jinglescode

places = []

with open(kml_filename, "r") as file:
    content = file.readlines()
    content = "".join(content)
    bs_content = BeautifulSoup(content, "xml")

    placemarks = bs_content.findAll('Placemark')
    for placemark in placemarks:

jinglescode

jinglescode

starting_point = 2 #@param {type:"integer"}
cur_index = starting_point

seq = [cur_index]
while len(seq) < len(list(df_distance_matrix.keys())):
    nearest_clusters = list(df_distance_matrix[cur_index].sort_values().index)
    for cluster_id in nearest_clusters:
        if cluster_id != cur_index and cluster_id not in seq:
            seq.append(cluster_id)
            cur_index = cluster_id

jinglescode

from scipy.spatial.distance import cdist

distance_matrix = cdist(
    mean_lat_long_by_group.values, 
    mean_lat_long_by_group.values
)

df_distance_matrix = pd.DataFrame(distance_matrix)
df_distance_matrix

jinglescode

Name	Latitude	Longitude	Cluster	Day
Athens International Airport	37.9356467	23.9484156	2	1
Acropolis of Athens	37.9715323	23.7257492	2	1
Pl. Agias Irinis 2	37.977418	23.7280221	2	1
Diporto - Secret underground restaurant	37.9806622	23.7257688	2	1
Temple of Zeus	37.9692838	23.7331012	2	1
Plaka	37.9725529	23.7303363999999	2	1
Temple of Olympian Zeus	37.9693	23.7331	2	1
Lake Vouliagmeni	37.8078002	23.7855018	2	1

jinglescode

	0	1	2	3	4	5	6	7	8	9	10	11
0	0.000000	11.987656	9.896897	11.599586	10.742770	0.386050	12.197858	11.100726	0.249281	12.021981	12.517198	11.246962
1	11.987656	0.000000	2.276986	1.396634	2.084259	11.607277	1.117249	1.660945	11.797155	1.488543	1.208088	1.837654
2	9.896897	2.276986	0.000000	2.706433	2.515520	9.523493	2.987206	2.456373	9.720741	3.096684	3.240456	2.751974
3	11.599586	1.396634	2.706433	0.000000	0.935321	11.214140	0.658161	0.507003	11.391950	0.439252	0.966409	0.500744
4	10.742770	2.084259	2.515520	0.935321	0.000000	10.356811	1.593083	0.454365	10.530636	1.306551	1.900750	0.504926
5	0.386050	11.607277	9.523493	11.214140	10.356811	0.000000	11.813022	10.715118	0.211347	11.636331	12.132428	10.861026
6	12.197858	1.117249	2.987206	0.658161	1.593083	11.813022	0.000000	1.155043	11.993443	0.439558	0.320395	1.143226
7	11.100726	1.660945	2.456373	0.507003	0.454365	10.715118	1.155043	0.000000	10.892023	0.921615	1.469345	0.297166

jinglescode

Cluster	Latitude	Longitude
0	40.846395	14.281423
1	36.411881	25.418702
2	37.958535	23.747617
3	35.359073	24.500997
4	35.449291	23.570038
5	40.645347	14.610990
6	35.325403	25.158296
7	35.517232	24.019294

jinglescode

Name	Latitude	Longitude
Athens International Airport	37.9356467	23.9484156
Ancient Agora of Athens	37.9746507	23.7219716
Tzistarakis Mosque	37.9759204	23
Roman Forum	37.9743749	23.7255435
Theatre of Dionysus	37.9703658	23.7278553
Parthenon	37.9715285	23.7267166
Acropolis Museum	37.9684499	23.7285227
Temple of Olympian Zeus	37.9693	23

jinglescode

jinglescode

import torch
import torch.nn as nn

class conv_block(nn.Module):
    def __init__(self, in_ch, out_ch):
        super(conv_block, self).__init__()

        self.conv = nn.Sequential(
            nn.Conv2d(in_ch, out_ch, kernel_size=3, stride=1, padding=1, bias=True),
            nn.BatchNorm2d(out_ch),