Skip to content

Make CSV seperators raw strings to avoid invalid escape sequence erro… #110

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

Open
wants to merge 1 commit into
base: develop
Choose a base branch
from
Open

Make CSV seperators raw strings to avoid invalid escape sequence erro… #110

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions src/pyannote/database/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,7 +90,7 @@ def load_trial(file_trial):
"""

trials = pd.read_table(
file_trial, sep="\s+", names=["reference", "uri1", "uri2"]
file_trial, sep=r"\s+", names=["reference", "uri1", "uri2"]
)

for _, reference, uri1, uri2 in trials.itertuples():
Expand Down Expand Up @@ -289,7 +289,7 @@ def __init__(self, ctm: Path):
"confidence": float,
}
self.data_ = pd.read_csv(
ctm, names=names, dtype=dtype, sep="\s+"
ctm, names=names, dtype=dtype, sep=r"\s+"
).groupby("uri")

def __call__(self, current_file: ProtocolFile) -> Union["Doc", None]:
Expand Down Expand Up @@ -354,7 +354,7 @@ def __init__(self, mapping: Path):
"uri": str,
}
self.data_ = pd.read_csv(
mapping, names=names, dtype=dtype, sep="\s+"
mapping, names=names, dtype=dtype, sep=r"\s+"
)

# get colum 'value' dtype, allowing us to acces it during subset
Expand Down
10 changes: 5 additions & 5 deletions src/pyannote/database/util.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -179,7 +179,7 @@ def load_rttm(file_rttm, keep_type="SPEAKER"):
file_rttm,
names=names,
dtype=dtype,
sep="\s+",
sep=r"\s+",
keep_default_na=True,
)

Expand Down Expand Up @@ -213,7 +213,7 @@ def load_stm(file_stm):
dtype = {"uri": str, "speaker": str, "start": float, "end": float}
data = pd.read_csv(
file_stm,
sep="\s+",
sep=r"\s+",
usecols=[0, 2, 3, 4],
dtype=dtype,
names=list(dtype),
Expand Down Expand Up @@ -250,7 +250,7 @@ def load_mdtm(file_mdtm):
file_mdtm,
names=names,
dtype=dtype,
sep="\s+",
sep=r"\s+",
keep_default_na=False,
)

Expand Down Expand Up @@ -281,7 +281,7 @@ def load_uem(file_uem):

names = ["uri", "NA1", "start", "end"]
dtype = {"uri": str, "start": float, "end": float}
data = pd.read_csv(file_uem, names=names, dtype=dtype, sep="\s+")
data = pd.read_csv(file_uem, names=names, dtype=dtype, sep=r"\s+")

timelines = dict()
for uri, parts in data.groupby("uri"):
Expand All @@ -306,7 +306,7 @@ def load_lab(path, uri: str = None) -> Annotation:

names = ["start", "end", "label"]
dtype = {"start": float, "end": float, "label": str}
data = pd.read_csv(path, names=names, dtype=dtype, sep="\s+")
data = pd.read_csv(path, names=names, dtype=dtype, sep=r"\s+")

annotation = Annotation(uri=uri)
for i, turn in data.iterrows():
Expand Down