format

Signed-off-by: Haoyang Li <[email protected]>
rapidsai · Jul 2, 2024 · aa6c36b · aa6c36b
1 parent 1f58e98
commit aa6c36b
Show file tree

Hide file tree

Showing 7 changed files with 66 additions and 69 deletions.
diff --git a/cpp/include/cudf/aggregation.hpp b/cpp/include/cudf/aggregation.hpp
@@ -83,44 +83,44 @@ class aggregation {
    * @brief Possible aggregation operations
    */
   enum Kind {
-    SUM,             ///< sum reduction
-    PRODUCT,         ///< product reduction
-    MIN,             ///< min reduction
-    MAX,             ///< max reduction
-    COUNT_VALID,     ///< count number of valid elements
-    COUNT_ALL,       ///< count number of elements
-    ANY,             ///< any reduction
-    ALL,             ///< all reduction
-    SUM_OF_SQUARES,  ///< sum of squares reduction
-    MEAN,            ///< arithmetic mean reduction
-    M2,              ///< sum of squares of differences from the mean
-    VARIANCE,        ///< variance
-    STD,             ///< standard deviation
-    MEDIAN,          ///< median reduction
-    QUANTILE,        ///< compute specified quantile(s)
-    ARGMAX,          ///< Index of max element
-    ARGMIN,          ///< Index of min element
-    NUNIQUE,         ///< count number of unique elements
-    NTH_ELEMENT,     ///< get the nth element
-    ROW_NUMBER,      ///< get row-number of current index (relative to rolling window)
-    EWMA,            ///< get exponential weighted moving average at current index
-    RANK,            ///< get rank of current index
-    COLLECT_LIST,    ///< collect values into a list
-    COLLECT_SET,     ///< collect values into a list without duplicate entries
-    LEAD,            ///< window function, accesses row at specified offset following current row
-    LAG,             ///< window function, accesses row at specified offset preceding current row
-    PTX,             ///< PTX  UDF based reduction
-    CUDA,            ///< CUDA UDF based reduction
-    MERGE_LISTS,     ///< merge multiple lists values into one list
-    MERGE_SETS,      ///< merge multiple lists values into one list then drop duplicate entries
-    MERGE_M2,        ///< merge partial values of M2 aggregation,
-    COVARIANCE,      ///< covariance between two sets of elements
-    CORRELATION,     ///< correlation between two sets of elements
-    TDIGEST,         ///< create a tdigest from a set of input values
-    MERGE_TDIGEST,   ///< create a tdigest by merging multiple tdigests together
-    HISTOGRAM,       ///< compute frequency of each element
-    MERGE_HISTOGRAM, ///< merge partial values of HISTOGRAM aggregation,
-    MIN_BY           ///< min reduction by another column
+    SUM,              ///< sum reduction
+    PRODUCT,          ///< product reduction
+    MIN,              ///< min reduction
+    MAX,              ///< max reduction
+    COUNT_VALID,      ///< count number of valid elements
+    COUNT_ALL,        ///< count number of elements
+    ANY,              ///< any reduction
+    ALL,              ///< all reduction
+    SUM_OF_SQUARES,   ///< sum of squares reduction
+    MEAN,             ///< arithmetic mean reduction
+    M2,               ///< sum of squares of differences from the mean
+    VARIANCE,         ///< variance
+    STD,              ///< standard deviation
+    MEDIAN,           ///< median reduction
+    QUANTILE,         ///< compute specified quantile(s)
+    ARGMAX,           ///< Index of max element
+    ARGMIN,           ///< Index of min element
+    NUNIQUE,          ///< count number of unique elements
+    NTH_ELEMENT,      ///< get the nth element
+    ROW_NUMBER,       ///< get row-number of current index (relative to rolling window)
+    EWMA,             ///< get exponential weighted moving average at current index
+    RANK,             ///< get rank of current index
+    COLLECT_LIST,     ///< collect values into a list
+    COLLECT_SET,      ///< collect values into a list without duplicate entries
+    LEAD,             ///< window function, accesses row at specified offset following current row
+    LAG,              ///< window function, accesses row at specified offset preceding current row
+    PTX,              ///< PTX  UDF based reduction
+    CUDA,             ///< CUDA UDF based reduction
+    MERGE_LISTS,      ///< merge multiple lists values into one list
+    MERGE_SETS,       ///< merge multiple lists values into one list then drop duplicate entries
+    MERGE_M2,         ///< merge partial values of M2 aggregation,
+    COVARIANCE,       ///< covariance between two sets of elements
+    CORRELATION,      ///< correlation between two sets of elements
+    TDIGEST,          ///< create a tdigest from a set of input values
+    MERGE_TDIGEST,    ///< create a tdigest by merging multiple tdigests together
+    HISTOGRAM,        ///< compute frequency of each element
+    MERGE_HISTOGRAM,  ///< merge partial values of HISTOGRAM aggregation,
+    MIN_BY            ///< min reduction by another column
   };
 
   aggregation() = delete;

diff --git a/cpp/include/cudf/detail/aggregation/aggregation.hpp b/cpp/include/cudf/detail/aggregation/aggregation.hpp
@@ -42,7 +42,7 @@ class simple_aggregations_collector {  // Declares the interface for the simple
                                                           class product_aggregation const& agg);
   virtual std::vector<std::unique_ptr<aggregation>> visit(data_type col_type,
                                                           class min_aggregation const& agg);
-  virtual std::vector<std::unique_ptr<aggregation>> visit(data_type col_type, 
+  virtual std::vector<std::unique_ptr<aggregation>> visit(data_type col_type,
                                                           class min_by_aggregation const& agg);
   virtual std::vector<std::unique_ptr<aggregation>> visit(data_type col_type,
                                                           class max_aggregation const& agg);
@@ -238,7 +238,6 @@ class min_by_aggregation final : public groupby_aggregation, public reduce_aggre
   void finalize(aggregation_finalizer& finalizer) const override { finalizer.visit(*this); }
 };
 
-
 /**
  * @brief Derived class for specifying a max aggregation
  */

diff --git a/cpp/src/aggregation/aggregation.cpp b/cpp/src/aggregation/aggregation.cpp
@@ -644,7 +644,7 @@ template std::unique_ptr<rolling_aggregation> make_argmin_aggregation<rolling_ag
 template std::unique_ptr<groupby_aggregation> make_argmin_aggregation<groupby_aggregation>();
 
 /// Factory to create a MIN_BY aggregation
-template <typename Base> 
+template <typename Base>
 std::unique_ptr<Base> make_min_by_aggregation()
 {
   return std::make_unique<detail::min_by_aggregation>();

diff --git a/cpp/src/groupby/sort/aggregate.cpp b/cpp/src/groupby/sort/aggregate.cpp
@@ -203,13 +203,11 @@ void aggregate_result_functor::operator()<aggregation::MIN_BY>(aggregation const
 {
   if (cache.has_result(values, agg)) return;
 
-  cache.add_result(values,
-                  agg,
-                  detail::group_min_by(get_grouped_values(),
-                                       helper.group_labels(stream),
-                                       helper.num_groups(stream),
-                                       stream,
-                                       mr));
+  cache.add_result(
+    values,
+    agg,
+    detail::group_min_by(
+      get_grouped_values(), helper.group_labels(stream), helper.num_groups(stream), stream, mr));
 }
 
 template <>

diff --git a/cpp/src/groupby/sort/group_min_by.cu b/cpp/src/groupby/sort/group_min_by.cu
@@ -34,7 +34,7 @@ std::unique_ptr<column> group_min_by(column_view const& structs_column,
                                      rmm::device_async_resource_ref mr)
 {
   auto structs_view = cudf::structs_column_view{structs_column};
-  auto const orders     = structs_view.get_sliced_child(1);
+  auto const orders = structs_view.get_sliced_child(1);
 
   auto indices = type_dispatcher(orders.type(),
                                  group_reduction_dispatcher<aggregation::ARGMIN>{},
@@ -47,11 +47,11 @@ std::unique_ptr<column> group_min_by(column_view const& structs_column,
   auto indices_view = indices->mutable_view();
 
   auto res = cudf::detail::gather(table_view{{structs_column}},
-                                           indices_view,
-                                           out_of_bounds_policy::NULLIFY,
-                                           cudf::detail::negative_index_policy::NOT_ALLOWED,
-                                           stream,
-                                           mr);
+                                  indices_view,
+                                  out_of_bounds_policy::NULLIFY,
+                                  cudf::detail::negative_index_policy::NOT_ALLOWED,
+                                  stream,
+                                  mr);
 
   return std::move(res->release()[0]);
 }

diff --git a/cpp/tests/groupby/min_by_tests.cpp b/cpp/tests/groupby/min_by_tests.cpp
@@ -38,14 +38,14 @@ TYPED_TEST(groupby_min_by_test, basic)
   if (std::is_same_v<V, bool>) return;
 
   cudf::test::fixed_width_column_wrapper<K> keys{1, 2, 3, 1, 2, 2, 1, 3, 3, 2};
-  cudf::test::fixed_width_column_wrapper<K> values {4, 1, 2, 3, 4, 5, 6, 7, 8, 9};
-  cudf::test::fixed_width_column_wrapper<V> orders {1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
-  cudf::test::structs_column_wrapper vals {values, orders};
+  cudf::test::fixed_width_column_wrapper<K> values{4, 1, 2, 3, 4, 5, 6, 7, 8, 9};
+  cudf::test::fixed_width_column_wrapper<V> orders{1, 2, 3, 4, 5, 6, 7, 8, 9, 10};
+  cudf::test::structs_column_wrapper vals{values, orders};
 
-  cudf::test::fixed_width_column_wrapper<K> expect_keys   {1, 2, 3};
-  cudf::test::fixed_width_column_wrapper<K> expect_values {4, 1, 2};
-  cudf::test::fixed_width_column_wrapper<V> expect_orders {1, 2, 3};
-  cudf::test::structs_column_wrapper expect_vals {expect_values, expect_orders};
+  cudf::test::fixed_width_column_wrapper<K> expect_keys{1, 2, 3};
+  cudf::test::fixed_width_column_wrapper<K> expect_values{4, 1, 2};
+  cudf::test::fixed_width_column_wrapper<V> expect_orders{1, 2, 3};
+  cudf::test::structs_column_wrapper expect_vals{expect_values, expect_orders};
 
   auto agg = cudf::make_min_by_aggregation<cudf::groupby_aggregation>();
   test_single_agg(keys, vals, expect_keys, expect_vals, std::move(agg));
@@ -58,20 +58,20 @@ struct groupby_min_by_string_test : public cudf::test::BaseFixture {};
 
 TEST_F(groupby_min_by_string_test, basic)
 {
-  cudf::test::fixed_width_column_wrapper<K> keys   {1, 2, 3, 1, 2, 2, 1, 3, 3, 2};
-  cudf::test::fixed_width_column_wrapper<K> values {4, 1, 2, 3, 4, 5, 6, 7, 8, 9};
+  cudf::test::fixed_width_column_wrapper<K> keys{1, 2, 3, 1, 2, 2, 1, 3, 3, 2};
+  cudf::test::fixed_width_column_wrapper<K> values{4, 1, 2, 3, 4, 5, 6, 7, 8, 9};
   cudf::test::strings_column_wrapper orders{
     "año", "bit", "₹1", "aaa", "zit", "bat", "aab", "$1", "€1", "wut"};
-  cudf::test::structs_column_wrapper vals {values, orders};
+  cudf::test::structs_column_wrapper vals{values, orders};
 
-  cudf::test::fixed_width_column_wrapper<K> expect_keys   {1, 2, 3};
-  cudf::test::fixed_width_column_wrapper<K> expect_values {3, 5, 7};
+  cudf::test::fixed_width_column_wrapper<K> expect_keys{1, 2, 3};
+  cudf::test::fixed_width_column_wrapper<K> expect_values{3, 5, 7};
   cudf::test::strings_column_wrapper expect_orders{"aaa", "bat", "$1"};
-  cudf::test::structs_column_wrapper expect_vals {expect_values, expect_orders};
+  cudf::test::structs_column_wrapper expect_vals{expect_values, expect_orders};
 
   auto agg = cudf::make_min_by_aggregation<cudf::groupby_aggregation>();
   test_single_agg(keys, vals, expect_keys, expect_vals, std::move(agg));
 
   auto agg2 = cudf::make_min_by_aggregation<cudf::groupby_aggregation>();
   test_single_agg(keys, vals, expect_keys, expect_vals, std::move(agg2), force_use_sort_impl::YES);
-}
+}
diff --git a/java/src/main/java/ai/rapids/cudf/GroupByAggregation.java b/java/src/main/java/ai/rapids/cudf/GroupByAggregation.java
@@ -121,7 +121,7 @@ public static GroupByAggregation min() {
   public static GroupByAggregation minBy() {
     return new GroupByAggregation(Aggregation.minBy());
   }
-  
+
   /**
    * Max Aggregation
    */
-Original file line number
+Diff line change
@@ Expand Up / @@ -121,7 +121,7 @@ public static GroupByAggregation min() { @@
       public static GroupByAggregation minBy() {
         return new GroupByAggregation(Aggregation.minBy());
       }
       /**
        * Max Aggregation
        */
@@ Expand Down @@