daru 0.1.5 → 0.1.6

data/lib/daru/io/sql_data_source.rb

@@ -73,6 +73,8 @@ module Daru
         query = String.try_convert(query) or
           raise ArgumentError, "Query must be a string, #{query.class} received"
 
+        db = attempt_sqlite3_connection(db) if db.is_a?(String) && Pathname(db).exist?
+
         case db
         when DBI::DatabaseHandle
           DbiAdapter.new(db, query)
@@ -82,6 +84,14 @@ module Daru
           raise ArgumentError, "Unknown database adapter type #{db.class}"
         end
       end
+
+      def attempt_sqlite3_connection(db)
+        DBI.connect("DBI:SQLite3:#{db}")
+      rescue SQLite3::NotADatabaseException
+        raise ArgumentError, "Expected #{db} to point to a SQLite3 database"
+      rescue NameError
+        raise NameError, "In order to establish a connection to #{db}, please require 'dbi'"
+      end
     end
   end
 end

data/lib/daru/iruby/templates/dataframe.html.erb

@@ -1,52 +1,5 @@
+<b> Daru::DataFrame<%= name ? ": #{name} " : ''%>(<%=nrows%>x<%=ncols%>) </b>
 <table>
-  <tr>
-    <th colspan='<%= @vectors.size+1 %>'>Daru::DataFrame<%= name ? ": #{name} " : ''%>(<%=nrows%>x<%=ncols%>)</th>
-  </tr>
-
-  <% if @vectors.is_a? MultiIndex %>
-    <% Daru::IRuby::Helpers.tuples_with_colspans(@vectors).each_with_index do |tuple, idx| %>
-      <tr>
-        <% if idx.zero? %>
-          <th rowspan="<%= @vectors.width %>"></th>
-        <% end %>
-        <% tuple.each do |idx, span| %>
-          <th colspan="<%= span %>"><%= idx %></th>
-        <% end %>
-      </tr>
-    <% end %>
-  <% else %>
-    <tr>
-      <th></th>
-      <% @vectors.each do |vector| %>
-        <th><%=vector%></th>
-      <% end %>
-    </tr>
-  <% end %>
-
-  <% @index.first(threshold).each_with_index do |index, pos| %>
-    <tr>
-      <td><%= index %></td>
-      <% row.at(pos).each do |element| %>
-        <td><%= element.to_s %></td>
-      <% end %>
-    </tr>
-  <% end %>
-
-  <% if nrows > threshold %>
-    <tr>
-      <% (@vectors.size + 1).times do %>
-        <td>...</td>
-      <% end %>
-    </tr>
-
-    <% last_index = @index.to_a.last
-       last_row = row_at @index.size-1 %>
-
-    <tr>
-      <td><%= last_index %></td>
-        <% last_row.each do |element| %>
-          <td><%= element.to_s %></td>
-        <% end %>
-    </tr>
-  <% end %>
+  <%= table_thead %>
+  <%= table_tbody %>
 </table>

data/lib/daru/iruby/templates/dataframe_mi.html.erb

@@ -1,58 +1,5 @@
+<b> Daru::DataFrame<%= name ? ": #{name} " : ''%>(<%=nrows%>x<%=ncols%>) </b>
 <table>
-  <tr>
-    <th colspan='<%= @vectors.size+index.width %>'>Daru::DataFrame<%= name ? ": #{name} " : ''%>(<%=nrows%>x<%=ncols%>)</th>
-  </tr>
-  <% if @vectors.is_a? MultiIndex %>
-    <% Daru::IRuby::Helpers.tuples_with_colspans(@vectors).each_with_index do |tuple, idx| %>
-      <tr>
-        <% if idx.zero? %>
-          <th colspan="<%= index.width %>" rowspan="<%= @vectors.width %>"></th>
-        <% end %>
-        <% tuple.each do |idx, span| %>
-          <th colspan="<%= span %>"><%= idx %></th>
-        <% end %>
-      </tr>
-    <% end %>
-  <% else %>
-    <tr>
-      <th colspan="<%= index.width %>"></th>
-      <% @vectors.each do |vector| %>
-        <th><%=vector%></th>
-      <% end %>
-    </tr>
-  <% end %>
-
-  <% Daru::IRuby::Helpers.tuples_with_rowspans(@index).first(threshold).zip(@index.to_a).each do |tuple, index| %>
-    <tr>
-      <% tuple.each do |idx, span| %>
-        <th rowspan="<%= span %>"><%= idx %></th>
-      <% end %>
-      <% row[index].each do |element| %>
-        <td><%= element.to_s %></td>
-      <% end %>
-    </tr>
-  <% end %>
-
-  <% if nrows > threshold %>
-    <tr>
-      <% index.width.times do %>
-        <th>...</th>
-      <% end %>
-      <% @vectors.size.times do %>
-        <td>...</td>
-      <% end %>
-    </tr>
-
-    <% last_index = @index.to_a.last
-       last_row = row[last_index] %>
-
-    <tr>
-      <% last_index.each do |idx| %>
-        <th><%= idx %></td>
-      <% end %>
-      <% last_row.each do |element| %>
-        <td><%= element.to_s %></td>
-      <% end %>
-    </tr>
-  <% end %>
+  <%= table_thead %>
+  <%= table_tbody %>
 </table>

data/lib/daru/iruby/templates/dataframe_mi_tbody.html.erb

@@ -0,0 +1,35 @@
+<tbody>
+  <% Daru::IRuby::Helpers.tuples_with_rowspans(@index).first(threshold).zip(@index.to_a).each do |tuple, index| %>
+    <tr>
+      <% tuple.each do |idx, span| %>
+        <th rowspan="<%= span %>"><%= idx %></th>
+      <% end %>
+      <% row[index].each do |element| %>
+        <td><%= element.to_s %></td>
+      <% end %>
+    </tr>
+  <% end %>
+
+  <% if nrows > threshold %>
+    <tr>
+      <% index.width.times do %>
+        <th>...</th>
+      <% end %>
+      <% @vectors.size.times do %>
+        <td>...</td>
+      <% end %>
+    </tr>
+
+    <% last_index = @index.to_a.last
+       last_row = row[last_index] %>
+
+    <tr>
+      <% last_index.each do |idx| %>
+        <th><%= idx %></td>
+      <% end %>
+      <% last_row.each do |element| %>
+        <td><%= element.to_s %></td>
+      <% end %>
+    </tr>
+  <% end %>
+</tbody>

data/lib/daru/iruby/templates/dataframe_mi_thead.html.erb

@@ -0,0 +1,21 @@
+<thead>
+  <% if @vectors.is_a? MultiIndex %>
+    <% Daru::IRuby::Helpers.tuples_with_colspans(@vectors).each_with_index do |tuple, idx| %>
+      <tr>
+        <% if idx.zero? %>
+          <th colspan="<%= index.width %>" rowspan="<%= @vectors.width %>"></th>
+        <% end %>
+        <% tuple.each do |idx, span| %>
+          <th colspan="<%= span %>"><%= idx %></th>
+        <% end %>
+      </tr>
+    <% end %>
+  <% else %>
+    <tr>
+      <th colspan="<%= index.width %>"></th>
+      <% @vectors.each do |vector| %>
+        <th><%=vector%></th>
+      <% end %>
+    </tr>
+  <% end %>
+</thead>

data/lib/daru/iruby/templates/dataframe_tbody.html.erb

@@ -0,0 +1,28 @@
+<tbody>
+  <% @index.first(threshold).each_with_index do |index, pos| %>
+    <tr>
+      <td><%= index %></td>
+      <% row.at(pos).each do |element| %>
+        <td><%= element.to_s %></td>
+      <% end %>
+    </tr>
+  <% end %>
+
+  <% if nrows > threshold %>
+    <tr>
+      <% (@vectors.size + 1).times do %>
+        <td>...</td>
+      <% end %>
+    </tr>
+
+    <% last_index = @index.to_a.last
+       last_row = row_at @index.size-1 %>
+
+    <tr>
+      <td><%= last_index %></td>
+        <% last_row.each do |element| %>
+          <td><%= element.to_s %></td>
+        <% end %>
+    </tr>
+  <% end %>
+</tbody>

data/lib/daru/iruby/templates/dataframe_thead.html.erb

@@ -0,0 +1,21 @@
+<thead>
+  <% if @vectors.is_a? MultiIndex %>
+    <% Daru::IRuby::Helpers.tuples_with_colspans(@vectors).each_with_index do |tuple, idx| %>
+      <tr>
+        <% if idx.zero? %>
+          <th rowspan="<%= @vectors.width %>"></th>
+        <% end %>
+        <% tuple.each do |idx, span| %>
+          <th colspan="<%= span %>"><%= idx %></th>
+        <% end %>
+      </tr>
+    <% end %>
+  <% else %>
+    <tr>
+      <th></th>
+      <% @vectors.each do |vector| %>
+        <th><%=vector%></th>
+      <% end %>
+    </tr>
+  <% end %>
+</thead>

data/lib/daru/iruby/templates/vector.html.erb

@@ -1,27 +1,5 @@
+<b> Daru::Vector(<%= size %>)<%= ':category' if category? %> </b>
 <table>
-  <tr>
-    <th colspan="2">Daru::Vector(<%= size %>)<%= ':category' if category? %></th>
-  </tr>
-  <% if name %>
-    <tr>
-        <th> </th>
-        <th><%= name %></th>
-    </tr>
-  <% end %>
-
-  <% @index.each_with_index.first(threshold).each do |index, pos| %>
-    <tr>
-      <td><%= index %></td>
-      <td><%= self.at(pos) %></td>
-    </tr>
-  <% end %>
-
-  <% if size > threshold %>
-    <% last_index = @index.size-1 %>
-    <tr><td>...</td><td>...</td></tr>
-    <tr>
-      <td><%= last_index %></td>
-      <td><%= self.at last_index %></td>
-    </tr>
-  <% end %>
+  <%= table_thead %>
+  <%= table_tbody %>
 </table>

data/lib/daru/iruby/templates/vector_mi.html.erb

@@ -1,36 +1,5 @@
+<b> Daru::Vector(<%= size %>)<%= ':category' if category? %> </b>
 <table>
-  <tr>
-    <th colspan="<%= index.width+1 %>">Daru::Vector(<%= size %>)<%= ':category' if category? %></th>
-  </tr>
-  <% if name %>
-    <tr>
-        <th colspan="<%= index.width %>"> </th>
-        <th><%= name %></th>
-    </tr>
-  <% end %>
-
-  <% Daru::IRuby::Helpers.tuples_with_rowspans(@index).first(threshold).zip(to_a).each do |tuple, value| %>
-    <tr>
-      <% tuple.each do |idx, span| %>
-        <th rowspan="<%= span %>"><%= idx %></th>
-      <% end %>
-      <td><%= value %></td>
-    </tr>
-  <% end %>
-
-  <% if size > threshold %>
-    <% last_index = @index.to_a.last %>
-    <tr>
-      <% last_index.size.times do %>
-        <th>...</th>
-      <% end %>
-      <td>...</td>
-    </tr>
-    <tr>
-      <% last_index.each do |idx| %>
-        <th><%= idx %></td>
-      <% end %>
-      <td><%= self[last_index] %></td>
-    </tr>
-  <% end %>
+  <%= table_thead %>
+  <%= table_tbody %>
 </table>

data/lib/daru/iruby/templates/vector_mi_tbody.html.erb

@@ -0,0 +1,26 @@
+<tbody>
+  <% Daru::IRuby::Helpers.tuples_with_rowspans(@index).first(threshold).zip(to_a).each do |tuple, value| %>
+    <tr>
+      <% tuple.each do |idx, span| %>
+        <th rowspan="<%= span %>"><%= idx %></th>
+      <% end %>
+      <td><%= value %></td>
+    </tr>
+  <% end %>
+
+  <% if size > threshold %>
+    <% last_index = @index.to_a.last %>
+    <tr>
+      <% last_index.size.times do %>
+        <th>...</th>
+      <% end %>
+      <td>...</td>
+    </tr>
+    <tr>
+      <% last_index.each do |idx| %>
+        <th><%= idx %></td>
+      <% end %>
+      <td><%= self[last_index] %></td>
+    </tr>
+  <% end %>
+</tbody>

data/lib/daru/iruby/templates/vector_mi_thead.html.erb

@@ -0,0 +1,8 @@
+<thead>
+  <% if name %>
+    <tr>
+        <th colspan="<%= index.width %>"> </th>
+        <th><%= name %></th>
+    </tr>
+  <% end %>
+</thead>

data/lib/daru/iruby/templates/vector_tbody.html.erb

@@ -0,0 +1,17 @@
+<tbody>
+  <% @index.each_with_index.first(threshold).each do |index, pos| %>
+    <tr>
+      <td><%= index %></td>
+      <td><%= self.at(pos) %></td>
+    </tr>
+  <% end %>
+
+  <% if size > threshold %>
+    <% last_index = @index.size-1 %>
+    <tr><td>...</td><td>...</td></tr>
+    <tr>
+      <td><%= last_index %></td>
+      <td><%= self.at last_index %></td>
+    </tr>
+  <% end %>
+</tbody>

data/lib/daru/iruby/templates/vector_thead.html.erb

@@ -0,0 +1,8 @@
+<thead>
+  <% if name %>
+    <tr>
+        <th> </th>
+        <th><%= name %></th>
+    </tr>
+  <% end %>
+</thead>

data/lib/daru/maths/statistics/dataframe.rb

@@ -22,7 +22,7 @@ module Daru
         #   Calculate the minimum value of each numeric vector
         # @!method product
         #   Compute the product of each numeric vector
-        [:mean, :variance_sample, :range, :median, :mode, :std, :sum, :count, :min, :product].each do |meth|
+        %i[mean variance_sample range median mode std sum count min product].each do |meth|
           define_method(meth) do
             compute_stats meth
           end
@@ -70,9 +70,9 @@ module Daru
         # @!method rolling_variance
         #   Calculate moving variance
         #   @param [Integer] n (10) Loopback length. Default to 10.
-        [
-          :cumsum,:standardize,:acf,:ema,:rolling_mean,:rolling_median,:rolling_max,
-          :rolling_min,:rolling_count,:rolling_std,:rolling_variance, :rolling_sum
+        %i[
+          cumsum standardize acf ema rolling_mean rolling_median rolling_max
+          rolling_min rolling_count rolling_std rolling_variance rolling_sum
         ].each do |meth|
           define_method(meth) do |*args|
             apply_method_to_numerics meth, *args
@@ -88,7 +88,7 @@ module Daru
         # be applied to numeric vectors. Default is [:count, :mean, :std, :max,
         # :min]. Methods will be applied in the specified order.
         def describe methods=nil
-          methods ||= [:count, :mean, :std, :min, :max]
+          methods ||= %i[count mean std min max]
 
           description_hash = {}
           numeric_vectors.each do |vec|
@@ -133,17 +133,15 @@ module Daru
         # Calculate sample variance-covariance between the numeric vectors.
         def covariance
           cache = Hash.new do |h, (col, row)|
-            h[[col, row]] = vector_cov(self[row],self[col])
+            value = vector_cov(self[row],self[col])
+            h[[col, row]] = value
+            h[[row, col]] = value
           end
           vectors = numeric_vectors
 
           mat_rows = vectors.collect do |row|
             vectors.collect do |col|
-              if row == col
-                self[row].variance
-              else
-                cache[[col,row]]
-              end
+              row == col ? self[row].variance : cache[[col,row]]
             end
           end
 

data/lib/daru/maths/statistics/vector.rb

@@ -19,10 +19,6 @@ module Daru
           @data.product
         end
 
-        def min
-          @data.min
-        end
-
         def range
           max - min
         end
@@ -45,7 +41,7 @@ module Daru
         # be applied to vectors. Default is [:count, :mean, :std, :max,
         # :min]. Methods will be applied in the specified order.
         def describe methods=nil
-          methods ||= [:count, :mean, :std, :min, :max]
+          methods ||= %i[count mean std min max]
           description = methods.map { |m| send(m) }
           Daru::Vector.new(description, index: methods, name: :statistics)
         end
@@ -70,24 +66,129 @@ module Daru
           reject_values(*Daru::MISSING_VALUES).uniq.reset_index!
         end
 
-        # Maximum element of the vector.
+        # Returns the maximum value present in the vector.
         #
-        # @param return_type [Symbol] Data type of the returned value. Defaults
-        #   to returning only the maximum number but passing *:vector* will return
-        #   a Daru::Vector with the index of the corresponding maximum value.
-        def max return_type=:stored_type
-          max_value = @data.max
-          if return_type == :vector
-            Daru::Vector.new({index_of(max_value) => max_value}, name: @name, dtype: @dtype)
-          else
-            max_value
-          end
+        # @example
+        #
+        #   dv = Daru::Vector.new (["Tyrion", "Daenerys", "Jon Starkgaryen"]), index: Daru::Index.new([:t, :d, :j])
+        #   #=>
+        #   #   #<Daru::Vector(3)>
+        #   #       t   Tyrion
+        #   #       d   Daenerys
+        #   #       j   Jon Starkgaryen
+        #
+        #   dv.max
+        #   #=> "Tyrion"
+        #
+        #   dv.max(2) { |a,b| a.size <=> b.size }
+        #   #=> ["Jon Starkgaryen","Daenerys"]
+        #
+        #   dv.max(2) { |i| i.size }
+        #   #=> ["Jon Starkgaryen","Daenerys"]
+        def max(size=nil, &block)
+          data = @data.data.to_a
+          data = if block_given?
+                   if block.parameters.count == 1 # Object block like { |x| x.size }
+                     data.sort_by(&block)
+                   else # Comparative block like { |a,b| a.size <=> b.size }
+                     data.sort(&block)
+                   end
+                 else
+                   data.sort
+                 end
+          size.nil? ? data.last : data[data.count-size..-1].reverse
+        end
+
+        # Returns the index of the maximum value present in the vector.
+        #
+        # @example
+        #
+        #   dv = Daru::Vector.new (["Tyrion", "Daenerys", "Jon Starkgaryen"]), index: Daru::Index.new([:t, :d, :j])
+        #   #=>
+        #   #   #<Daru::Vector(3)>
+        #   #       t   Tyrion
+        #   #       d   Daenerys
+        #   #       j   Jon Starkgaryen
+        #
+        #   dv.index_of_max
+        #   #=> :t
+        #
+        #   dv.index_of_max(2) { |a,b| a.size <=> b.size }
+        #   #=> [:j, :d]
+        #
+        #   dv.max(2) { |i| i.size }
+        #   #=> [:j, :d]
+        def index_of_max(size=nil,&block)
+          data = @data.data.to_a
+          indx = @index.to_a
+          vals = max(size,&block)
+          vals.is_a?(Array) ? (vals.map { |x| indx[data.index(x)] }) : indx[data.index(vals)]
+        end
+
+        # Returns the minimum value present in the vector.
+        #
+        # @example
+        #
+        #   dv = Daru::Vector.new (["Tyrion", "Daenerys", "Jon Starkgaryen"]), index: Daru::Index.new([:t, :d, :j])
+        #   #=>
+        #   #   #<Daru::Vector(3)>
+        #   #       t   Tyrion
+        #   #       d   Daenerys
+        #   #       j   Jon Starkgaryen
+        #
+        #   dv.min
+        #   #=> "Daenerys"
+        #
+        #   dv.min(2) { |a,b| a.size <=> b.size }
+        #   #=> ["Tyrion","Daenerys"]
+        #
+        #   dv.min(2) { |i| i.size }
+        #   #=> ["Tyrion","Daenerys"]
+        def min(size=nil, &block)
+          data = @data.data.to_a
+          data = if block_given?
+                   if block.parameters.count == 1 # Object block like { |x| x.size }
+                     data.sort_by(&block)
+                   else # Comparative block like { |a,b| a.size <=> b.size }
+                     data.sort(&block)
+                   end
+                 else
+                   data.sort
+                 end
+          size.nil? ? data.first : data[0..size-1]
+        end
+
+        # Returns the index of the minimum value present in the vector.
+        #
+        # @example
+        #
+        #   dv = Daru::Vector.new (["Tyrion", "Daenerys", "Jon Starkgaryen"]), index: Daru::Index.new([:t, :d, :j])
+        #   #=>
+        #   #   #<Daru::Vector(3)>
+        #   #       t   Tyrion
+        #   #       d   Daenerys
+        #   #       j   Jon Starkgaryen
+        #
+        #   dv.index_of_min
+        #   #=> :d
+        #
+        #   dv.index_of_min(2) { |a,b| a.size <=> b.size }
+        #   #=> [:t, :d]
+        #
+        #   dv.index_of_min(2) { |i| i.size }
+        #   #=> [:t, :d]
+        def index_of_min(size=nil,&block)
+          data = @data.data.to_a
+          indx = @index.to_a
+          vals = min(size,&block)
+          vals.is_a?(Array) ? (vals.map { |x| indx[data.index(x)] }) : indx[data.index(vals)]
         end
 
-        # Return a Vector with the max element and its index.
+        # Return the maximum element present in the Vector, as a Vector.
         # @return [Daru::Vector]
         def max_index
-          max :vector
+          max_value = @data.max
+          Daru::Vector.new({index_of(max_value) => max_value}, name: @name, dtype: @dtype)
         end
 
         def frequencies
@@ -470,7 +571,7 @@ module Daru
         # @!method rolling_variance
         #   Calculate rolling variance
         #   @param [Integer] n (10) Loopback length
-        [:count, :mean, :median, :max, :min, :sum, :std, :variance].each do |meth|
+        %i[count mean median max min sum std variance].each do |meth|
           define_method("rolling_#{meth}".to_sym) do |n=10|
             rolling(meth, n)
           end
@@ -581,26 +682,28 @@ module Daru
 
         # Moving Average Convergence-Divergence.
         # Calculates the MACD (moving average convergence-divergence) of the time
-        # series - this is a comparison of a fast EMA with a slow EMA.
-        #
-        # == Arguments
-        # * *fast*: integer, (default = 12) - fast component of MACD
-        # * *slow*: integer, (default = 26) - slow component of MACD
-        # * *signal*: integer, (default = 9) - signal component of MACD
+        # series.
+        # @see https://en.wikipedia.org/wiki/MACD
         #
-        # == Usage
+        # @param fast [Integer] fast period of MACD (default 12)
+        # @param slow [Integer] slow period of MACD (default 26)
+        # @param signal [Integer] signal period of MACD (default 9)
         #
+        # @example Create a series and calculate MACD values
         #   ts = Daru::Vector.new((1..100).map { rand })
         #            # => [0.69, 0.23, 0.44, 0.71, ...]
-        #   ts.macd(13)
+        #   macdseries, macdsignal, macdhist = ts.macd
+        #   macdseries, macdsignal, macdhist = ts.macd(13)
+        #   macdseries, macdsignal, macdhist = ts.macd(signal=5)
         #
-        # == Returns
+        # @return [Array<Daru::Vector>] macdseries, macdsignal and macdhist are
+        #   returned as an array of three Daru::Vectors
         #
-        # Array of two Daru::Vectors - comparison of fast EMA with slow and EMA with
-        # signal value
         def macd(fast=12, slow=26, signal=9)
-          series = ema(fast) - ema(slow)
-          [series, series.ema(signal)]
+          macdseries = ema(fast) - ema(slow)
+          macdsignal = macdseries.ema(signal)
+          macdhist = macdseries - macdsignal
+          [macdseries, macdsignal, macdhist]
         end
 
         # Calculates the autocorrelation coefficients of the series.
@@ -688,6 +791,10 @@ module Daru
         alias :ss :sum_of_squares
         alias :percentil :percentile
         alias :se :standard_error
+        alias :max_by :max
+        alias :min_by :min
+        alias :index_of_max_by :index_of_max
+        alias :index_of_min_by :index_of_min
 
         private