def run(self):
dprint_func_ir(self.func_ir, "starting IO")
topo_order = find_topo_order(self.func_ir.blocks)
for label in topo_order:
new_body = []
# copies are collected before running the pass since
# variables typed in locals are assigned late
self._get_reverse_copies(self.func_ir.blocks[label].body)
for inst in self.func_ir.blocks[label].body:
if isinstance(inst, ir.Assign):
inst_list = self._run_assign(inst)
new_body.extend(inst_list)
elif isinstance(inst, ir.StaticSetItem):
inst_list = self._run_static_setitem(inst)
new_body.extend(inst_list)
else:
new_body.append(inst)
self.func_ir.blocks[label].body = new_body
# iterative remove dead to make sure all extra code (e.g. df vars) is removed
while remove_dead(self.func_ir.blocks, self.func_ir.arg_names,
self.func_ir):
pass
self.func_ir._definitions = get_definitions(self.func_ir.blocks)
dprint_func_ir(self.func_ir, "after IO")
if debug_prints():
print("h5 files: ", self.h5_files)
print("h5 dsets: ", self.h5_dsets)
def visit_vars_sort(sort_node, callback, cbdata):
if debug_prints(): # pragma: no cover
print("visiting sort vars for:", sort_node)
print("cbdata: ", sorted(cbdata.items()))
sort_node.key_arr = visit_vars_inner(sort_node.key_arr, callback, cbdata)
for col_name in list(sort_node.df_vars.keys()):
sort_node.df_vars[col_name] = visit_vars_inner(
sort_node.df_vars[col_name], callback, cbdata)
def visit_vars_filter(filter_node, callback, cbdata):
if debug_prints(): # pragma: no cover
print("visiting filter vars for:", filter_node)
print("cbdata: ", sorted(cbdata.items()))
filter_node.bool_arr = visit_vars_inner(filter_node.bool_arr, callback,
cbdata)
for col_name in list(filter_node.df_in_vars.keys()):
filter_node.df_in_vars[col_name] = visit_vars_inner(
filter_node.df_in_vars[col_name], callback, cbdata)
for col_name in list(filter_node.df_out_vars.keys()):
filter_node.df_out_vars[col_name] = visit_vars_inner(
filter_node.df_out_vars[col_name], callback, cbdata)
def visit_vars_csv(csv_node, callback, cbdata):
if debug_prints(): # pragma: no cover
print("visiting csv vars for:", csv_node)
print("cbdata: ", sorted(cbdata.items()))
# update output_vars
new_out_vars = []
for col_var in csv_node.out_vars:
new_var = visit_vars_inner(col_var, callback, cbdata)
new_out_vars.append(new_var)
csv_node.out_vars = new_out_vars
csv_node.file_name = visit_vars_inner(csv_node.file_name, callback, cbdata)
return
def visit_vars_join(join_node, callback, cbdata):
if debug_prints(): # pragma: no cover
print("visiting join vars for:", join_node)
print("cbdata: ", sorted(cbdata.items()))
# left
for col_name in list(join_node.left_vars.keys()):
join_node.left_vars[col_name] = visit_vars_inner(
join_node.left_vars[col_name], callback, cbdata)
# right
for col_name in list(join_node.right_vars.keys()):
join_node.right_vars[col_name] = visit_vars_inner(
join_node.right_vars[col_name], callback, cbdata)
# output
for col_name in list(join_node.df_out_vars.keys()):
join_node.df_out_vars[col_name] = visit_vars_inner(
join_node.df_out_vars[col_name], callback, cbdata)
def dprint(*s):
if debug_prints():
print(*s)
from .svc import SVC
from .naive_bayes import MultinomialNB
from hpat.utils import debug_prints
try:
from . import d4p
except ImportError:
if debug_prints(): # pragma: no cover
print("daal4py import error")
def run(self):
blocks = self.func_ir.blocks
topo_order = find_topo_order(blocks)
for label in topo_order:
new_body = []
for inst in blocks[label].body:
if isinstance(inst, ir.Assign):
out_nodes = self._run_assign(inst)
if isinstance(out_nodes, list):
new_body.extend(out_nodes)
if isinstance(out_nodes, dict):
label = include_new_blocks(blocks, out_nodes, label,
new_body)
new_body = []
if isinstance(out_nodes, tuple):
gen_blocks, post_nodes = out_nodes
label = include_new_blocks(blocks, gen_blocks, label,
new_body)
new_body = post_nodes
else:
new_body.append(inst)
blocks[label].body = new_body
if debug_prints(): # pragma: no cover
print("--- types before Series replacement:", self.typemap)
print("calltypes: ", self.calltypes)
replace_series = {}
for vname, typ in self.typemap.items():
if isinstance(typ, SeriesType):
# print("replacing series type", vname)
new_typ = series_to_array_type(typ)
replace_series[vname] = new_typ
# replace array.call() variable types
if isinstance(typ, types.BoundFunction) and isinstance(
typ.this, SeriesType):
this = series_to_array_type(typ.this)
# TODO: handle string arrays, etc.
assert typ.typing_key.startswith('array.')
attr = typ.typing_key[len('array.'):]
resolver = getattr(ArrayAttribute, 'resolve_' + attr)
# methods are either installed with install_array_method or
# using @bound_function in arraydecl.py
if hasattr(resolver, '__wrapped__'):
resolver = bound_function(typ.typing_key)(
resolver.__wrapped__)
new_typ = resolver(ArrayAttribute(self.typingctx), this)
replace_series[vname] = new_typ
for vname, typ in replace_series.items():
self.typemap.pop(vname)
self.typemap[vname] = typ
replace_calltype = {}
# replace sig of getitem/setitem/... series type with array
for call, sig in self.calltypes.items():
if sig is None:
continue
assert isinstance(sig, Signature)
sig.return_type = if_series_to_array_type(sig.return_type)
sig.args = tuple(map(if_series_to_array_type, sig.args))
# XXX: side effect: force update of call signatures
if isinstance(call, ir.Expr) and call.op == 'call':
# StencilFunc requires kws for typing so sig.args can't be used
# reusing sig.args since some types become Const in sig
argtyps = sig.args[:len(call.args)]
kwtyps = {name: self.typemap[v.name] for name, v in call.kws}
new_sig = self.typemap[call.func.name].get_call_type(
self.typingctx, argtyps, kwtyps)
# calltypes of things like BoundFunction (array.call) need to
# be update for lowering to work
# XXX: new_sig could be None for things like np.int32()
if call in self.calltypes and new_sig is not None:
old_sig = self.calltypes[call]
# fix types with undefined dtypes in empty_inferred, etc.
return_type = _fix_typ_undefs(new_sig.return_type,
old_sig.return_type)
args = tuple(
_fix_typ_undefs(a, b)
for a, b in zip(new_sig.args, old_sig.args))
replace_calltype[call] = Signature(return_type, args,
new_sig.recvr,
new_sig.pysig)
for call, sig in replace_calltype.items():
self.calltypes.pop(call)
self.calltypes[call] = sig
if debug_prints(): # pragma: no cover
print("--- types after Series replacement:", self.typemap)
print("calltypes: ", self.calltypes)
self.func_ir._definitions = get_definitions(self.func_ir.blocks)
return if_series_to_unbox(self.return_type)
