Allow to define the threshold between a housing and a station

Fix #101.

doc/0.getting_started.md

@@ -121,6 +121,9 @@ List of configuration options:
   fetch personal data from housing posts and store them in database. Such
   personal data include contact phone number for instance. By default,
   Flatisfy does not store such personal data.
+* `max_distance_housing_station` is the maximum distance (in meters) between
+  an housing and a public transport station found for this housing (default is
+  `1500`). This is useful to avoid false-positive.
 
 _Note:_ In production, you can either use the `serve` command with a reliable
 webserver instead of the default Bottle webserver (specifying a `webserver`

flatisfy/config.py

@@ -44,6 +44,9 @@ DEFAULT_CONFIG = {
     # Whether or not to store personal data from housing posts (phone number
     # etc)
     "store_personal_data": False,
+    # Max distance between an housing and a found station, to avoid
+    # false-positive
+    "max_distance_housing_station": 1500,
     # Navitia API key
     "navitia_api_key": None,
     # Number of filtering passes to run
@@ -140,6 +143,7 @@ def validate_config(config, check_with_data):
         assert config["smtp_to"] is None or isinstance(config["smtp_to"], list)
 
         assert isinstance(config["store_personal_data"], bool)
+        assert isinstance(config["max_distance_housing_station"], int) or isinstance(config["max_distance_housing_station"], float)  # noqa: E501
 
         # Ensure constraints are ok
         assert config["constraints"]

flatisfy/filters/metadata.py

@@ -240,18 +240,17 @@ def guess_postal_code(flats_list, constraint, config, distance_threshold=20000):
     return flats_list
 
 
-def guess_stations(flats_list, constraint, config, distance_threshold=1500):
+def guess_stations(flats_list, constraint, config):
     """
     Try to match the station field with a list of available stations nearby.
 
     :param flats_list: A list of flats dict.
     :param constraint: The constraint that the ``flats_list`` should satisfy.
     :param config: A config dict.
-    :param distance_threshold: Maximum distance (in meters) between the center
-        of the postal code and the station to consider it ok.
 
     :return: An updated list of flats dict with guessed nearby stations.
     """
+    distance_threshold = config['max_distance_housing_station']
     opendata = {
         "postal_codes": data.load_data(PostalCode, constraint, config),
         "stations": data.load_data(PublicTransport, constraint, config)