def surface_search(search_params: list, db=False) -> list:
if db:
current_url, pagesnr, database = search_url(search_params, db)
else:
current_url, pagesnr = search_url(search_params, db)
data = []
for i in range(pagesnr):
for item in surface_data(current_url):
data.append(item)
current_url = next_page(current_url, i + 1)
assert data != []
data = scalg.score_columns(data, [2, 3, 4], [0, 1, 0])
data.sort(key=lambda d: d[-1])
undup = []
undup_indexes = []
for i, d in enumerate(data):
if d[-1] in undup:
undup_indexes.append(i)
else:
undup.append(d[-1])
for i in sorted(undup_indexes, reverse=True):
del data[i]
return (data, database) if db else data
def test_score_columns(self, ):
req_result = [[2016, 21999, 62000, 181, 1.4911330049261085],
[2013, 21540, 89000, 223, 0.5665024630541872],
[2015, 18900, 100000, 223, 1.6666666666666665],
[2013, 24200, 115527, 223, 0.12972085385878485],
[2016, 24990, 47300, 223, 1.0]]
result = scalg.score_columns(DATA, [0, 1], WEIGHTS)
assert result == req_result
def get_pollution(self, location: str) -> list:
if type(location) == str:
user_coords = self._user_location(location)
else:
user_coords = location
item = self.kmz_obj.coords_item(user_coords)
edges, image = self.kmz_obj.load_images(item[1],
single=True,
neighbours=True)
closest_unique_spots = find_pollution_coords(user_coords, edges, image)
for i, spot in enumerate(closest_unique_spots):
elevation = self.gmaps.elevation(spot)[0]['elevation']
weather = self._coords_weather(spot)
distance = geodesic(user_coords, spot).km
closest_unique_spots[i] = [spot, distance, elevation] + weather
scored = scalg.score_columns(closest_unique_spots, [1, 2, 4],
[0, 1, 0])
return user_coords, sorted(scored, key=lambda x: x[-1])[-1]
def surface_search(search_params: list, db=False) -> list:
if db:
current_url, pagesnr, database = search_url(search_params, db)
else:
current_url, pagesnr = search_url(search_params, db)
data = []
for i in range(pagesnr):
for item in surface_data(current_url + "&lang=en"):
data.append(item)
current_url = next_page(current_url, i + 1)
assert data != []
data = scalg.score_columns(data, [2, 3, 4], [0, 1, 0])
if db:
return data, database
else:
return data
def search(search_params: list, db=False) -> list:
if db:
current_url, pagesnr, database = search_url(search_params, db)
else:
current_url, pagesnr = search_url(search_params, db)
# get links
car_links = []
for i in range(pagesnr):
for link in get_page_listings(current_url + "&lang=en"):
car_links.append(link)
current_url = next_page(current_url, i + 1)
assert len(car_links) != 0
data = [get_car_data(link + "&lang=en") for link in car_links]
data = scalg.score_columns(data, [2, 3, 4], [0, 1, 0])
if db:
return database, data
else:
return data
import os, sys, inspect
currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(currentdir)
sys.path.insert(0, parentdir)
import scalg
DATA = [
[2016, 21999, 62000, 181],
[2013, 21540, 89000, 223],
[2015, 18900, 100000, 223],
[2013, 24200, 115527, 223],
[2016, 24990, 47300, 223],
]
if __name__ == "__main__":
print(scalg.score_columns(DATA, [0, 1], [1, 0, 0, 1]))