Skip to content

REF: do string itemsize casting earlier #30085

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 5, 2019
Merged

REF: do string itemsize casting earlier #30085

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1477e05
REF: do string itemsize casting earlier
jbrockmendel Dec 5, 2019
f1e8c3c
Merge branch 'master' of https://github.com/pandas-dev/pandas into re…
jbrockmendel Dec 5, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 11 additions & 14 deletions pandas/io/pytables.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2326,7 +2326,7 @@ def set_kind(self):
if self.typ is None:
self.typ = getattr(self.description, self.cname, None)

def set_atom(self, block, itemsize: int, data_converted, use_str: bool):
def set_atom(self, block, data_converted, use_str: bool):
""" create and setup my atom from the block b """

# short-cut certain block types
Expand All @@ -2342,18 +2342,19 @@ def set_atom(self, block, itemsize: int, data_converted, use_str: bool):
self.set_atom_complex(block)

elif use_str:
self.set_atom_string(itemsize, data_converted)
self.set_atom_string(data_converted)
else:
# set as a data block
self.set_atom_data(block)

def get_atom_string(self, shape, itemsize):
return _tables().StringCol(itemsize=itemsize, shape=shape[0])

def set_atom_string(self, itemsize: int, data_converted: np.ndarray):
def set_atom_string(self, data_converted: np.ndarray):
itemsize = data_converted.dtype.itemsize
self.kind = "string"
self.typ = self.get_atom_string(data_converted.shape, itemsize)
self.set_data(data_converted.astype(f"|S{itemsize}", copy=False))
self.set_data(data_converted)

def get_atom_coltype(self, kind=None):
""" return the PyTables column class for this column """
Expand Down Expand Up @@ -3904,7 +3905,7 @@ def get_blk_items(mgr, blocks):
existing_col = None

new_name = name or f"values_block_{i}"
itemsize, data_converted, use_str = _maybe_convert_for_string_atom(
data_converted, use_str = _maybe_convert_for_string_atom(
new_name,
b,
existing_col=existing_col,
Expand All @@ -3916,12 +3917,7 @@ def get_blk_items(mgr, blocks):

col = klass.create_for_block(i=i, name=new_name, version=self.version)
col.values = list(b_items)
col.set_atom(
block=b,
itemsize=itemsize,
data_converted=data_converted,
use_str=use_str,
)
col.set_atom(block=b, data_converted=data_converted, use_str=use_str)
col.update_info(self.info)
col.set_pos(j)

Expand Down Expand Up @@ -4793,7 +4789,7 @@ def _maybe_convert_for_string_atom(
use_str = False

if not block.is_object:
return block.dtype.itemsize, block.values, use_str
return block.values, use_str

dtype_name = block.dtype.name
inferred_type = lib.infer_dtype(block.values, skipna=False)
Expand All @@ -4808,7 +4804,7 @@ def _maybe_convert_for_string_atom(
)

elif not (inferred_type == "string" or dtype_name == "object"):
return block.dtype.itemsize, block.values, use_str
return block.values, use_str

use_str = True

Expand Down Expand Up @@ -4852,7 +4848,8 @@ def _maybe_convert_for_string_atom(
if eci > itemsize:
itemsize = eci

return itemsize, data_converted, use_str
data_converted = data_converted.astype(f"|S{itemsize}", copy=False)
return data_converted, use_str


def _convert_string_array(data, encoding, errors, itemsize=None):
Expand Down