使用Python将excel文件中的数据提取到txt中

 1 # -*- coding: UTF-8 -*-
 2 import sys
 3 import json
 4  
 5 import pandas as pd
 6 import numpy as np
 7  
 8 filename=r‘C:\Users\lenovo\Desktop\that.txt‘ 
 9 raw_score = r‘C:\Users\lenovo\Desktop\data1.xlsx‘
10 #读取excel保存成txt格式
11 excel_file = pd.read_excel(raw_score)
12 excel_file.to_csv(filename, sep=‘ ‘, index=False)

 1 import numpy as np
 2 import matplotlib.pyplot as plt
 3  
 4 # 加载数据
 5 def loadDataSet(fileName):
 6     data = np.loadtxt(fileName,delimiter=‘ ‘)
 7     return data
 8  
 9 # 欧氏距离计算
10 def distEclud(x,y):
11     return np.sqrt(np.sum((x-y)**2))  # 计算欧氏距离
12  
13 # 为给定数据集构建一个包含K个随机质心的集合
14 def randCent(dataSet,k):
15     m,n = dataSet.shape
16     centroids = np.zeros((k,n))
17     for i in range(k):
18         index = int(np.random.uniform(0,m)) #
19         centroids[i,:] = dataSet[index,:]
20     return centroids
21  
22 # k均值聚类
23 def KMeans(dataSet,k):
24  
25     m = np.shape(dataSet)[0]  #行的数目
26     # 第一列存样本属于哪一簇
27     # 第二列存样本的到簇的中心点的误差
28     clusterAssment = np.mat(np.zeros((m,2)))
29     clusterChange = True
30  
31     # 第1步 初始化centroids
32     centroids = randCent(dataSet,k)
33     while clusterChange:
34         clusterChange = False
35  
36         # 遍历所有的样本（行数）
37         for i in range(m):
38             minDist = 100000.0
39             minIndex = -1
40  
41             # 遍历所有的质心
42             #第2步 找出最近的质心
43             for j in range(k):
44                 # 计算该样本到质心的欧式距离
45                 distance = distEclud(centroids[j,:],dataSet[i,:])
46                 if distance < minDist:
47                     minDist = distance
48                     minIndex = j
49             # 第 3 步：更新每一行样本所属的簇
50             if clusterAssment[i,0] != minIndex:
51                 clusterChange = True
52                 clusterAssment[i,:] = minIndex,minDist**2
53         #第 4 步：更新质心
54         for j in range(k):
55             pointsInCluster = dataSet[np.nonzero(clusterAssment[:,0].A == j)[0]]  # 获取簇类所有的点
56             centroids[j,:] = np.mean(pointsInCluster,axis=0)   # 对矩阵的行求均值
57  
58     print("Congratulations,cluster complete!")
59     return centroids,clusterAssment
60  
61 def showCluster(dataSet,k,centroids,clusterAssment):
62     m,n = dataSet.shape
63     if n != 2:
64         print("数据不是二维的")
65         return 1
66  
67     mark = [‘or‘, ‘ob‘, ‘og‘, ‘ok‘, ‘^r‘, ‘+r‘, ‘sr‘, ‘dr‘, ‘<r‘, ‘pr‘]
68     if k > len(mark):
69         print("k值太大了")
70         return 1
71  
72     # 绘制所有的样本
73     for i in range(m):
74         markIndex = int(clusterAssment[i,0])
75         plt.plot(dataSet[i,0],dataSet[i,1],mark[markIndex])
76         plt.annotate(i+1,(dataSet[i,0],dataSet[i,1]))
77  
78     mark = [‘Dr‘, ‘Db‘, ‘Dg‘, ‘Dk‘, ‘^b‘, ‘+b‘, ‘sb‘, ‘db‘, ‘<b‘, ‘pb‘]
79     # 绘制质心
80     for i in range(k):
81         print(‘质心：‘,str(centroids[i,0])+‘ ‘+str(centroids[i,1]))
82         plt.plot(centroids[i,0],centroids[i,1],mark[i])
83     plt.title(‘Clustering map of specialists‘)
84     plt.show()
85 
86 
87 dataSet = loadDataSet(r‘C:\Users\lenovo\Desktop\normal.txt‘)
88 k = 3
89 centroids,clusterAssment = KMeans(dataSet,k)
90  
91 showCluster(dataSet,k,centroids,clusterAssment)

  1 /*
  2 *language:c++
  3 *version:11
  4 *encoding:GBK
  5 *made by Luo Wenshui
  6 *last modified:2020/5/10
  7 *data file:input.txt
  8 */
  9 #include<iostream>
 10 #include<map> 
 11 #include<math.h>
 12 #include<string.h>
 13 #include<algorithm> 
 14 #include<cstdio>
 15 using namespace std;
 16 inline int read(){
 17     int ans=0,w=1;
 18     char ch=getchar();
 19     while(!isdigit(ch)){if(ch==‘-‘)w=-1;ch=getchar();}
 20     while(isdigit(ch))ans=(ans<<3)+(ans<<1)+ch-‘0‘,ch=getchar();
 21     return ans*w;
 22 }
 23 int n,m,t;
 24 const int maxn=1200;
 25 const int maxm=50; 
 26 struct node{//每一件参赛作品 
 27     double final_score;
 28     double raw_score[4];
 29     int score_givener[4];
 30     double std_score[4];
 31     int rank;//该作品在所有参赛作品中的排序 
 32 }a[maxn];
 33 struct specialist{ 
 34     double raw_score[100];
 35     double std_score[100];
 36     int num_of_work[100];//每次评阅的作品编号 
 37     int count;//表示专家批阅的项目数量；
 38     double std;//该专家打分的标准差
 39     double mean;//该专家打分的均值 
 40     int rank[maxn];//该专家对相应编号作品的打分在该专家所有分数中的排名
 41     double delta0i,delta1i;
 42     double P0i,P1i;//定义为P0i=1-delta0i,P1i=1-delta1i
 43     double P0T,P1T;//专家多次比赛获得的平均可行度水平，本论文中不涉及 
 44     int kide;//专家在聚类之后所属的类别 
 45 }E[maxm];
 46 struct work{//对所有作品确定排名的排序类 
 47     int index;
 48     double score;
 49 }w[maxn]; 
 50 double R[maxm][maxm];//相似度矩阵 
 51 double total_mean;//所有专家打分的均值
 52 double total_std;//所有专家打分的标准差 
 53 int kide[100]={3,2,3,3,3,2,3,3,3,1,3,2,2,1,3,3,3,2,3,2,1,3,2,3,2,1,2,3,2,1,3,2,3,3,3,3,2,1,3,3,3,2,2,3,1};//专家类别表，由聚类分析得出 
 54 double get_std(specialist& s)//获取每个专家打分的标准差 
 55 {
 56     double mean=0.0;
 57     for(int i = 1; i <= s.count; i ++ )//计算均值 
 58     {
 59         mean+=s.raw_score[i];
 60     }
 61     mean/=s.count; 
 62     double ans = 0.0;
 63     for(int i = 1; i <= s.count; i ++ )
 64     {
 65         ans+=(s.raw_score[i]-mean)*(s.raw_score[i]-mean);
 66     }
 67     return sqrt(ans/s.count); 
 68 }
 69 double get_mean(specialist& s)//获取s打分的均值 
 70 {
 71     double ans = 0.0;
 72     for(int i = 1; i <= s.count; i ++ )
 73     {
 74         ans += s.raw_score[i];
 75     }
 76     return ans/s.count;
 77 }
 78 int get_rank(double score,specialist& s)//获取某一得分在专家所有打分中的排名 
 79 {
 80     int rank = 0;
 81     for(int i = 0; i <= s.count; i ++ )
 82     {
 83         if(s.raw_score[i] < score)rank++;
 84     }
 85     return rank;
 86 }
 87 double get_delta0i(specialist& Ei)//获取专家E[i]的delta0i 
 88 {
 89     double ans = 0.0;
 90     for(int j = 1; j <= Ei.count; j ++ )
 91     {
 92         double final_score = a[Ei.num_of_work[j]].final_score;//专家Ei在评阅的作品j的总评得分 
 93         ans += fabs(Ei.raw_score[j]-final_score)/final_score;
 94     }
 95     return ans/(double)Ei.count;
 96 }
 97 double get_delta1i(specialist& Ei)//获取专家E[i]的delta1i 
 98 {
 99     double ans = 0.0;
100     int count = Ei.count;
101     for(int j = 1; j <= Ei.count; j ++ )
102     {
103         double rank = a[Ei.num_of_work[j]].rank;//Ei评阅的第j件作品的总评排序 
104         ans += fabs((double)Ei.rank[j]-rank)/(double)(count-1); 
105     }
106     return ans/count;
107 } 
108 void get_R()//计算定义的相似度矩阵 
109 {
110     double M = -1e10;
111     for(int i = 1; i <= 45; i ++ )
112     {
113         for(int j = 1; j <= 45; j ++ )
114         {
115             double P0i = E[i].P0i;
116             double P0j = E[j].P0i;
117             double P1i = E[i].P1i;
118             double P1j = E[j].P1i;
119             double tmp = P0i*P0j+P1i*P1j;
120             M = max(M,tmp);    
121             if(i == j)R[i][j]=1;
122             else
123             {
124                 R[i][j]=tmp;
125             }
126         }
127     }
128     for(int i = 1; i <= 45; i ++ )
129     {
130         for( int j = 1; j <= 45; j ++ )
131         {
132             if(i==j)continue;
133             R[i][j] = R[i][j]/M;//映射到(0,1)区间 
134         }
135      } 
136 }
137 double  get_total_mean()//获得总体均值 
138 {
139     double ans = 0.0;
140     for(int i = 1; i <= 1046; i ++ )
141     {
142         ans += a[i].final_score;
143     } 
144     return ans/1046;
145 }
146 double get_total_std()//获得总体方差 
147 {
148     double ans = 0.0;
149     int count = 0;
150     for(int i = 1; i <= 45;i ++ )
151     {
152         count += E[i].count;
153         for(int j = 1; j <= E[i].count; j ++ )
154         {
155             int num = E[i].num_of_work[j];
156             ans += pow(a[num].final_score-E[i].raw_score[j],2);
157         }
158      }
159      return  sqrt(ans/count);
160 }
161 void display();//展示专家信息
162 void display_R();//展示相关系数矩阵 
163 void display_P();//打印可信度表 
164 struct test{ 
165     int index;
166 }; 
167 
168 bool cmp(work& a1,work& a2){return a1.score<a2.score;}//按照得分进行升序排序 
169 int main()
170 {
171     freopen("input.txt","r",stdin);
172 //    freopen("output.txt","w",stdout);
173     std::ios::sync_with_stdio(false);
174     int number,number_of_work;
175     double tmp;
176     int x;
177     double tmp1,tmp2; 
178     for(int i = 1;i <= 1046;i ++)//获取1046条数据 
179     {
180         cin>>tmp;
181         number = (int)tmp;
182         cin>>a[number].final_score;
183         w[i].index = i;
184         w[i].score = a[number].final_score;
185     //获取三个专家的信息 
186         for(int j = 1; j <= 3; j ++ )
187         {
188             cin>>tmp;
189             number = (int)tmp;
190             cin>>tmp1>>tmp2;
191              
192             int count = ++E[number].count;
193             E[number].raw_score[count]=tmp1;
194             E[number].std_score[count]=tmp2;
195             E[number].num_of_work[count]=i;//评阅的作品编号 
196             
197             a[i].raw_score[j] = tmp1;
198             a[i].score_givener[j] = number;
199             a[i].std_score[j] = tmp2;
200         }
201     }
202     
203     for(int i = 1; i <= 45; i ++ )
204     {
205         E[i].std = get_std(E[i]);
206         E[i].mean = get_mean(E[i]);
207         for(int j = 1; j <= E[i].count; j ++ )//计算在E[i]所打的分中作品Aj的排名 
208         {
209             E[i].rank[j] = get_rank(E[i].raw_score[j],E[i]);
210         }
211     }
212     sort(w+1,w+1046+1,cmp);//对作品final_score进行升序排序
213     for(int i = 1; i <=1046; i ++ )
214     {
215         a[w[i].index].rank=i;//得到每件作品的排名 
216     } 
217     
218     for(int i = 1; i <= 45; i ++ )//获取每位专家的分值偏差和排序偏差与可信度 
219     {
220         E[i].delta0i = get_delta0i(E[i]);
221         E[i].delta1i = get_delta1i(E[i]); 
222         E[i].P0i = 1 - E[i].delta0i;
223         E[i].P1i = 1 - E[i].delta1i;
224     }
225 //    cout<<get_total_mean()<<" "<<get_total_std()<<endl;
226 //    display();//通过display 函数可以展示每一个专家的详细信息 
227 //    get_R();//计算相关矩阵 
228 //    display_R();
229 //    
230 //    display_P();
231 }
232 void display()
233 {
234     cout<<"四元组（a,b,c,d) => 该专家第a次批阅了作品b，给了c分，该作品的标准分是d"<<endl;
235     for(int j = 1; j <= 45; j ++ )
236     {
237         cout<<"第"<<j<<"个专家："<<endl;
238         cout<<"总体："<<E[j].count<<endl; 
239         for(int i = 1; i <= E[j].count; i ++ )
240         {
241             cout<<"("<<i<<","<<E[j].num_of_work[i]<<","<<E[j].raw_score[j]<<","<<E[j].std_score[i]<<")"<<endl;
242             cout<<"该作品在该专家所以给分中的排名："<<E[1].rank[i]<<endl;
243         } 
244         cout<<"标准差:"<<E[j].std<<endl;
245         cout<<"delta0i = "<<E[j].delta0i<<endl;
246         cout<<"delta1i = "<<E[j].delta1i<<endl;
247         
248         cout<<"P0i = "<<E[j].P0i<<endl;
249         cout<<"P1i = "<<E[j].P1i<<endl; 
250         cout<<"#########################################################"<<endl; 
251     }
252 }
253 void display_R()
254 {
255     cout<<" ";
256     for(int i = 1;i <= 45; i ++ )
257     {
258         cout<<"("<<i<<")"<<"  ";
259     }
260     cout<<endl;
261     for(int i = 1; i <= 45; i ++ )
262     {
263         cout<<"("<<i<<")"<<" ";
264         for(int j = 1; j <= 45; j ++ )
265         {
266             cout<<R[i][j]<<" ";
267         }
268         cout<<endl;
269     }
270 }
271 void display_P() 
272 {
273     cout<<"可信度矩阵"<<endl; 
274     for(int i = 1; i <= 45; i ++ )
275     {
276         cout<<E[i].P0i<<" "<<E[i].P1i<<endl;
277     }
278 }