Esempio n. 1
0
    def table_irs(self):
        b = ir.TrueIR()
        table_read = ir.TableRead(
            'src/test/resources/backward_compatability/1.0.0/table/0.ht',
            False, None)
        table_read_row_type = hl.dtype(
            'struct{idx: int32, f32: float32, i64: int64, m: float64, astruct: struct{a: int32, b: float64}, mstruct: struct{x: int32, y: str}, aset: set<str>, mset: set<float64>, d: dict<array<str>, float64>, md: dict<int32, str>, h38: locus<GRCh38>, ml: locus<GRCh37>, i: interval<locus<GRCh37>>, c: call, mc: call, t: tuple(call, str, str), mt: tuple(locus<GRCh37>, bool)}'
        )

        matrix_read = ir.MatrixRead(
            'src/test/resources/backward_compatability/1.0.0/matrix_table/0.hmt',
            False, False)

        range = ir.TableRange(10, 4)
        table_irs = [
            ir.TableUnkey(table_read),
            ir.TableKeyBy(table_read, ['m', 'd'], 1, True),
            ir.TableFilter(table_read, b), table_read,
            ir.MatrixColsTable(matrix_read),
            ir.TableAggregateByKey(table_read,
                                   ir.MakeStruct([('a', ir.I32(5))])),
            ir.TableKeyByAndAggregate(table_read,
                                      ir.MakeStruct([('a', ir.I32(5))]),
                                      ir.MakeStruct([('b', ir.I32(5))]), 1, 2),
            ir.TableJoin(table_read, ir.TableRange(100, 10), 'inner'),
            ir.MatrixEntriesTable(matrix_read),
            ir.MatrixRowsTable(matrix_read),
            ir.TableParallelize(
                'Table{global:Struct{},key:None,row:Struct{a:Int32}}',
                ir.Value(hl.tarray(hl.tstruct(a=hl.tint32)), [{
                    'a': None
                }, {
                    'a': 5
                }, {
                    'a': -3
                }]), None),
            ir.TableMapRows(
                table_read,
                ir.MakeStruct([('a',
                                ir.GetField(ir.Ref('row', table_read_row_type),
                                            'f32')), ('b', ir.F64(-2.11))]),
                None, None),
            ir.TableMapGlobals(
                table_read,
                ir.MakeStruct([('foo', ir.NA(hl.tarray(hl.tint32)))]),
                ir.Value(hl.tstruct(), {})),
            ir.TableRange(100, 10),
            ir.TableRepartition(table_read, 10, False),
            ir.TableUnion([ir.TableRange(100, 10),
                           ir.TableRange(50, 10)]),
            ir.TableExplode(table_read, 'mset'),
            ir.TableHead(table_read, 10),
            ir.TableOrderBy(ir.TableUnkey(table_read), [('m', 'A'),
                                                        ('m', 'D')]),
            ir.TableDistinct(table_read),
            ir.LocalizeEntries(matrix_read, '__entries')
        ]

        return table_irs
Esempio n. 2
0
    def test_matrix_ir_parses(self):
        hl.index_bgen(resource('example.8bits.bgen'),
                      reference_genome=hail.get_reference('GRCh37'),
                      contig_recoding={'01': '1'})

        collect_sig = ir.AggSignature('Collect', [], None, [hl.tint32])
        collect = ir.MakeStruct([('x',
                                  ir.ApplyAggOp([ir.I32(0)], [], None,
                                                collect_sig,
                                                hl.tarray(hl.tint32)))])

        matrix_read = ir.MatrixRead(
            resource('backward_compatability/1.0.0/matrix_table/0.hmt'), False,
            False)
        table_read = ir.TableRead(
            resource('backward_compatability/1.0.0/table/0.ht'), False, None)

        matrix_irs = [
            ir.MatrixUnionRows(ir.MatrixRange(5, 5, 1),
                               ir.MatrixRange(5, 5, 1)),
            ir.UnlocalizeEntries(ir.LocalizeEntries(matrix_read, '__entries'),
                                 ir.MatrixColsTable(matrix_read), '__entries'),
            ir.MatrixAggregateRowsByKey(matrix_read, collect, collect),
            ir.MatrixAggregateColsByKey(matrix_read, collect, collect),
            ir.MatrixRange(1, 1, 10),
            ir.MatrixImportVCF([resource('sample.vcf')], False, False,
                               None, None, False, ['GT'],
                               hail.get_reference('GRCh37'), {}, True, False),
            ir.MatrixImportBGEN([resource('example.8bits.bgen')], ['GP'],
                                resource('example.sample'), {}, 10, 1,
                                ['varid'], None),
            ir.MatrixFilterRows(matrix_read, ir.FalseIR()),
            ir.MatrixFilterCols(matrix_read, ir.FalseIR()),
            ir.MatrixFilterEntries(matrix_read, ir.FalseIR()),
            ir.MatrixChooseCols(matrix_read, [1, 0]),
            ir.MatrixMapCols(matrix_read, ir.MakeStruct([('x', ir.I64(20))]),
                             ['x']),
            ir.MatrixKeyRowsBy(matrix_read, ['row_i64'], False),
            ir.MatrixMapRows(ir.MatrixKeyRowsBy(matrix_read, []),
                             ir.MakeStruct([('x', ir.I64(20))])),
            ir.MatrixMapEntries(matrix_read,
                                ir.MakeStruct([('x', ir.I64(20))])),
            ir.MatrixMapGlobals(matrix_read,
                                ir.MakeStruct([('x', ir.I64(20))])),
            ir.TableToMatrixTable(table_read, ['f32', 'i64'], ['m', 'astruct'],
                                  ['aset'], ['mset'], 100),
            ir.MatrixCollectColsByKey(matrix_read),
            ir.MatrixExplodeRows(matrix_read, ['row_aset']),
            ir.MatrixExplodeCols(matrix_read, ['col_aset']),
            ir.MatrixAnnotateRowsTable(matrix_read, table_read, '__foo', None),
            ir.MatrixAnnotateColsTable(matrix_read, table_read, '__foo'),
        ]

        for x in matrix_irs:
            try:
                Env.hail().expr.Parser.parse_matrix_ir(str(x))
            except Exception as e:
                raise ValueError(str(x)) from e