Add Apply<TResult>method to PrimitiveDataFrameColumn (dotnet#2807)

* Add Apply method to PrimitiveDataFrameColumn and its container * Add TestApply test * Remove unused df variable in DataFrameTests * Add xml doc comments to Apply method
pgovind · Jan 13, 2020 · 0fa210d · 0fa210d
1 parent 838350b
commit 0fa210d
Show file tree

Hide file tree

Showing 3 changed files with 64 additions and 0 deletions.
diff --git a/src/Microsoft.Data.Analysis/PrimitiveColumnContainer.cs b/src/Microsoft.Data.Analysis/PrimitiveColumnContainer.cs
@@ -251,6 +251,40 @@ public void ApplyElementwise(Func<T?, long, T?> func)
             }
         }
 
+        public void Apply<TResult>(Func<T?, TResult?> func, PrimitiveColumnContainer<TResult> resultContainer)
+            where TResult : unmanaged
+        {
+            for (int b = 0; b < Buffers.Count; b++)
+            {
+                ReadOnlyDataFrameBuffer<T> buffer = Buffers[b];
+                long prevLength = checked(Buffers[0].Length * b);
+                DataFrameBuffer<T> mutableBuffer = DataFrameBuffer<T>.GetMutableBuffer(buffer);
+                Buffers[b] = mutableBuffer;
+                Span<T> span = mutableBuffer.Span;
+                DataFrameBuffer<byte> mutableNullBitMapBuffer = DataFrameBuffer<byte>.GetMutableBuffer(NullBitMapBuffers[b]);
+                NullBitMapBuffers[b] = mutableNullBitMapBuffer;
+                Span<byte> nullBitMapSpan = mutableNullBitMapBuffer.Span;
+
+                ReadOnlyDataFrameBuffer<TResult> resultBuffer = resultContainer.Buffers[b];
+                long resultPrevLength = checked(resultContainer.Buffers[0].Length * b);
+                DataFrameBuffer<TResult> resultMutableBuffer = DataFrameBuffer<TResult>.GetMutableBuffer(resultBuffer);
+                resultContainer.Buffers[b] = resultMutableBuffer;
+                Span<TResult> resultSpan = resultMutableBuffer.Span;
+                DataFrameBuffer<byte> resultMutableNullBitMapBuffer = DataFrameBuffer<byte>.GetMutableBuffer(resultContainer.NullBitMapBuffers[b]);
+                resultContainer.NullBitMapBuffers[b] = resultMutableNullBitMapBuffer;
+                Span<byte> resultNullBitMapSpan = resultMutableNullBitMapBuffer.Span;
+
+                for (int i = 0; i < span.Length; i++)
+                {
+                    long curIndex = i + prevLength;
+                    bool isValid = IsValid(nullBitMapSpan, i);
+                    TResult? value = func(isValid ? span[i] : default(T?));
+                    resultSpan[i] = value.GetValueOrDefault();
+                    SetValidityBit(resultNullBitMapSpan, i, value != null);
+                }
+            }
+        }
+
         // Faster to use when we already have a span since it avoids indexing
         public bool IsValid(ReadOnlySpan<byte> bitMapBufferSpan, int index)
         {

diff --git a/src/Microsoft.Data.Analysis/PrimitiveDataFrameColumn.cs b/src/Microsoft.Data.Analysis/PrimitiveDataFrameColumn.cs
@@ -487,6 +487,19 @@ public override Dictionary<TKey, ICollection<long>> GroupColumnValues<TKey>()
 
         public void ApplyElementwise(Func<T?, long, T?> func) => _columnContainer.ApplyElementwise(func);
 
+        /// <summary>
+        /// Applies a function to all the values
+        /// </summary>
+        /// <typeparam name="TResult">The new column's type</typeparam>
+        /// <param name="func">The function to apply</param>
+        /// <returns>A new PrimitiveDataFrameColumn containing the new values</returns>
+        public PrimitiveDataFrameColumn<TResult> Apply<TResult>(Func<T?, TResult?> func) where TResult : unmanaged
+        {
+            var resultColumn = new PrimitiveDataFrameColumn<TResult>("Result", Length);
+            _columnContainer.Apply(func, resultColumn._columnContainer);
+            return resultColumn;
+        }
+
         /// <summary>
         /// Clips values beyond the specified thresholds
         /// </summary>

diff --git a/tests/Microsoft.Data.Analysis.Tests/DataFrameTests.cs b/tests/Microsoft.Data.Analysis.Tests/DataFrameTests.cs
@@ -1946,6 +1946,7 @@ public void TestMutationOnRows()
                 }
             }
         }
+
         [Fact]
         public void TestAppendRow()
         {
@@ -2027,5 +2028,21 @@ public void TestAppendEmptyValue()
             Assert.Equal(13, df.Rows.Count);
             Assert.Equal(1, df.Columns[2].NullCount);
         }
+
+        [Fact]
+        public void TestApply()
+        {
+            int[] values = { 1, 2, 3, 4, 5 };
+            var col = new PrimitiveDataFrameColumn<int>("Ints", values);
+            PrimitiveDataFrameColumn<double> newCol = col.Apply(i => i + 0.5d);
+
+            Assert.Equal(values.Length, newCol.Length);
+
+            for (int i = 0; i < newCol.Length; i++)
+            {
+                Assert.Equal(col[i], values[i]); // Make sure values didn't change
+                Assert.Equal(newCol[i], values[i] + 0.5d);
+            }
+        }
     }
 }