Add support for fractional weights in approx_percentile

presto-docs/src/main/sphinx/functions/aggregate.rst

@@ -182,29 +182,29 @@ Approximate Aggregate Functions
 .. function:: approx_percentile(x, w, percentage) -> [same as x]
 
     Returns the approximate weighed percentile for all input values of ``x``
-    using the per-item weight ``w`` at the percentage ``p``. The weight must be
-    an integer value of at least one. It is effectively a replication count for
-    the value ``x`` in the percentile set. The value of ``p`` must be between
-    zero and one and must be constant for all input rows.
+    using the per-item weight ``w`` at the percentage ``p``. Weights must be
+    strictly positive. Integer-value weights can be thought of as a replication
+    count for the value ``x`` in the percentile set. The value of ``p`` must be
+    between zero and one and must be constant for all input rows.
 
 .. function:: approx_percentile(x, w, percentage, accuracy) -> [same as x]
 
     Returns the approximate weighed percentile for all input values of ``x``
     using the per-item weight ``w`` at the percentage ``p``, with a maximum rank
-    error of ``accuracy``. The weight must be an integer value of at least one.
-    It is effectively a replication count for the value ``x`` in the percentile
-    set. The value of ``p`` must be between zero and one and must be constant
-    for all input rows. ``accuracy`` must be a value greater than zero and less
-    than one, and it must be constant for all input rows.
+    error of ``accuracy``. Weights must be strictly positive. Integer-value
+    weights can be thought of as a replication count for the value ``x`` in the
+    percentile set. The value of ``p`` must be between zero and one and must be
+    constant for all input rows. ``accuracy`` must be a value greater than zero
+    and less than one, and it must be constant for all input rows.
 
 .. function:: approx_percentile(x, w, percentages) -> array<[same as x]>
 
     Returns the approximate weighed percentile for all input values of ``x``
     using the per-item weight ``w`` at each of the given percentages specified
-    in the array. The weight must be an integer value of at least one. It is
-    effectively a replication count for the value ``x`` in the percentile set.
-    Each element of the array must be between zero and one, and the array must
-    be constant for all input rows.
+    in the array. Weights must be strictly positive. Integer-value weights can
+    be thought of as a replication count for the value ``x`` in the percentile
+    set. Each element of the array must be between zero and one, and the array
+    must be constant for all input rows.
 
 .. function:: approx_set(x) -> HyperLogLog
     :noindex:

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateDoublePercentileAggregations.java

@@ -43,13 +43,13 @@ public static void input(@AggregationState DigestAndPercentileState state, @SqlT
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile)
     {
         ApproximateLongPercentileAggregations.weightedInput(state, doubleToSortableLong(value), weight, percentile);
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
     {
         ApproximateLongPercentileAggregations.weightedInput(state, doubleToSortableLong(value), weight, percentile, accuracy);
     }

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateDoublePercentileArrayAggregations.java

@@ -43,7 +43,7 @@ public static void input(@AggregationState DigestAndPercentileArrayState state,
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType("array(double)") Block percentilesArrayBlock)
+    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.DOUBLE) double value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType("array(double)") Block percentilesArrayBlock)
     {
         ApproximateLongPercentileArrayAggregations.weightedInput(state, doubleToSortableLong(value), weight, percentilesArrayBlock);
     }

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateLongPercentileAggregations.java

@@ -54,7 +54,7 @@ public static void input(@AggregationState DigestAndPercentileState state, @SqlT
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile)
     {
         checkWeight(weight);
 
@@ -75,7 +75,7 @@ public static void weightedInput(@AggregationState DigestAndPercentileState stat
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
     {
         checkWeight(weight);
 
@@ -133,7 +133,7 @@ public static void output(@AggregationState DigestAndPercentileState state, Bloc
         }
     }
 
-    private static void checkWeight(long weight)
+    private static void checkWeight(double weight)
     {
         checkCondition(weight > 0, INVALID_FUNCTION_ARGUMENT, "percentile weight must be > 0");
     }

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateLongPercentileArrayAggregations.java

@@ -51,7 +51,7 @@ public static void input(@AggregationState DigestAndPercentileArrayState state,
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType("array(double)") Block percentilesArrayBlock)
+    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.BIGINT) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType("array(double)") Block percentilesArrayBlock)
     {
         initializePercentilesArray(state, percentilesArrayBlock);
         initializeDigest(state);

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateRealPercentileAggregations.java

@@ -45,13 +45,13 @@ public static void input(@AggregationState DigestAndPercentileState state, @SqlT
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile)
     {
         ApproximateLongPercentileAggregations.weightedInput(state, floatToSortableInt(intBitsToFloat((int) value)), weight, percentile);
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
+    public static void weightedInput(@AggregationState DigestAndPercentileState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType(StandardTypes.DOUBLE) double percentile, @SqlType(StandardTypes.DOUBLE) double accuracy)
     {
         ApproximateLongPercentileAggregations.weightedInput(state, floatToSortableInt(intBitsToFloat((int) value)), weight, percentile, accuracy);
     }

presto-main/src/main/java/io/prestosql/operator/aggregation/ApproximateRealPercentileArrayAggregations.java

@@ -45,7 +45,7 @@ public static void input(@AggregationState DigestAndPercentileArrayState state,
     }
 
     @InputFunction
-    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.BIGINT) long weight, @SqlType("array(double)") Block percentilesArrayBlock)
+    public static void weightedInput(@AggregationState DigestAndPercentileArrayState state, @SqlType(StandardTypes.REAL) long value, @SqlType(StandardTypes.DOUBLE) double weight, @SqlType("array(double)") Block percentilesArrayBlock)
     {
         ApproximateLongPercentileArrayAggregations.weightedInput(state, floatToSortableInt(intBitsToFloat((int) value)), weight, percentilesArrayBlock);
     }

presto-main/src/test/java/io/prestosql/block/BlockAssertions.java

@@ -405,6 +405,15 @@ public static Block createLongRepeatBlock(int value, int length)
         return builder.build();
     }
 
+    public static Block createDoubleRepeatBlock(double value, int length)
+    {
+        BlockBuilder builder = DOUBLE.createFixedSizeBlockBuilder(length);
+        for (int i = 0; i < length; i++) {
+            DOUBLE.writeDouble(builder, value);
+        }
+        return builder.build();
+    }
+
     public static Block createTimestampsWithTimezoneBlock(Long... values)
     {
         BlockBuilder builder = TIMESTAMP_WITH_TIME_ZONE.createFixedSizeBlockBuilder(values.length);