Address comments and handle WordBags and HashedWordBags

Author: wschin

docs/samples/Microsoft.ML.Samples/Dynamic/NgramExtraction.cs

@@ -61,7 +61,7 @@ public static void NgramTransform()
             // 'e' - 1 '<?>' - 2 'd' - 1 '=' - 4 'R' - 1 'U' - 1 'D' - 2 'E' - 1 'u' - 1 ',' - 1 '2' - 1
             // 'B' - 0 'e' - 6 's' - 3 't' - 6 '<?>' - 9 'g' - 2 'a' - 2 'm' - 2 'I' - 0 ''' - 0 'v' - 0 ...
             // Preview of the CharsTwoGrams column obtained after processing the input.
-            var charsTwoGramColumn = transformedData_twochars.GetColumn<VBuffer<float>>(transformedData_onechars.Schema["CharsUnigrams"]);
+            var charsTwoGramColumn = transformedData_twochars.GetColumn<VBuffer<float>>(transformedData_twochars.Schema["CharsTwograms"]);
             transformedData_twochars.Schema["CharsTwograms"].GetSlotNames(ref slotNames);
             printHelper("CharsTwograms", charsTwoGramColumn, slotNames);
 

src/Microsoft.ML.StaticPipe/TextStaticExtensions.cs

@@ -310,15 +310,15 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,
         /// <param name="ngramLength">Ngram length.</param>
         /// <param name="skipLength">Maximum number of tokens to skip when constructing an ngram.</param>
         /// <param name="allLengths">Whether to include all ngram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
-        /// <param name="maxNumTerms">Maximum number of ngrams to store in the dictionary.</param>
+        /// <param name="maximumNgramsCount">Maximum number of ngrams to store in the dictionary.</param>
         /// <param name="weighting">Statistical measure used to evaluate how important a word is to a document in a corpus.</param>
-        public static Vector<float> ToBagofWords(this Scalar<string> input,
+        public static Vector<float> ProduceWordBags(this Scalar<string> input,
             int ngramLength = 1,
             int skipLength = 0,
             bool allLengths = true,
-            int maxNumTerms = 10000000,
+            int maximumNgramsCount = 10000000,
             NgramExtractingEstimator.WeightingCriteria weighting = NgramExtractingEstimator.WeightingCriteria.Tf)
-                => new OutPipelineColumn(input, ngramLength, skipLength, allLengths, maxNumTerms, weighting);
+                => new OutPipelineColumn(input, ngramLength, skipLength, allLengths, maximumNgramsCount, weighting);
     }
 
     /// <summary>
@@ -397,7 +397,7 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,
         /// It does so by hashing each ngram and using the hash value as the index in the bag.
         /// </summary>
         /// <param name="input">The column to apply to.</param>
-        /// <param name="hashBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
+        /// <param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>
         /// <param name="ngramLength">Ngram length.</param>
         /// <param name="skipLength">Maximum number of tokens to skip when constructing an ngram.</param>
         /// <param name="allLengths">Whether to include all ngram lengths up to <paramref name="ngramLength"/> or only <paramref name="ngramLength"/>.</param>
@@ -407,14 +407,14 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,
         /// Text representation of original values are stored in the slot names of the  metadata for the new column.Hashing, as such, can map many initial values to one.
         /// <paramref name="invertHash"/> specifies the upper bound of the number of distinct input values mapping to a hash that should be retained.
         /// <value>0</value> does not retain any input values. <value>-1</value> retains all input values mapping to each hash.</param>
-        public static Vector<float> ToBagofHashedWords(this Scalar<string> input,
-            int hashBits = 16,
+        public static Vector<float> ProduceHashedWordBags(this Scalar<string> input,
+            int numberOfBits = 16,
             int ngramLength = 1,
             int skipLength = 0,
             bool allLengths = true,
             uint seed = 314489979,
             bool ordered = true,
-            int invertHash = 0) => new OutPipelineColumn(input, hashBits, ngramLength, skipLength, allLengths, seed, ordered, invertHash);
+            int invertHash = 0) => new OutPipelineColumn(input, numberOfBits, ngramLength, skipLength, allLengths, seed, ordered, invertHash);
     }
 
     /// <summary>
@@ -485,8 +485,8 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,
         /// Produces a bag of counts of ngrams (sequences of consecutive words ) in a given tokenized text.
         /// It does so by building a dictionary of ngrams and using the id in the dictionary as the index in the bag.
         ///
-        /// /// <see cref="ProduceNgrams"/> is different from <see cref="WordBagEstimatorStaticExtensions.ToBagofWords"/>
-        /// in a way that <see cref="ProduceNgrams"/> takes tokenized text as input while <see cref="WordBagEstimatorStaticExtensions.ToBagofWords"/> tokenizes text internally.
+        /// /// <see cref="ProduceNgrams"/> is different from <see cref="WordBagEstimatorStaticExtensions.ProduceWordBags"/>
+        /// in a way that <see cref="ProduceNgrams"/> takes tokenized text as input while <see cref="WordBagEstimatorStaticExtensions.ProduceWordBags"/> tokenizes text internally.
         /// </summary>
         /// <param name="input">The column to apply to.</param>
         /// <param name="ngramLength">Ngram length.</param>
@@ -571,8 +571,8 @@ public override IEstimator<ITransformer> Reconcile(IHostEnvironment env,
         /// Produces a bag of counts of ngrams (sequences of consecutive words of length 1-n) in a given tokenized text.
         /// It does so by hashing each ngram and using the hash value as the index in the bag.
         ///
-        /// <see cref="ProduceHashedNgrams"/> is different from <see cref="WordHashBagEstimatorStaticExtensions.ToBagofHashedWords"/>
-        /// in a way that <see cref="ProduceHashedNgrams"/> takes tokenized text as input while <see cref="WordHashBagEstimatorStaticExtensions.ToBagofHashedWords"/> tokenizes text internally.
+        /// <see cref="ProduceHashedNgrams"/> is different from <see cref="WordHashBagEstimatorStaticExtensions.ProduceHashedWordBags"/>
+        /// in a way that <see cref="ProduceHashedNgrams"/> takes tokenized text as input while <see cref="WordHashBagEstimatorStaticExtensions.ProduceHashedWordBags"/> tokenizes text internally.
         /// </summary>
         /// <param name="input">The column to apply to.</param>
         /// <param name="numberOfBits">Number of bits to hash into. Must be between 1 and 30, inclusive.</param>

src/Microsoft.ML.Transforms/Text/NgramHashingTransformer.cs

@@ -945,11 +945,14 @@ public ColumnOptions(string name,
                 if (invertHash != 0 && numberOfBits >= 31)
                     throw Contracts.ExceptParam(nameof(numberOfBits), $"Cannot support invertHash for a {0} bit hash. 30 is the maximum possible.", numberOfBits);
 
-                if (NgramLength + SkipLength > NgramBufferBuilder.MaxSkipNgramLength)
+                if (ngramLength == 1 && skipLength != 0)
+                    throw Contracts.ExceptUserArg(nameof(skipLength), $"Number of skips can only be one when the maximum n-gram's length is one.");
+                if (ngramLength + skipLength > NgramBufferBuilder.MaxSkipNgramLength)
                 {
                     throw Contracts.ExceptUserArg(nameof(skipLength),
                         $"The sum of skipLength and ngramLength must be less than or equal to {NgramBufferBuilder.MaxSkipNgramLength}");
                 }
+
                 FriendlyNames = null;
                 Name = name;
                 InputColumnNamesArray = inputColumnNames;

src/Microsoft.ML.Transforms/Text/NgramTransform.cs

@@ -846,20 +846,15 @@ internal ColumnOptions(string name,
                 int[] maximumNgramsCounts,
                 string inputColumnName = null)
             {
-                Name = name;
-                InputColumnName = inputColumnName ?? name;
-                NgramLength = ngramLength;
-                Contracts.CheckUserArg(0 < NgramLength && NgramLength <= NgramBufferBuilder.MaxSkipNgramLength, nameof(ngramLength));
-                SkipLength = skipLength;
-                if (NgramLength + SkipLength > NgramBufferBuilder.MaxSkipNgramLength)
-                {
+                if (ngramLength == 1 && skipLength != 0)
+                    throw Contracts.ExceptUserArg(nameof(skipLength), $"Number of skips can only be one when the maximum n-gram's length is one.");
+                if (ngramLength + skipLength > NgramBufferBuilder.MaxSkipNgramLength)
                     throw Contracts.ExceptUserArg(nameof(skipLength),
                         $"The sum of skipLength and ngramLength must be less than or equal to {NgramBufferBuilder.MaxSkipNgramLength}");
-                }
-                AllLengths = allLengths;
-                Weighting = weighting;
+                Contracts.CheckUserArg(0 < ngramLength && ngramLength <= NgramBufferBuilder.MaxSkipNgramLength, nameof(ngramLength));
+
                 var limits = new int[ngramLength];
-                if (!AllLengths)
+                if (!allLengths)
                 {
                     Contracts.CheckUserArg(Utils.Size(maximumNgramsCounts) == 0 ||
                         Utils.Size(maximumNgramsCounts) == 1 && maximumNgramsCounts[0] > 0, nameof(maximumNgramsCounts));
@@ -873,6 +868,13 @@ internal ColumnOptions(string name,
                     limits = Utils.BuildArray(ngramLength, i => i < Utils.Size(maximumNgramsCounts) ? maximumNgramsCounts[i] : extend);
                 }
                 _maximumNgramsCounts = ImmutableArray.Create(limits);
+
+                Name = name;
+                InputColumnName = inputColumnName ?? name;
+                NgramLength = ngramLength;
+                SkipLength = skipLength;
+                AllLengths = allLengths;
+                Weighting = weighting;
             }
         }