def evaluate_model(model, model_type, num_of_classes, candidate_feature_set, data_set):
'''This method uses the inputted feature subset to cluster the inputted data and
scores performance using a LDA-like objective function.'''
# Convert candidate_feature_set representation from
# f_1, ... f_d to the list of indices of the f_i = 1
# (for example, [1 0 0 1 0] -> [0 3]
candidate_feature_set = \
[idx for idx in xrange(len(candidate_feature_set)) if candidate_feature_set[idx] == 1]
if model_type == "Kmeans":
model = KMeans(num_of_classes)
elif model_type == "HAC":
model = HAC(num_of_classes)
model.cluster(data_set[:,candidate_feature_set])
return model.calculate_performance()
def perform_SFS_feature_selection(model, model_type, num_of_classes, data_set):
# Create a boolean string, 1 = include feature, 0 = leave it out
feature_set = [i for i in xrange(data_set.shape[1])]
chosen_features = []
chosen_clusters = []
base_performance = float("-inf")
# while there are still features to choose from...
while len(feature_set) > 0:
# initialize performance metrics
best_performance = float("-inf")
best_clusters = []
#print "best performance = %f" % best_performance
# Pick a feature that hasn't be chosen yet and train the model
for feature in feature_set:
chosen_features.append(feature)
# Train model
if model_type == "Kmeans":
model = KMeans(num_of_classes)
elif model_type == "HAC":
model = HAC(num_of_classes)
#print "Modeling with %s" % chosen_features
clusters = model.cluster(data_set)
# Calculate performance via LDA-like objective function
current_performance = model.calculate_performance()
#print "model performance = %f" % current_performance
# if this combo of features beats the best performance so far
# take note...
if current_performance > best_performance:
best_performance = current_performance
best_feature = feature
best_clusters = clusters
#print "best performance updated to %f" % best_performance
chosen_features.remove(feature)
# If best noted performance beats the best performance we've seen
# so far, add to chosen features
if best_performance > base_performance:
base_performance = best_performance
feature_set.remove(best_feature)
chosen_features.append(best_feature)
chosen_clusters = best_clusters
#print "base performance = %f" % base_performance
else:
#print "best performance = %f" % base_performance
break
return chosen_features, chosen_clusters
data_file = open(test[0])
print "Running with %s" % test[0]
for line in data_file:
line_split = line.split(',')
data_instances.append(map(float, line_split))
data_instances = np.array(data_instances)
# Run SFS using k-means and HAC
kmeans_model = KMeans(test[1])
hac_model = HAC(test[1])
# Glass dataset
if "glass" in test[0]:
kmeans_sfs_glass = np.array([1,3])
kmeans_model.cluster(data_instances[:,kmeans_sfs_glass])
print "Kmeans SFS glass performance = %f" % kmeans_model.calculate_performance()
kmeans_ga_glass = np.array([0,1,2,3,4,5,6])
kmeans_model = KMeans(test[1])
kmeans_model.cluster(data_instances[:,kmeans_ga_glass])
print "Kmeans GA glass performance = %f" % kmeans_model.calculate_performance()
hac_sfs_glass = np.array([0])
hac_model.cluster(data_instances[:,hac_sfs_glass])
print "HAC SFS glass performance = %f" % hac_model.calculate_performance()
# Iris dataset
elif "iris" in test[0]:
kmeans_sfs_iris = np.array([1])
kmeans_model = KMeans(test[1])
kmeans_model.cluster(data_instances[:,kmeans_sfs_iris])
print "Running with %s" % test[0]
for line in data_file:
line_split = line.split(',')
data_instances.append(map(float, line_split))
data_instances = np.array(data_instances)
# Run SFS using k-means and HAC
kmeans_model = KMeans(test[1])
hac_model = HAC(test[1])
# Glass dataset
if "glass" in test[0]:
kmeans_sfs_glass = np.array([1, 3])
kmeans_model.cluster(data_instances[:, kmeans_sfs_glass])
print("K-means SFS glass performance = %f" %
kmeans_model.calculate_performance())
kmeans_ga_glass = np.array([0, 1, 2, 3, 4, 5, 6])
kmeans_model = KMeans(test[1])
kmeans_model.cluster(data_instances[:, kmeans_ga_glass])
print("K-means GA glass performance = %f" %
kmeans_model.calculate_performance())
hac_sfs_glass = np.array([0])
hac_model.cluster(data_instances[:, hac_sfs_glass])
print("HAC SFS glass performance = %f" %
hac_model.calculate_performance())
# Iris dataset
elif "iris" in test[0]:
kmeans_sfs_iris = np.array([1])
