moreo
/
QuaPy
1
0
Fork 1
Code Issues Pull Requests Releases Wiki Activity

Merge pull request #52 from aesuli/read_csv 

Fix regex for whitespace delimiter in CSV reads
This commit is contained in:
Andrea Esuli 2026-02-23 09:32:53 +01:00 committed by GitHub
parent f4ac6da7a4 c1ae85950a
commit 5374ef3cae
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
quapy/data/datasets.py
View File

@ -486,7 +486,7 @@ def fetch_UCIBinaryLabelledCollection(dataset_name, data_home=None, standardize=
# fall back to direct download when needed # fall back to direct download when needed
if group == "german": if group == "german":
with download_tmp_file("statlog/german", "german.data-numeric") as tmp: with download_tmp_file("statlog/german", "german.data-numeric") as tmp:
df = pd.read_csv(tmp, header=None, delim_whitespace=True) df = pd.read_csv(tmp, header=None, sep="\\s+")
X, y = df.iloc[:, 0:24].astype(float).values, df[24].astype(int).values X, y = df.iloc[:, 0:24].astype(float).values, df[24].astype(int).values
elif group == "ctg": elif group == "ctg":
with download_tmp_file("00193", "CTG.xls") as tmp: with download_tmp_file("00193", "CTG.xls") as tmp:
@ -500,7 +500,7 @@ def fetch_UCIBinaryLabelledCollection(dataset_name, data_home=None, standardize=
y = df["NSP"].astype(int).values y = df["NSP"].astype(int).values
elif group == "semeion": elif group == "semeion":
with download_tmp_file("semeion", "semeion.data") as tmp: with download_tmp_file("semeion", "semeion.data") as tmp:
df = pd.read_csv(tmp, header=None, sep='\s+') df = pd.read_csv(tmp, header=None, sep="\\s+")
X = df.iloc[:, 0:256].astype(float).values X = df.iloc[:, 0:256].astype(float).values
y = df[263].values # 263 stands for digit 8 (labels are one-hot vectors from col 256-266) y = df[263].values # 263 stands for digit 8 (labels are one-hot vectors from col 256-266)
else: else: