[已解决]py文件idle打不开，求助

linkz

我想请问一下，我这个代码使用pycharm写的，在pycharm上也能跑。但是为什么用python3.7自带的idle却打不开
代码在附件，因为有一个csv文件，所以只能打包发 呜呜呜

最佳答案

月排行榜 / 总排行榜

XiaoPaiShen

2020-1-12 08:37:05

在 main.py 中的注释中，有些看起来像斜体的字母，在 idle 中不支持，我把他们替换后就可以打开了

1. import random
   
2. from copy import deepcopy
   
3. from itertools import groupby
   
4. from statistics import median
   
5. 
   
6. # This function should have one parameter, a file name (including, if necessary, its path).
   
7. # The function should read this CSV file and return a matrix (list of lists) in which a row
   
8. # in the file is a row in the matrix. If the file has N rows, the matrix should have N
   
9. # elements (each element is a list). Notice that in CSV files a comma separates columns
   
10. # (CSV = comma separated values). You can assume the file will contain solely numeric values
    
11. # (and commas, of course) with no quotes.
    
12. def load_from_csv(fileName):
    
13.     # Use list to save matrix
    
14.     res = []
    
15.     # Use a loop structure to read each line in the data file.
    
16.     with open(fileName) as f:
    
17.         lines = f.readlines()
    
18.         for l in lines:
    
19.             res.append(l.strip().split(','))
    
20.     return res
    
21. 
    
22. 
    
23. # This function should have two parameters, both of them lists. It should return the Manhattan
    
24. # distance between the two lists. For details about this distance, read the appendix.
    
25. def get_distance(l1, l2):
    
26.     # Use a judgment structure to determine whether the length of list1 and list2 are the same
    
27.     if len(l1) != len(l2):
    
28.         print('Error! List1 and List2 are not the same length!')
    
29.         return -1
    
30.     else:
    
31.         d = 0
    
32.         # Use a loop structure look into each index of two lists
    
33.         for i in range(len(l1)):
    
34.             d += abs(l1[i] - l2[i])
    
35.         return d
    
36. 
    
37. 
    
38. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
39. # look into all the elements of the data matrix in this column number, and return the highest value.
    
40. def get_max(m, c):
    
41.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
42.     if c >= len(m[0]):
    
43.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
44.         return -1
    
45.     else:
    
46.         # Loop through each row of a matrix using a loop structure
    
47.         maxValue = m[0][c]
    
48.         for r in m:
    
49.             # Determine if the current value is greater than the maximum
    
50.             if r[c] > maxValue:
    
51.                 maxValue = r[c]
    
52.         return maxValue
    
53. 
    
54. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
55. # look into all the elements of the data matrix in this column number, and return the lowest value.
    
56. def get_min(m, c):
    
57.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
58.     if c >= len(m[0]):
    
59.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
60.         return -1
    
61.     else:
    
62.         # Loop through each row of a matrix using a loop structure
    
63.         minValue = m[0][c]
    
64.         for r in m:
    
65.             # Determines whether the current value is smaller than the minimum value
    
66.             if r[c] < minValue:
    
67.                 minValue = r[c]
    
68.         return minValue
    
69. 
    
70. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
71. # look into all the elements of the data matrix in this column number, and return the average of this column number.
    
72. def get_mean(m, c):
    
73.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
74.     if c >= len(m[0]):
    
75.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
76.         return -1
    
77.     else:
    
78.         # Loop through each row of a matrix using a loop structure
    
79.         mean = 0
    
80.         for r in m:
    
81.             mean += float(r[c])
    
82.         return mean/len(m)
    
83. 
    
84. # This function should take one parameter, a matrix (list of lists). It should return a matrix containing
    
85. # the standardised version of the matrix passed as a parameter. This function should somehow use the get_max
    
86. # and get_min functions. For details on how to standardise a matrix, read the appendix.
    
87. def get_standardised_matrix(m):
    
88.     maxList = [ get_max(m,c) for c in range(len(m[0]))]
    
89.     minList = [ get_min(m,c) for c in range(len(m[0]))]
    
90.     meanList = [ get_mean(m,c) for c in range(len(m[0]))]
    
91.     lists = []
    
92.     for r in m:
    
93.         l = []
    
94.         for c, i in enumerate(r):
    
95.             l.append((float(i) - float(meanList[c]))/(float(maxList[c])-float(minList[c])))
    
96.         lists.append(l)
    
97.     return lists
    
98. 
    
99. 
    
100. # This function should have two parameters: a matrix (list of lists), and a column number. It should return
     
101. #  the median of the values in the data matrix at the column number passed as a parameter. Details about
     
102. # median can be easily found online, eg. https://en.wikipedia.org/wiki/Median.
     
103. def get_median(m, c):
     
104.     l = [float(r[c]) for r in m]
     
105.     return median(l)
     
106. 
     
107. 
     
108. # This function should have three parameters: (i) a matrix (list of lists), (iii) the list S, (iii) the value
     
109. # of K. This function should implement the Step 6 of the algorithm described in the appendix. It should return
     
110. # a list containing K elements, c1, c2, ... , cK. Clearly, each of these elements is also a list.
     
111. def get_centroids(m, S, K):
     
112.     res = []
     
113.     for i in range(K):
     
114.         c = []
     
115.         # select those rows that have been assigned to cluster k.
     
116.         m_i = [x for index, x in enumerate(m) if S[index] == i]
     
117.         # Each element j of ckshould be equal to the median of the column D'j
     
118.         for j in range(len(m[0])):
     
119.             c.append(get_median(m_i, j))
     
120.         # Update ck.
     
121.         res.append(c)
     
122.     return res
     
123. 
     
124. 
     
125. # This function should have two parameters: a data matrix (list of lists) and the number of groups to be
     
126. # created (K). This function follows the algorithm described in the appendix. It should return a list
     
127. # S (defined in the appendix). This function should use the other functions you wrote as much as possible.
     
128. # Do not keep repeating code you already wrote.
     
129. def get_groups(D, K):
     
130.     S = []
     
131.     # Select K different rows from the data matrix at random.
     
132.     c_list = deepcopy(random.sample(D, K))
     
133.     while True:
     
134.         S_temp = []
     
135.         for i in range(len(D)):
     
136.             # Calculate the Manhattan distance between data row D'i and each of the lists c1, c2, ... , cK. cK
     
137.             dist = get_distance(D[i], c_list[0])
     
138.             s_i = 0
     
139.             for index, c_i in enumerate(c_list):
     
140.                 if get_distance(D[i], c_i) < dist:
     
141.                     dist = get_distance(D[i], c_i)
     
142.                     s_i = index
     
143.             # Assign the row D'i to the cluster of the nearest c
     
144.             S_temp.append(s_i)
     
145.         #  If the previous step does not change S, stop
     
146.         if S_temp == S:
     
147.             break
     
148.         else:
     
149.             S = deepcopy(S_temp)
     
150.         c_list = get_centroids(D, S, K)
     
151.     return S
     
152. 
     
153. 
     
154. def run_test():
     
155.     # load data file
     
156.     fileName = 'Data(1).csv'
     
157.     m = load_from_csv(fileName)
     
158.     # get standardised matrix
     
159.     D = get_standardised_matrix(m)
     
160.     res = []
     
161.     # run experiments with K = 2, 3, 4, 5, 6.
     
162.     for K in range(2,7):
     
163.         res.append(get_groups(D, K))
     
164.     # print the result
     
165.     for K in range(2, 7):
     
166.         print("="*100)
     
167.         print("K = " + str(K) + ":")
     
168.         print(res[K-2])
     
169.         # show how many entities (wines) have been assigned to each group
     
170.         for key, group in groupby(sorted(res[K-2])):
     
171.             print("group " + str(key) + ": " + str(len(list(group))))
     
172.                
     
173. if __name__ == "__main__":
     
174.     # test::load_from_csv(fileName)
     
175.     # fileName = 'Data(1).csv'
     
176.     # m = load_from_csv(fileName)
     
177. 
     
178.     # # test::get_distance(l1, l2)
     
179.     # l1 = [1,2,3]
     
180.     # l2 = [4,5,6]
     
181.     # print(get_distance(l1, l2))
     
182. 
     
183.     # c = 1
     
184.     # # test::get_max(m, c)
     
185.     # maxValue = get_max(m, c)
     
186.     # print(maxValue)
     
187. 
     
188.     # # test::get_min(m, c)
     
189.     # minValue = get_min(m, c)
     
190.     # print(minValue)
     
191.    
     
192.     # # test::get_mean(m, c)
     
193.     # meanValue = get_mean(m, c)
     
194.     # print(meanValue)
     
195. 
     
196.     # # test::get_standardised_matrix(m)
     
197.     # D = get_standardised_matrix(m)
     
198.     # print(D)
     
199. 
     
200.     # # test::get_median(m, c)
     
201.     # print(get_median(m, c))
     
202. 
     
203.     # K = 2
     
204.     # S = [0, 0, 0, 1, 1, 1]
     
205.     # # test::get_centroids(m, S, K)
     
206.     # c_k = get_centroids(m, S, K)
     
207.     # print(c_k)
     
208. 
     
209.     # # test::get_groups(D, K)
     
210.     # S = get_groups(m, K)
     
211.     # print(S)
     
212. 
     
213.     # test::run_test()
     
214.     run_test()

复制代码

跳转到最佳答案楼层

Judie

哇 我unpack出来有很多个file诶？

哇...

linkz

Judie 发表于 2020-1-12 02:54
哇 我unpack出来有很多个file诶？

哇...

我打开只有两个诶，就那个data和main，你能跑main.py的脚本吗？

Judie

linkz 发表于 2020-1-11 14:50
我打开只有两个诶，就那个data和main，你能跑main.py的脚本吗？

不可以 但我用notepad++可以打开那个main
._main的那个打开就是那个specify file encoding页面 我点ok就说是fail什么的

linkz

Judie 发表于 2020-1-12 03:56
不可以 但我用notepad++可以打开那个main
._main的那个打开就是那个specify file encoding页面 我点ok ...

我用pycharm也可以跑那个main，但是用idle就不能跑，是代码有问题吗。。

XiaoPaiShen

在 main.py 中的注释中，有些看起来像斜体的字母，在 idle 中不支持，我把他们替换后就可以打开了

1. import random
   
2. from copy import deepcopy
   
3. from itertools import groupby
   
4. from statistics import median
   
5. 
   
6. # This function should have one parameter, a file name (including, if necessary, its path).
   
7. # The function should read this CSV file and return a matrix (list of lists) in which a row
   
8. # in the file is a row in the matrix. If the file has N rows, the matrix should have N
   
9. # elements (each element is a list). Notice that in CSV files a comma separates columns
   
10. # (CSV = comma separated values). You can assume the file will contain solely numeric values
    
11. # (and commas, of course) with no quotes.
    
12. def load_from_csv(fileName):
    
13.     # Use list to save matrix
    
14.     res = []
    
15.     # Use a loop structure to read each line in the data file.
    
16.     with open(fileName) as f:
    
17.         lines = f.readlines()
    
18.         for l in lines:
    
19.             res.append(l.strip().split(','))
    
20.     return res
    
21. 
    
22. 
    
23. # This function should have two parameters, both of them lists. It should return the Manhattan
    
24. # distance between the two lists. For details about this distance, read the appendix.
    
25. def get_distance(l1, l2):
    
26.     # Use a judgment structure to determine whether the length of list1 and list2 are the same
    
27.     if len(l1) != len(l2):
    
28.         print('Error! List1 and List2 are not the same length!')
    
29.         return -1
    
30.     else:
    
31.         d = 0
    
32.         # Use a loop structure look into each index of two lists
    
33.         for i in range(len(l1)):
    
34.             d += abs(l1[i] - l2[i])
    
35.         return d
    
36. 
    
37. 
    
38. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
39. # look into all the elements of the data matrix in this column number, and return the highest value.
    
40. def get_max(m, c):
    
41.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
42.     if c >= len(m[0]):
    
43.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
44.         return -1
    
45.     else:
    
46.         # Loop through each row of a matrix using a loop structure
    
47.         maxValue = m[0][c]
    
48.         for r in m:
    
49.             # Determine if the current value is greater than the maximum
    
50.             if r[c] > maxValue:
    
51.                 maxValue = r[c]
    
52.         return maxValue
    
53. 
    
54. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
55. # look into all the elements of the data matrix in this column number, and return the lowest value.
    
56. def get_min(m, c):
    
57.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
58.     if c >= len(m[0]):
    
59.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
60.         return -1
    
61.     else:
    
62.         # Loop through each row of a matrix using a loop structure
    
63.         minValue = m[0][c]
    
64.         for r in m:
    
65.             # Determines whether the current value is smaller than the minimum value
    
66.             if r[c] < minValue:
    
67.                 minValue = r[c]
    
68.         return minValue
    
69. 
    
70. # This function should have two parameters, a matrix (list of lists) and a column number. It should
    
71. # look into all the elements of the data matrix in this column number, and return the average of this column number.
    
72. def get_mean(m, c):
    
73.     # Use a judgment structure to determine if the column number is less than the number of columns in the matrix
    
74.     if c >= len(m[0]):
    
75.         print('Error! The column number should be smaller than the number of columns in the matrix')
    
76.         return -1
    
77.     else:
    
78.         # Loop through each row of a matrix using a loop structure
    
79.         mean = 0
    
80.         for r in m:
    
81.             mean += float(r[c])
    
82.         return mean/len(m)
    
83. 
    
84. # This function should take one parameter, a matrix (list of lists). It should return a matrix containing
    
85. # the standardised version of the matrix passed as a parameter. This function should somehow use the get_max
    
86. # and get_min functions. For details on how to standardise a matrix, read the appendix.
    
87. def get_standardised_matrix(m):
    
88.     maxList = [ get_max(m,c) for c in range(len(m[0]))]
    
89.     minList = [ get_min(m,c) for c in range(len(m[0]))]
    
90.     meanList = [ get_mean(m,c) for c in range(len(m[0]))]
    
91.     lists = []
    
92.     for r in m:
    
93.         l = []
    
94.         for c, i in enumerate(r):
    
95.             l.append((float(i) - float(meanList[c]))/(float(maxList[c])-float(minList[c])))
    
96.         lists.append(l)
    
97.     return lists
    
98. 
    
99. 
    
100. # This function should have two parameters: a matrix (list of lists), and a column number. It should return
     
101. #  the median of the values in the data matrix at the column number passed as a parameter. Details about
     
102. # median can be easily found online, eg. https://en.wikipedia.org/wiki/Median.
     
103. def get_median(m, c):
     
104.     l = [float(r[c]) for r in m]
     
105.     return median(l)
     
106. 
     
107. 
     
108. # This function should have three parameters: (i) a matrix (list of lists), (iii) the list S, (iii) the value
     
109. # of K. This function should implement the Step 6 of the algorithm described in the appendix. It should return
     
110. # a list containing K elements, c1, c2, ... , cK. Clearly, each of these elements is also a list.
     
111. def get_centroids(m, S, K):
     
112.     res = []
     
113.     for i in range(K):
     
114.         c = []
     
115.         # select those rows that have been assigned to cluster k.
     
116.         m_i = [x for index, x in enumerate(m) if S[index] == i]
     
117.         # Each element j of ckshould be equal to the median of the column D'j
     
118.         for j in range(len(m[0])):
     
119.             c.append(get_median(m_i, j))
     
120.         # Update ck.
     
121.         res.append(c)
     
122.     return res
     
123. 
     
124. 
     
125. # This function should have two parameters: a data matrix (list of lists) and the number of groups to be
     
126. # created (K). This function follows the algorithm described in the appendix. It should return a list
     
127. # S (defined in the appendix). This function should use the other functions you wrote as much as possible.
     
128. # Do not keep repeating code you already wrote.
     
129. def get_groups(D, K):
     
130.     S = []
     
131.     # Select K different rows from the data matrix at random.
     
132.     c_list = deepcopy(random.sample(D, K))
     
133.     while True:
     
134.         S_temp = []
     
135.         for i in range(len(D)):
     
136.             # Calculate the Manhattan distance between data row D'i and each of the lists c1, c2, ... , cK. cK
     
137.             dist = get_distance(D[i], c_list[0])
     
138.             s_i = 0
     
139.             for index, c_i in enumerate(c_list):
     
140.                 if get_distance(D[i], c_i) < dist:
     
141.                     dist = get_distance(D[i], c_i)
     
142.                     s_i = index
     
143.             # Assign the row D'i to the cluster of the nearest c
     
144.             S_temp.append(s_i)
     
145.         #  If the previous step does not change S, stop
     
146.         if S_temp == S:
     
147.             break
     
148.         else:
     
149.             S = deepcopy(S_temp)
     
150.         c_list = get_centroids(D, S, K)
     
151.     return S
     
152. 
     
153. 
     
154. def run_test():
     
155.     # load data file
     
156.     fileName = 'Data(1).csv'
     
157.     m = load_from_csv(fileName)
     
158.     # get standardised matrix
     
159.     D = get_standardised_matrix(m)
     
160.     res = []
     
161.     # run experiments with K = 2, 3, 4, 5, 6.
     
162.     for K in range(2,7):
     
163.         res.append(get_groups(D, K))
     
164.     # print the result
     
165.     for K in range(2, 7):
     
166.         print("="*100)
     
167.         print("K = " + str(K) + ":")
     
168.         print(res[K-2])
     
169.         # show how many entities (wines) have been assigned to each group
     
170.         for key, group in groupby(sorted(res[K-2])):
     
171.             print("group " + str(key) + ": " + str(len(list(group))))
     
172.                
     
173. if __name__ == "__main__":
     
174.     # test::load_from_csv(fileName)
     
175.     # fileName = 'Data(1).csv'
     
176.     # m = load_from_csv(fileName)
     
177. 
     
178.     # # test::get_distance(l1, l2)
     
179.     # l1 = [1,2,3]
     
180.     # l2 = [4,5,6]
     
181.     # print(get_distance(l1, l2))
     
182. 
     
183.     # c = 1
     
184.     # # test::get_max(m, c)
     
185.     # maxValue = get_max(m, c)
     
186.     # print(maxValue)
     
187. 
     
188.     # # test::get_min(m, c)
     
189.     # minValue = get_min(m, c)
     
190.     # print(minValue)
     
191.    
     
192.     # # test::get_mean(m, c)
     
193.     # meanValue = get_mean(m, c)
     
194.     # print(meanValue)
     
195. 
     
196.     # # test::get_standardised_matrix(m)
     
197.     # D = get_standardised_matrix(m)
     
198.     # print(D)
     
199. 
     
200.     # # test::get_median(m, c)
     
201.     # print(get_median(m, c))
     
202. 
     
203.     # K = 2
     
204.     # S = [0, 0, 0, 1, 1, 1]
     
205.     # # test::get_centroids(m, S, K)
     
206.     # c_k = get_centroids(m, S, K)
     
207.     # print(c_k)
     
208. 
     
209.     # # test::get_groups(D, K)
     
210.     # S = get_groups(m, K)
     
211.     # print(S)
     
212. 
     
213.     # test::run_test()
     
214.     run_test()

复制代码

心驰神往

python能写.exe可执行程序吗