github.com/apache/beam/sdks/v2@v2.48.2/go/test/integration/transforms/xlang/dataframe/dataframe.go (about)

     1  // Licensed to the Apache Software Foundation (ASF) under one or more
     2  // contributor license agreements.  See the NOTICE file distributed with
     3  // this work for additional information regarding copyright ownership.
     4  // The ASF licenses this file to You under the Apache License, Version 2.0
     5  // (the "License"); you may not use this file except in compliance with
     6  // the License.  You may obtain a copy of the License at
     7  //
     8  //    http://www.apache.org/licenses/LICENSE-2.0
     9  //
    10  // Unless required by applicable law or agreed to in writing, software
    11  // distributed under the License is distributed on an "AS IS" BASIS,
    12  // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    13  // See the License for the specific language governing permissions and
    14  // limitations under the License.
    15  
    16  package dataframe
    17  
    18  import (
    19  	"reflect"
    20  
    21  	"github.com/apache/beam/sdks/v2/go/pkg/beam"
    22  	"github.com/apache/beam/sdks/v2/go/pkg/beam/testing/passert"
    23  	"github.com/apache/beam/sdks/v2/go/pkg/beam/transforms/xlang/dataframe"
    24  )
    25  
    26  func init() {
    27  	beam.RegisterType(reflect.TypeOf((*TestRow)(nil)).Elem())
    28  }
    29  
    30  type TestRow struct {
    31  	A int64 `beam:"a"`
    32  	B int32 `beam:"b"`
    33  }
    34  
    35  func DataframeTransform(expansionAddr string) *beam.Pipeline {
    36  	row0 := TestRow{A: int64(100), B: int32(1)}
    37  	row1 := TestRow{A: int64(100), B: int32(2)}
    38  	row2 := TestRow{A: int64(100), B: int32(3)}
    39  	row3 := TestRow{A: int64(200), B: int32(4)}
    40  
    41  	p, s := beam.NewPipelineWithRoot()
    42  
    43  	input := beam.Create(s, row0, row1, row3)
    44  	outCol := dataframe.Transform(s, "lambda df: df.groupby('a').sum()", input, reflect.TypeOf((*TestRow)(nil)).Elem(), dataframe.WithExpansionAddr(expansionAddr), dataframe.WithIndexes())
    45  
    46  	passert.Equals(s, outCol, row2, row3)
    47  	return p
    48  }