Skip to content

Fix/pandas loc indexing #97

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
pavank-v wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix/pandas loc indexing #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bb1641d
fix(data_model): replace mutable default DataFrame with default_facto…
pavank-v Nov 4, 2025
76d2689
Fix: replace set indexing with list & use .loc in test_data_model
pavank-v Nov 4, 2025
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
18 changes: 9 additions & 9 deletions logai/dataloader/data_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,15 +34,15 @@ class LogRecordObject:
:param _index: The indices of the log data.
"""

timestamp: pd.DataFrame = pd.DataFrame()
attributes: pd.DataFrame = pd.DataFrame()
resource: pd.DataFrame = pd.DataFrame()
trace_id: pd.DataFrame = pd.DataFrame()
span_id: pd.DataFrame = pd.DataFrame()
severity_text: pd.DataFrame = pd.DataFrame()
severity_number: pd.DataFrame = pd.DataFrame()
body: pd.DataFrame = pd.DataFrame()
labels: pd.DataFrame = pd.DataFrame()
timestamp: pd.DataFrame = field(default_factory=pd.DataFrame)
attributes: pd.DataFrame = field(default_factory=pd.DataFrame)
resource: pd.DataFrame = field(default_factory=pd.DataFrame)
trace_id: pd.DataFrame = field(default_factory=pd.DataFrame)
span_id: pd.DataFrame = field(default_factory=pd.DataFrame)
severity_text: pd.DataFrame = field(default_factory=pd.DataFrame)
severity_number: pd.DataFrame = field(default_factory=pd.DataFrame)
body: pd.DataFrame = field(default_factory=pd.DataFrame)
labels: pd.DataFrame = field(default_factory=pd.DataFrame)
_index: np.array = field(init=False)

def __post_init__(self):
Expand Down
10 changes: 6 additions & 4 deletions tests/logai/data_loader/test_data_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -92,16 +92,18 @@ def test_serialize_deserialize(self):

def test_dropna(self, hdfs_logrecord):
logrecord = hdfs_logrecord
null_indices = set(np.random.randint(len(logrecord.body), size=5))
logrecord.body[constants.LOGLINE_NAME][null_indices] = None
null_indices = list(np.random.randint(len(logrecord.body), size=5))
col = logrecord.body.columns[0]
logrecord.body.loc[null_indices, col] = None
logrecord_notnull = logrecord.dropna()
any_null = dict(logrecord_notnull.body.isnull().any()).values()
assert True not in any_null

def test_select_by_index(self, bgl_logrecord):
logrecord = bgl_logrecord
indices_to_select = set(np.random.randint(len(logrecord.body), size=50))
body_to_select = logrecord.body[constants.LOGLINE_NAME][indices_to_select]
indices_to_select = list(np.random.randint(len(logrecord.body), size=50))
col = logrecord.body.columns[0]
body_to_select = logrecord.body.loc[indices_to_select, col]
ids_to_select = logrecord.span_id[constants.SPAN_ID][indices_to_select]
logrecord = logrecord.select_by_index(indices=indices_to_select, inplace=True)
selected_body = logrecord.body[constants.LOGLINE_NAME]
Expand Down