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
def table_irs(self):
b = ir.TrueIR()
table_read = ir.TableRead(
ir.TableNativeReader(resource('backward_compatability/1.0.0/table/0.ht'), None, False), False)
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(
ir.MatrixNativeReader(resource('backward_compatability/1.0.0/matrix_table/0.hmt'), None, False),
False, False)
range = ir.TableRange(10, 4)
table_irs = [
ir.TableKeyBy(table_read, ['m', 'd'], False),
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', 1),
ir.MatrixEntriesTable(matrix_read),
ir.MatrixRowsTable(matrix_read),
ir.TableParallelize(ir.MakeStruct([
('rows', ir.Literal(hl.tarray(hl.tstruct(a=hl.tint32)), [{'a':None}, {'a':5}, {'a':-3}])),
('global', ir.MakeStruct([]))]), None),
ir.TableMapRows(
ir.TableKeyBy(table_read, []),
ir.MakeStruct([
('a', ir.GetField(ir.Ref('row'), 'f32')),
('b', ir.F64(-2.11))])),
ir.TableMapGlobals(
table_read,
ir.MakeStruct([
('foo', ir.NA(hl.tarray(hl.tint32)))])),
ir.TableRange(100, 10),
ir.TableRepartition(table_read, 10, ir.RepartitionStrategy.COALESCE),
ir.TableUnion(
[ir.TableRange(100, 10), ir.TableRange(50, 10)]),
ir.TableExplode(table_read, ['mset']),
ir.TableHead(table_read, 10),
ir.TableOrderBy(ir.TableKeyBy(table_read, []), [('m', 'A'), ('m', 'D')]),
ir.TableDistinct(table_read),
ir.CastMatrixToTable(matrix_read, '__entries', '__cols'),
ir.TableRename(table_read, {'idx': 'idx_foo'}, {'global_f32': 'global_foo'}),
ir.TableMultiWayZipJoin([table_read, table_read], '__data', '__globals'),
ir.MatrixToTableApply(matrix_read, {'name': 'LinearRegressionRowsSingle', 'yFields': ['col_m'], 'xField': 'entry_m', 'covFields': [], 'rowBlockSize': 10, 'passThrough': []}),
ir.TableToTableApply(table_read, {'name': 'TableFilterPartitions', 'parts': [0], 'keep': True}),
ir.TableFilterIntervals(table_read, [hl.utils.Interval(hl.utils.Struct(row_idx=0), hl.utils.Struct(row_idx=10))], hl.tstruct(row_idx=hl.tint32), keep=False),
]
return table_irs
def test_matrix_ir_parses(self):
hl.index_bgen(resource('example.8bits.bgen'),
reference_genome=hl.get_reference('GRCh37'),
contig_recoding={'01': '1'})
collect = ir.MakeStruct([('x', ir.ApplyAggOp('Collect', [], None, [ir.I32(0)]))])
matrix_read = ir.MatrixRead(
ir.MatrixNativeReader(resource('backward_compatability/1.0.0/matrix_table/0.hmt')), False, False)
table_read = ir.TableRead(
ir.TableNativeReader(resource('backward_compatability/1.0.0/table/0.ht')), False)
matrix_range = ir.MatrixRead(ir.MatrixRangeReader(1, 1, 10))
matrix_irs = [
ir.MatrixRepartition(matrix_range, 100, ir.RepartitionStrategy.SHUFFLE),
ir.MatrixUnionRows(matrix_range, matrix_range),
ir.MatrixDistinctByRow(matrix_range),
ir.MatrixRowsHead(matrix_read, 5),
ir.CastTableToMatrix(
ir.CastMatrixToTable(matrix_read, '__entries', '__cols'),
'__entries',
'__cols',
[]),
ir.MatrixAggregateRowsByKey(matrix_read, collect, collect),
ir.MatrixAggregateColsByKey(matrix_read, collect, collect),
matrix_read,
matrix_range,
ir.MatrixRead(ir.MatrixVCFReader(resource('sample.vcf'), ['GT'], hl.tfloat64, None, None, None, None,
False, True, False, True, None, None, None)),
ir.MatrixRead(ir.MatrixBGENReader(resource('example.8bits.bgen'), None, {}, 10, 1, 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'),
ir.MatrixAnnotateColsTable(matrix_read, table_read, '__foo'),
ir.MatrixToMatrixApply(matrix_read, {'name': 'MatrixFilterPartitions', 'parts': [0], 'keep': True})
]
for x in matrix_irs:
try:
Env.hail().expr.ir.IRParser.parse_matrix_ir(str(x))
except Exception as e:
raise ValueError(str(x)) from e
