region_grid = RegionGrid(config=c)
region_grid.load_weighted_mtx()
tmp = pd.DataFrame(region_grid.feature_matrix, index = region_grid.idx_coor_map.values())
autoencoder_embed = c['autoencoder_embedding_file']
regionencoder_embed = c['embedding_file']
gcn_all_embed = '{}gcn_all_embedding.txt'.format(c['data_dir_main'])
gcn_sg_embed = '{}gcn_skipgram_embedding.txt'.format(c['data_dir_main'])
gcn_flow_embed = '{}gcn_flow_embedding.txt'.format(c['data_dir_main'])
concat_embed ='{}concat_global_embedding.txt'.format(c['data_dir_main'])
if task == 'house_price':
input_data = region_grid.load_housing_data(c['housing_data_file'])
re_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, c['embedding_file'])
autoencoder_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, c['autoencoder_embedding_file'])
gcn_skipgram_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, gcn_sg_embed)
gcn_flow_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, gcn_flow_embed)
gcn_all_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, gcn_all_embed)
gcn_ae_concat_mod = HousePriceModel(region_grid.idx_coor_map, c, n_epochs, c['autoencoder_embedding_file'],
gcn_all_embed)
elif task == 'check_in':
input_data = region_grid.get_checkin_counts(metric="mean")
# init prediction models
re_mod = CheckinModel(region_grid.idx_coor_map, c, n_epochs, c['embedding_file'])
gcn_all_mod = CheckinModel(region_grid.idx_coor_map, c, n_epochs, gcn_all_embed)
gcn_skipgram_mod = CheckinModel(region_grid.idx_coor_map, c, n_epochs, gcn_sg_embed)
import sys
import os
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
from config import get_config
from grid.create_grid import RegionGrid
import numpy as np
import matplotlib.pyplot as plt
plt.rc('text', usetex=True)
plt.rc('font', family='serif')
import geopandas as gpd
c = get_config()
region_grid = RegionGrid(config=c)
house_price = region_grid.load_housing_data(c['housing_data_file'])
print(house_price.head())
checkin = region_grid.get_checkin_counts(metric="mean")
trim = np.percentile(house_price['priceSqft'], 99)
print(trim)
house_price = house_price[house_price['priceSqft'] < trim]
house_price.to_csv(c['data_dir_main'] + 'zillow_house_price_trim.csv',
index=False)
checkin.to_csv(c['data_dir_main'] + "checkin.csv", index=False)
print(checkin.head())
#checkin.checkins.hist()
#plt.show()
#plt.clf()