def calc_stats_dt(srs: dd.Series) -> Dict[str, str]:
"""
Calculate stats from a datetime column
Parameters
----------
srs
a datetime column
Returns
-------
Dict[str, str]
Dictionary that contains Overview
"""
size = len(srs) # include nan
count = srs.count() # exclude nan
uniq_count = srs.nunique()
overview_dict = {
"Distinct Count": uniq_count,
"Unique (%)": uniq_count / count,
"Missing": size - count,
"Missing (%)": 1 - (count / size),
"Memory Size": srs.memory_usage(),
"Minimum": srs.min(),
"Maximum": srs.max(),
}
return overview_dict
def calc_stats_dt(srs: dd.Series) -> Dict[str, str]:
"""
Calculate stats from a datetime column
"""
size = srs.shape[0] # include nan
count = srs.count() # exclude nan
# nunique_approx() has error when type is datetime
try:
uniq_count = srs.nunique_approx()
except: # pylint: disable=W0702
uniq_count = srs.nunique()
overview_dict = {
"Distinct Count": uniq_count,
"Approximate Unique (%)": uniq_count / count,
"Missing": size - count,
"Missing (%)": 1 - (count / size),
"Memory Size": srs.memory_usage(deep=True),
"Minimum": srs.min(),
"Maximum": srs.max(),
}
return overview_dict