def user_rating_clustering():
data = data_helpers.read_feature_data(
file_path='../data/user_movie_rating')
ms_model = MeanShift()
predict_labels = ms_model.fit_predict(data)
cluster_centers_indices = ms_model.cluster_centers_
print(predict_labels)
def customer_clustering():
data = data_helpers.read_feature_data(file_path='../data/customer_data')
kmean_model = KMeans(n_clusters=4)
predict_labels = kmean_model.fit_predict(data)
cluster_centers_indices = kmean_model.cluster_centers_
print(predict_labels)
total_guess_num = 800
correct_guess_num = 0
predict_label_count_matrix = [[0, 0, 0, 0], [0, 0, 0, 0], [0, 0, 0, 0],
[0, 0, 0, 0]]
for id_, label_ in enumerate(predict_labels):
if id_ < 200:
predict_label_count_matrix[0][label_] += 1
elif id_ < 400:
predict_label_count_matrix[1][label_] += 1
elif id_ < 600:
predict_label_count_matrix[2][label_] += 1
else:
predict_label_count_matrix[3][label_] += 1
for i in range(4):
correct_guess_num += max(predict_label_count_matrix[i])
accuracy = float(correct_guess_num) / float(total_guess_num)
print('accuracy:' + str(accuracy))
return data, predict_labels
def customer_clustering():
data = data_helpers.read_feature_data(
file_path='../data/customer_data_min')
aff_prop_model = AffinityPropagation(convergence_iter=150, max_iter=1000)
aff_prop_model.fit(data)
cluster_centers_indices = aff_prop_model.cluster_centers_indices_
labels = aff_prop_model.labels_
print(labels)
return data, labels
def load_train_data(file_path='../data/customer_salary_satisfaction'):
train_data = data_helpers.read_feature_data(file_path)
feature_dim = len(train_data[0]) - 1
feature_data = []
target_data = []
for data_sample in train_data:
feature_vec = []
for id_ in range(feature_dim):
feature_vec.append(data_sample[id_])
feature_data.append(feature_vec)
target_data.append(data_sample[feature_dim])
return feature_data, target_data
def load_train_data(file_path='../data/customer_off_time_salary_satisfaction'):
train_data = data_helpers.read_feature_data(file_path)
feature_dim = len(train_data[0]) - 1
feature_data = []
target_data = []
for data_sample in train_data:
feature_vec = []
for id_ in range(feature_dim):
feature_vec.append(data_sample[id_])
feature_data.append(feature_vec)
target_data.append(data_sample[feature_dim])
return feature_data, target_data
def customer_clustering():
data = data_helpers.read_feature_data(file_path='./data/customer_data_min')
# 2-dimensions array
aff_prop_model = AffinityPropagation(convergence_iter=150, max_iter=1000)
# number iteration:
# - convergence: 150
# - max: 1000
aff_prop_model.fit(data) # train model
cluster_centers_indices = aff_prop_model.cluster_centers_indices_
labels = aff_prop_model.labels_
print(labels)
return data, labels
def load_train_data(file_path, label_pos=-1):
train_data = data_helpers.read_feature_data(file_path)
feature_dim = len(train_data[0]) - 1
feature_data = []
target_data = []
if label_pos == 0:
feature_ids = range(1, feature_dim + 1)
else:
feature_ids = range(feature_dim)
for data_sample in train_data:
feature_vec = []
for id_ in feature_ids:
feature_vec.append(data_sample[id_])
feature_data.append(feature_vec)
target_data.append(data_sample[label_pos])
return feature_data, target_data