teratail
回答率
85.47%
質問するログイン新規登録
トップPythonに関する質問python K-meansクラスタリングのエラー　※ご教示お願い致します。

編集履歴

質問編集履歴

4

コードの位置

2022/10/19 01:19

投稿

mable
mable

スコア2

test CHANGED
File without changes
test CHANGED
@@ -153,9 +153,9 @@
153
153
  num = num + 1
154
154
 
155
155
  dfh = pd.read_csv("point.csv",names=["cluster_id","latitude","longitude"])
156
- B = pd.read_csv("pps.csv",usecols=["#people"])
156
+ B = pd.read_csv("pps.csv",usecols=["people"])
157
- #dfh2= pd.DataFrame(B['#people'])
157
+ #dfh2= pd.DataFrame(B['people'])
158
- dfh['#people']= B
158
+ dfh['people']= B
159
159
  dfh.to_csv("point.csv")
160
160
  ```
161
161
 
PythonExcel

3

コードを戻した

2022/10/18 06:29

投稿

mable
mable

スコア2

test CHANGED
File without changes
test CHANGED
@@ -49,9 +49,98 @@
49
49
  ```python
50
50
  ソースコード
51
51
 
52
+ #1回目の訪問先の抽出
53
+
54
+ from matplotlib import pyplot as plt
55
+ from sklearn import datasets, preprocessing
56
+ from sklearn.cluster import KMeans
57
+ import numpy as np
58
+ import pandas as pd
59
+ import cartopy.crs as ccrs
60
+ import cartopy.io.shapereader as shpreader
61
+
62
+ pd.set_option('display.max_rows',600)
63
+ #前処理後のcsvを読み込み
64
+ yomi=pd.read_csv("simulationkai.csv")
65
+ df=pd.read_csv("simulationkai.csv",usecols=["longitude","latitude"])
66
+
67
+ # DataFrameに変換
68
+ print(df.head())
69
+ # データの整形
70
+ X = df
71
+
72
+
73
+ # クラスタリング
74
+ cls = KMeans(n_clusters=4)
75
+
76
+ result = cls.fit(X)
77
+ X['cluster'] = result.labels_
78
+ PC= pd.DataFrame(X['cluster'])
79
+ PC
80
+ df.head()
81
+ #yomiのデータフレームにcluster(クラスタ番号)を追加する
82
+ yomi['cluster_id']=PC
83
+ yomi
84
+
85
+ #yomi(元データにクラスタ番号を追加したもの)をallclsdata.csvに保存する
86
+ yomi.to_csv("allclsdata.csv")
87
+
88
+ D = X.sort_values(by="cluster")
89
+ D = D.drop_duplicates(subset='cluster')
90
+ D
91
+ # 各クラスタ内のデータ数をカウント
92
+ V = X['cluster'].value_counts()
93
+ V
94
+ # 各クラスタの番号とデータ数をclsvalue.csvに保存
95
+ V.to_csv("clsvalue.csv")
96
+
97
+
98
+ # クラスタの重心確認
99
+ C = pd.DataFrame(result.cluster_centers_)
100
+ C
101
+
102
+ C.iloc[0, :]
103
+
104
+
105
+ lat= X['latitude'].tolist()
106
+ lon= X['longitude'].tolist()
107
+
108
+ clat=C[0].tolist()
109
+ clon=C[1].tolist()
110
+
111
+
112
+ #から1800までのクラスタのデータからそれぞれ同じ被験者の重複を省いてデータ人数を取得して順番にCSVにまとめる
113
+ from csv import writer
114
+ #pp = pd.DataFrame
115
+ #ppi = pd.DataFrame
116
+ #yomiからWhile文でN番目のクラスタのデータのみ抽出
117
+ i = 0
118
+ while i <= 3:
119
+ yomic = yomi[yomi['cluster_id']== i]
120
+ #N番目のクラスタdfから被験者idの重複を消す
121
+ yomics = yomic.drop_duplicates(subset=["id_questionnaire"])
122
+ #N番目の加工後データの行数をCSVに付け足す
123
+ #file = [i,len(yomics)]
124
+ #ppi = pp.append([file], ignore_index=True)
125
+ #ppi.to_csv("pp.csv")
126
+ list_data=[i,len(yomics)]
127
+ with open('pp.csv', 'a', newline='') as f_object:
128
+ writer_object = writer(f_object)
129
+ writer_object.writerow(list_data)
130
+ f_object.close()
131
+ i = i + 1
132
+ #else:
133
+ #ppi.to_csv("pp.csv")
134
+
135
+ #pp.csv内の人数を降順にしたものをpps.csvに保存
136
+ PP = pd.read_csv("pp.csv",names=["cls","people"])
137
+ T = PP.sort_values(by=["people"],ascending=False)
138
+ T.to_csv("pps.csv")
139
+ PP.to_csv("pp.csv")
140
+
52
141
  #pps.csvの上から順番にクラスタ番号を引き出してその番号の座標をCから引き出す
53
142
  num = 0
54
- while num <= 99:
143
+ while num <= 3:
55
144
  Tn = T.iloc[num,0]
56
145
  #Tno = Tn + 1
57
146
  Cn = C.iloc[Tn,0]
@@ -64,9 +153,9 @@
64
153
  num = num + 1
65
154
 
66
155
  dfh = pd.read_csv("point.csv",names=["cluster_id","latitude","longitude"])
67
- B = pd.read_csv("pps.csv",usecols=["people"])
156
+ B = pd.read_csv("pps.csv",usecols=["#people"])
68
- #dfh2= pd.DataFrame(B['people'])
157
+ #dfh2= pd.DataFrame(B['#people'])
69
- dfh['people']= B
158
+ dfh['#people']= B
70
159
  dfh.to_csv("point.csv")
71
160
  ```
72
161
 
PythonExcel

2

最初のエラーを記載

2022/10/18 06:19

投稿

mable
mable

スコア2

test CHANGED
File without changes
test CHANGED
@@ -13,43 +13,32 @@
13
13
  エラーメッセージ
14
14
 
15
15
 
16
- >>> #pps.csvの上から順番にクラスタ番号を引き出してその番号の座標をCから引き出す
17
- >>> num = 0
18
- >>> while num <= 3:
19
- ... Tn = T.iloc[num,0]
20
- ... #Tno = Tn + 1
21
- ... Cn = C.iloc[Tn,0]
22
- ... Cn2 = C.iloc[Tn,1]
23
- ... list_data2=[Tn,Cn,Cn2]
24
- ... with open('point.csv', 'a', newline='') as f_object:
25
- ... writer_object = writer(f_object)
16
+ C:\datasyori>python hoge.py
26
- ... writer_object.writerow(list_data2)
27
- ... f_object.close()
28
- ... num = num + 1
17
+ latitude longitude
29
- ...
18
+ 0 35.693590 139.712202
19
+ 1 35.693497 139.712096
20
+ 2 35.693217 139.712261
21
+ 3 35.693549 139.712430
22
+ 4 35.693621 139.712501
30
23
  Traceback (most recent call last):
31
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 769, in _validate_tuple_indexer
24
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 769, in _validate_tuple_indexer
32
- self._validate_key(k, i)
25
+ self._validate_key(k, i)
33
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1378, in _validate_key
26
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1378, in _validate_key
34
- raise ValueError(f"Can only index by location with a [{self._valid_types}]")
27
+ raise ValueError(f"Can only index by location with a [{self._valid_types}]")
35
28
  ValueError: Can only index by location with a [integer, integer slice (START point is INCLUDED, END point is EXCLUDED), listlike of integers, boolean array]
36
29
 
37
30
  The above exception was the direct cause of the following exception:
38
31
 
39
32
  Traceback (most recent call last):
40
- File "<stdin>", line 4, in <module>
33
+ File "C:\datasyori\hoge.py", line 95, in <module>
34
+ Cn = C.iloc[Tn,0]
41
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 961, in __getitem__
35
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 961, in __getitem__
42
- return self._getitem_tuple(key)
36
+ return self._getitem_tuple(key)
43
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1458, in _getitem_tuple
37
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1458, in _getitem_tuple
44
- tup = self._validate_tuple_indexer(tup)
38
+ tup = self._validate_tuple_indexer(tup)
45
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 771, in _validate_tuple_indexer
39
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 771, in _validate_tuple_indexer
46
- raise ValueError(
40
+ raise ValueError(
47
41
  ValueError: Location based indexing can only have [integer, integer slice (START point is INCLUDED, END point is EXCLUDED), listlike of integers, boolean array] types
48
- >>> dfh = pd.read_csv("point.csv",names=["cluster_id","latitude","longitude"])
49
- >>> B = pd.read_csv("pps.csv",usecols=["people"])
50
- >>> #dfh2= pd.DataFrame(B['people'])
51
- >>> dfh['people']= B
52
- >>> dfh.to_csv("point.csv")
53
42
 
54
43
 
55
44
  ```
@@ -59,94 +48,6 @@
59
48
 
60
49
  ```python
61
50
  ソースコード
62
- #1回目の訪問先の抽出
63
-
64
- from matplotlib import pyplot as plt
65
- from sklearn import datasets, preprocessing
66
- from sklearn.cluster import KMeans
67
- import numpy as np
68
- import pandas as pd
69
- import cartopy.crs as ccrs
70
- import cartopy.io.shapereader as shpreader
71
-
72
- pd.set_option('display.max_rows',600)
73
- #前処理後のcsvを読み込み
74
- yomi=pd.read_csv("simulationkai.csv")
75
- df=pd.read_csv("simulationkai.csv",usecols=["longitude","latitude"])
76
-
77
- # DataFrameに変換
78
- print(df.head())
79
- # データの整形
80
- X = df
81
-
82
-
83
- # クラスタリング
84
- cls = KMeans(n_clusters=100)
85
-
86
- result = cls.fit(X)
87
- X['cluster'] = result.labels_
88
- PC= pd.DataFrame(X['cluster'])
89
- PC
90
- df.head()
91
- #yomiのデータフレームにcluster(クラスタ番号)を追加する
92
- yomi['cluster_id']=PC
93
- yomi
94
-
95
- #yomi(元データにクラスタ番号を追加したもの)をallclsdata.csvに保存する
96
- yomi.to_csv("allclsdata.csv")
97
-
98
- D = X.sort_values(by="cluster")
99
- D = D.drop_duplicates(subset='cluster')
100
- D
101
- # 各クラスタ内のデータ数をカウント
102
- V = X['cluster'].value_counts()
103
- V
104
- # 各クラスタの番号とデータ数をclsvalue.csvに保存
105
- V.to_csv("clsvalue.csv")
106
-
107
-
108
- # クラスタの重心確認
109
- C = pd.DataFrame(result.cluster_centers_)
110
- C
111
-
112
- C.iloc[0, :]
113
-
114
-
115
- lat= X['latitude'].tolist()
116
- lon= X['longitude'].tolist()
117
-
118
- clat=C[0].tolist()
119
- clon=C[1].tolist()
120
-
121
-
122
- #から100までのクラスタのデータからそれぞれ同じ被験者の重複を省いてデータ人数を取得して順番にCSVにまとめる
123
- from csv import writer
124
- #pp = pd.DataFrame
125
- #ppi = pd.DataFrame
126
- #yomiからWhile文でN番目のクラスタのデータのみ抽出
127
- i = 0
128
- while i <= 99:
129
- yomic = yomi[yomi['cluster_id']== i]
130
- #N番目のクラスタdfから被験者idの重複を消す
131
- yomics = yomic.drop_duplicates(subset=["id_questionnaire"])
132
- #N番目の加工後データの行数をCSVに付け足す
133
- #file = [i,len(yomics)]
134
- #ppi = pp.append([file], ignore_index=True)
135
- #ppi.to_csv("pp.csv")
136
- list_data=[i,len(yomics)]
137
- with open('pp.csv', 'a', newline='') as f_object:
138
- writer_object = writer(f_object)
139
- writer_object.writerow(list_data)
140
- f_object.close()
141
- i = i + 1
142
- #else:
143
- #ppi.to_csv("pp.csv")
144
-
145
- #pp.csv内の人数を降順にしたものをpps.csvに保存
146
- PP = pd.read_csv("pp.csv",names=["cls","people"])
147
- T = PP.sort_values(by=["people"],ascending=False)
148
- T.to_csv("pps.csv")
149
- PP.to_csv("pp.csv")
150
51
 
151
52
  #pps.csvの上から順番にクラスタ番号を引き出してその番号の座標をCから引き出す
152
53
  num = 0
@@ -171,8 +72,7 @@
171
72
 
172
73
  ### 試したこと
173
74
 
174
- peopleの値がみつからないなどと書いてあったのでしっかりと確認しましたがデータにもあるのでよく理解できない。
175
- BがdefineなどあるがBの定義もしているのでどこが違うのでしょうか。
75
+ 勉強不足でエラーの内容が全く分かっていません
176
76
 
177
77
  ### 補足情報（FW/ツールのバージョンなど）
178
78
  Python 3.10.4 (tags/v3.10.4:9d38120, Mar 23 2022, 23:13:41) [MSC v.1929 64 bit (AMD64)] on win32
PythonExcel

1

新たなコード

2022/10/18 05:17

投稿

mable
mable

スコア2

test CHANGED
File without changes
test CHANGED
@@ -12,62 +12,43 @@
12
12
  ```python
13
13
  エラーメッセージ
14
14
 
15
+
15
- #pps.csvの上から順番にクラスタ番号を引き出してその番号の座標をCから引き出す
16
+ >>> #pps.csvの上から順番にクラスタ番号を引き出してその番号の座標をCから引き出す
16
17
  >>> num = 0
17
- >>> while num <= 99:
18
+ >>> while num <= 3:
18
- ... Tn = T.iloc[num,0]
19
+ ... Tn = T.iloc[num,0]
19
- ... #Tno = Tn + 1
20
+ ... #Tno = Tn + 1
20
- ... Cn = C.iloc[Tn,0]
21
+ ... Cn = C.iloc[Tn,0]
21
- ... Cn2 = C.iloc[Tn,1]
22
+ ... Cn2 = C.iloc[Tn,1]
22
- ... list_data2=[Tn,Cn,Cn2]
23
+ ... list_data2=[Tn,Cn,Cn2]
23
- ... with open('point.csv', 'a', newline='') as f_object:
24
+ ... with open('point.csv', 'a', newline='') as f_object:
24
- ... writer_object = writer(f_object)
25
+ ... writer_object = writer(f_object)
25
- ... writer_object.writerow(list_data2)
26
+ ... writer_object.writerow(list_data2)
26
- ... f_object.close()
27
+ ... f_object.close()
27
- ... num = num + 1
28
+ ... num = num + 1
28
29
  ...
29
30
  Traceback (most recent call last):
30
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 769, in _validate_tuple_indexer
31
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 769, in _validate_tuple_indexer
31
- self._validate_key(k, i)
32
+ self._validate_key(k, i)
32
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1378, in _validate_key
33
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1378, in _validate_key
33
- raise ValueError(f"Can only index by location with a [{self._valid_types}]")
34
+ raise ValueError(f"Can only index by location with a [{self._valid_types}]")
34
35
  ValueError: Can only index by location with a [integer, integer slice (START point is INCLUDED, END point is EXCLUDED), listlike of integers, boolean array]
35
36
 
36
37
  The above exception was the direct cause of the following exception:
37
38
 
38
39
  Traceback (most recent call last):
39
- File "<stdin>", line 4, in <module>
40
+ File "<stdin>", line 4, in <module>
40
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 961, in __getitem__
41
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 961, in __getitem__
41
- return self._getitem_tuple(key)
42
+ return self._getitem_tuple(key)
42
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1458, in _getitem_tuple
43
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 1458, in _getitem_tuple
43
- tup = self._validate_tuple_indexer(tup)
44
+ tup = self._validate_tuple_indexer(tup)
44
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 771, in _validate_tuple_indexer
45
+ File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\core\indexing.py", line 771, in _validate_tuple_indexer
45
- raise ValueError(
46
+ raise ValueError(
46
47
  ValueError: Location based indexing can only have [integer, integer slice (START point is INCLUDED, END point is EXCLUDED), listlike of integers, boolean array] types
47
48
  >>> dfh = pd.read_csv("point.csv",names=["cluster_id","latitude","longitude"])
48
- >>> B = pd.read_csv("pps.csv",usecols=["#people"])
49
+ >>> B = pd.read_csv("pps.csv",usecols=["people"])
49
- Traceback (most recent call last):
50
- File "<stdin>", line 1, in <module>
51
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\util\_decorators.py", line 311, in wrapper
52
- return func(*args, **kwargs)
53
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\readers.py", line 680, in read_csv
54
- return _read(filepath_or_buffer, kwds)
55
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\readers.py", line 575, in _read
56
- parser = TextFileReader(filepath_or_buffer, **kwds)
57
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\readers.py", line 933, in __init__
58
- self._engine = self._make_engine(f, self.engine)
59
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\readers.py", line 1235, in _make_engine
60
- return mapping[engine](f, **self.options)
61
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\c_parser_wrapper.py", line 131, in __init__
62
- self._validate_usecols_names(usecols, self.orig_names)
63
- File "C:\Users\mable\AppData\Local\Programs\Python\Python310\lib\site-packages\pandas\io\parsers\base_parser.py", line 913, in _validate_usecols_names
64
- raise ValueError(
65
- ValueError: Usecols do not match columns, columns expected but not found: ['#people']
66
- >>> #dfh2= pd.DataFrame(B['#people'])
50
+ >>> #dfh2= pd.DataFrame(B['people'])
67
- >>> dfh['#people']= B
51
+ >>> dfh['people']= B
68
- Traceback (most recent call last):
69
- File "<stdin>", line 1, in <module>
70
- NameError: name 'B' is not defined
71
52
  >>> dfh.to_csv("point.csv")
72
53
 
73
54
 
@@ -182,9 +163,9 @@
182
163
  num = num + 1
183
164
 
184
165
  dfh = pd.read_csv("point.csv",names=["cluster_id","latitude","longitude"])
185
- B = pd.read_csv("pps.csv",usecols=["#people"])
166
+ B = pd.read_csv("pps.csv",usecols=["people"])
186
- #dfh2= pd.DataFrame(B['#people'])
167
+ #dfh2= pd.DataFrame(B['people'])
187
- dfh['#people']= B
168
+ dfh['people']= B
188
169
  dfh.to_csv("point.csv")
189
170
  ```
190
171
 
PythonExcel