Fix

Author: phillity

kMeans/centroidfile_1d.txt

@@ -0,0 +1,2 @@
+1
+3

kMeans/centroidfile_1d.txt - Shortcut.lnk

@@ -0,0 +1,9 @@
+2
+3
+4
+10
+11
+12
+20
+25
+30

kMeans/datafile_1d.txt

@@ -0,0 +1,150 @@
+5.1,3.5,1.4,0.2,Iris-setosa
+4.9,3.0,1.4,0.2,Iris-setosa
+4.7,3.2,1.3,0.2,Iris-setosa
+4.6,3.1,1.5,0.2,Iris-setosa
+5.0,3.6,1.4,0.2,Iris-setosa
+5.4,3.9,1.7,0.4,Iris-setosa
+4.6,3.4,1.4,0.3,Iris-setosa
+5.0,3.4,1.5,0.2,Iris-setosa
+4.4,2.9,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.4,3.7,1.5,0.2,Iris-setosa
+4.8,3.4,1.6,0.2,Iris-setosa
+4.8,3.0,1.4,0.1,Iris-setosa
+4.3,3.0,1.1,0.1,Iris-setosa
+5.8,4.0,1.2,0.2,Iris-setosa
+5.7,4.4,1.5,0.4,Iris-setosa
+5.4,3.9,1.3,0.4,Iris-setosa
+5.1,3.5,1.4,0.3,Iris-setosa
+5.7,3.8,1.7,0.3,Iris-setosa
+5.1,3.8,1.5,0.3,Iris-setosa
+5.4,3.4,1.7,0.2,Iris-setosa
+5.1,3.7,1.5,0.4,Iris-setosa
+4.6,3.6,1.0,0.2,Iris-setosa
+5.1,3.3,1.7,0.5,Iris-setosa
+4.8,3.4,1.9,0.2,Iris-setosa
+5.0,3.0,1.6,0.2,Iris-setosa
+5.0,3.4,1.6,0.4,Iris-setosa
+5.2,3.5,1.5,0.2,Iris-setosa
+5.2,3.4,1.4,0.2,Iris-setosa
+4.7,3.2,1.6,0.2,Iris-setosa
+4.8,3.1,1.6,0.2,Iris-setosa
+5.4,3.4,1.5,0.4,Iris-setosa
+5.2,4.1,1.5,0.1,Iris-setosa
+5.5,4.2,1.4,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+5.0,3.2,1.2,0.2,Iris-setosa
+5.5,3.5,1.3,0.2,Iris-setosa
+4.9,3.1,1.5,0.1,Iris-setosa
+4.4,3.0,1.3,0.2,Iris-setosa
+5.1,3.4,1.5,0.2,Iris-setosa
+5.0,3.5,1.3,0.3,Iris-setosa
+4.5,2.3,1.3,0.3,Iris-setosa
+4.4,3.2,1.3,0.2,Iris-setosa
+5.0,3.5,1.6,0.6,Iris-setosa
+5.1,3.8,1.9,0.4,Iris-setosa
+4.8,3.0,1.4,0.3,Iris-setosa
+5.1,3.8,1.6,0.2,Iris-setosa
+4.6,3.2,1.4,0.2,Iris-setosa
+5.3,3.7,1.5,0.2,Iris-setosa
+5.0,3.3,1.4,0.2,Iris-setosa
+7.0,3.2,4.7,1.4,Iris-versicolor
+6.4,3.2,4.5,1.5,Iris-versicolor
+6.9,3.1,4.9,1.5,Iris-versicolor
+5.5,2.3,4.0,1.3,Iris-versicolor
+6.5,2.8,4.6,1.5,Iris-versicolor
+5.7,2.8,4.5,1.3,Iris-versicolor
+6.3,3.3,4.7,1.6,Iris-versicolor
+4.9,2.4,3.3,1.0,Iris-versicolor
+6.6,2.9,4.6,1.3,Iris-versicolor
+5.2,2.7,3.9,1.4,Iris-versicolor
+5.0,2.0,3.5,1.0,Iris-versicolor
+5.9,3.0,4.2,1.5,Iris-versicolor
+6.0,2.2,4.0,1.0,Iris-versicolor
+6.1,2.9,4.7,1.4,Iris-versicolor
+5.6,2.9,3.6,1.3,Iris-versicolor
+6.7,3.1,4.4,1.4,Iris-versicolor
+5.6,3.0,4.5,1.5,Iris-versicolor
+5.8,2.7,4.1,1.0,Iris-versicolor
+6.2,2.2,4.5,1.5,Iris-versicolor
+5.6,2.5,3.9,1.1,Iris-versicolor
+5.9,3.2,4.8,1.8,Iris-versicolor
+6.1,2.8,4.0,1.3,Iris-versicolor
+6.3,2.5,4.9,1.5,Iris-versicolor
+6.1,2.8,4.7,1.2,Iris-versicolor
+6.4,2.9,4.3,1.3,Iris-versicolor
+6.6,3.0,4.4,1.4,Iris-versicolor
+6.8,2.8,4.8,1.4,Iris-versicolor
+6.7,3.0,5.0,1.7,Iris-versicolor
+6.0,2.9,4.5,1.5,Iris-versicolor
+5.7,2.6,3.5,1.0,Iris-versicolor
+5.5,2.4,3.8,1.1,Iris-versicolor
+5.5,2.4,3.7,1.0,Iris-versicolor
+5.8,2.7,3.9,1.2,Iris-versicolor
+6.0,2.7,5.1,1.6,Iris-versicolor
+5.4,3.0,4.5,1.5,Iris-versicolor
+6.0,3.4,4.5,1.6,Iris-versicolor
+6.7,3.1,4.7,1.5,Iris-versicolor
+6.3,2.3,4.4,1.3,Iris-versicolor
+5.6,3.0,4.1,1.3,Iris-versicolor
+5.5,2.5,4.0,1.3,Iris-versicolor
+5.5,2.6,4.4,1.2,Iris-versicolor
+6.1,3.0,4.6,1.4,Iris-versicolor
+5.8,2.6,4.0,1.2,Iris-versicolor
+5.0,2.3,3.3,1.0,Iris-versicolor
+5.6,2.7,4.2,1.3,Iris-versicolor
+5.7,3.0,4.2,1.2,Iris-versicolor
+5.7,2.9,4.2,1.3,Iris-versicolor
+6.2,2.9,4.3,1.3,Iris-versicolor
+5.1,2.5,3.0,1.1,Iris-versicolor
+5.7,2.8,4.1,1.3,Iris-versicolor
+6.3,3.3,6.0,2.5,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+7.1,3.0,5.9,2.1,Iris-virginica
+6.3,2.9,5.6,1.8,Iris-virginica
+6.5,3.0,5.8,2.2,Iris-virginica
+7.6,3.0,6.6,2.1,Iris-virginica
+4.9,2.5,4.5,1.7,Iris-virginica
+7.3,2.9,6.3,1.8,Iris-virginica
+6.7,2.5,5.8,1.8,Iris-virginica
+7.2,3.6,6.1,2.5,Iris-virginica
+6.5,3.2,5.1,2.0,Iris-virginica
+6.4,2.7,5.3,1.9,Iris-virginica
+6.8,3.0,5.5,2.1,Iris-virginica
+5.7,2.5,5.0,2.0,Iris-virginica
+5.8,2.8,5.1,2.4,Iris-virginica
+6.4,3.2,5.3,2.3,Iris-virginica
+6.5,3.0,5.5,1.8,Iris-virginica
+7.7,3.8,6.7,2.2,Iris-virginica
+7.7,2.6,6.9,2.3,Iris-virginica
+6.0,2.2,5.0,1.5,Iris-virginica
+6.9,3.2,5.7,2.3,Iris-virginica
+5.6,2.8,4.9,2.0,Iris-virginica
+7.7,2.8,6.7,2.0,Iris-virginica
+6.3,2.7,4.9,1.8,Iris-virginica
+6.7,3.3,5.7,2.1,Iris-virginica
+7.2,3.2,6.0,1.8,Iris-virginica
+6.2,2.8,4.8,1.8,Iris-virginica
+6.1,3.0,4.9,1.8,Iris-virginica
+6.4,2.8,5.6,2.1,Iris-virginica
+7.2,3.0,5.8,1.6,Iris-virginica
+7.4,2.8,6.1,1.9,Iris-virginica
+7.9,3.8,6.4,2.0,Iris-virginica
+6.4,2.8,5.6,2.2,Iris-virginica
+6.3,2.8,5.1,1.5,Iris-virginica
+6.1,2.6,5.6,1.4,Iris-virginica
+7.7,3.0,6.1,2.3,Iris-virginica
+6.3,3.4,5.6,2.4,Iris-virginica
+6.4,3.1,5.5,1.8,Iris-virginica
+6.0,3.0,4.8,1.8,Iris-virginica
+6.9,3.1,5.4,2.1,Iris-virginica
+6.7,3.1,5.6,2.4,Iris-virginica
+6.9,3.1,5.1,2.3,Iris-virginica
+5.8,2.7,5.1,1.9,Iris-virginica
+6.8,3.2,5.9,2.3,Iris-virginica
+6.7,3.3,5.7,2.5,Iris-virginica
+6.7,3.0,5.2,2.3,Iris-virginica
+6.3,2.5,5.0,1.9,Iris-virginica
+6.5,3.0,5.2,2.0,Iris-virginica
+6.2,3.4,5.4,2.3,Iris-virginica
+5.9,3.0,5.1,1.8,Iris-virginica

kMeans/datafile_2d.txt - Shortcut.lnk

@@ -0,0 +1,131 @@
+# Tyler Phillips
+# CSCI57300 Data Mining
+# k-Means
+
+import sys
+import numpy as np
+
+# k-Means function
+# Args:
+# D - nxd data matrix
+# mu - kxd centroid matrix
+# k - cluster count
+# eps - convergence tolarence
+def kMeans(D, k, mu, eps=0.0001):
+ # Get dimensions of nxd D matrix
+ n, d = D.shape 
+
+ # If mu is not preset
+ if np.array_equal(mu,np.zeros((k,d))):
+ # Randomly intialize k centroids in kxd mu matrix
+ mu_list = np.random.choice(n,size=k,replace=False)
+ for i,id in enumerate(mu_list):
+ mu[i,:] = D[id,:]
+
+ # Intialize previous mu matrix
+ prev_mu = np.zeros((k,d))
+ 
+ # Intialize iteration count
+ iter = 1
+
+ while True:
+ # Clusters as list of k lists
+ C = [[] for i in range(k)]
+ labels = [[] for i in range(k)]
+
+ # Cluster assignment step
+ for i in range(n):
+ min_dist = sys.float_info.max
+ min_idx = -1
+ # Get distances between x_i (D[i,:]) and each centriod in mu
+ for j in range(k):
+ dist = np.linalg.norm(D[i,:] - mu[j,:])
+ if dist < min_dist:
+ min_dist = dist
+ min_idx = j
+ # Add x_i to cluster corresponding to minimum distance
+ C[min_idx].append(D[i,:])
+ labels[min_idx].append(i+1)
+ 
+ # Centroid update step
+ for i in range(k):
+ # Update centriod mu_i as average of cluster C_i elements
+ if len(C[i]) > 1:
+ mu[i,:] = np.sum(C[i], axis=0) / len(C[i])
+
+ # Check for convergence
+ if np.linalg.norm(mu - prev_mu) <= eps:
+ return C, labels, mu, iter
+
+ # Print update
+ #print("Iteration " + str(iter) + ":")
+ #for i in range(k):
+ #print("c_" + str(i) + ":" + str(C[i]) + " mu_" + str(i) + ":" + str(mu[i,:]))
+ #print("||mu - mu_prev||:" + str(check) + "\n") 
+
+ # Update iteration count
+ iter += 1
+ # Update previous mu
+ prev_mu = np.copy(mu)
+
+# Sum of squared error helper function
+def SSE(C, mu):
+ sse = 0
+ for c_i in C:
+ sse = sse + np.linalg.norm(c_i - mu) ** 2
+ return sse
+
+
+
+
+
+# Get the arguments list 
+argv = str(sys.argv)
+print(str(argv))
+
+# Get number of arguments
+argc = len(sys.argv)
+
+# Print error if not enough arguments
+if argc < 3:
+ sys.exit("Datafile and k arguments are required!")
+
+# Read in D data matrix
+if sys.argv[1] == "iris.data.txt" or sys.argv[1] == "iris.txt":
+ D = np.loadtxt(sys.argv[1],delimiter=',',usecols=(0,1,2,3))
+else:
+ D = np.loadtxt(sys.argv[1],delimiter=',')
+if len(D.shape) < 2:
+ D = D.reshape((D.shape[0],1))
+
+# Read in k centroid count
+k = int(sys.argv[2])
+
+# Read in mu centroid id list if given
+mu = np.zeros((k,D.shape[1]))
+mu_list = None
+if argc > 3:
+ mu_list = np.loadtxt(sys.argv[3],dtype=int,delimiter=',')
+ for i,id in enumerate(mu_list):
+ mu[i,:] = D[id-1,:]
+
+C, labels, mu, iter = kMeans(D, k, mu)
+total_sse = 0
+
+# Print input information
+n, d = D.shape
+print("Number of Datapoints: n=" + str(n))
+print("Number of Dimensions: d=" + str(d))
+print("Number of Clusters: k=" + str(k))
+print("\n")
+
+# Print results
+print("Convergence after " + str(iter) + " iterations:")
+for i in range(k):
+ print("-----Cluster " + str(i) + "---------------")
+ print(str(len(C[i])) + " elements:" + str(labels[i]))
+ print("mu_" + str(i) + ":" + str(mu[i,:]))
+ print("SSE_" + str(i) + ":" + str(SSE(C[i],mu[i,:])))
+ total_sse = total_sse + SSE(C[i],mu[i,:])
+print("/n")
+print("Total SSE :" + str(total_sse))