From 08abda0e74398e7fade2afc3d254d4e8ce1e3cea Mon Sep 17 00:00:00 2001
From: Vojtaz <wojprz@st.amu..edu.pl>
Date: Sat, 24 Apr 2021 21:08:04 +0200
Subject: [PATCH] =?UTF-8?q?zadanie-k-=C5=9Brednie?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 clusters.py      |  32 +++
 dev-0/out.tsv    |  87 ++++++
 skrypt-dev-0.py  |  20 ++
 skrypt-test-A.py |  20 ++
 test-A/out.tsv   | 691 +++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 850 insertions(+)
 create mode 100644 clusters.py
 create mode 100644 dev-0/out.tsv
 create mode 100644 skrypt-dev-0.py
 create mode 100644 skrypt-test-A.py
 create mode 100644 test-A/out.tsv

diff --git a/clusters.py b/clusters.py
new file mode 100644
index 0000000..b6259a1
--- /dev/null
+++ b/clusters.py
@@ -0,0 +1,32 @@
+import matplotlib.pyplot as plt
+from sklearn.cluster import KMeans
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.preprocessing import MaxAbsScaler
+
+
+
+K = range(1, 87)
+W = range(1, 683)
+
+mms = MaxAbsScaler()
+
+with open("test-A/in.tsv") as file:
+    corpus = file.readlines()
+    vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = True)
+    vectorizer = TfidfVectorizer()
+    vectors = vectorizer.fit_transform(corpus)
+    mms.fit(vectors)
+    transformed = mms.transform(vectors)
+
+    Sum_of_squered_distances = []
+
+    for k in W:
+        km = KMeans(n_clusters=k)
+        km = km.fit(transformed)
+        Sum_of_squered_distances.append(km.inertia_)
+
+    plt.plot(W, Sum_of_squered_distances, 'bx-')
+    plt.xlabel('k')
+    plt.ylabel('Sum_of_squered_distances')
+    plt.show()
\ No newline at end of file
diff --git a/dev-0/out.tsv b/dev-0/out.tsv
new file mode 100644
index 0000000..6915e4f
--- /dev/null
+++ b/dev-0/out.tsv
@@ -0,0 +1,87 @@
+18
+ 4
+ 6
+12
+24
+22
+27
+ 3
+ 4
+ 8
+26
+22
+ 0
+13
+25
+15
+33
+24
+23
+24
+16
+11
+ 7
+10
+ 20
+11
+21
+ 7
+34
+32
+27
+27
+17
+ 5
+25
+17
+13
+ 1
+21
+12
+ 4
+30
+17
+12
+18
+29
+31
+24
+  3
+17
+20
+ 6
+27
+11
+14
+10
+24
+24
+27
+28
+17
+19
+30
+24
+22
+11
+ 2
+18
+ 5
+31
+16
+23
+ 18
+ 9
+24
+ 3
+20
+14
+12
+ 3
+ 8
+ 3
+ 8
+24
+ 9
+ 1
+24
\ No newline at end of file
diff --git a/skrypt-dev-0.py b/skrypt-dev-0.py
new file mode 100644
index 0000000..7196f44
--- /dev/null
+++ b/skrypt-dev-0.py
@@ -0,0 +1,20 @@
+from sklearn.cluster import KMeans
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+import matplotlib.pyplot as plt
+
+
+
+
+with open("dev-0/in.tsv") as file:
+    corpus = file.readlines()
+    vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = True)
+    vectors = vectorizer.fit_transform(corpus)
+
+    kmeans = KMeans(n_clusters=35, random_state = 0).fit(vectors)
+    prediction = kmeans.fit_predict(vectors)
+    labels = kmeans.labels_
+    labels = np.array2string(labels, precision=2, separator='\n', suppress_small=True)
+
+    file = open("dev-0/out.tsv", "w")
+    file.write(labels[1:-1])
\ No newline at end of file
diff --git a/skrypt-test-A.py b/skrypt-test-A.py
new file mode 100644
index 0000000..c8a0bab
--- /dev/null
+++ b/skrypt-test-A.py
@@ -0,0 +1,20 @@
+from sklearn.cluster import KMeans
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+import matplotlib.pyplot as plt
+
+
+
+
+with open("test-A/in.tsv") as file:
+    corpus = file.readlines()
+    vectorizer = TfidfVectorizer(ngram_range=(1,2), use_idf = True)
+    vectors = vectorizer.fit_transform(corpus)
+
+    kmeans = KMeans(n_clusters=255, random_state = 0).fit(vectors)
+    prediction = kmeans.fit_predict(vectors)
+    labels = kmeans.labels_
+    labels = np.array2string(labels, precision=2, separator='\n', suppress_small=True)
+
+    file = open("test-A/out.tsv", "w")
+    file.write(labels[1:-1])
\ No newline at end of file
diff --git a/test-A/out.tsv b/test-A/out.tsv
new file mode 100644
index 0000000..0c61e22
--- /dev/null
+++ b/test-A/out.tsv
@@ -0,0 +1,691 @@
+ 63
+130
+223
+128
+113
+107
+227
+ 27
+ 70
+129
+203
+ 73
+174
+160
+ 17
+244
+ 93
+205
+  93
+ 17
+185
+ 38
+ 20
+117
+165
+ 53
+111
+ 78
+194
+ 98
+147
+254
+ 20
+ 97
+ 68
+ 58
+  73
+ 77
+143
+125
+ 51
+ 14
+186
+  4
+ 48
+204
+164
+  9
+223
+ 17
+223
+155
+209
+117
+  46
+ 95
+131
+156
+218
+240
+105
+166
+111
+ 52
+ 17
+ 43
+ 80
+107
+108
+139
+ 35
+ 68
+ 140
+145
+132
+227
+252
+235
+211
+  8
+184
+ 13
+ 44
+136
+110
+ 57
+209
+235
+228
+ 51
+ 119
+106
+ 68
+ 92
+103
+166
+ 63
+ 48
+193
+200
+151
+ 86
+ 47
+ 26
+218
+172
+135
+ 39
+  74
+ 65
+ 50
+156
+ 70
+142
+ 69
+ 92
+177
+ 33
+ 79
+176
+ 12
+ 82
+ 26
+144
+157
+143
+ 247
+ 15
+ 84
+  9
+106
+ 67
+105
+ 77
+224
+ 68
+127
+  8
+ 44
+ 29
+ 89
+ 59
+ 12
+ 29
+  53
+131
+ 65
+ 29
+170
+ 95
+ 93
+103
+177
+ 17
+137
+ 73
+ 18
+ 30
+145
+ 38
+ 41
+104
+  71
+ 21
+ 35
+ 92
+ 44
+220
+ 68
+ 68
+146
+ 85
+217
+ 14
+140
+ 44
+243
+ 83
+176
+149
+  10
+  9
+ 88
+171
+ 53
+138
+ 82
+ 22
+ 27
+210
+ 63
+  5
+ 73
+133
+196
+ 30
+209
+223
+ 176
+ 63
+175
+112
+ 63
+ 40
+129
+103
+223
+  9
+130
+  6
+106
+ 91
+104
+  6
+ 30
+ 73
+ 101
+ 20
+ 36
+ 70
+ 17
+126
+106
+193
+ 23
+ 67
+ 41
+234
+ 96
+ 73
+131
+ 87
+ 95
+173
+  16
+ 70
+ 67
+117
+169
+131
+ 57
+ 70
+ 43
+ 87
+207
+ 32
+102
+102
+ 40
+ 21
+ 62
+ 33
+  13
+ 64
+112
+ 23
+ 57
+204
+ 41
+ 12
+ 95
+101
+242
+168
+127
+ 75
+131
+146
+112
+ 91
+ 206
+185
+210
+152
+187
+180
+ 40
+ 50
+ 12
+215
+148
+ 61
+132
+  8
+ 64
+ 11
+114
+156
+ 161
+ 20
+ 74
+164
+233
+ 79
+159
+102
+103
+ 11
+186
+ 78
+ 40
+ 74
+  2
+210
+126
+ 83
+ 211
+181
+ 19
+ 57
+130
+ 54
+ 76
+174
+ 96
+146
+135
+150
+179
+ 98
+166
+ 44
+ 38
+177
+ 231
+122
+177
+132
+158
+ 40
+ 85
+167
+213
+ 15
+182
+223
+  8
+ 76
+ 17
+ 56
+104
+105
+  64
+ 17
+137
+ 12
+222
+ 31
+ 62
+158
+ 72
+ 66
+ 54
+241
+129
+251
+102
+161
+162
+166
+ 229
+195
+ 79
+152
+102
+212
+223
+174
+ 21
+ 41
+130
+232
+ 73
+154
+101
+ 56
+ 15
+ 28
+  45
+251
+ 53
+201
+239
+249
+  6
+ 50
+124
+ 73
+123
+107
+163
+ 43
+111
+223
+219
+157
+  57
+113
+ 18
+120
+ 40
+209
+ 95
+ 81
+ 45
+ 17
+246
+ 86
+ 24
+ 34
+ 99
+ 11
+101
+  8
+  15
+ 61
+ 21
+210
+139
+198
+ 39
+114
+ 72
+ 20
+ 41
+112
+142
+113
+154
+ 17
+133
+ 80
+  21
+ 14
+ 10
+170
+ 14
+ 57
+117
+ 20
+ 32
+223
+ 99
+191
+ 93
+ 33
+244
+ 10
+194
+ 40
+   7
+ 14
+185
+ 75
+ 25
+ 77
+253
+ 21
+175
+210
+ 79
+144
+237
+226
+125
+103
+142
+225
+ 192
+ 51
+122
+118
+ 51
+134
+215
+ 40
+112
+104
+208
+ 36
+ 41
+ 23
+ 99
+245
+178
+171
+ 182
+102
+112
+ 19
+123
+223
+  9
+197
+ 84
+ 77
+ 64
+ 29
+110
+  7
+230
+  1
+ 57
+ 77
+  71
+ 76
+ 42
+ 76
+ 86
+ 48
+ 16
+119
+ 20
+  2
+169
+ 94
+149
+ 93
+  2
+  9
+  4
+135
+  41
+ 49
+228
+216
+183
+199
+236
+174
+ 10
+214
+ 51
+ 97
+100
+ 34
+184
+238
+ 61
+172
+ 142
+ 29
+113
+ 25
+ 81
+ 16
+  0
+254
+ 39
+ 64
+215
+175
+ 37
+ 78
+ 67
+ 13
+ 39
+ 57
+  68
+ 43
+ 16
+223
+132
+ 27
+141
+161
+ 77
+ 85
+ 27
+  3
+223
+223
+135
+ 58
+211
+ 31
+  64
+162
+ 31
+136
+ 95
+ 87
+189
+ 16
+169
+ 57
+ 13
+ 95
+202
+102
+ 33
+ 69
+ 72
+100
+  42
+250
+ 63
+105
+ 24
+192
+223
+ 17
+ 61
+ 17
+ 95
+132
+ 90
+109
+ 25
+160
+ 73
+ 86
+  63
+ 26
+ 73
+  5
+  7
+ 21
+  2
+ 19
+116
+ 38
+188
+142
+105
+ 22
+195
+135
+ 47
+153
+  94
+ 21
+ 60
+115
+ 77
+ 39
+ 44
+ 80
+ 36
+121
+ 17
+ 57
+240
+ 95
+229
+220
+100
+ 45
+  78
+ 58
+210
+171
+ 13
+ 31
+ 70
+126
+ 55
+112
+ 31
+221
+132
+ 16
+190
+ 65
+ 77
+248
+  81
+ 14
+ 53
+150
+ 86
+103
+165
+ 41
+118
+199
+183
+133
+ 79
+ 20
+ 32
+  3
+202
+ 41
+ 254
+223
+ 17
+ 26
+ 63
+134
+ 41
\ No newline at end of file