Skip to content
Open
Changes from all commits
Commits
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: 5 additions & 1 deletion scripts/dump_bin.py
Original file line number Diff line number Diff line change
Expand Up @@ -170,6 +170,7 @@ def _get_source_data(self, file_path: Path) -> pd.DataFrame:
df = read_as_df(file_path, low_memory=False)
if self.date_field_name in df.columns:
df[self.date_field_name] = pd.to_datetime(df[self.date_field_name])
df.dropna(subset=[self.date_field_name], inplace=True)
# df.drop_duplicates([self.date_field_name], inplace=True)
return df

Expand Down Expand Up @@ -240,7 +241,10 @@ def data_merge_calendar(self, df: pd.DataFrame, calendars_list: List[pd.Timestam

@staticmethod
def get_datetime_index(df: pd.DataFrame, calendar_list: List[pd.Timestamp]) -> int:
return calendar_list.index(df.index.min())
min_index = df.index.min()
if pd.isnull(min_index):
raise ValueError("DataFrame index minimum value is NaT, cannot find in calendar_list")
return calendar_list.index(min_index)

def _data_to_bin(self, df: pd.DataFrame, calendar_list: List[pd.Timestamp], features_dir: Path):
if df.empty:
Expand Down