MAHAL

exec.py

@@ -2,13 +2,6 @@ import pandas as pd
 import xlsxwriter
 
 
-def exulidean(row1, row2):
-    s = 0
-    for p, q in zip(row1, row2):
-        s += ((p - q) ** 2) ** 0.5  # 421.30
-    return s
-
-
 def matrixToxls(matrix, filename):
     workbook = xlsxwriter.Workbook(filename)
     worksheet = workbook.add_worksheet()
@@ -18,14 +11,19 @@ def matrixToxls(matrix, filename):
     workbook.close()
 
 
-resultEculidean = []
+def exulidean(row1, row2):
+    s = 0
+    for p, q in zip(row1, row2):
+        s += ((p - q) ** 2)
+    return s ** 0.5
+
 
 if __name__ == "__main__":
     df = pd.read_excel('dataset2.xls', sheet_name="forestfires").to_numpy()
+    resultEculidean = []
     for row in df:
         tmp = []
         for row2 in df:
-            # [12312,3123,21321,3543,667,313,21,4,346,54,745,6........]
-            tmp.append(exulidean(row, row2))
+            tmp.append(exulidean(row, row2))  # [0,x,    ]
         resultEculidean.append(tmp)
     matrixToxls(resultEculidean, "eculidean.xls")

mahal.py

@@ -0,0 +1,82 @@
+import pandas as pd
+import xlsxwriter
+from random import uniform
+import math
+import numpy as np
+
+
+def calucateMean(df) -> tuple:
+    mean = []
+    maximum = []
+    minimum = []
+    for col in range(df.shape[1]):  # 0 ta 10
+        mean.append(0)
+        maximum.append(0)
+        minimum.append(math.inf)
+        for row in df:
+            if (row[col] > maximum[col]):
+                maximum[col] = row[col]
+            if (row[col] < minimum[col]):
+                minimum[col] = row[col]
+            mean[col] += row[col]
+        mean[col] = mean[col] / len(df)
+    v = []
+    for i in range(df.shape[1]):
+        v.append(uniform(minimum[i], maximum[i]))
+    vm = []
+    for j in range(df.shape[1]):
+        vm.append(mean[j] - v[j])
+    return (mean, vm)
+
+
+def variance(col, mean) -> list:
+    var = 0
+    for row in df:
+        var += (row[col] - mean[col]) ** 2
+    var /= (df.shape[0]-1)
+    return var
+
+
+def covariance(col1, col2, mean):
+    cov = 0
+    for row in df:
+        cov += (row[col1] - mean[col1])*(row[col2] - mean[col2])
+    cov /= (df.shape[0] - 1)
+    return cov
+
+
+def matrixCov(df, mean):
+    matrix = []
+    for col1 in range(df.shape[1]):
+        tmp = []
+        for col2 in range(df.shape[1]):
+            if (col1 == col2):
+                tmp.append(variance(col1, mean))
+            else:
+                tmp.append(covariance(col1, col2, mean))
+        matrix.append(tmp)
+    return matrix
+
+
+def multiply(matrix1, matrix2):
+    matrix = [0 for i in range(len(matrix1))]
+    col = 0
+    for i in range(len(matrix1)):
+        for j in range(matrix2.shape[1]):
+            matrix[i] = matrix1[i] * matrix2[i][col]
+        col += 1
+    return matrix
+
+
+def multiplyTwoList(list1, list2):
+    return sum([i*j for i, j in zip(list1, list2)])
+
+
+if __name__ == "__main__":
+    df = pd.read_excel('dataset2.xls', sheet_name="forestfires").to_numpy()
+    (mean, vm) = calucateMean(df)
+    matrix = matrixCov(df, mean)
+    invc_matrix = np.linalg.inv(matrix)
+    res = multiply(vm, invc_matrix)
+    res = multiplyTwoList(res, vm)
+    print(res**0.5)