def nmf_run():
"""
非负矩阵分解 run
:return:
"""
# 1、导入用户商品矩阵
print("----------- 1、load data -----------")
data_matrix = FTool.LoadData(file_name="data.txt").load_data_with_none()
# 2、利用梯度下降法对矩阵进行分解
print("----------- 2、training -----------")
w_matrix, h_matrix = train(data_matrix, 5, 10000, 1e-5)
# 3、保存分解后的结果
print("----------- 3、save decompose -----------")
with FTool.SaveModel(file_name="w_matrix") as save_file:
save_file.save_model_mul(w_matrix)
with FTool.SaveModel(file_name="h_matrix") as save_file:
save_file.save_model_mul(h_matrix)
# 4、预测
print("----------- 4、prediction -----------")
predict = prediction(data_matrix, w_matrix, h_matrix, 0)
# 进行Top-K推荐
print("----------- 5、top_k recommendation ------------")
top_recommend = top_k(predict, 2)
print(top_recommend)
print(w_matrix * h_matrix)
def mf_run():
"""
Matrix Factorization-based Recommend run
:return:
"""
# 1、导入用户商品矩阵
print("----------- 1、load data -----------")
data_matrix = FTool.LoadData(file_name="data.txt").load_data_with_none()
# 2、利用梯度下降法对矩阵进行分解
print("----------- 2、training -----------")
p, q = grad_ascent(data_matrix, 3, 0.0002, 0.02,
5000) # 由于样本过少, 迭代次数增加min loss也不会继续收敛
# 3、保存分解后的结果
print("----------- 3、save decompose -----------")
with FTool.SaveModel(file_name="p_result") as save_file:
save_file.save_model_mul(p)
with FTool.SaveModel(file_name="q_result") as save_file:
save_file.save_model_mul(q)
# 4、预测
print("----------- 4、prediction -----------")
predict = prediction(data_matrix, p, q, 0)
# 进行Top-K推荐
print("----------- 5、top_k recommendation ------------")
top_recommend = top_k(predict, 2)
print(top_recommend)
print(p * q)
def mean_shift():
"""
Mean Shift 执行函数
:return:
"""
# 导入数据集
print("----------1.load data ------------")
data = load_data("data", 2)
x_data = [_data[0] for _data in data]
y_data = [_data[1] for _data in data]
with FTool.PaintingWithList(name="Mean Shift") as paint:
paint.painting_simple_list(x_data, y_data)
# 训练，h=2
print("----------2.training ------------")
points, shift_points, cluster = train_mean_shift(data, 2)
# 保存所属的类别文件
print("----------3.1.save sub ------------")
with FTool.SaveModel(file_name="sub_1") as save_model:
save_model.save_model_mul(np.mat(cluster))
print("----------3.2.save center ------------")
# 保存聚类中心
with FTool.SaveModel(file_name="center_1") as save_model:
save_model.save_model_mul(shift_points)
after_x = list()
after_y = list()
for _position in range(len(shift_points)):
after_x.append(shift_points[_position, 0])
after_y.append(shift_points[_position, 1])
with FTool.PaintingWithList(name="Mean Shift Result") as paint:
paint.painting_list_with_label(after_x, after_y, cluster)
def k_means_pp():
"""
K-Means ++ 实现
:return:
"""
k = 4 # 聚类中心的个数
file_path = "data.txt"
# 1、导入数据
print("---------- 1.load data ------------")
data, _, _ = FTool.LoadData(file_name=file_path).load_data(
feature_end=0, need_label_length=True, need_list=True)
x_data = [_data[0] for _data in data]
y_data = [_data[1] for _data in data]
with FTool.PaintingWithList(name="K-Means") as paint:
paint.painting_simple_list(x_data, y_data)
# 2、KMeans++的聚类中心初始化方法
print("---------- 2.K-Means++ generate centers ------------")
data = np.mat(data)
centroids = get_centroids(data, k)
# 3、聚类计算
print("---------- 3.k-Means ------------")
sub_center = k_means_function(data, k, centroids)
# 4、保存所属的类别文件
print("---------- 4.save subCenter ------------")
with FTool.SaveModel(file_name="sub_pp") as save_model:
save_model.save_model_mul(sub_center)
# 5、保存聚类中心
print("---------- 5.save centroids ------------")
with FTool.SaveModel(file_name="center_pp") as save_model:
save_model.save_model_mul(centroids)
def k_means(k_class: int):
"""
The K-Means Function
:param k_class: 聚类中心的个数
:return:
"""
k = k_class # 聚类中心的个数
file_path = "data.txt"
# 1、导入数据
print("---------- 1.load data ------------")
data, _, _ = FTool.LoadData(file_name=file_path).load_data(feature_end=0, need_label_length=True, need_list=True)
x_data = [_data[0] for _data in data]
y_data = [_data[1] for _data in data]
with FTool.PaintingWithList(name="K-Means") as paint:
paint.painting_simple_list(x_data, y_data)
# 2、随机初始化k个聚类中心
print("---------- 2.random center ------------")
data = np.mat(data)
centroids = rand_cent(data, k)
# 3、聚类计算
print("---------- 3.kmeans ------------")
sub_center = k_means_function(data, k, centroids)
# 4、保存所属的类别文件
print("---------- 4.save subCenter ------------")
with FTool.SaveModel(file_name="sub") as save_model:
save_model.save_model_mul(sub_center)
# 5、保存聚类中心
print("---------- 5.save centroids ------------")
with FTool.SaveModel(file_name="center") as save_model:
save_model.save_model_mul(centroids)