class MyPLS():
def __init__(self,
n_components=2,
scale=True,
max_iter=500,
tol=1e-06,
copy=True):
self.pls = PLSRegression(n_components, scale, max_iter, tol, copy)
def fit(self, X, Y):
self.pls.fit(X, Y)
return self.pls
def predict(self, X, copy=True):
return self.pls.predict(X, copy).flatten()
def score(self, X, Y, sample_weight=None):
return self.pls.score(X, Y, sample_weight)
def get_params(self, deep=True):
return self.pls.get_params(deep)
def set_params(self, **parameters):
self.pls.set_params(**parameters)
return self
@property
def intercept_(self):
return 0
@property
def coeff_(self):
return self.pls.coef_
def test_parameters(self):
""" Testing parameters of Model class. """
#1.)
#create instance of PLS model using Model class & creating instance
# using SKlearn libary, comparing if the parameters of both instances are equal
pls_parameters = {"n_components": 20, "scale": False, "max_iter": 200}
model = Model(algorithm="PlsRegression", parameters=pls_parameters)
pls_model = PLSRegression(n_components=20, scale="svd", max_iter=200)
for k, v in model.model.get_params().items():
self.assertIn(k, list(pls_model.get_params()))
#2.)
rf_parameters = {"n_estimators": 200, "max_depth": 50,"min_samples_split": 10}
model = Model(algorithm="RandomForest", parameters=rf_parameters)
rf_model = RandomForestRegressor(n_estimators=200, max_depth=50, min_samples_split=10)
for k, v in model.model.get_params().items():
self.assertIn(k, list(rf_model.get_params()))
#3.)
knn_parameters = {"n_neighbors": 10, "weights": "distance", "algorithm": "ball_tree"}
model = Model(algorithm="KNN", parameters=knn_parameters)
knn_model = KNeighborsRegressor(n_neighbors=10, weights='distance', algorithm="kd_tree")
for k, v in model.model.get_params().items():
self.assertIn(k, list(knn_model.get_params()))
#4.)
svr_parameters = {"kernel": "poly", "degree": 5, "coef0": 1}
model = Model(algorithm="SVR",parameters=svr_parameters)
svr_model = SVR(kernel='poly', degree=5, coef0=1)
for k, v in model.model.get_params().items():
self.assertIn(k, list(svr_model.get_params()))
#5.)
ada_parameters = {"n_estimators": 150, "learning_rate": 1.2, "loss": "square"}
model = Model(algorithm="AdaBoost", parameters=ada_parameters)
ada_model = AdaBoostRegressor(n_estimators=150, learning_rate=1.2, loss="square")
for k, v in model.model.get_params().items():
self.assertIn(k, list(ada_model.get_params()))
#6.)
bagging_parameters = {"n_estimators": 50, "max_samples": 1.5, "max_features": 2}
model = Model(algorithm="Bagging", parameters=bagging_parameters)
bagging_model = BaggingRegressor(n_estimators=50, max_samples=1.5, max_features="square")
for k, v in model.model.get_params().items():
self.assertIn(k, list(bagging_model.get_params()))
#7.)
lasso_parameters = {"alpha": 1.5, "max_iter": 500, "tol": 0.004}
model = Model(algorithm="lasso", parameters=lasso_parameters)
lasso_model = Lasso(alpha=1.5, max_iter=500, tol=0.004)
for k, v in model.model.get_params().items():
self.assertIn(k, list(lasso_model.get_params()))
def _pls_regression_train(table, feature_cols, label_cols, n_components=2, scale=True, max_iter=500, tol=1e-6):
pls_model = PLS(n_components=n_components, scale=scale, max_iter=max_iter, tol=tol)
_, features = check_col_type(table, feature_cols)
_, labels = check_col_type(table, label_cols)
pls_model.fit(features, labels)
predict = pls_model.predict(features)
_mean_absolute_error = mean_absolute_error(labels, predict)
_mean_squared_error = mean_squared_error(labels, predict)
_r2_score = r2_score(labels, predict)
result_table = pd.DataFrame.from_items([
['Metric', ['Mean Absolute Error', 'Mean Squared Error', 'R2 Score']],
['Score', [_mean_absolute_error, _mean_squared_error, _r2_score]]
])
label_name = {
'n_components': 'Number of components',
'scale': "Scale",
'max_iter': 'Max iteration',
'tol': 'Tolerance'
}
get_param = pls_model.get_params()
param_table = pd.DataFrame.from_items([
['Parameter', list(label_name.values())],
['Value', [get_param[x] for x in list(label_name.keys())]]
])
rb = BrtcReprBuilder()
rb.addMD(strip_margin("""
| ### PLS Regression Result
| {result}
| ### Parameters
| {list_parameters}
""".format(result=pandasDF2MD(result_table), list_parameters=pandasDF2MD(param_table)
)))
model = _model_dict('pls_regression_model')
model['feature_cols'] = feature_cols
model['label'] = label_cols
model['mean_absolute_error'] = _mean_absolute_error
model['mean_squared_error'] = _mean_squared_error
model['r2_score'] = _r2_score
model['max_iter'] = max_iter
model['tol'] = tol
model['pls_model'] = pls_model
model['_repr_brtc_'] = rb.get()
return {'model': model}
class PLS(Model):
# X represents the features, Y represents the labels
X = None
Y = None
prediction = None
model = None
def __init__(self, X=None, Y=None, n_components=2, type='regressor', cfg=False):
self.name = 'PLS'
if X is not None:
self.X = X
if Y is not None:
self.Y = Y
self.type = type
self.cfg = cfg
self.n_components = n_components
self.model = PLSRegression(n_components=n_components)
def fit(self, X=None, Y=None):
if X is not None:
self.X = X
if Y is not None:
self.Y = Y
print('PLS Train started............')
self.model.fit(self.X, self.Y)
print('PLS completed..........')
return self.model
def fit_transform(self, X=None, Y=None):
if X is not None:
self.X = X
if Y is not None:
self.Y = Y
print('PLS Train/Transform started............')
self.X = self.model.fit_transform(self.X)
print('PLS completed..........')
self.X = pd.DataFrame(self.X)
return self.X
def predict(self, test_features):
print('Prediction started............')
self.predictions = self.model.predict(test_features)
print('Prediction completed..........')
return self.predictions
def save(self):
if self.cfg:
f = open('pls_configs.txt', 'w')
f.write(json.dumps(self.model.get_params()))
f.close()
print('No models will be saved for PLS')
def featureImportance(self):
# if X_headers is None:
# X_headers = list(self.X)
#
# feature_importance_ = zip(self.model.coef_.reshape(1,-1)[0], X_headers)
# feature_importance = set(feature_importance_)
return self.model.coef_
def getAccuracy(self, test_labels, predictions, origin=0, hitmissr=0.8):
correct = 0
df = pd.DataFrame(data=predictions.flatten())
for i in range(len(df)):
if 1 - abs(df.values[i] - test_labels.values[i])/abs(df.values[i]) >= hitmissr:
correct = correct + 1
return float(correct)/len(df)
def getConfusionMatrix(self, test_labels, predictions, label_headers):
return 'No Confusion Matrix for Regression'
def getRSquare(self, test_labels, predictions, mode='single'):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
if mode == 'multiple':
errors = r2_score(test_labels, df, multioutput='variance_weighted')
else:
errors = r2_score(test_labels, df)
return errors
else:
return 'No RSquare for Classification'
def getMSE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = mean_squared_error(test_labels, df)
return errors
else:
return 'No MSE for Classification'
def getMAPE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = np.mean(np.abs((test_labels - df.values) / test_labels)) * 100
return errors.values[0]
else:
return 'No MAPE for Classification'
def getRMSE(self, test_labels, predictions):
df = pd.DataFrame(data=predictions.flatten())
if self.type == 'regressor':
errors = sqrt(mean_squared_error(test_labels, df))
return errors
else:
return 'No RMSE for Classification'
l_p_t.append(vec_p)
l_c_t.append(vec_c)
j += 1
sorted_p = np.asarray(l_p)
sorted_c = np.asarray(l_c) #Convert the input to an array
plc = PLSCanonical()
plc.fit_transform(sorted_c, sorted_p)
sorted_c, sorted_p = plc.transform(sorted_c, sorted_p)
sorted_c_test = np.asarray(l_c_t)
sorted_p_test = np.asarray(l_p_t)
sorted_c_test, sorted_p_test = plc.transform(sorted_c_test, sorted_p_test)
plr = PLSRegression()
plr.fit(sorted_c, sorted_p)
params = plr.get_params()
plr.set_params(**params)
y_score = plr.predict(sorted_c_test)
sim_count = 0
print("Test Similarity: ")
for i in range(len(y_score)):
result_sim = 1 - spatial.distance.cosine(y_score[i], sorted_p_test[i])
if result_sim >= 0.85:
sim_count += 1
print("Data " + str(i + 1) + " : " + str(result_sim))
accuracy = float(sim_count) / float(len(y_score))
print("Accuracy: " + str(accuracy))
pls_HLJ = PLSRegression(n_components=2)
pls_HLJ.fit(X_PLSR_HLJ, Y_PLSR_HLJ)
# X_train_r, Y_train_r = pls_XZ.transform(X_PLSR_HLJ, Y_PLSR_HLJ)
# PLSRegression(copy=True, max_iter=500, n_components=2, scale=True, tol=1e-06)
Y_PLSpred_HLJ = pls_HLJ.predict(X_PLSR_HLJ)
Y_PLSpred_HLJ = np.vstack((Y_PLSpred_HLJ).T)[0]
# print(Y_PLSpred_HLJ)
# print(Y_train_r)
Y_PLSpred = np.vstack((Y_PLSpred_XZ, Y_PLSpred_XJ, Y_PLSpred_HLJ))# Pls预测值
Y_PLSpred_Target = np.vstack((Y_PLSR_XZ, Y_PLSR_XJ, Y_PLSR_HLJ)) # 目标值
# print(Y_PLSpred)
# print(Y_PLSpred)
aaa = pls_HLJ.get_params(deep=True) # 获取参数
print(aaa)
# 计算均方误差
def Rmse(predictions, targets):
return np.sqrt(np.mean((predictions - targets) ** 2))
rmse = {}
for ip in np.arange(3):
rmse[ip] = Rmse(Y_PLSpred_Target[ip, :], Y_PLSpred[ip, :])
print(rmse)
y22 = np.zeros((21, 6))
y22_1 = np.zeros((21, 6))
def main():
args = parser.parse_args()
# 模型选择及输入参数
model_name = {
1: 'PLSR',
2: 'LS-SVR',
3: 'GPR',
4: 'FCN',
5: 'LSTM',
6: 'GCN',
7: 'MC-GCN',
8: 'GC-LSTM'
}
print(model_name)
model_select = list(input('Select models:'))
# 初始化结果
results = {
'adj': [],
'r2': [],
'rmse': [],
'loss_hist': [],
'prediction': []
}
# os.mkdir('Results')
f = open('Results/params.txt', 'w+')
f.write('Parameters setting:\n{}\n\n'.format(args.__dict__))
# 导入数据
data = pd.read_excel('8号机磨煤机C_正常.xlsx',
index_col=0,
header=1,
nrows=args.length + 5001)
data = data.iloc[5001:, :]
# 数据划分
predict_variable = [3, 12, 15, 20, 23]
y = data.iloc[:, predict_variable]
X = data.drop(columns=y.columns)
X_train, y_train = X.iloc[:int(args.length * args.train_size
)], y.iloc[:int(args.length *
args.train_size)]
X_test, y_test = X.iloc[int(args.length * args.train_size
):], y.iloc[int(args.length *
args.train_size):]
# 导出数据
# X_train.to_csv('Results/X_train.csv', header=False, index=False)
# X_test.to_csv('Results/X_test.csv', header=False, index=False)
# y_train.to_csv('Results/y_train.csv', header=False, index=False)
# y_test.to_csv('Results/y_test.csv', header=False, index=False)
# 设定种子
np.random.seed(args.seed)
torch.manual_seed(args.seed)
# 多次实验
for exp in range(args.n_exp):
print('=====Experiment({}/{})====='.format(exp + 1, args.n_exp))
f.write('=====Experiment({}/{})=====\n'.format(exp + 1, args.n_exp))
results['adj'].append({})
results['r2'].append({})
results['rmse'].append({})
results['loss_hist'].append({})
results['prediction'].append({})
# PLSR
if '1' in model_select:
flag = 1
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = PLSRegression(args.n_components).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# LS-SVR
if '2' in model_select:
flag = 2
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = LssvrModel(args.c, args.sigma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# GPR
if '3' in model_select:
flag = 3
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
kernel = DotProduct() * RBF(args.length_scale,
(args.length_scale, args.length_scale))
reg = GaussianProcessRegressor(kernel=kernel,
alpha=args.alpha).fit(
X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# FCN
if '4' in model_select:
flag = 4
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = FcnModel(X_train.shape[1], y_train.shape[1],
(1024, 256, 256, 256), args.n_epoch,
args.batch_size, args.lr, args.weight_decay,
args.step_size, args.gamma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
results['loss_hist'][-1].update({model_name[flag]: reg.loss_hist})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# LSTM
if '5' in model_select:
flag = 5
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = LstmModel(X_train.shape[1], y_train.shape[1], (1024, ),
(256, 256, 256), args.seq_len, args.n_epoch,
args.batch_size, args.lr, args.weight_decay,
args.step_size, args.gamma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
results['loss_hist'][-1].update({model_name[flag]: reg.loss_hist})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# GCN
if '6' in model_select:
flag = 6
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = GcnModel(X_train.shape[1], y_train.shape[1], (1024, ),
(256, 256, 256), args.graph_reg, args.self_con,
args.n_epoch, args.batch_size, args.lr,
args.weight_decay, args.step_size,
args.gamma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
results['loss_hist'][-1].update({model_name[flag]: reg.loss_hist})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# MC-GCN
if '7' in model_select:
flag = 7
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = McgcnModel(X_train.shape[1], (1024, ), (256, ), (256, 256),
y_train.shape[1], args.graph_reg, args.self_con,
args.n_epoch, args.batch_size, args.lr,
args.weight_decay, args.step_size,
args.gamma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['adj'][-1].update({model_name[flag]: reg.adj})
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
results['loss_hist'][-1].update({model_name[flag]: reg.loss_hist})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# GC-LSTM
if '8' in model_select:
flag = 8
print('====={}====='.format(model_name[flag]))
f.write('====={}=====\n'.format(model_name[flag]))
# 训练&测试
t1 = time.time()
reg = GclstmModel(X_train.shape[1], (1024, ), (256, ), (256, 256),
y_train.shape[1], args.seq_len, args.graph_reg,
args.self_con, args.n_epoch, args.batch_size,
args.lr, args.weight_decay, args.step_size,
args.gamma).fit(X_train, y_train)
t2 = time.time()
y_pred = reg.predict(X_test)
t3 = time.time()
y_fit = reg.predict(X_train)
print(reg.get_params())
print('Time:\nFit: {:.3f}s Pred: {:.3f}s'.format(t2 - t1, t3 - t2))
print('R2:\nFit: {} Pred: {}'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 写入文件
f.write(str(reg.get_params()) + '\n')
f.write('Time:\nFit: {:.3f}s Pred: {:.3f}s\n'.format(
t2 - t1, t3 - t2))
f.write('R2:\nFit: {} Pred: {}\n'.format(
r2_score(y_train, y_fit, multioutput='raw_values'),
r2_score(y_test, y_pred, multioutput='raw_values')))
# 存储结果和模型
index = r2_rmse(y_test, y_pred, y.columns, f)
results['adj'][-1].update({model_name[flag]: reg.adj})
results['r2'][-1].update({model_name[flag]: index[0]})
results['rmse'][-1].update({model_name[flag]: index[1]})
results['prediction'][-1].update({model_name[flag]: y_pred})
results['loss_hist'][-1].update({model_name[flag]: reg.loss_hist})
joblib.dump(
reg, 'Results/{}-{}.model'.format(model_name[flag], exp + 1))
# 存储结果
np.save('Results/results.npy', results)
f.close()
if len(temp4) == 600 and len(temp3) == 300:
x_n.append(temp4)
y_n.append(temp3)
npx = np.asarray(x, dtype=np.float64)
npy = np.asarray(y, dtype=np.float64)
npxn = np.asarray(x_n, dtype=np.float64)
npyn = np.asarray(y_n, dtype=np.float64)
cca = PLSCanonical(n_components=2)
cca.fit_transform(npx, npy)
npx, npy = cca.transform(npx, npy)
npxn, npyn = cca.transform(npxn, npyn)
pls.fit(npx, npy)
params = pls.get_params(deep=True)
print(params)
pls.set_params(**params)
y_score = pls.predict(npxn)
sim_count = 0
tol = 0.1
for index in range(len(y_score)):
sub_result = np.subtract(y_score, npyn)
result = 1 - spatial.distance.cosine(y_score[index], npyn[index])
print("similarity of test example " + str(index) + " = " + str(result))
if (1 - math.fabs(result)) <= tol:
sim_count += 1