def loadData(self):
l = LoadData()
data_cluster = l.loadData('wine-clustering.csv')
self.std_scaler = StandardScaler()
self.min_max_scaler = MinMaxScaler()
data_cluster[data_cluster.columns] = self.std_scaler.fit_transform(
data_cluster)
data_cluster[data_cluster.columns] = self.min_max_scaler.fit_transform(
data_cluster)
# print(data_cluster.mean())
# data = data_cluster.to_numpy()
# np.savetxt('data.txt', data, fmt='%.1f')
# coverience_matrix = np.dot(np.transpose(data),
# data) / (data.shape[1] - 1)
# np.savetxt('matrix.txt', coverience_matrix, fmt='%.1f')
# pca
self.pca_2 = PCA(2)
self.pca_2_result = self.pca_2.fit_transform(data_cluster)
self.data = data_cluster
def loadData(self, filename):
l = LoadData()
self.data = l.loadData(filename)
# encoding=utf-8
'''
Created on 2018年1月6日
@author: yufangzheng
'''
from LoadData import LoadData;
from Model import SVD;
if __name__ == "__main__":
feature = 100
steps = 30
alpha = 0.009
lambda1 = 0.01
ld = LoadData()
filename_train = '/home/zwp/work/Dataset/ws/train/sparseness5/training1.txt'
filename_test = '/home/zwp/work/Dataset/ws/test/sparseness5/test1.txt';
train, test = ld.loadData(filename_train, filename_test)
model = SVD(train,test,feature,steps,alpha,lambda1)
model.initialParameter()
model.learnMF()
MAE,RMSE = model.calMAEAndRMSE()
print (MAE,RMSE)
def loadData(self, train_size):
l = LoadData()
self.data = l.loadData(train_size)
