def main():
train_flats = files.export_flats(config.TRAIN_FILE)
test_flats = files.export_flats(config.TEST_FILE)
train_flats_data = files.get_flats_data(train_flats)
test_flats_data = files.get_flats_data(test_flats)
classified_flats = classify_flats(train_flats_data)
avg_vals = {}
for k, v in classified_flats.items():
avg_vals[k] = get_avg_class(v)
labels, predictions = get_errors(test_flats_data, avg_vals)
print(get_quality(labels, predictions))
def main():
# restore()
flats = files.export_flats(config.FLATS_FILE)
for flat in flats:
if flat['rating'] != '0':
flat['rating'] = '0'
files.save_flats(flats, config.FLATS_FILE)
def split_dataset():
flats = files.export_flats(config.FLATS_FILE)
full_flats, not_full_flats = [], []
for flat in flats:
if is_full_info(flat):
full_flats.append(flat)
else:
not_full_flats.append(flat)
return full_flats, not_full_flats
def create_db(num):
flats = files.export_flats(FLATS_FILE)
flats_data = files.get_flats_data(flats)
print('Creating DB...')
users = []
it = 0
while True:
user = generate_user()
rs = {1: 0, 2: 0, 3: 0, 4: 0, 5: 0}
for flat_data in flats_data:
res = rate(flat_data, user)
rs[res] += 1
std_dev = np.std(tuple(rs.values()))
if std_dev < 400:
users.append(user)
it += 1
print(f'Generating user {it}/{num}...')
if it == num:
break
flats_users = {}
flats_cnt = len(flats)
flats_it = 1
for flat in flats:
flats_users[flat['link']] = {}
flat_data = files.get_flat_data(flat)
user_it = 1
print(f'Rating {flats_it}/{flats_cnt}...')
for user in users:
user_name = 'user_{}'.format(user_it)
r = str(rate(flat_data, user))
flats_users[flat['link']][user_name] = r
user_it += 1
flats_it += 1
# for k, v in flats_users.items():
# print(k, v)
save_users(flats_users, USERS_FILE)
from lightgbm import LGBMClassifier
import files
from config import *
import math
def get_quality_rmse(labels, predictions):
sum = 0
n = len(labels)
for i in range(n):
num = (predictions[i]-labels[i])**2
sum += num/n
return math.sqrt(sum)
train_flats = files.export_flats(TRAIN_FILE)
test_flats = files.export_flats(TEST_FILE)
train_flats_data = files.get_flats_data(train_flats)
test_flats_data = files.get_flats_data(test_flats)
def get_xy(flats_data, n = None):
if n == None:
n = len(flats_data)
X = []
Y = []
cnt = 0
for flat_data in flats_data:
x = []
y = flat_data['rating']
for k, v in flat_data.items():
if k != 'rating':
x.append(v)
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_auc_score
from config import *
from files import export_flats, get_flats_data
from math import radians, cos, sin, acos
import numpy as np
model = RandomForestClassifier(n_estimators=21, oob_score=True, random_state=1)
train_flats = export_flats(TRAIN_FILE)
test_flats = export_flats(TEST_FILE)
train_flats_data = get_flats_data(train_flats)
test_flats_data = get_flats_data(test_flats)
def calculate_distance(location1, location2):
radius = 6371
lat1 = radians(location1[0])
lng1 = radians(location1[1])
lat2 = radians(location2[0])
lng2 = radians(location2[1])
distance = radius * acos(
sin(lat1) * sin(lat2) + cos(lat1) * cos(lat2) * cos(lng1 - lng2))
return distance
def get_center_distance(coordinates):
town_center = (43.240544, 76.917604)
dist = calculate_distance(coordinates, town_center)
return dist
def main():
flats = files.export_flats(config.FLATS_FILE)
train_flats = flats[:3000]
test_flats = flats[3000:]
files.save_flats(train_flats, config.TRAIN_FILE)
files.save_flats(test_flats, config.TEST_FILE)