statsample 1.5.0 → 2.0.0

data/lib/statsample/regression.rb

@@ -25,8 +25,8 @@ module Statsample
       # * x: independent Vector
       # * y: dependent Vector
       # <b>Usage:</b>
-      #   x=100.times.collect {|i| rand(100)}.to_numeric
-      #   y=100.times.collect {|i| 2+x[i]*2+rand()}.to_numeric
+      #   x = Daru::Vector.new(100.times.collect {|i| rand(100)})
+      #   y = Daru::Vector.new(100.times.collect {|i| 2+x[i]*2+rand()})
       #   sr=Statsample::Regression.simple(x,y)
       #   sr.a
       #   => 2.51763295177808
@@ -49,7 +49,7 @@ module Statsample
       #     * :pairwise: uses correlation matrix. Use with caution.
       # 
       # <b>Usage:</b>
-      #   lr=Statsample::Regression::multiple(ds,'y')
+      #   lr=Statsample::Regression::multiple(ds,:y)
       def self.multiple(ds,y_var, opts=Hash.new)
         missing_data= (opts[:missing_data].nil? ) ? :listwise : opts.delete(:missing_data)
         if missing_data==:pairwise

data/lib/statsample/regression/multiple.rb

@@ -6,12 +6,12 @@ module Statsample
     #  Use:.
     #
     #  require 'statsample'
-    #  a=1000.times.collect {rand}.to_numeric
-    #  b=1000.times.collect {rand}.to_numeric
-    #  c=1000.times.collect {rand}.to_numeric
-    #  ds={'a'=>a,'b'=>b,'c'=>c}.to_dataset
-    #  ds['y']=ds.collect{|row| row['a']*5+row['b']*3+row['c']*2+rand()}
-    #  lr=Statsample::Regression.multiple(ds,'y')
+    #  a = Daru::Vector.new(1000.times.collect {rand})
+    #  b = Daru::Vector.new(1000.times.collect {rand})
+    #  c = Daru::Vector.new(1000.times.collect {rand})
+    #  ds= Daru::DataFrame.new({:a => a,:b => b,:c => c})
+    #  ds[:y]=ds.collect{|row| row[:a]*5 + row[:b]*3 + row[:c]*2 + rand()}
+    #  lr=Statsample::Regression.multiple(ds, :y)
     #  puts lr.summary
     #  Summary for regression of a,b,c over y
     #  *************************************************************
@@ -53,8 +53,8 @@ module Statsample
         def initialize(matrix,y_var, opts=Hash.new)
           matrix.extend Statsample::CovariateMatrix
           @matrix=matrix
-          @fields=matrix.fields-y_var
-          @y_var=y_var
+          @fields=matrix.fields - y_var
+          @y_var = y_var
           @q=@y_var.size
           @matrix_cor=matrix.correlation
           @matrix_cor_xx = @matrix_cor.submatrix(@fields)
@@ -84,8 +84,6 @@ module Statsample
           vxy.quo(@q)
         end
       end
-      
-      
     end
   end
 end

data/lib/statsample/regression/multiple/alglibengine.rb

@@ -9,108 +9,115 @@ module Multiple
 # If you need pairwise, use RubyEngine
 # Example:
 #
-#   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:numeric)
-#   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:numeric)
-#   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:numeric)
-#   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:numeric)
-#   ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
-#   lr=Statsample::Regression::Multiple::AlglibEngine.new(ds,'y')
+#   @a = Daru::Vector.new([1,3,2,4,3,5,4,6,5,7])
+#   @b = Daru::Vector.new([3,3,4,4,5,5,6,6,4,4])
+#   @c = Daru::Vector.new([11,22,30,40,50,65,78,79,99,100])
+#   @y = Daru::Vector.new([3,4,5,6,7,8,9,10,20,30])
+#   ds = Daru::DataFrame.new({:a => @a,:b => @b,:c => @c,:y => @y})
+#   lr=Statsample::Regression::Multiple::AlglibEngine.new(ds, :y)
 #            
 class AlglibEngine < BaseEngine
   def initialize(ds,y_var, opts=Hash.new)
     super    
-    @ds=ds.dup_only_valid
-    @ds_valid=@ds
-    @dy=@ds[@y_var]
-    @ds_indep=ds.dup(ds.fields-[y_var])
+    @ds       = ds.dup_only_valid
+    @ds_valid = @ds
+    @dy       = @ds[@y_var]
+    @ds_indep = ds.dup(ds.vectors.to_a - [y_var])
     # Create a custom matrix
-    columns=[]
-    @fields=[]
-    @ds.fields.each{|f|
-        if f!=@y_var
-            columns.push(@ds[f].to_a)
-            @fields.push(f)
-        end
-    }
-    @dep_columns=columns.dup
+    columns = []
+    @fields = []
+    @ds.vectors.each do |f|
+      if f != @y_var
+        columns.push(@ds[f].to_a)
+        @fields.push(f)
+      end
+    end
+    @dep_columns = columns.dup
     columns.push(@ds[@y_var])
     matrix=Matrix.columns(columns)
     @lr_s=nil
     @lr=::Alglib::LinearRegression.build_from_matrix(matrix)
     @coeffs=assign_names(@lr.coeffs)
-    
   end
     
-    def _dump(i)
-        Marshal.dump({'ds'=>@ds,'y_var'=>@y_var})
-    end
-    def self._load(data)
-        h=Marshal.load(data)
-        self.new(h['ds'], h['y_var'])
-    end
-    
-    def coeffs
-        @coeffs
-    end
-    # Coefficients using a constant
-    # Based on http://www.xycoon.com/ols1.htm
-    def matrix_resolution
-        mse_p=mse
-        columns=@dep_columns.dup.map {|xi| xi.map{|i| i.to_f}}
-        columns.unshift([1.0]*@ds.cases)
-        y=Matrix.columns([@dy.data.map  {|i| i.to_f}])
-        x=Matrix.columns(columns)
-        xt=x.t
-        matrix=((xt*x)).inverse*xt
-        matrix*y
-    end
-    def r2
-        r**2
-    end
-    def r
-        Bivariate::pearson(@dy,predicted)
-    end  
-    def sst
-        @dy.ss
-    end
-    def constant
-        @lr.constant
-    end
-    def standarized_coeffs
-        l=lr_s
-        assign_names(l.coeffs)
-    end
-    def lr_s
-        if @lr_s.nil?
-            build_standarized
-        end
-        @lr_s
-    end
-    def build_standarized
-        @ds_s=@ds.standarize
-        columns=[]
-        @ds_s.fields.each{|f|
-            columns.push(@ds_s[f].to_a) unless f==@y_var
-        }
-        @dep_columns_s=columns.dup
-        columns.push(@ds_s[@y_var])
-        matrix=Matrix.columns(columns)
-        @lr_s=Alglib::LinearRegression.build_from_matrix(matrix)
-    end
-    def process(v)
-        @lr.process(v)
-    end
-    def process_s(v)
-        lr_s.process(v)
-    end
-    # ???? Not equal to SPSS output
-    def standarized_residuals
-        res=residuals
-        red_sd=residuals.sds
-        res.collect {|v|
-            v.quo(red_sd)
-        }.to_vector(:numeric)
+  def _dump(i)
+    Marshal.dump({'ds'=>@ds,'y_var'=>@y_var})
+  end
+
+  def self._load(data)
+    h=Marshal.load(data)
+    self.new(h['ds'], h['y_var'])
+  end
+      
+  def coeffs
+    @coeffs
+  end
+  # Coefficients using a constant
+  # Based on http://www.xycoon.com/ols1.htm
+  def matrix_resolution
+    mse_p=mse
+    columns=@dep_columns.dup.map {|xi| xi.map{|i| i.to_f}}
+    columns.unshift([1.0]*@ds.cases)
+    y=Matrix.columns([@dy.data.map  {|i| i.to_f}])
+    x=Matrix.columns(columns)
+    xt=x.t
+    matrix=((xt*x)).inverse*xt
+    matrix*y
+  end
+
+  def r2
+    r**2
+  end
+
+  def r
+    Bivariate::pearson(@dy,predicted)
+  end  
+
+  def sst
+    @dy.ss
+  end
+
+  def constant
+    @lr.constant
+  end
+
+  def standarized_coeffs
+    l=lr_s
+    assign_names(l.coeffs)
+  end
+
+  def lr_s
+    if @lr_s.nil?
+      build_standarized
     end
+    @lr_s
+  end
+
+  def build_standarized
+    @ds_s=@ds.standardize
+    columns=[]
+    @ds_s.vectors.each{|f|
+      columns.push(@ds_s[f].to_a) unless f == @y_var
+    }
+    @dep_columns_s=columns.dup
+    columns.push(@ds_s[@y_var])
+    matrix=Matrix.columns(columns)
+    @lr_s=Alglib::LinearRegression.build_from_matrix(matrix)
+  end
+
+  def process(v)
+    @lr.process(v)
+  end
+
+  def process_s(v)
+    lr_s.process(v)
+  end
+  # ???? Not equal to SPSS output
+  def standarized_residuals
+    res    = residuals
+    red_sd = residuals.sds
+    Daru::Vector.new(res.collect {|v| v.quo(red_sd) })
+  end
 end
 end
 end

data/lib/statsample/regression/multiple/baseengine.rb

@@ -19,13 +19,12 @@ module Statsample
         end
         def initialize(ds, y_var, opts = Hash.new)
           @ds=ds
-          @predictors_n=@ds.fields.size-1
-          @total_cases=@ds.cases
-          @cases=@ds.cases
+          @predictors_n=@ds.vectors.size-1
+          @total_cases=@ds.nrows
+          @cases=@ds.nrows
           @y_var=y_var
           @r2=nil
-          @name=_("Multiple Regression:  %s over %s") % [ ds.fields.join(",") , @y_var]
-          
+          @name=_("Multiple Regression:  %s over %s") % [ ds.vectors.to_a.join(",") , @y_var]
           
           opts_default={:digits=>3}
           @opts=opts_default.merge opts
@@ -33,7 +32,6 @@ module Statsample
           @opts.each{|k,v|
             self.send("#{k}=",v) if self.respond_to? k
           }
-          
         end
         # Calculate F Test
         def anova
@@ -45,15 +43,17 @@ module Statsample
         end
         # Retrieves a vector with predicted values for y
         def predicted
-          @total_cases.times.collect { |i|
-            invalid=false
-            vect=@dep_columns.collect {|v| invalid=true if v[i].nil?; v[i]}
-            if invalid
-              nil
-            else
-              process(vect)
+          Daru::Vector.new(
+            @total_cases.times.collect do |i|
+              invalid = false
+              vect = @dep_columns.collect {|v| invalid = true if v[i].nil?; v[i]}
+              if invalid
+                nil
+              else
+                process(vect)
+              end
             end
-          }.to_vector(:numeric)
+          )
         end
         # Retrieves a vector with standarized values for y
         def standarized_predicted
@@ -61,15 +61,17 @@ module Statsample
         end
         # Retrieves a vector with residuals values for y
         def residuals
-          (0...@total_cases).collect{|i|
-            invalid=false
-            vect=@dep_columns.collect{|v| invalid=true if v[i].nil?; v[i]}
-            if invalid or @ds[@y_var][i].nil?
-              nil
-            else
-              @ds[@y_var][i] - process(vect)
+          Daru::Vector.new(
+            (0...@total_cases).collect do |i|
+              invalid=false
+              vect=@dep_columns.collect{|v| invalid=true if v[i].nil?; v[i]}
+              if invalid or @ds[@y_var][i].nil?
+                nil
+              else
+                @ds[@y_var][i] - process(vect)
+              end
             end
-          }.to_vector(:numeric)
+          )
         end
         # R Multiple
         def r
@@ -131,12 +133,10 @@ module Statsample
         # Tolerance for a given variable
         # http://talkstats.com/showthread.php?t=5056
         def tolerance(var)
-          ds=assign_names(@dep_columns)
-          ds.each{|k,v|
-          ds[k]=v.to_vector(:numeric)
-          }
-          lr=self.class.new(ds.to_dataset,var)
-          1-lr.r2
+          ds = assign_names(@dep_columns)
+          ds.each { |k,v| ds[k] = Daru::Vector.new(v) }
+          lr = self.class.new(Daru::DataFrame.new(ds),var)
+          1 - lr.r2
         end
         # Tolerances for each coefficient
         def coeffs_tolerances
@@ -165,12 +165,12 @@ module Statsample
         def estimated_variance_covariance_matrix
           #mse_p=mse
           columns=[]
-          @ds_valid.fields.each{|k|
-            v=@ds_valid[k]
-            columns.push(v.data) unless k==@y_var
+          @ds_valid.vectors.each{|k|
+            v = @ds_valid[k]
+            columns.push(v.to_a) unless k == @y_var
           }
           columns.unshift([1.0]*@valid_cases)
-          x=Matrix.columns(columns)
+          x=::Matrix.columns(columns)
           matrix=((x.t*x)).inverse * mse
           matrix.collect {|i| Math::sqrt(i) if i>=0 }
         end

data/lib/statsample/regression/multiple/gslengine.rb

@@ -9,43 +9,44 @@ if Statsample.has_gsl?
         # If you need pairwise, use RubyEngine
         # Example:
         #
-        #   @a=[1,3,2,4,3,5,4,6,5,7].to_vector(:numeric)
-        #   @b=[3,3,4,4,5,5,6,6,4,4].to_vector(:numeric)
-        #   @c=[11,22,30,40,50,65,78,79,99,100].to_vector(:numeric)
-        #   @y=[3,4,5,6,7,8,9,10,20,30].to_vector(:numeric)
-        #   ds={'a'=>@a,'b'=>@b,'c'=>@c,'y'=>@y}.to_dataset
-        #   lr=Statsample::Regression::Multiple::GslEngine.new(ds,'y')
+        #   @a = Daru::Vector.new([1,3,2,4,3,5,4,6,5,7])
+        #   @b = Daru::Vector.new([3,3,4,4,5,5,6,6,4,4])
+        #   @c = Daru::Vector.new([11,22,30,40,50,65,78,79,99,100])
+        #   @y = Daru::Vector.new([3,4,5,6,7,8,9,10,20,30])
+        #   ds = Daru::DataFrame.new({:a => @a,:b => @b,:c => @c,:y => @y})
+        #   lr=Statsample::Regression::Multiple::GslEngine.new(ds,:y)
         #
         class GslEngine < BaseEngine
           def initialize(ds,y_var, opts=Hash.new)
             super
-            @ds=ds.dup_only_valid
-            @ds_valid=@ds
-            @valid_cases=@ds_valid.cases
-            @dy=@ds[@y_var]
-            @ds_indep=ds.dup(ds.fields-[y_var])
+            @ds          = ds.dup_only_valid
+            @ds_valid    = @ds
+            @valid_cases = @ds_valid.nrows
+            @dy          = @ds[@y_var]
+            @ds_indep    = ds.dup(ds.vectors.to_a - [y_var])
             # Create a custom matrix
             columns=[]
             @fields=[]
-            max_deps = GSL::Matrix.alloc(@ds.cases, @ds.fields.size)
-            constant_col=@ds.fields.size-1
-            for i in 0...@ds.cases
+            max_deps = GSL::Matrix.alloc(@ds.nrows, @ds.vectors.size)
+            constant_col=@ds.vectors.size-1
+            for i in 0...@ds.nrows
               max_deps.set(i,constant_col,1)
             end
-            j=0
-            @ds.fields.each{|f|
-              if f!=@y_var
-                @ds[f].each_index{|i1|
+            j = 0
+            @ds.vectors.each do |f|
+              if f != @y_var
+                @ds[f].each_index do |i1|
                   max_deps.set(i1,j,@ds[f][i1])
-                }
+                end
+
                 columns.push(@ds[f].to_a)
                 @fields.push(f)
-                j+=1
+                j += 1
               end
-            }
-            @dep_columns=columns.dup
-            @lr_s=nil
-            c, @cov, @chisq, @status = GSL::MultiFit.linear(max_deps, @dy.gsl)
+            end
+            @dep_columns = columns.dup
+            @lr_s        = nil
+            c, @cov, @chisq, @status = GSL::MultiFit.linear(max_deps, @dy.to_gsl)
             @constant=c[constant_col]
             @coeffs_a=c.to_a.slice(0...constant_col)
             @coeffs=assign_names(@coeffs_a)
@@ -97,7 +98,7 @@ if Statsample.has_gsl?
             @lr_s
           end
           def build_standarized
-            @ds_s=@ds.standarize
+            @ds_s=@ds.standardize
             @lr_s=GslEngine.new(@ds_s,@y_var)
           end
           def process_s(v)
@@ -107,24 +108,20 @@ if Statsample.has_gsl?
           def standarized_residuals
             res=residuals
             red_sd=residuals.sds
-            res.collect {|v|
-              v.quo(red_sd)
-            }.to_vector(:numeric)
+            Daru::Vector.new(res.collect {|v| v.quo(red_sd) })
           end
 
           # Standard error for coeffs
           def coeffs_se
-            out={}
-            evcm=estimated_variance_covariance_matrix
-            @ds_valid.fields.each_with_index do |f,i|
-
-              mi=i+1
-              next if f==@y_var
-              out[f]=evcm[mi,mi]
+            out  = {}
+            evcm = estimated_variance_covariance_matrix
+            @ds_valid.vectors.to_a.each_with_index do |f,i|
+              mi = i+1
+              next if f == @y_var
+              out[f] = evcm[mi,mi]
             end
             out
           end
-
         end
       end
     end