def compute_projection_scalar_expr(
expr,
parent,
data,
scope: Scope = None,
timecontext: Optional[TimeContext] = None,
**kwargs,
):
name = expr.get_name()
assert name is not None, 'Scalar selection name is None'
op = expr.op()
parent_table_op = parent.table.op()
data_columns = frozenset(data.columns)
if scope is None:
scope = Scope()
scope = scope.merge_scopes(
Scope(
{
t:
map_new_column_names_to_data(
remap_overlapping_column_names(parent_table_op, t,
data_columns),
data,
)
},
timecontext,
) for t in op.root_tables())
scalar = execute(expr, scope=scope, **kwargs)
result = pd.Series([scalar], name=name).repeat(len(data.index))
result.index = data.index
return result
def execute_and_reset(
expr,
params=None,
scope=None,
timecontext: Optional[TimeContext] = None,
aggcontext=None,
**kwargs,
):
"""Execute an expression against data that are bound to it. If no data
are bound, raise an Exception.
Notes
-----
The difference between this function and :func:`~ibis.dask.core.execute`
is that this function resets the index of the result, if the result has
an index.
Parameters
----------
expr : ibis.expr.types.Expr
The expression to execute
params : Mapping[ibis.expr.types.Expr, object]
The data that an unbound parameter in `expr` maps to
scope : Mapping[ibis.expr.operations.Node, object]
Additional scope, mapping ibis operations to data
timecontext : Optional[TimeContext]
timecontext needed for execution
aggcontext : Optional[ibis.dask.aggcontext.AggregationContext]
An object indicating how to compute aggregations. For example,
a rolling mean needs to be computed differently than the mean of a
column.
kwargs : Dict[str, object]
Additional arguments that can potentially be used by individual node
execution
Returns
-------
result : Union[
dask.dataframe.Series,
dask.dataframe.DataFrame,
ibis.dask.core.simple_types
]
Raises
------
ValueError
* If no data are bound to the input expression
"""
result = execute(
expr,
params=params,
scope=scope,
timecontext=timecontext,
aggcontext=aggcontext,
**kwargs,
)
if isinstance(result, dd.DataFrame):
schema = expr.schema()
df = result.reset_index()
return df[schema.names]
elif isinstance(result, dd.Series):
return result.reset_index(drop=True)
return result
def dask_execute_node_expr_list(op, sequence, **kwargs):
if all(type(s) != dd.Series for s in sequence):
execute_node_expr_list(op, sequence, **kwargs)
columns = [e.get_name() for e in op.exprs]
schema = ibis.schema(list(zip(columns, (e.type() for e in op.exprs))))
data = {col: [execute(el, **kwargs)] for col, el in zip(columns, sequence)}
return schema.apply_to(
dd.from_pandas(pd.DataFrame(data, columns=columns), npartitions=1))
def insert(
self, path, key, expr, format='table', data_columns=True, **kwargs
):
path = self.root / path
data = execute(expr)
data.to_hdf(
str(path), key, format=format, data_columns=data_columns, **kwargs
)
def _compute_predicates(
table_op,
predicates,
data,
scope: Scope,
timecontext: Optional[TimeContext],
**kwargs,
):
"""Compute the predicates for a table operation.
Parameters
----------
table_op : TableNode
predicates : List[ir.Column]
data : pd.DataFrame
scope : Scope
timecontext: Optional[TimeContext]
kwargs : dict
Returns
-------
computed_predicate : pd.Series[bool]
Notes
-----
This handles the cases where the predicates are computed columns, in
addition to the simple case of named columns coming directly from the input
table.
"""
for predicate in predicates:
# Map each root table of the predicate to the data so that we compute
# predicates on the result instead of any left or right tables if the
# Selection is on a Join. Project data to only inlude columns from
# the root table.
root_tables = predicate.op().root_tables()
# handle suffixes
data_columns = frozenset(data.columns)
additional_scope = Scope()
for root_table in root_tables:
mapping = remap_overlapping_column_names(table_op, root_table,
data_columns)
new_data = map_new_column_names_to_data(mapping, data)
additional_scope = additional_scope.merge_scope(
Scope({root_table: new_data}, timecontext))
scope = scope.merge_scope(additional_scope)
yield execute(predicate, scope=scope, **kwargs)
def compute_sort_key(key, data, timecontext, scope=None, **kwargs):
by = key.to_expr()
try:
if isinstance(by, str):
return by, None
return by.get_name(), None
except com.ExpressionError:
if scope is None:
scope = Scope()
scope = scope.merge_scopes(
Scope({t: data}, timecontext) for t in by.op().root_tables())
new_column = execute(by, scope=scope, **kwargs)
name = ibis.util.guid()
new_column.name = name
return name, new_column
def compute_projection_column_expr(
expr,
parent,
data,
scope: Scope,
timecontext: Optional[TimeContext],
**kwargs,
):
result_name = expr._safe_name
op = expr.op()
parent_table_op = parent.table.op()
if isinstance(op, ops.TableColumn):
# slightly faster path for simple column selection
name = op.name
assert isinstance(name, str)
if name in data:
return data[name].rename(result_name or name)
if not isinstance(parent_table_op, ops.Join):
raise KeyError(name)
suffix = util.get_join_suffix_for_op(op, parent_table_op)
return data.loc[:, name + suffix].rename(result_name or name)
data_columns = frozenset(data.columns)
scope = scope.merge_scopes(
Scope(
{
t:
map_new_column_names_to_data(
remap_overlapping_column_names(parent_table_op, t,
data_columns),
data,
)
},
timecontext,
) for t in op.root_tables())
result = coerce_to_output(
execute(expr, scope=scope, timecontext=timecontext, **kwargs),
expr,
data.index,
)
return result
def insert(self, path, expr, **kwargs):
path = self.root / path
df = execute(expr)
table = pa.Table.from_pandas(df)
pq.write_table(table, str(path))
def insert(self, path, expr, index=False, **kwargs):
path = self.root / path
data = execute(expr)
data.to_csv(str(path), index=index, **kwargs)
def execute_window_op(
op,
data,
window,
scope: Scope = None,
timecontext: Optional[TimeContext] = None,
aggcontext=None,
clients=None,
**kwargs,
):
if window.how == "range" and any(
not isinstance(ob.type(), (dt.Time, dt.Date, dt.Timestamp))
for ob in window._order_by):
raise NotImplementedError(
"The pandas backend only implements range windows with temporal "
"ordering keys")
operand = op.expr
# pre execute "manually" here because otherwise we wouldn't pickup
# relevant scope changes from the child operand since we're managing
# execution of that by hand
operand_op = operand.op()
adjusted_timecontext = None
if timecontext:
arg_timecontexts = compute_time_context(op,
timecontext=timecontext,
clients=clients,
scope=scope)
# timecontext is the original time context required by parent node
# of this Window, while adjusted_timecontext is the adjusted context
# of this Window, since we are doing a manual execution here, use
# adjusted_timecontext in later execution phases
adjusted_timecontext = arg_timecontexts[0]
pre_executed_scope = pre_execute(
operand_op,
*clients,
scope=scope,
timecontext=adjusted_timecontext,
aggcontext=aggcontext,
**kwargs,
)
if scope is None:
scope = pre_executed_scope
else:
scope = scope.merge_scope(pre_executed_scope)
(root, ) = op.root_tables()
root_expr = root.to_expr()
data = execute(
root_expr,
scope=scope,
timecontext=adjusted_timecontext,
clients=clients,
aggcontext=aggcontext,
**kwargs,
)
following = window.following
order_by = window._order_by
if (order_by and following != 0
and not isinstance(operand_op, ops.ShiftBase)):
raise com.OperationNotDefinedError(
'Window functions affected by following with order_by are not '
'implemented')
group_by = window._group_by
grouping_keys = [
key_op.name if isinstance(key_op, ops.TableColumn) else execute(
key,
scope=scope,
clients=clients,
timecontext=adjusted_timecontext,
aggcontext=aggcontext,
**kwargs,
) for key, key_op in zip(group_by,
map(operator.methodcaller('op'), group_by))
]
order_by = window._order_by
if not order_by:
ordering_keys = []
post_process: Callable[
[Any, pd.DataFrame, List[str], List[str], Optional[TimeContext]],
pd.Series, ]
if group_by:
if order_by:
(
sorted_df,
grouping_keys,
ordering_keys,
) = util.compute_sorted_frame(
data,
order_by,
group_by=group_by,
timecontext=adjusted_timecontext,
**kwargs,
)
source = sorted_df.groupby(grouping_keys, sort=True)
post_process = _post_process_group_by_order_by
else:
source = data.groupby(grouping_keys, sort=False)
post_process = _post_process_group_by
else:
if order_by:
source, grouping_keys, ordering_keys = util.compute_sorted_frame(
data, order_by, timecontext=adjusted_timecontext, **kwargs)
post_process = _post_process_order_by
else:
source = data
post_process = _post_process_empty
# Here groupby object should be add to the corresponding node in scope
# for execution, data will be overwrite to a groupby object, so we
# force an update regardless of time context
new_scope = scope.merge_scopes(
[
Scope({t: source}, adjusted_timecontext)
for t in operand.op().root_tables()
],
overwrite=True,
)
aggcontext = get_aggcontext(
window,
scope=scope,
operand=operand,
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
**kwargs,
)
result = execute(
operand,
scope=new_scope,
timecontext=adjusted_timecontext,
aggcontext=aggcontext,
clients=clients,
**kwargs,
)
result = post_process(
result,
data,
ordering_keys,
grouping_keys,
adjusted_timecontext,
)
assert len(data) == len(
result
), 'input data source and computed column do not have the same length'
# trim data to original time context
result = trim_window_result(result, timecontext)
return result
def execute_node_value_list(op, _, **kwargs):
return [execute(arg, **kwargs) for arg in op.values]
def execute_alias(op, _, **kwargs):
# just compile the underlying argument because the naming is handled
# by the translator for the top level expression
return execute(op.arg, **kwargs)
def execute_aggregation_dataframe(
op,
data,
metrics,
by,
having,
predicates,
sort_keys,
scope=None,
timecontext: Optional[TimeContext] = None,
**kwargs,
):
assert metrics, 'no metrics found during aggregation execution'
if sort_keys:
raise NotImplementedError(
'sorting on aggregations not yet implemented')
if predicates:
predicate = functools.reduce(
operator.and_,
(execute(p, scope=scope, timecontext=timecontext, **kwargs)
for p in predicates),
)
data = data.loc[predicate]
columns: Dict[str, str] = {}
if op.by:
grouping_key_pairs = list(zip(by, map(operator.methodcaller('op'),
by)))
grouping_keys = [
by_op.name if isinstance(by_op, ops.TableColumn) else execute(
by, scope=scope, timecontext=timecontext, **kwargs).rename(
by.get_name()) for by, by_op in grouping_key_pairs
]
columns.update((by_op.name, by.get_name())
for by, by_op in grouping_key_pairs
if hasattr(by_op, 'name'))
source = data.groupby(grouping_keys)
else:
source = data
scope = scope.merge_scope(Scope({op.table.op(): source}, timecontext))
pieces = [
coerce_to_output(
execute(metric, scope=scope, timecontext=timecontext, **kwargs),
metric,
) for metric in metrics
]
result = pd.concat(pieces, axis=1)
# If grouping, need a reset to get the grouping key back as a column
if by:
result = result.reset_index()
result.columns = [columns.get(c, c) for c in result.columns]
if having:
# .having(...) is only accessible on groupby, so this should never
# raise
if not by:
raise ValueError(
'Filtering out aggregation values is not allowed without at '
'least one grouping key')
# TODO(phillipc): Don't recompute identical subexpressions
predicate = functools.reduce(
operator.and_,
(execute(h, scope=scope, timecontext=timecontext, **kwargs)
for h in having),
)
assert len(predicate) == len(
result), 'length of predicate does not match length of DataFrame'
result = result.loc[predicate.values]
return result
def execute_table_array_view(op, _, **kwargs):
return execute(op.table).squeeze()
