liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-13 15:56:57 +08:00
Code Activity

Merge branch 'main' of https://github.com/you-n-g/qlib into main

Browse Source
This commit is contained in:
Alex Wang
2020-11-26 14:35:35 +08:00
parent 28b11886dd 305b9372c7
commit 7a5153f7c7
39 changed files with 809 additions and 637 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
qlib/contrib/model/catboost_model.py
View File

@@ -34,14 +34,14 @@ class CatBoostModel(Model):
def fit(
self,
dataset: DatasetH,
num_boost_round=1000,
early_stopping_rounds=50,
verbose_eval=20,
evals_result=dict(),
num_boost_round = 1000,
early_stopping_rounds = 50,
verbose_eval = 20,
evals_result = dict(),
**kwargs
):
df_train, df_valid = dataset.prepare(
["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
["train", "valid"], col_set = ["feature", "label"], data_key = DataHandlerLP.DK_L
)
x_train, y_train = df_train["feature"], df_train["label"]
x_valid, y_valid = df_valid["feature"], df_valid["label"]
@@ -52,8 +52,8 @@ class CatBoostModel(Model):
else:
raise ValueError("CatBoost doesn't support multi-label training")
train_pool = Pool(data=x_train, label=y_train_1d)
valid_pool = Pool(data=x_valid, label=y_valid_1d)
train_pool = Pool(data = x_train, label = y_train_1d)
valid_pool = Pool(data = x_valid, label = y_valid_1d)
# Initialize the catboost model
self._params["iterations"] = num_boost_round
@@ -63,7 +63,7 @@ class CatBoostModel(Model):
self.model = CatBoost(self._params, **kwargs)
# train the model
self.model.fit(train_pool, eval_set=valid_pool, use_best_model=True, **kwargs)
self.model.fit(train_pool, eval_set = valid_pool, use_best_model = True, **kwargs)
evals_result = self.model.get_evals_result()
evals_result["train"] = list(evals_result["learn"].values())[0]
@@ -72,8 +72,8 @@ class CatBoostModel(Model):
def predict(self, dataset):
if self.model is None:
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(x_test.values), index=x_test.index)
x_test = dataset.prepare("test", col_set = "feature")
return pd.Series(self.model.predict(x_test.values), index = x_test.index)
if __name__ == "__main__":

23
qlib/contrib/model/pytorch_gats.py
View File

@@ -28,14 +28,12 @@ class GAT(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimensions for each time step
metric : str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -119,11 +117,7 @@ class GAT(Model):
seed,
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.GAT_model = GATModel(
d_feat=self.d_feat,
hidden_size=self.hidden_size,
@@ -213,7 +207,6 @@ class GAT(Model):
losses = []
indices = np.arange(len(x_values))
np.random.shuffle(indices)
for i in range(len(indices))[:: self.batch_size]:
@@ -377,7 +370,6 @@ class GATModel(nn.Module):
self.fc_out = nn.Linear(hidden_size, 1)
self.leaky_relu = nn.LeakyReLU()
self.softmax = nn.Softmax(dim=1)
self.d_feat = d_feat
def cal_convariance(self, x, y): # the 2nd dimension of x and y are the same
@@ -396,12 +388,7 @@ class GATModel(nn.Module):
out, _ = self.rnn(x)
hidden = out[:, -1, :]
hidden = self.bn1(hidden)
gamma = self.cal_convariance(hidden, hidden)
# gamma = hidden.mm(torch.t(hidden))
# gamma = self.leaky_relu(gamma)
# gamma = self.softmax(gamma)
# gamma = gamma * (torch.ones(x.shape[0], x.shape[0]).to(device) - torch.diag(torch.ones(x.shape[0])).to(device))
output = gamma.mm(hidden)
output = self.fc(output)
output = self.bn2(output)

17
qlib/contrib/model/pytorch_gru.py
View File

@@ -28,14 +28,10 @@ class GRU(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimension for each time step
metric: str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -112,10 +108,6 @@ class GRU(Model):
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.gru_model = GRUModel(
d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
)
@@ -251,7 +243,6 @@ class GRU(Model):
# train
self.logger.info("training...")
self._fitted = True
# return
for step in range(self.n_epochs):
self.logger.info("Epoch%d:", step)

17
qlib/contrib/model/pytorch_lstm.py
View File

@@ -28,14 +28,10 @@ class LSTM(Model):
Parameters
----------
input_dim : int
input dimension
output_dim : int
output dimension
layers : tuple
layer sizes
lr : float
learning rate
d_feat : int
input dimension for each time step
metric: str
the evaluate metric used in early stop
optimizer : str
optimizer name
GPU : str
@@ -112,10 +108,6 @@ class LSTM(Model):
)
)
if loss not in {"mse", "binary"}:
raise NotImplementedError("loss {} is not supported!".format(loss))
self._scorer = mean_squared_error if loss == "mse" else roc_auc_score
self.lstm_model = LSTMModel(
d_feat=self.d_feat, hidden_size=self.hidden_size, num_layers=self.num_layers, dropout=self.dropout
)
@@ -251,7 +243,6 @@ class LSTM(Model):
# train
self.logger.info("training...")
self._fitted = True
# return
for step in range(self.n_epochs):
self.logger.info("Epoch%d:", step)

36
qlib/contrib/model/xgboost.py
View File

@@ -22,25 +22,23 @@ from ...data.dataset.handler import DataHandlerLP
class XGBModel(Model):
"""XGBModel Model"""
def __init__(self, obj="mse", **kwargs):
if obj not in {"mse", "binary"}:
raise NotImplementedError
self._params = {"obj": obj}
def __init__(self, **kwargs):
self._params = {}
self._params.update(kwargs)
self.model = None
def fit(
self,
dataset: DatasetH,
num_boost_round=1000,
early_stopping_rounds=50,
verbose_eval=20,
evals_result=dict(),
num_boost_round = 1000,
early_stopping_rounds = 50,
verbose_eval = 20,
evals_result = dict(),
**kwargs
):
df_train, df_valid = dataset.prepare(
["train", "valid"], col_set=["feature", "label"], data_key=DataHandlerLP.DK_L
["train", "valid"], col_set = ["feature", "label"], data_key = DataHandlerLP.DK_L
)
x_train, y_train = df_train["feature"], df_train["label"]
x_valid, y_valid = df_valid["feature"], df_valid["label"]
@@ -51,16 +49,16 @@ class XGBModel(Model):
else:
raise ValueError("XGBoost doesn't support multi-label training")
dtrain = xgb.DMatrix(x_train.values, label=y_train_1d)
dvalid = xgb.DMatrix(x_valid.values, label=y_valid_1d)
dtrain = xgb.DMatrix(x_train.values, label = y_train_1d)
dvalid = xgb.DMatrix(x_valid.values, label = y_valid_1d)
self.model = xgb.train(
self._params,
dtrain=dtrain,
num_boost_round=num_boost_round,
evals=[(dtrain, "train"), (dvalid, "valid")],
early_stopping_rounds=early_stopping_rounds,
verbose_eval=verbose_eval,
evals_result=evals_result,
dtrain = dtrain,
num_boost_round = num_boost_round,
evals = [(dtrain, "train"), (dvalid, "valid")],
early_stopping_rounds = early_stopping_rounds,
verbose_eval = verbose_eval,
evals_result = evals_result,
**kwargs
)
evals_result["train"] = list(evals_result["train"].values())[0]
@@ -69,5 +67,5 @@ class XGBModel(Model):
def predict(self, dataset):
if self.model is None:
raise ValueError("model is not fitted yet!")
x_test = dataset.prepare("test", col_set="feature")
return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index=x_test.index)
x_test = dataset.prepare("test", col_set = "feature")
return pd.Series(self.model.predict(xgb.DMatrix(x_test.values)), index = x_test.index)