fix(aggregate): support mean as synonym avg

CONTRIBUTING.md

@@ -196,18 +196,18 @@ Below is a checklist of what you need to do to add a new scalar function to Data
 Below is a checklist of what you need to do to add a new aggregate function to DataFusion:
 
 - Add the actual implementation of an `Accumulator` and `AggregateExpr`:
-  - [here](datafusion/src/physical_plan/string_expressions.rs) for string functions
-  - [here](datafusion/src/physical_plan/math_expressions.rs) for math functions
-  - [here](datafusion/src/physical_plan/datetime_expressions.rs) for datetime functions
-  - create a new module [here](datafusion/src/physical_plan) for other functions
-- In [src/physical_plan/aggregates](datafusion/src/physical_plan/aggregates.rs), add:
-  - a new variant to `BuiltinAggregateFunction`
+  - [here](datafusion/physical-expr/src/string_expressions.rs) for string functions
+  - [here](datafusion/physical-expr/src/math_expressions.rs) for math functions
+  - [here](datafusion/physical-expr/src/datetime_expressions.rs) for datetime functions
+  - create a new module [here](datafusion/physical-expr/src) for other functions
+- In [datafusion/expr/src](datafusion/expr/src/aggregate_function.rs), add:
+  - a new variant to `AggregateFunction`
   - a new entry to `FromStr` with the name of the function as called by SQL
   - a new line in `return_type` with the expected return type of the function, given an incoming type
   - a new line in `signature` with the signature of the function (number and types of its arguments)
   - a new line in `create_aggregate_expr` mapping the built-in to the implementation
   - tests to the function.
-- In [tests/sql.rs](datafusion/tests/sql.rs), add a new test where the function is called through SQL against well known data and returns the expected result.
+- In [tests/sql](datafusion/core/tests/sql), add a new test where the function is called through SQL against well known data and returns the expected result.
 
 ## How to display plans graphically
 

datafusion/core/tests/sql/aggregates.rs

@@ -1777,6 +1777,41 @@ async fn simple_avg() -> Result<()> {
     Ok(())
 }
 
+#[tokio::test]
+async fn simple_mean() -> Result<()> {
+    let schema = Schema::new(vec![Field::new("a", DataType::Int32, false)]);
+
+    let batch1 = RecordBatch::try_new(
+        Arc::new(schema.clone()),
+        vec![Arc::new(Int32Array::from_slice(&[1, 2, 3]))],
+    )?;
+    let batch2 = RecordBatch::try_new(
+        Arc::new(schema.clone()),
+        vec![Arc::new(Int32Array::from_slice(&[4, 5]))],
+    )?;
+
+    let ctx = SessionContext::new();
+
+    let provider = MemTable::try_new(Arc::new(schema), vec![vec![batch1], vec![batch2]])?;
+    ctx.register_table("t", Arc::new(provider))?;
+
+    let result = plan_and_collect(&ctx, "SELECT MEAN(a) FROM t").await?;
+
+    let batch = &result[0];
+    assert_eq!(1, batch.num_columns());
+    assert_eq!(1, batch.num_rows());
+
+    let values = batch
+        .column(0)
+        .as_any()
+        .downcast_ref::<Float64Array>()
+        .expect("failed to cast version");
+    assert_eq!(values.len(), 1);
+    // mean(1,2,3,4,5) = 3.0
+    assert_eq!(values.value(0), 3.0_f64);
+    Ok(())
+}
+
 #[tokio::test]
 async fn query_sum_distinct() -> Result<()> {
     let schema = Arc::new(Schema::new(vec![

datafusion/expr/src/aggregate_function.rs

@@ -105,6 +105,7 @@ impl FromStr for AggregateFunction {
             "max" => AggregateFunction::Max,
             "count" => AggregateFunction::Count,
             "avg" => AggregateFunction::Avg,
+            "mean" => AggregateFunction::Avg,
             "sum" => AggregateFunction::Sum,
             "approx_distinct" => AggregateFunction::ApproxDistinct,
             "array_agg" => AggregateFunction::ArrayAgg,