Statistics: single precision support on Covariance #235

src/Numerics/Statistics/ArrayStatistics.cs

@@ -434,9 +434,9 @@ namespace MathNet.Numerics.Statistics
                 return double.NaN;
             }
 
-            var mean1 = Mean(samples1);
-            var mean2 = Mean(samples2);
-            var covariance = 0.0;
+            double mean1 = Mean(samples1);
+            double mean2 = Mean(samples2);
+            double covariance = 0.0;
             for (int i = 0; i < samples1.Length; i++)
             {
                 covariance += (samples1[i] - mean1)*(samples2[i] - mean2);
@@ -445,6 +445,36 @@ namespace MathNet.Numerics.Statistics
             return covariance/(samples1.Length - 1);
         }
 
+        /// <summary>
+        /// Estimates the unbiased population covariance from the provided two sample arrays.
+        /// On a dataset of size N will use an N-1 normalizer (Bessel's correction).
+        /// Returns NaN if data has less than two entries or if any entry is NaN.
+        /// </summary>
+        /// <param name="samples1">First sample array.</param>
+        /// <param name="samples2">Second sample array.</param>
+        public static double Covariance(float[] samples1, float[] samples2)
+        {
+            if (samples1.Length != samples2.Length)
+            {
+                throw new ArgumentException(Resources.ArgumentVectorsSameLength);
+            }
+
+            if (samples1.Length <= 1)
+            {
+                return double.NaN;
+            }
+
+            double mean1 = Mean(samples1);
+            double mean2 = Mean(samples2);
+            double covariance = 0.0;
+            for (int i = 0; i < samples1.Length; i++)
+            {
+                covariance += (samples1[i] - mean1) * (samples2[i] - mean2);
+            }
+
+            return covariance / (samples1.Length - 1);
+        }
+
         /// <summary>
         /// Evaluates the population covariance from the full population provided as two arrays.
         /// On a dataset of size N will use an N normalizer and would thus be biased if applied to a subset.
@@ -464,9 +494,9 @@ namespace MathNet.Numerics.Statistics
                 return double.NaN;
             }
 
-            var mean1 = Mean(population1);
-            var mean2 = Mean(population2);
-            var covariance = 0.0;
+            double mean1 = Mean(population1);
+            double mean2 = Mean(population2);
+            double covariance = 0.0;
             for (int i = 0; i < population1.Length; i++)
             {
                 covariance += (population1[i] - mean1)*(population2[i] - mean2);
@@ -475,6 +505,36 @@ namespace MathNet.Numerics.Statistics
             return covariance/population1.Length;
         }
 
+        /// <summary>
+        /// Evaluates the population covariance from the full population provided as two arrays.
+        /// On a dataset of size N will use an N normalizer and would thus be biased if applied to a subset.
+        /// Returns NaN if data is empty or if any entry is NaN.
+        /// </summary>
+        /// <param name="population1">First population array.</param>
+        /// <param name="population2">Second population array.</param>
+        public static double PopulationCovariance(float[] population1, float[] population2)
+        {
+            if (population1.Length != population2.Length)
+            {
+                throw new ArgumentException(Resources.ArgumentVectorsSameLength);
+            }
+
+            if (population1.Length == 0)
+            {
+                return double.NaN;
+            }
+
+            double mean1 = Mean(population1);
+            double mean2 = Mean(population2);
+            double covariance = 0.0;
+            for (int i = 0; i < population1.Length; i++)
+            {
+                covariance += (population1[i] - mean1) * (population2[i] - mean2);
+            }
+
+            return covariance / population1.Length;
+        }
+
         /// <summary>
         /// Estimates the root mean square (RMS) also known as quadratic mean from the unsorted data array.
         /// Returns NaN if data is empty or any entry is NaN.

src/Numerics/Statistics/Statistics.cs

@@ -508,6 +508,22 @@ namespace MathNet.Numerics.Statistics
                 : StreamingStatistics.Covariance(samples1, samples2);
         }
 
+        /// <summary>
+        /// Estimates the unbiased population covariance from the provided samples.
+        /// On a dataset of size N will use an N-1 normalizer (Bessel's correction).
+        /// Returns NaN if data has less than two entries or if any entry is NaN.
+        /// </summary>
+        /// <param name="samples1">A subset of samples, sampled from the full population.</param>
+        /// <param name="samples2">A subset of samples, sampled from the full population.</param>
+        public static double Covariance(this IEnumerable<float> samples1, IEnumerable<float> samples2)
+        {
+            var array1 = samples1 as float[];
+            var array2 = samples2 as float[];
+            return array1 != null && array2 != null
+                ? ArrayStatistics.Covariance(array1, array2)
+                : StreamingStatistics.Covariance(samples1, samples2);
+        }
+
         /// <summary>
         /// Estimates the unbiased population covariance from the provided samples.
         /// On a dataset of size N will use an N-1 normalizer (Bessel's correction).
@@ -537,6 +553,22 @@ namespace MathNet.Numerics.Statistics
                 : StreamingStatistics.PopulationCovariance(population1, population2);
         }
 
+        /// <summary>
+        /// Evaluates the population covariance from the provided full populations.
+        /// On a dataset of size N will use an N normalizer and would thus be biased if applied to a subset.
+        /// Returns NaN if data is empty or if any entry is NaN.
+        /// </summary>
+        /// <param name="population1">The full population data.</param>
+        /// <param name="population2">The full population data.</param>
+        public static double PopulationCovariance(this IEnumerable<float> population1, IEnumerable<float> population2)
+        {
+            var array1 = population1 as float[];
+            var array2 = population2 as float[];
+            return array1 != null && array2 != null
+                ? ArrayStatistics.PopulationCovariance(array1, array2)
+                : StreamingStatistics.PopulationCovariance(population1, population2);
+        }
+
         /// <summary>
         /// Evaluates the population covariance from the provided full populations.
         /// On a dataset of size N will use an N normalize and would thus be biased if applied to a subset.

src/Numerics/Statistics/StreamingStatistics.cs

@@ -448,6 +448,18 @@ namespace MathNet.Numerics.Statistics
             return n > 1 ? comoment/(n - 1) : double.NaN;
         }
 
+        /// <summary>
+        /// Estimates the unbiased population covariance from the provided two sample enumerable sequences, in a single pass without memoization.
+        /// On a dataset of size N will use an N-1 normalizer (Bessel's correction).
+        /// Returns NaN if data has less than two entries or if any entry is NaN.
+        /// </summary>
+        /// <param name="samples1">First sample stream.</param>
+        /// <param name="samples2">Second sample stream.</param>
+        public static double Covariance(IEnumerable<float> samples1, IEnumerable<float> samples2)
+        {
+            return Covariance(samples1.Select(x => (double)x), samples2.Select(x => (double)x));
+        }
+
         /// <summary>
         /// Evaluates the population covariance from the full population provided as two enumerable sequences, in a single pass without memoization.
         /// On a dataset of size N will use an N normalizer and would thus be biased if applied to a subset.
@@ -489,6 +501,18 @@ namespace MathNet.Numerics.Statistics
             return comoment/n;
         }
 
+        /// <summary>
+        /// Evaluates the population covariance from the full population provided as two enumerable sequences, in a single pass without memoization.
+        /// On a dataset of size N will use an N normalizer and would thus be biased if applied to a subset.
+        /// Returns NaN if data is empty or if any entry is NaN.
+        /// </summary>
+        /// <param name="population1">First population stream.</param>
+        /// <param name="population2">Second population stream.</param>
+        public static double PopulationCovariance(IEnumerable<float> population1, IEnumerable<float> population2)
+        {
+            return PopulationCovariance(population1.Select(x => (double)x), population2.Select(x => (double)x));
+        }
+
         /// <summary>
         /// Estimates the root mean square (RMS) also known as quadratic mean from the enumerable, in a single pass without memoization.
         /// Returns NaN if data is empty or any entry is NaN.