def _get_agg_typ(self, grp, args, code):
f_ir = numba.ir_utils.get_ir_of_code(
{
'np': np,
'numba': numba,
'sdc': sdc
}, code)
out_data = []
out_columns = []
# add key columns of not as_index
if not grp.as_index:
for k in grp.keys:
out_columns.append(k)
ind = grp.df_type.columns.index(k)
out_data.append(grp.df_type.data[ind])
# get output type for each selected column
for c in grp.selection:
out_columns.append(c)
ind = grp.df_type.columns.index(c)
data = grp.df_type.data[ind]
_, out_dtype, _ = numba.typed_passes.type_inference_stage(
self.context, f_ir, (data, ), None)
out_arr = _get_series_array_type(out_dtype)
out_data.append(out_arr)
out_res = DataFrameType(tuple(out_data), None, tuple(out_columns))
# XXX output becomes series if single output and explicitly selected
if len(grp.selection
) == 1 and grp.explicit_select and grp.as_index:
out_res = arr_to_series_type(out_data[0])
return signature(out_res, *args)
def generic(self, args, kws):
assert not kws
df, values, index, columns, aggfunc, _pivot_values = args
if not (isinstance(values, types.StringLiteral)
and isinstance(index, types.StringLiteral)
and isinstance(columns, types.StringLiteral)):
raise ValueError(
"pivot_table() only support string constants for"
"'values', 'index' and 'columns' arguments")
values = values.literal_value
index = index.literal_value
columns = columns.literal_value
# get output data type
data = df.data[df.columns.index(values)]
func = get_agg_func(None, aggfunc.literal_value, None)
f_ir = numba.ir_utils.get_ir_of_code(
{
'np': np,
'numba': numba,
'sdc': sdc
}, func.__code__)
_, out_dtype, _ = numba.typed_passes.type_inference_stage(
self.context, f_ir, (data, ), None)
out_arr_typ = _get_series_array_type(out_dtype)
pivot_vals = _pivot_values.meta
n_vals = len(pivot_vals)
out_df = DataFrameType((out_arr_typ, ) * n_vals, None,
tuple(pivot_vals))
return signature(out_df, *args)
def get_hiframes_dtypes(df):
"""get hiframe data types for a pandas dataframe
"""
col_names = df.columns.tolist()
hi_typs = [
_get_series_array_type(_infer_series_dtype(df[cname]))
for cname in col_names
]
return tuple(hi_typs)