fileConfig((Path.cwd() / 'config') / 'logging.cfg')
logger = getLogger()
+
class MeteoFrance:
- def __init__(self, latitude = 47.25, longitude = 6.0333, nb_stations = 3,
- start = datetime.strptime('19960101000000', '%Y%m%d%H%M%S'),
- end = datetime.now(),
- features = []):
+ _latitude = None
+ _longitude = None
+ _nb_stations = None
+ _start = None
+ _end = None
+ _features = None
+
+ def __init__(self, config_file):
'''
Constructor of the MeteoFrance source of feature.
-
- - It will reinitiate the data directory, if asked in the config
- features.cfg file.
- - It searches for the nb_stations meteo stations closest to the provided
- point (longitude and latitude)
-
- For more information about this source of feature, see:
- https://donneespubliques.meteofrance.fr/?fond=produit&id_produit=90&id_rubrique=32
-
- Parameters:
- latitude (float): The latitude from which we want the meteo features.
- longitude (float): The longitude from which we want the meteo features.
- nb_stations (int): Number of closest stations to consider.
- features (list): Weather features that have to be integrated, according
- to their names in meteofrance_features.csv (cf. config directory)
-
'''
- self._latitude = latitude
- self._longitude = longitude
- self._nb_stations = nb_stations
- self._start = start
- self._end = end
- self._features = features
+ self._config = ConfigParser()
+ self._config.read(config_file)
+
+ self._latitude = self._config['POSITION'].getfloat('latitude')
+ self._longitude = self._config['POSITION'].getfloat('longitude')
self._data_directory = (Path.cwd() / 'data') / 'features' / 'meteo_france'
self._dated_features = None
# Re-creating data directory architecture for MeteoFrance, if asked
- config = ConfigParser()
- config.read((Path.cwd() / 'config') / 'features.cfg')
- if eval(config['meteofrance']['regenerate']):
+ if self._config['GENERAL'].getboolean('regenerate'):
self._regenerate_directory()
# Collecting the closest meteo station
+ self._nb_stations = self._config['STATIONS'].getint('nb_stations')
self._stations = self._get_stations()
+ # Collecting meteofrance features
+ self._features = [section for section in self._config
+ if self._config.has_option(section, 'numerical')
+ and (self._config[section]['numerical'] or
+ self._config[section]['categorical'])]
+
+
+
+ @property
+ def start(self):
+ return self._start
+
+ @start.setter
+ def start(self, x):
+ self._start = x
+
+
+ @property
+ def end(self):
+ return self._end
+
+ @end.setter
+ def end(self, x):
+ self._end = x
+
+
+ @property
+ def latitude(self):
+ return self._latitude
+
+ @latitude.setter
+ def latitude(self, x):
+ self._latitude = x
+
+
+ @property
+ def longitude(self):
+ return self._longitude
+
+ @longitude.setter
+ def longitude(self, x):
+ self._longitude = x
+
+
+ @property
+ def nb_stations(self):
+ return self._nb_stations
+
+ @nb_stations.setter
+ def nb_stations(self, x):
+ self._nb_stations = x
def _regenerate_directory(self):
dict: the dictionary of features per datestamp
'''
if self._dated_features == None:
- csv_file = Path.cwd() / 'config' / 'features' / 'meteofrance_features.csv'
- logger.info(f'Collecting meteo feature information from {csv_file}')
+ logger.info('Collecting meteofrance feature information')
# A dictionary for the features
- with open(csv_file, "r") as f:
- reader = DictReader(f, delimiter=',')
- dico_features = {row["abbreviation"]:
- {
- 'name': row['name'], # feature name
- 'type': row['type'] # qualitative (2) or quantitative (1)
- }
- for row in reader if row['name'] in self._features}
+ dico_features = {self._config[section]["abbreviation"]:
+ {
+ 'name': section, # feature name
+ 'numerical': self._config[section]['numerical'],
+ 'categorical': self._config[section]['categorical']
+ }
+ for section in self._features}
dir_data = Path.cwd() / 'data' / 'features' / 'meteo_france' / 'historical'
self._dated_features = {}
- for csv_meteo in listdir(dir_data):
+ for csv_meteo in sorted(listdir(dir_data)):
date = datetime.strptime(csv_meteo.split('.')[1], '%Y%m')
- if date >= self._start and date <= self._end:
+ if (date >= self._start and date <= self._end)\
+ or (date.year == self._start.year and date.month == self._start.month)\
+ or (date.year == self._end.year and date.month == self._end.month):
logger.info(f'Inserting {csv_meteo} in intervention dictionary')
with open(dir_data / csv_meteo, "r") as f:
reader = DictReader(f, delimiter=';')
for row in reader:
if row['numer_sta'] in self._stations:
date = datetime.strptime(row['date'], '%Y%m%d%H%M%S')
- self._dated_features.setdefault(date,{}).update({dico_features[feat]['name']+'_'+str(self._stations.index(row['numer_sta'])): eval(row[feat].replace('mq','None')) for feat in dico_features})
+ if date >= self._start and date <= self._end:
+ self._dated_features.setdefault(date,{}).update({dico_features[feat]['name']+'_'+str(self._stations.index(row['numer_sta'])): eval(row[feat].replace('mq','None')) for feat in dico_features})
return self._dated_features
