veritable 0.1.2.30 → 0.1.3.31

data/CHANGELOG.txt

@@ -1,3 +1,7 @@
+veritable-ruby 0.1.3 - July 12, 2012
+    * Support for similar API call to retrieve rows similar to a target row
+    * Implemented count-batching for predictions
+
 veritable-ruby 0.1.2 - July 9, 2012
     * Added check for maximum count value (100000)
 

data/lib/veritable/api.rb

@@ -554,8 +554,8 @@ module Veritable
     # Scores how related columns are to a column of interest
     #
     # ==== Arguments
-    # * +column_id+ -- the id of the column of interest
-    # * +start+ -- the column id from which to start the cursor. Columns with related scores greater than or equal to the score of column +start+ will be returned by the cursor. Default is +nil+, in which case all columns in the table will be returned by the cursor.
+    # * +column_id+ -- the name of the column of interest
+    # * +start+ -- the column name from which to start the cursor. Columns with related scores greater than or equal to the score of column +start+ will be returned by the cursor. Default is +nil+, in which case all columns in the table will be returned by the cursor.
     # * +limit+ -- optionally limits the number of columns returned by the cursor. Default is +nil+, in which case the number of columns returned will not be limited.
     #
     # ==== Returns
@@ -578,6 +578,45 @@ module Veritable
       end
     end
 
+    # Returns rows which are similar to a target row in the context
+    # of a particular column of interest.
+    #
+    # ==== Arguments
+    # * +row+ -- either a row '_id' string or a row hash corrsponding to the target row. If a row hash is provided, it must contain an '_id' key whose value is the '_id' of a row present in the table at the time of the analysis
+    # * +column_id+ -- the name of the column of interest.
+    # * +max_rows+ -- the maximum number of similar rows to return. Default is +10+. The actual number of similar rows returned will be less than or equal to max_rows.
+    # * +return_data+ -- if +true+, the full row content will be returned. If +false+, only the '_id' field for each row will be returned. Default is +true+.
+    #
+    # ==== Returns
+    # An array of row entries ordered from most similar to least similar. 
+    # Each row entry is an array with the first element being the row and 
+    # the second element being a relatedness score between 0 to 1.
+    # 
+    # See also: https://dev.priorknowledge.com/docs/client/ruby  
+    def similar_to(row, column_id, opts={:max_rows => 10, :return_data => true})
+      if row.is_a? String
+        row = {'_id' => row}
+      end
+      if not row.is_a? Hash
+        raise VeritableError.new("Similar -- Must provide an existing row to get similar!")
+      end
+      update if running?
+      if succeeded?
+        doc = post(link('similar'), {:data => row, :column => column_id, 
+                                     :max_rows => 10, :return_data => true}.update(opts))
+        return doc['data']
+      elsif running?
+        raise VeritableError.new("Similar -- Analysis with id #{_id} is still running and not yet ready to calculate similar.")
+      elsif failed?
+        raise VeritableError.new("Similar -- Analysis with id #{_id} has failed and cannot calculate similar.")
+      else
+        raise VeritableError.new("Similar -- Shouldn't be here -- please let us know at support@priorknowledge.com.")
+      end
+    end
+
+    
+    
+    
     # Returns a string representation of the analysis resource
     def inspect; to_s; end
 
@@ -618,16 +657,22 @@ module Veritable
     
     private
     
-    def execute_batch(batch, count, preds)
+    def execute_batch(batch, count, preds, maxcells)
         if batch.size == 0
             return
         end
         if batch.size == 1
             data = batch[0]
+            ncols = (data.values.select {|v| v.nil?}).size
+            max_batch_count = (ncols == 0) ? count : (maxcells/ncols).to_i
+            res = []
+            while res.size < count do
+                batch_count = [max_batch_count, count - res.size].min
+                res = res + post(link('predict'), {'data' => data, 'count' => batch_count, 'return_fixed' => false})
+            end
         else
-            data = batch
+            res = post(link('predict'), {'data' => batch, 'count' => count, 'return_fixed' => false})
         end
-        res = post(link('predict'), {'data' => data, 'count' => count, 'return_fixed' => false})
         if not res.is_a? Array
           begin
             res.to_s
@@ -661,16 +706,15 @@ module Veritable
             if tcols > maxcols
                 raise VeritableError.new("Predict -- Cannot predict for row #{row['_request_id']} with more than #{maxcols} combined fixed and predicted values.")
             end
-            n = ncols * count
-            if n > maxcells
-                raise VeritableError.new("Predict -- Cannot predict for row #{row['_request_id']} with #{ncols} missing values and count #{count}: exceeds predicted cell limit of #{maxcells}.")
+            if ncols > maxcells
+                raise VeritableError.new("Predict -- Cannot predict for row #{row['_request_id']} with #{ncols} missing values: exceeds predicted cell limit of #{maxcells}.")
             end
         }
         rows.each {|row|
             ncols = (row.values.select {|v| v.nil?}).size
             n = ncols * count
             if (ncells + n) > maxcells
-                execute_batch(batch, count, preds)
+                execute_batch(batch, count, preds, maxcells)
                 ncells = n
                 batch = [row]
             else
@@ -678,7 +722,7 @@ module Veritable
                 ncells = ncells + n
             end
         }
-        execute_batch(batch, count, preds)
+        execute_batch(batch, count, preds, maxcells)
         return preds
       else
         raise VeritableError.new("Predict -- Shouldn't be here -- please let us know at support@priorknowledge.com.")

data/lib/veritable/version.rb

@@ -1,5 +1,5 @@
 module Veritable
 
   # The current version of veritable-ruby
-  VERSION = "0.1.2.30"
+  VERSION = "0.1.3.31"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: veritable
 version: !ruby/object:Gem::Version
-  version: 0.1.2.30
+  version: 0.1.3.31
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2012-07-09 00:00:00.000000000 Z
+date: 2012-07-13 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rest-client
@@ -173,7 +173,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 810707972233102190
+      hash: 4376636797931241119
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -182,7 +182,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: 810707972233102190
+      hash: 4376636797931241119
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.24