Skip to content
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

Jump to bottom

Speedup dependencies dtypes #363

Closed
wants to merge 3 commits into from
Closed

Speedup dependencies dtypes #363

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a05b58e
Speed up audb.Dependencies dtypes
hagenw Feb 6, 2024
5897602
Finish implementation
hagenw Feb 6, 2024
a6386c3
Be explicit to use object as dtype for index
hagenw Feb 7, 2024
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
8 changes: 4 additions & 4 deletions audb/core/define.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,16 +48,16 @@ class DependField:
}

DEPEND_FIELD_DTYPES = {
DependField.ARCHIVE: "string",
DependField.ARCHIVE: "object",
DependField.BIT_DEPTH: "int32",
DependField.CHANNELS: "int32",
DependField.CHECKSUM: "string",
DependField.CHECKSUM: "object",
DependField.DURATION: "float64",
DependField.FORMAT: "string",
DependField.FORMAT: "object",
DependField.REMOVED: "int32",
DependField.SAMPLING_RATE: "int32",
DependField.TYPE: "int32",
DependField.VERSION: "string",
DependField.VERSION: "object",
}


Expand Down
1 change: 0 additions & 1 deletion audb/core/dependencies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -307,7 +307,6 @@ def load(self, path: str):
na_filter=False,
dtype=dtype_mapping,
)
self._df.index = self._df.index.astype("string")

def removed(self, file: str) -> bool:
r"""Check if file is marked as removed.
Expand Down
2 changes: 1 addition & 1 deletion benchmarks/benchmark-dependency-methods.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@
df[column] = df[column].astype(dtype)
df.set_index("file", inplace=True)
df.index.name = None
df.index = df.index.astype("string")
df.index = df.index.astype("object")
df.to_pickle(data_cache)

# === Create dependency object ===
Expand Down
2 changes: 0 additions & 2 deletions tests/test_dependencies.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,7 +52,6 @@ def deps():
df = pd.DataFrame.from_records(ROWS)
df.set_index("file", inplace=True)
# Ensure correct dtype
df.index = df.index.astype("string")
for name, dtype in zip(
audb.core.define.DEPEND_FIELD_NAMES.values(),
audb.core.define.DEPEND_FIELD_DTYPES.values(),
Expand Down Expand Up @@ -82,7 +81,6 @@ def test_init(deps):

def test_call(deps):
expected_df = pd.DataFrame.from_records(ROWS).set_index("file")
expected_df.index = expected_df.index.astype("string")
for name, dtype in zip(
audb.core.define.DEPEND_FIELD_NAMES.values(),
audb.core.define.DEPEND_FIELD_DTYPES.values(),
Expand Down
Loading