def calcHiddenOutputs(self, input, center, std, data):
knn = KNN(2, data)
dist_between = knn.get_euclidean_distance(input, center)
# print(type(input[1]))
#print(type(center[1]))
# print(dist_between)
output = np.exp(-1 / (2 * std**2) * dist_between**2)
# print(output)
return output
def test_euclidean(self):
"""
Test if euclidean distance is working
:return:
"""
data = Data('abalone', pd.read_csv(r'data/abalone.data', header=None), 8) # load data
df = data.df.sample(n=10) # minimal data frame
data.split_data(data_frame=df) # sets test and train data
knn = KNN(5, data)
print(knn.get_euclidean_distance(df.iloc[1], df.iloc[2]))
def getMaxDistMeans(self, mean_list, data):
maxDist = 0
knn = KNN(2, data)
for clust in mean_list:
for clus2 in mean_list:
# compare against all other medoids
curDist = knn.get_euclidean_distance()
if curDist > maxDist:
maxDist = curDist
# print(maxDist)
return maxDist
def getMaxDist(self, medoids_list, data):
maxDist = 0
knn = KNN(2, data)
for medoid in medoids_list:
for medoid2 in medoids_list:
# compare against all other medoids
curDist = knn.get_euclidean_distance(medoid.row, medoid2.row)
if curDist > maxDist:
maxDist = curDist
# print(maxDist)
return maxDist
def predict_centroids(
self, centroids,
data_set): # Method to return closest cluster to test data
for _, data in data_set[data_set].iterrows(
): # Loops through the rows of the data set
distance = None # Initializes distance
closest_centroid = None # Keeps track of the current closes centroid cluster
closest_centroid_euclidian_distance = None # Keeps track of the closest euclidian distance.
cluster_val = 1
for centroid in centroids: # Loops through the k centroid points
euclid_distance = KNN.get_euclidean_distance(
centroid, data
) # Gets the distance between the centroid and the data point
if distance is None or euclid_distance < distance: # Updates the distance to keep track of the closest point
distance = euclid_distance
# closest_centroid = centroid
closest_centroid = cluster_val
closest_centroid_euclidian_distance = distance
cluster_val += 1
def cluster_data(self, clusters,
data_set): # Loop until clusters have converged
previous_clusters = [] # Initializes to check if previous value mached
while (True):
current_clusters = []
for point in range(len(clusters)): # Appends an empty list
current_clusters.append([])
for _, value in data_set.iterrows(): # Loop rows of the data set
cluster_key = 0 # Appends a key for the closest value of the dictionary
closest_point = [None, float('inf')
] # Index of dictionary, distance value
value = list(value) # Won't work without this
for row in clusters.values(
): # Loops through the values in the cluster to compare distance
distance = KNN.get_euclidean_distance(
row, value) # Gets the euclidean distance
if distance < closest_point[
1]: # Checks if it is closer than the previous closest point
closest_point = [cluster_key,
distance] # Sets the closest point
cluster_key += 1
current_clusters[closest_point[0]].append(
value
) # Appends the closest point to a the corresponding cluster
clusters = self.mean_clusters(
current_clusters, data_set) # Gets the updated k-mean clusters
if previous_clusters == current_clusters:
print(
'-------------------------- K-Means has converged ------------------'
)
cluster_list = []
for cluster in clusters.values(
): # Convert the k-means points to a list
cluster_list.append(cluster)
return cluster_list
previous_clusters = current_clusters