def get_isd_data(self, station, year):
filename_format = '/pub/data/noaa/{year}/{station}-{year}.gz'
lines = self._retreive_file_lines(filename_format, station, year)
dates = pd.date_range("{}-01-01 00:00".format(year),
"{}-12-31 23:00".format(int(year) + 1),
freq='H', tz=pytz.UTC)
series = pd.Series(None, index=dates, dtype=float)
for line in lines:
if line[87:92].decode('utf-8') == "+9999":
temp_C = float("nan")
else:
temp_C = float(line[87:92]) / 10.
date_str = line[15:27].decode('utf-8')
# there can be multiple readings per hour, so set all to minute 0
dt = pytz.UTC.localize(datetime.strptime(date_str, "%Y%m%d%H%M")).replace(minute=0)
# only set the temp if it's the first encountered in the hour.
if pd.isnull(series.ix[dt]):
series[dt] = temp_C
return series
评论列表
文章目录