def _construct_norm_arrays(file_path: str, metadata_path: str, fold: int = None, filesystem: S3FS = None) -> \
Tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
""" Return arrays with normalisation factors to be used """
chunk_name = os.path.basename(file_path)
df = pd.read_csv(
filesystem.open(metadata_path)
) if filesystem is not None else pd.read_csv(metadata_path)
df = df[df.chunk == chunk_name]
if fold is not None:
df = df[df.fold == fold]
perc99 = df[[
'norm_perc99_b0', 'norm_perc99_b1', 'norm_perc99_b2', 'norm_perc99_b3'
]].values
meanstd_mean = df[[
'norm_meanstd_mean_b0', 'norm_meanstd_mean_b1', 'norm_meanstd_mean_b2',
'norm_meanstd_mean_b3'
]].values
meanstd_median = df[[
'norm_meanstd_median_b0', 'norm_meanstd_median_b1',
'norm_meanstd_median_b2', 'norm_meanstd_median_b3'
]].values
meanstd_std = df[[
'norm_meanstd_std_b0', 'norm_meanstd_std_b1', 'norm_meanstd_std_b2',
'norm_meanstd_std_b3'
]].values
return perc99, meanstd_mean, meanstd_median, meanstd_std
def load_dates(filesystem: S3FS, tile_name: str) -> List[datetime]:
""" Load a json file with dates from the bucket and parse out dates
"""
path = f'/{tile_name}/userdata.json'
with filesystem.open(path, 'r') as fp:
userdata = json.load(fp)
dates_list = json.loads(userdata['dates'])
return [parse(date) for date in dates_list]
def load_metadata(filesystem: S3FS, config: PredictionConfig) -> pd.DataFrame:
""" Load DataFrame with info about normalisation factors """
metadata_dir = os.path.dirname(config.metadata_path)
if not filesystem.exists(metadata_dir):
filesystem.makedirs(metadata_dir)
df = pd.read_csv(filesystem.open(f'{config.metadata_path}'))
normalisation_factors = df.groupby(
pd.to_datetime(df.timestamp).dt.to_period("M")).max()
normalisation_factors['month'] = pd.to_datetime(
normalisation_factors.timestamp).dt.month
return normalisation_factors