def execute_with_scope(expr, scope, aggcontext=None, clients=None, **kwargs):
"""Execute an expression `expr`, with data provided in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
The expression to execute.
scope : collections.Mapping
A dictionary mapping :class:`~ibis.expr.operations.Node` subclass
instances to concrete data such as a pandas DataFrame.
aggcontext : Optional[ibis.pandas.aggcontext.AggregationContext]
Returns
-------
result : scalar, pd.Series, pd.DataFrame
"""
op = expr.op()
# Call pre_execute, to allow clients to intercept the expression before
# computing anything *and* before associating leaf nodes with data. This
# allows clients to provide their own data for each leaf.
if clients is None:
clients = list(find_backends(expr))
if aggcontext is None:
aggcontext = agg_ctx.Summarize()
pre_executed_scope = pre_execute(op,
*clients,
scope=scope,
aggcontext=aggcontext,
**kwargs)
new_scope = toolz.merge(scope, pre_executed_scope)
result = execute_until_in_scope(
expr,
new_scope,
aggcontext=aggcontext,
clients=clients,
# XXX: we *explicitly* pass in scope and not new_scope here so that
# post_execute sees the scope of execute_with_scope, not the scope of
# execute_until_in_scope
post_execute_=functools.partial(
post_execute,
scope=scope,
aggcontext=aggcontext,
clients=clients,
**kwargs,
),
**kwargs,
)
return result
def execute_with_scope(expr, scope, aggcontext=None, clients=None, **kwargs):
"""Execute an expression `expr`, with data provided in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
The expression to execute.
scope : collections.Mapping
A dictionary mapping :class:`~ibis.expr.operations.Node` subclass
instances to concrete data such as a pandas DataFrame.
aggcontext : Optional[ibis.pandas.aggcontext.AggregationContext]
Returns
-------
result : scalar, pd.Series, pd.DataFrame
"""
op = expr.op()
# Call pre_execute, to allow clients to intercept the expression before
# computing anything *and* before associating leaf nodes with data. This
# allows clients to provide their own data for each leaf.
if clients is None:
clients = list(find_backends(expr))
if aggcontext is None:
aggcontext = agg_ctx.Summarize()
pre_executed_scope = pre_execute(
op, *clients, scope=scope, aggcontext=aggcontext, **kwargs
)
new_scope = toolz.merge(scope, pre_executed_scope)
result = execute_until_in_scope(
expr,
new_scope,
aggcontext=aggcontext,
clients=clients,
# XXX: we *explicitly* pass in scope and not new_scope here so that
# post_execute sees the scope of execute_with_scope, not the scope of
# execute_until_in_scope
post_execute_=functools.partial(
post_execute,
scope=scope,
aggcontext=aggcontext,
clients=clients,
**kwargs,
),
**kwargs,
)
return result
def execute_until_in_scope(expr,
scope,
aggcontext=None,
clients=None,
post_execute_=None,
**kwargs):
"""Execute until our op is in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
scope : Mapping
aggcontext : Optional[AggregationContext]
clients : List[ibis.client.Client]
kwargs : Mapping
"""
# these should never be None
assert aggcontext is not None, 'aggcontext is None'
assert clients is not None, 'clients is None'
assert post_execute_ is not None, 'post_execute_ is None'
# base case: our op has been computed (or is a leaf data node), so
# return the corresponding value
op = expr.op()
if op in scope:
return scope[op]
new_scope = execute_bottom_up(
expr,
scope,
aggcontext=aggcontext,
post_execute_=post_execute_,
clients=clients,
**kwargs,
)
new_scope = toolz.merge(new_scope,
pre_execute(op, *clients, scope=scope, **kwargs))
return execute_until_in_scope(
expr,
new_scope,
aggcontext=aggcontext,
clients=clients,
post_execute_=post_execute_,
**kwargs,
)
def execute_until_in_scope(
expr, scope, aggcontext=None, clients=None, post_execute_=None, **kwargs
):
"""Execute until our op is in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
scope : Mapping
aggcontext : Optional[AggregationContext]
clients : List[ibis.client.Client]
kwargs : Mapping
"""
# these should never be None
assert aggcontext is not None, 'aggcontext is None'
assert clients is not None, 'clients is None'
assert post_execute_ is not None, 'post_execute_ is None'
# base case: our op has been computed (or is a leaf data node), so
# return the corresponding value
op = expr.op()
if op in scope:
return scope[op]
new_scope = execute_bottom_up(
expr,
scope,
aggcontext=aggcontext,
post_execute_=post_execute_,
clients=clients,
**kwargs,
)
new_scope = toolz.merge(
new_scope, pre_execute(op, *clients, scope=scope, **kwargs)
)
return execute_until_in_scope(
expr,
new_scope,
aggcontext=aggcontext,
clients=clients,
post_execute_=post_execute_,
**kwargs,
)
def execute_window_op(op,
data,
window,
scope=None,
aggcontext=None,
clients=None,
**kwargs):
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()
pre_executed_scope = pre_execute(operand_op,
*clients,
scope=scope,
aggcontext=aggcontext,
**kwargs)
scope = toolz.merge(scope, pre_executed_scope)
(root, ) = op.root_tables()
root_expr = root.to_expr()
data = execute(
root_expr,
scope=scope,
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, 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 = ()
if group_by:
if order_by:
(
sorted_df,
grouping_keys,
ordering_keys,
) = util.compute_sorted_frame(data,
order_by,
group_by=group_by,
**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, **kwargs)
post_process = _post_process_order_by
else:
source = data
post_process = _post_process_empty
new_scope = toolz.merge(
scope,
OrderedDict((t, source) for t in operand.op().root_tables()),
factory=OrderedDict,
)
# figure out what the dtype of the operand is
operand_type = operand.type()
operand_dtype = operand_type.to_pandas()
aggcontext = get_aggcontext(
window,
operand=operand,
operand_dtype=operand_dtype,
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
)
result = execute(
operand,
scope=new_scope,
aggcontext=aggcontext,
clients=clients,
**kwargs,
)
series = post_process(result, data, ordering_keys, grouping_keys)
assert len(data) == len(
series
), 'input data source and computed column do not have the same length'
return series
def execute_window_op(op,
data,
window,
scope=None,
aggcontext=None,
clients=None,
**kwargs):
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()
pre_executed_scope = pre_execute(operand_op,
*clients,
scope=scope,
aggcontext=aggcontext,
**kwargs)
scope = toolz.merge(scope, pre_executed_scope)
root, = op.root_tables()
root_expr = root.to_expr()
data = execute(
root_expr,
scope=scope,
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, 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 = ()
if group_by:
if order_by:
(
sorted_df,
grouping_keys,
ordering_keys,
) = util.compute_sorted_frame(data,
order_by,
group_by=group_by,
**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, **kwargs)
post_process = _post_process_order_by
else:
source = data
post_process = _post_process_empty
new_scope = toolz.merge(
scope,
OrderedDict((t, source) for t in operand.op().root_tables()),
factory=OrderedDict,
)
# figure out what the dtype of the operand is
operand_type = operand.type()
operand_dtype = operand_type.to_pandas()
# no order by or group by: default summarization aggcontext
#
# if we're reducing and we have an order by expression then we need to
# expand or roll.
#
# otherwise we're transforming
if not grouping_keys and not ordering_keys:
aggcontext = agg_ctx.Summarize()
elif (isinstance(operand.op(),
(ops.Reduction, ops.CumulativeOp, ops.Any, ops.All))
and ordering_keys):
# XXX(phillipc): What a horror show
preceding = window.preceding
if preceding is not None:
max_lookback = window.max_lookback
assert not isinstance(operand.op(), ops.CumulativeOp)
aggcontext = agg_ctx.Moving(
preceding,
max_lookback,
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
else:
# expanding window
aggcontext = agg_ctx.Cumulative(
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
else:
# groupby transform (window with a partition by clause in SQL parlance)
aggcontext = agg_ctx.Transform(
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
result = execute(
operand,
scope=new_scope,
aggcontext=aggcontext,
clients=clients,
**kwargs,
)
series = post_process(result, data, ordering_keys, grouping_keys)
assert len(data) == len(
series
), 'input data source and computed column do not have the same length'
return series
def execute_until_in_scope(expr,
scope,
aggcontext=None,
clients=None,
post_execute_=None,
**kwargs):
"""Execute until our op is in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
scope : Mapping
aggcontext : Optional[AggregationContext]
clients : List[ibis.client.Client]
kwargs : Mapping
"""
# these should never be None
assert aggcontext is not None, 'aggcontext is None'
assert clients is not None, 'clients is None'
assert post_execute_ is not None, 'post_execute_ is None'
# base case: our op has been computed (or is a leaf data node), so
# return the corresponding value
op = expr.op()
if op in scope:
return scope
elif isinstance(op, ops.Literal):
# special case literals to avoid the overhead of dispatching
# execute_node
return {
op:
execute_literal(op,
op.value,
expr.type(),
aggcontext=aggcontext,
**kwargs)
}
pre_executed_scope = pre_execute(op,
*clients,
scope=scope,
aggcontext=aggcontext,
**kwargs)
new_scope = toolz.merge(scope, pre_executed_scope)
# Short circuit: if pre_execute puts op in scope, then we don't need to
# execute its computable_args
if op in new_scope:
return new_scope
# figure out what arguments we're able to compute on based on the
# expressions inputs. things like expressions, None, and scalar types are
# computable whereas ``list``s are not
computable_args = [arg for arg in op.inputs if is_computable_input(arg)]
# recursively compute each node's arguments until we've changed type
scopes = [
execute_until_in_scope(
arg,
new_scope,
aggcontext=aggcontext,
post_execute_=post_execute_,
clients=clients,
**kwargs,
) if hasattr(arg, 'op') else {
arg: arg
} for arg in computable_args
]
# if we're unable to find data then raise an exception
if not scopes and computable_args:
raise com.UnboundExpressionError(
'Unable to find data for expression:\n{}'.format(repr(expr)))
# there should be exactly one dictionary per computable argument
assert len(computable_args) == len(scopes)
new_scope = toolz.merge(new_scope, *scopes)
# pass our computed arguments to this node's execute_node implementation
data = [
new_scope[arg.op()] if hasattr(arg, 'op') else arg
for arg in computable_args
]
result = execute_node(
op,
*data,
scope=scope,
aggcontext=aggcontext,
clients=clients,
**kwargs,
)
computed = post_execute_(op, result)
return {op: computed}
def main_execute(expr: ir.Expr,
scope: Optional[Mapping] = None,
aggcontext: Optional[agg_ctx.AggregationContext] = None,
clients: Sequence[ibis.client.Client] = (),
params: Optional[Mapping] = None,
**kwargs: Any):
"""Execute an ibis expression against the pandas backend.
Parameters
----------
expr
scope
aggcontext
clients
params
"""
toposorted, dependencies = toposort(expr)
params = toolz.keymap(get_node, params if params is not None else {})
# Add to scope the objects that have no dependencies and are not ibis
# nodes. We have to filter out nodes for cases--such as zero argument
# UDFs--that do not have any dependencies yet still need to be evaluated.
full_scope = toolz.merge(
scope if scope is not None else {},
{
key: key
for key, parents in dependencies.items()
if not parents and not isinstance(key, ops.Node)
},
params,
)
if not clients:
clients = list(find_backends(expr))
if aggcontext is None:
aggcontext = agg_ctx.Summarize()
# give backends a chance to inject scope if needed
execute_first_scope = execute_first(expr.op(),
*clients,
scope=full_scope,
aggcontext=aggcontext,
**kwargs)
full_scope = toolz.merge(full_scope, execute_first_scope)
nodes = [node for node in toposorted if node not in full_scope]
# compute the nodes that are not currently in scope
for node in nodes:
# allow clients to pre compute nodes as they like
pre_executed_scope = pre_execute(node,
*clients,
scope=full_scope,
aggcontext=aggcontext,
**kwargs)
# merge the existing scope with whatever was returned from pre_execute
execute_scope = toolz.merge(full_scope, pre_executed_scope)
# if after pre_execute our node is in scope, then there's nothing to do
# in this iteration
if node in execute_scope:
full_scope = execute_scope
else:
# If we're evaluating a literal then we can be a bit quicker about
# evaluating the dispatch graph
if isinstance(node, ops.Literal):
executor = execute_literal
else:
executor = execute_node
# Gather the inputs we've already computed that the current node
# depends on
execute_args = [
full_scope[get_node(arg)] for arg in dependencies[node]
]
# execute the node with its inputs
execute_node_result = executor(
node,
*execute_args,
aggcontext=aggcontext,
scope=execute_scope,
clients=clients,
**kwargs,
)
# last change to perform any additional computation on the result
# before it gets added to scope for the next node
full_scope[node] = post_execute(
node,
execute_node_result,
clients=clients,
aggcontext=aggcontext,
scope=full_scope,
)
# the last node in the toposorted graph is the root and maps to the desired
# result in scope
last_node = toposorted[-1]
result = full_scope[last_node]
return result
def execute_window_op(
op, data, window, scope=None, aggcontext=None, clients=None, **kwargs
):
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()
pre_executed_scope = pre_execute(
operand_op, *clients, scope=scope, aggcontext=aggcontext, **kwargs
)
scope = toolz.merge(scope, pre_executed_scope)
root, = op.root_tables()
root_expr = root.to_expr()
data = execute(root_expr, scope=scope, 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, 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 = ()
if group_by:
if order_by:
(
sorted_df,
grouping_keys,
ordering_keys,
) = util.compute_sorted_frame(
data, order_by, group_by=group_by, **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, **kwargs
)
post_process = _post_process_order_by
else:
source = data
post_process = _post_process_empty
new_scope = toolz.merge(
scope,
OrderedDict((t, source) for t in operand.op().root_tables()),
factory=OrderedDict,
)
# figure out what the dtype of the operand is
operand_type = operand.type()
if isinstance(operand_type, dt.Integer) and operand_type.nullable:
operand_dtype = np.float64
else:
operand_dtype = operand.type().to_pandas()
# no order by or group by: default summarization aggcontext
#
# if we're reducing and we have an order by expression then we need to
# expand or roll.
#
# otherwise we're transforming
if not grouping_keys and not ordering_keys:
aggcontext = agg_ctx.Summarize()
elif isinstance(operand.op(), ops.Reduction) and ordering_keys:
# XXX(phillipc): What a horror show
preceding = window.preceding
if preceding is not None:
aggcontext = agg_ctx.Moving(
preceding,
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
else:
# expanding window
aggcontext = agg_ctx.Cumulative(
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
else:
# groupby transform (window with a partition by clause in SQL parlance)
aggcontext = agg_ctx.Transform(
parent=source,
group_by=grouping_keys,
order_by=ordering_keys,
dtype=operand_dtype,
)
result = execute(operand, scope=new_scope, aggcontext=aggcontext, **kwargs)
series = post_process(result, data, ordering_keys, grouping_keys)
assert len(data) == len(
series
), 'input data source and computed column do not have the same length'
return series
def execute_window_op(
op,
data,
window,
scope: Scope = None,
timecontext: Optional[TimeContext] = None,
aggcontext=None,
clients=None,
**kwargs,
):
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)
# timecontext is the original time context required by parent node
# of this WindowOp, 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,
)
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 = []
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,
)
# figure out what the dtype of the operand is
operand_type = operand.type()
operand_dtype = operand_type.to_pandas()
aggcontext = get_aggcontext(
window,
scope=scope,
operand=operand,
operand_dtype=operand_dtype,
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,
)
series = post_process(result, data, ordering_keys, grouping_keys)
assert len(data) == len(
series
), 'input data source and computed column do not have the same length'
# trim data to original time context
series = trim_with_timecontext(series, timecontext)
return series
def execute_until_in_scope(
expr,
scope: Scope,
timecontext: Optional[TimeContext] = None,
aggcontext=None,
clients=None,
post_execute_=None,
**kwargs,
) -> Scope:
"""Execute until our op is in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
scope : Scope
timecontext : Optional[TimeContext]
aggcontext : Optional[AggregationContext]
clients : List[ibis.client.Client]
kwargs : Mapping
"""
# these should never be None
assert aggcontext is not None, 'aggcontext is None'
assert clients is not None, 'clients is None'
assert post_execute_ is not None, 'post_execute_ is None'
# base case: our op has been computed (or is a leaf data node), so
# return the corresponding value
op = expr.op()
if scope.get_value(op, timecontext) is not None:
return scope
if isinstance(op, ops.Literal):
# special case literals to avoid the overhead of dispatching
# execute_node
return Scope(
{
op:
execute_literal(
op, op.value, expr.type(), aggcontext=aggcontext, **kwargs)
},
timecontext,
)
# figure out what arguments we're able to compute on based on the
# expressions inputs. things like expressions, None, and scalar types are
# computable whereas ``list``s are not
computable_args = [arg for arg in op.inputs if is_computable_input(arg)]
# pre_executed_states is a list of states with same the length of
# computable_args, these states are passed to each arg
if timecontext:
arg_timecontexts = compute_time_context(
op,
num_args=len(computable_args),
timecontext=timecontext,
clients=clients,
)
else:
arg_timecontexts = [None] * len(computable_args)
pre_executed_scope = pre_execute(
op,
*clients,
scope=scope,
timecontext=timecontext,
aggcontext=aggcontext,
**kwargs,
)
new_scope = scope.merge_scope(pre_executed_scope)
# Short circuit: if pre_execute puts op in scope, then we don't need to
# execute its computable_args
if new_scope.get_value(op, timecontext) is not None:
return new_scope
# recursively compute each node's arguments until we've changed type.
# compute_time_context should return with a list with the same length
# as computable_args, the two lists will be zipping together for
# further execution
if len(arg_timecontexts) != len(computable_args):
raise com.IbisError(
'arg_timecontexts differ with computable_arg in length '
f'for type:\n{type(op).__name__}.')
scopes = [
execute_until_in_scope(
arg,
new_scope,
timecontext=timecontext,
aggcontext=aggcontext,
post_execute_=post_execute_,
clients=clients,
**kwargs,
) if hasattr(arg, 'op') else Scope({arg: arg}, timecontext)
for (arg, timecontext) in zip(computable_args, arg_timecontexts)
]
# if we're unable to find data then raise an exception
if not scopes and computable_args:
raise com.UnboundExpressionError(
'Unable to find data for expression:\n{}'.format(repr(expr)))
# there should be exactly one dictionary per computable argument
assert len(computable_args) == len(scopes)
new_scope = new_scope.merge_scopes(scopes)
# pass our computed arguments to this node's execute_node implementation
data = [
new_scope.get_value(arg.op(), timecontext)
if hasattr(arg, 'op') else arg for arg in computable_args
]
result = execute_node(
op,
*data,
scope=scope,
timecontext=timecontext,
aggcontext=aggcontext,
clients=clients,
**kwargs,
)
computed = post_execute_(op, result, timecontext=timecontext)
return Scope({op: computed}, timecontext)
def execute_with_scope(
expr,
scope: Scope,
timecontext: Optional[TimeContext] = None,
aggcontext=None,
clients=None,
**kwargs,
):
"""Execute an expression `expr`, with data provided in `scope`.
Parameters
----------
expr : ibis.expr.types.Expr
The expression to execute.
scope : Scope
A Scope class, with dictionary mapping
:class:`~ibis.expr.operations.Node` subclass instances to concrete
data such as a pandas DataFrame.
timecontext : Optional[TimeContext]
A tuple of (begin, end) that is passed from parent Node to children
see [timecontext.py](ibis/pandas/execution/timecontext.py) for
detailed usage for this time context.
aggcontext : Optional[ibis.pandas.aggcontext.AggregationContext]
Returns
-------
result : scalar, pd.Series, pd.DataFrame
"""
op = expr.op()
# Call pre_execute, to allow clients to intercept the expression before
# computing anything *and* before associating leaf nodes with data. This
# allows clients to provide their own data for each leaf.
if clients is None:
clients = list(find_backends(expr))
if aggcontext is None:
aggcontext = agg_ctx.Summarize()
pre_executed_scope = pre_execute(
op,
*clients,
scope=scope,
timecontext=timecontext,
aggcontext=aggcontext,
**kwargs,
)
new_scope = scope.merge_scope(pre_executed_scope)
result = execute_until_in_scope(
expr,
new_scope,
timecontext=timecontext,
aggcontext=aggcontext,
clients=clients,
# XXX: we *explicitly* pass in scope and not new_scope here so that
# post_execute sees the scope of execute_with_scope, not the scope of
# execute_until_in_scope
post_execute_=functools.partial(
post_execute,
scope=scope,
timecontext=timecontext,
aggcontext=aggcontext,
clients=clients,
**kwargs,
),
**kwargs,
).get_value(op, timecontext)
return result
