-
Notifications
You must be signed in to change notification settings - Fork 0
/
zadanie1.py
132 lines (115 loc) · 5.13 KB
/
zadanie1.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
import csv
import numpy as np
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics.pairwise import euclidean_distances
from sklearn.cluster import KMeans
from sklearn.cluster import DBSCAN
if __name__ == '__main__':
allData = []
stringDictionary = {}
stringDictionaryKey = 1
countryDictionary = []
regionDictionary = []
print('\n---------NACITANIE A KONVERTOVANIE DAT-------ECH---')
with open('data_krajiny.csv', mode='r') as csv_file:
csv_reader = csv.reader(csv_file, delimiter=',')
line_count = 0
for row in csv_reader:
# how many rows do you want //prvych 30 krajin
if line_count == 31:
break
if line_count == 0:
print(row)
line_count += 1
else:
newLineOfArray = []
counter = -1
for x in row:
counter += 1
if counter == 10:
continue
# na zapamatanie regionu
if counter == 1:
regionDictionary.append(x)
# na zapamatanie country
if counter == 0:
countryDictionary.append(x)
continue
# ak je cislo, da, ak nie konvertuje
try:
floatValue = float(x)
newLineOfArray.append(floatValue)
except ValueError:
if not stringDictionary.get(x):
if x == '-' or x == '~0.0' or x == '-~0.0':
stringDictionary[x] = 0
else:
stringDictionary[x] = stringDictionaryKey
stringDictionaryKey += 1
newLineOfArray.append(stringDictionary[x])
elif stringDictionary.get(x):
newLineOfArray.append(stringDictionary[x])
allData.append(newLineOfArray)
line_count += 1
print(countryDictionary)
for row in allData:
print(row)
print('\n---------STRING and REGION(2. STLPEC) DICTIONARY----------')
print(stringDictionary)
print('\n---------ONLY REGION(2. STLPEC) DICTIONARY----------')
print(regionDictionary)
with open("allDataConvert.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerows(allData)
print('\n---------NORMALIZACIA VSETKYCH DAT----------')
scaler = MinMaxScaler()
scaler.fit(allData)
scaledAllData = scaler.transform(allData)
print(scaledAllData)
with open("normal.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerows(scaledAllData)
print('\n---------EUKLIDOVA VZDIALENOST----------')
euclideanAllData = euclidean_distances(scaledAllData, scaledAllData)
print(euclideanAllData)
with open("euclideanAllData.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerows(euclideanAllData)
print('\n---------K MEANS----------')
# pocet regionov a tak, to by bolo fajn opravit, ze dam pocet klastrov ako je regionov a ptm porovnam, ci to sedi s originialnimi datami
kmeans = KMeans(n_clusters=10).fit(scaledAllData)
# print(kmeans.cluster_centers_)
# kolko chcem skupin/klastrov
with open("K-means.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerow(countryDictionary)
csvWriter.writerow(kmeans.labels_)
csvWriter.writerow(regionDictionary)
set(kmeans.labels_)
print(kmeans.labels_)
print(set(kmeans.labels_))
print('\n---------DB SCAN----------')
dbscan = DBSCAN(eps=1.68, min_samples=1).fit(scaledAllData)
print(dbscan.labels_)
print(set(dbscan.labels_))
with open("DBscan.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerow(countryDictionary)
csvWriter.writerow(dbscan.labels_)
csvWriter.writerow(regionDictionary)
print('\n---------K MEANS - Cluster Centers----------')
# dataIndex = 0
with open("euclideanClusterCenters.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
for dataIndex in range(0, 10):
for data in scaledAllData:
foo = [kmeans.cluster_centers_[dataIndex], data]
# euclideanClusterCenters = euclidean_distances(kmeans.cluster_centers_[0], scaledAllData[0])
euclideanClusterCenters = euclidean_distances(foo, foo)
# print(euclideanClusterCenters)
csvWriter.writerows(euclideanClusterCenters)
with open("cluster_centers_.csv", 'w', newline='') as my_csv:
csvWriter = csv.writer(my_csv, delimiter=',')
csvWriter.writerows(kmeans.cluster_centers_)
# https://scikit-learn.org/stable/auto_examples/datasets/plot_iris_dataset.html
# https://scikit-learn.org/stable/datasets/index.html