20230106

.gitattributes

@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto

DTW_matrix.py

@@ -0,0 +1,87 @@
+import math
+import numpy as np
+import pandas as pd
+
+def dtw(file, num1):
+    num = num1
+    distmatrix = np.zeros((num, num))   #生成一个零矩阵，大小为num*num，方便填数据
+    for i in range(num):
+        t = file.iloc[:, i]     #取出第i个位置的值
+        for j in range(i + 1, num):
+            r = file.iloc[:, j]     #去除第i+1位置的值
+            if len(r) == 0:
+                print("Notdata：", file[j])
+            distmatrix[i, j] = mydtw_function2(t, r)    #调用计算函数，计算井i与井j的相似度
+            distmatrix[j, i] = distmatrix[i, j]         #(i,j)==(j,i)
+            distmatrix[i, i] = 1                        #(i,i)==1
+        # print("NO.{0}finish!".format(i))
+    return distmatrix
+
+def mydtw_function2(t, r):
+    n = len(t)
+    m = len(r)
+    t = np.array(t)
+    r = np.array(r)
+    d = np.zeros((n, m))
+    for i in range(n):
+        for j in range(m):
+            d[i, j] = np.sum((t[i] - r[j]) ** 2)
+    # 累积距离 Cumulative distance
+    D = np.ones((n, m)) * np.inf
+    D[0, 0] = d[0, 0]
+    # 动态规划 dynamic programming
+    for i in range(1, n):
+        for j in range(m):
+            D1 = D[i - 1, j]
+            if j > 0:
+                D2 = D[i - 1, j - 1]
+                D3 = D[i, j - 1]
+            else:
+                D2 = np.inf
+                D3 = np.inf
+            D[i, j] = d[i, j] + min([D1, D2, D3])
+    dist = D[n - 1, m - 1]
+    # 对结果进行处理
+    dist = math.exp(-dist)
+    return dist
+
+
+# 描述：使用DTW计算地址相似度的主程序
+# 输入：数据集名称（dataname）
+def dtw_adj(dataname):
+    """
+        函数介绍（中文版）
+        描述：根据数据集名称读取对应地质特征文件，并在此基础上调用DTW函数计算地址相似性矩阵
+        输入：数据集名称(dataname)
+        输出：地质相似度矩阵，该矩阵经过了np.mat()转换
+
+        Function introduction (English version)
+        Description: Read the corresponding geological feature file according to the dataset name, and call the DTW function to calculate the address similarity matrix
+        Input: dataset name (dataname)
+        Output: geological similarity matrix, which is transformed by np.mat()
+    """
+
+    # 01 读取数据 load_data
+    dfall = pd.read_csv(r'data/testdata/'+dataname+'_Details.csv')
+    num = dfall.shape[0]
+
+    # 02 归一化 normalization
+    dfmean = pd.DataFrame()  # 归一化之后的df
+    for i in range(3, dfall.shape[1]):  #取出相关的参数，准备处理
+        data1 = dfall.iloc[:, i]
+        max_value = np.max(data1)
+        min_value = np.min(data1)
+        range_value = max_value - min_value
+        mean_value = np.mean(data1)
+        data1 = (data1 - min_value) / range_value
+        dfmean = pd.concat([dfmean, data1], axis=1)  # 参数归一化之后的df
+
+    # 03 计算 calculation
+    dfmeant = pd.DataFrame(dfmean.T)    #转置，便于计算
+    num1 = dfmeant.shape[1]             #获得行数
+    distmatrix = dtw(dfmeant, num1)     #dtw计算主函数
+    dfmat = pd.DataFrame(distmatrix)    #输出结果转为DataFrame，便于后续计算
+
+    return dfmat
+
+

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2022 zzb1185
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Spatial_matrix.py

@@ -0,0 +1,34 @@
+import math
+import numpy as np
+import pandas as pd
+
+def spa_adj(dataname):
+    dfall = pd.read_csv(r'data/testdata/'+dataname+'_Details.csv')
+    dfxy = dfall.iloc[:, 1:3]  # 取出经纬度计算
+    # 01 计算邻近关系
+    num = dfxy.shape[0]  # 多少口井
+    dfnear = pd.DataFrame(columns=['a', 'b'])  # 临近矩阵
+    for i in range(num):
+        x1 = dfxy.iloc[i, 0]
+        y1 = dfxy.iloc[i, 1]
+        for j in range(num):
+            x2 = dfxy.iloc[j, 0]
+            y2 = dfxy.iloc[j, 1]
+            dis = ((x1 - x2) ** 2 + (y1 - y2) ** 2) ** (0.5)
+            if dis <= 350:  #350m
+                dfnear = dfnear.append(pd.DataFrame({'a': [i], 'b': [j]}))  # 临近矩阵
+    print("邻近关系计算完成")
+
+    # 02 组合
+    num_finished = 1
+    oh432 = np.zeros((num, num))
+    for row in range(dfnear.shape[0]):
+        input = dfnear.iloc[(row, 0)]
+        near = dfnear.iloc[(row, 1)]
+        oh432[input][near] = 1
+        print(row)
+
+    dfoh1 = pd.DataFrame(oh432)  # 完全体权重邻接矩阵
+    dfoh1.to_csv(r"data\testdata\test_Spamatrix.csv",index=False,header=None)
+    print("矩阵组装完成，保存在data中")
+    return dfoh1