Metadata fixes for the ValueMappingEstimator (dotnet#2098)

* The ValueMappingEstimator had a couple of issues when using setting the
Values as KeyTypes:
1) The output schema for the Estimator did not contain the KeyType
information in the metadata.
2) The reverse lookup of the metadata had the incorrect value.

This now sets the correct metadata on the output schema and uses the
value data for the reverse lookup. A test was added to confirm the
changes using the KeyToValueMapping appended to a ValueMappingEstimator
for the reverse lookup.

Fixes dotnet#2086
Fixes dotnet#2083

Author: singlis

src/Microsoft.ML.Data/Transforms/ValueMappingTransformer.cs

@@ -100,13 +100,14 @@ public override SchemaShape GetOutputSchema(SchemaShape inputSchema)
             var isKey = Transformer.ValueColumnType is KeyType;
             var columnType = (isKey) ? PrimitiveType.FromKind(DataKind.U4) :
                                     Transformer.ValueColumnType;
+            var metadataShape = SchemaShape.Create(Transformer.ValueColumnMetadata.Schema);
             foreach (var (Input, Output) in _columns)
             {
                 if (!inputSchema.TryFindColumn(Input, out var originalColumn))
                     throw Host.ExceptSchemaMismatch(nameof(inputSchema), "input", Input);
 
-                // Get the type from TOutputType
-                var col = new SchemaShape.Column(Output, vectorKind, columnType, isKey, originalColumn.Metadata);
+                // Create the Value column
+                var col = new SchemaShape.Column(Output, vectorKind, columnType, isKey, metadataShape);
                 resultDic[Output] = col;
             }
             return new SchemaShape(resultDic.Values);
@@ -191,18 +192,14 @@ internal static IDataView CreateDataView<TKey, TValue>(IHostEnvironment env,
                 // set of values. This is used for generating the metadata of
                 // the column.
                 HashSet<TValue> valueSet = new HashSet<TValue>();
-                HashSet<TKey> keySet = new HashSet<TKey>();
-                for (int i = 0; i < values.Count(); ++i)
+                foreach (var v in values)
                 {
-                    var v = values.ElementAt(i);
                     if (valueSet.Contains(v))
                         continue;
                     valueSet.Add(v);
-
-                    var k = keys.ElementAt(i);
-                    keySet.Add(k);
                 }
-                var metaKeys = keySet.ToArray();
+
+                var metaKeys = valueSet.ToArray();
 
                 // Key Values are treated in one of two ways:
                 // If the values are of type uint or ulong, these values are used directly as the keys types and no new keys are created.
@@ -387,7 +384,7 @@ protected ValueMappingTransformer(IHostEnvironment env, IDataView lookupMap,
             Host.CheckNonEmpty(valueColumn, nameof(valueColumn), "A value column must be specified when passing in an IDataView for the value mapping");
             _valueMap = CreateValueMapFromDataView(lookupMap, keyColumn, valueColumn);
             int valueColumnIdx = 0;
-            Host.Assert(lookupMap.Schema.TryGetColumnIndex(valueColumn, out valueColumnIdx));
+            Host.Check(lookupMap.Schema.TryGetColumnIndex(valueColumn, out valueColumnIdx));
             _valueMetadata = lookupMap.Schema[valueColumnIdx].Metadata;
 
             // Create the byte array of the original IDataView, this is used for saving out the data.