0 0 0 0 1
/// 0 .1 .6 .95 1 --- bits to the right follow a sqrt toward 1
///
/// Instead of sqrt, it's actually between x^POWMIN and x^POWMAX. The value of the bit becomes a percent from min to max
/// </remarks>
private static double[] ConvertToVector_LeftSignificant(double value, SOMConvertToVectorProps props)
{
const double POWMIN = .1;
const double POWMAX = .04;
// Convert to a different base
long scaledValue = Convert.ToInt64(value * props.Number_ScaleToLong);
int[] converted = MathND.ConvertToBase(scaledValue, props.Number_BaseConvertTo.Value);
if (converted.Length == 0)
{
// Zero, return 0s
return Enumerable.Range(0, props.Width).Select(o => 0d).ToArray();
}
else if (converted.Length > props.Width)
{
// Too big, return 1s
double maxValue = value < 0 ? -1d : 1d;
return Enumerable.Range(0, props.Width).Select(o => maxValue).ToArray();
}
// Normalize so it's between -1 and 1
double[] normalized = new double[converted.Length];
double baseDbl = props.Number_BaseConvertTo.Value.ToDouble();
// Leftmost bit
normalized[0] = converted[0].ToDouble() / baseDbl;
double absFirst = Math.Abs(normalized[0]);
// Bits to the right of the leftmost (their values are made to approach 1)
if (converted.Length > 1)
{
// The sqrt will be between 0 and 1, so scale the x and y
double yGap = 1d - absFirst;
double xScale = 1d / (normalized.Length - 1);
for (int cntr = 1; cntr < normalized.Length; cntr++)
{
// Y will be between these two curves
double yMin = Math.Pow(cntr * xScale, POWMIN);
double yMax = Math.Pow(cntr * xScale, POWMAX);
// Treat this bit like a percent between the two curves
double y = UtilityCore.GetScaledValue(yMin, yMax, 0, props.Number_BaseConvertTo.Value, Math.Abs(converted[cntr]));
y *= yGap;
y += absFirst;
if (normalized[0] < 0)
{
y = -y;
}
normalized[cntr] = y;
}
}
// Return, make sure the array is the right size
if (normalized.Length < props.Width)
{
return Enumerable.Range(0, props.Width - normalized.Length).
Select(o => 0d).
Concat(normalized).
ToArray();
}
else
{
return normalized;
}
}
/// <summary>
/// This converts the value into a normalized vector (values from -1 to 1 in each dimension)
/// </summary>
/// <remarks>
/// This is useful if you want to convert numbers into vectors
///
/// Say you want to do a SOM against a database. Each column needs to be mapped to a vector. Then all vectors of a row will get
/// stitched together to be one intance of ISOMInput.Weights
///
/// If one of the columns is numeric (maybe dollars or quantities), then you would use this method
///
/// The first step would be to prequery so see what the range of possible values are. Run that maximum expected value through
/// GetConvertBaseProps() to figure out what base to represent the numbers as. This method converts the number to that base,
/// then normalizes each digit to -1 to 1 (sort of like percent of base)
/// </remarks>
private static double[] ConvertToVector_Direct(double value, SOMConvertToVectorProps props)
{
// Convert to a different base
long scaledValue = Convert.ToInt64(value * props.Number_ScaleToLong);
int[] converted = MathND.ConvertToBase(scaledValue, props.Number_BaseConvertTo.Value);
// Too big, return 1s
if (converted.Length > props.Width)
{
double maxValue = value < 0 ? -1d : 1d;
return Enumerable.Range(0, props.Width).Select(o => maxValue).ToArray();
}
// Normalize (treat each item like a percent)
double baseDbl = props.Number_BaseConvertTo.Value.ToDouble();
double[] normalized = converted.
Select(o => o.ToDouble() / baseDbl).
ToArray();
// Return, make sure the array is the right size
if (normalized.Length < props.Width)
{
return Enumerable.Range(0, props.Width - normalized.Length).
Select(o => 0d).
Concat(normalized).
ToArray();
}
else
{
return normalized;
}
}
public static double[] ConvertToVector(string text, SOMFieldStats stats, SOMConvertToVectorProps convertProps)
{
switch (stats.FieldType)
{
case SOMFieldType.Integer:
case SOMFieldType.FloatingPoint:
#region numeric
double castDbl1 = string.IsNullOrWhiteSpace(text) ? 0d : double.Parse(text.Trim());
return ConvertToVector_LeftSignificant(castDbl1, convertProps);
#endregion
case SOMFieldType.DateTime:
#region date
DateTime castDt;
if (!DateTime.TryParse(text, out castDt))
{
castDt = stats.Date_Min.Value;
}
double castDbl2 = (castDt - stats.Date_Min.Value).TotalDays; // convertProps was built from "(stats.Date_Max - stats.Date_Min).TotalDays"
return ConvertToVector_LeftSignificant(castDbl2, convertProps);
#endregion
case SOMFieldType.AlphaNumeric:
case SOMFieldType.AnyText:
#region text
return ConvertToVector_Text(text, convertProps, stats.UniqueChars_NonWhitespace);
#endregion
default:
throw new ApplicationException("finish this: " + stats.FieldType.ToString());
}
}
private static Tuple<ColumnStats, SOMFieldStats, SOMConvertToVectorProps>[] GetFinalColumnStats(ColumnStats[] columns)
{
var retVal = new Tuple<ColumnStats, SOMFieldStats, SOMConvertToVectorProps>[columns.Length];
for (int cntr = 0; cntr < columns.Length; cntr++)
{
// Field
SOMFieldStats field = null;
if (columns[cntr].ForceText)
{
field = columns[cntr].FieldStatsText;
}
else
{
field = columns[cntr].FieldStats;
}
//TODO: look at overrides
// Convert
SOMConvertToVectorProps convertProps;
switch (field.FieldType)
{
case SOMFieldType.AlphaNumeric:
case SOMFieldType.AnyText:
convertProps = new SOMConvertToVectorProps(columns[cntr].Width, columns[cntr].Override_Text_Justify ?? TextAlignment.Center);
break;
case SOMFieldType.DateTime:
convertProps = SelfOrganizingMapsDB.GetConvertToProps(field.Date_Min.Value, field.Date_Max.Value, columns[cntr].Width);
break;
case SOMFieldType.FloatingPoint:
case SOMFieldType.Integer:
convertProps = SelfOrganizingMapsDB.GetConvertToProps(field.Numeric_Min.Value, field.Numeric_Max.Value, columns[cntr].Width);
break;
default:
throw new ApplicationException("Unknown SOMFieldType: " + field.FieldType.ToString());
}
// Build it
retVal[cntr] = Tuple.Create(columns[cntr], field, convertProps);
}
return retVal;
}
