liuyu/qlib
1
0
Fork 0
mirror of https://github.com/microsoft/qlib.git synced 2026-07-03 11:00:57 +08:00
Code Activity

Use average weights in DoubleEnsemble. (#1205)

Browse Source 
* Use average weights in DoubleEnsemble.

* Use average weights in DoubleEnsemble.

Co-authored-by: lwwang1995 <lewenwang@msrawsa02.corp.microsoft.com>
This commit is contained in:
Lewen Wang
2022-07-17 23:02:46 +08:00
committed by GitHub
parent 6fddae9965
commit d149c2b177
4 changed files with 15 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha158.yaml
View File

@@ -37,7 +37,7 @@ task:
kwargs:
base_model: "gbm"
loss: mse
num_models: 6
num_models: 3
enable_sr: True
enable_fs: True
alpha1: 1
@@ -53,11 +53,8 @@ task:
- 0.4
sub_weights:
- 1
- 0.2
- 0.2
- 0.2
- 0.2
- 0.2
- 1
- 1
epochs: 28
colsample_bytree: 0.8879
learning_rate: 0.2

9
examples/benchmarks/DoubleEnsemble/workflow_config_doubleensemble_Alpha360.yaml
View File

@@ -44,7 +44,7 @@ task:
kwargs:
base_model: "gbm"
loss: mse
num_models: 6
num_models: 3
enable_sr: True
enable_fs: True
alpha1: 1
@@ -60,11 +60,8 @@ task:
- 0.4
sub_weights:
- 1
- 0.2
- 0.2
- 0.2
- 0.2
- 0.2
- 1
- 1
epochs: 136
colsample_bytree: 0.8879
learning_rate: 0.0421

5
examples/benchmarks/README.md
View File

@@ -43,8 +43,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
| TFT (Bryan Lim, et al.) | Alpha158(with selected 20 features) | 0.0358±0.00 | 0.2160±0.03 | 0.0116±0.01 | 0.0720±0.03 | 0.0847±0.02 | 0.8131±0.19 | -0.1824±0.03 |
| MLP | Alpha158 | 0.0376±0.00 | 0.2846±0.02 | 0.0429±0.00 | 0.3220±0.01 | 0.0895±0.02 | 1.1408±0.23 | -0.1103±0.02 |
| LightGBM(Guolin Ke, et al.) | Alpha158 | 0.0448±0.00 | 0.3660±0.00 | 0.0469±0.00 | 0.3877±0.00 | 0.0901±0.00 | 1.0164±0.00 | -0.1038±0.00 |
| DoubleEnsemble(Chuheng Zhang, et al.) | Alpha158 | 0.0544±0.00 | 0.4340±0.00 | 0.0523±0.00 | 0.4284±0.01 | 0.1168±0.01 | 1.3384±0.12 | -0.1036±0.01 |
| DoubleEnsemble(Chuheng Zhang, et al.) | Alpha158 | 0.0521±0.00 | 0.4223±0.01 | 0.0502±0.00 | 0.4117±0.01 | 0.1158±0.01 | 1.3432±0.11 | -0.0920±0.01 |
### Alpha360 dataset
@@ -56,7 +55,7 @@ The numbers shown below demonstrate the performance of the entire `workflow` of
| Localformer(Juyong Jiang, et al.) | Alpha360 | 0.0404±0.00 | 0.2932±0.04 | 0.0542±0.00 | 0.4110±0.03 | 0.0246±0.02 | 0.3211±0.21 | -0.1095±0.02 |
| CatBoost((Liudmila Prokhorenkova, et al.) | Alpha360 | 0.0378±0.00 | 0.2714±0.00 | 0.0467±0.00 | 0.3659±0.00 | 0.0292±0.00 | 0.3781±0.00 | -0.0862±0.00 |
| XGBoost(Tianqi Chen, et al.) | Alpha360 | 0.0394±0.00 | 0.2909±0.00 | 0.0448±0.00 | 0.3679±0.00 | 0.0344±0.00 | 0.4527±0.02 | -0.1004±0.00 |
| DoubleEnsemble(Chuheng Zhang, et al.) | Alpha360 | 0.0404±0.00 | 0.3023±0.00 | 0.0495±0.00 | 0.3898±0.00 | 0.0468±0.01 | 0.6302±0.20 | -0.0860±0.01 |
| DoubleEnsemble(Chuheng Zhang, et al.) | Alpha360 | 0.0390±0.00 | 0.2946±0.01 | 0.0486±0.00 | 0.3836±0.01 | 0.0462±0.01 | 0.6151±0.18 | -0.0915±0.01 |
| LightGBM(Guolin Ke, et al.) | Alpha360 | 0.0400±0.00 | 0.3037±0.00 | 0.0499±0.00 | 0.4042±0.00 | 0.0558±0.00 | 0.7632±0.00 | -0.0659±0.00 |
| TCN(Shaojie Bai, et al.) | Alpha360 | 0.0441±0.00 | 0.3301±0.02 | 0.0519±0.00 | 0.4130±0.01 | 0.0604±0.02 | 0.8295±0.34 | -0.1018±0.03 |
| ALSTM (Yao Qin, et al.) | Alpha360 | 0.0497±0.00 | 0.3829±0.04 | 0.0599±0.00 | 0.4736±0.03 | 0.0626±0.02 | 0.8651±0.31 | -0.0994±0.03 |

11
qlib/contrib/model/double_ensemble.py
View File

@@ -44,7 +44,7 @@ class DEnsembleModel(Model, FeatureInt):
if sample_ratios is None: # the default values for sample_ratios
sample_ratios = [0.8, 0.7, 0.6, 0.5, 0.4]
if sub_weights is None: # the default values for sub_weights
sub_weights = [1.0, 0.2, 0.2, 0.2, 0.2, 0.2]
sub_weights = [1] * self.num_models
if not len(sample_ratios) == bins_fs:
raise ValueError("The length of sample_ratios should be equal to bins_fs.")
self.sample_ratios = sample_ratios
@@ -87,7 +87,9 @@ class DEnsembleModel(Model, FeatureInt):
loss_curve = self.retrieve_loss_curve(model_k, df_train, features)
pred_k = self.predict_sub(model_k, df_train, features)
pred_sub.iloc[:, k] = pred_k
pred_ensemble = pred_sub.iloc[:, : k + 1].mean(axis=1)
pred_ensemble = (pred_sub.iloc[:, : k + 1] * self.sub_weights[0 : k + 1]).sum(axis=1) / np.sum(
self.sub_weights[0 : k + 1]
)
loss_values = pd.Series(self.get_loss(y_train.values.squeeze(), pred_ensemble.values))
if self.enable_sr:
@@ -159,8 +161,8 @@ class DEnsembleModel(Model, FeatureInt):
h["bins"] = pd.cut(h["h_value"], self.bins_sr)
h_avg = h.groupby("bins")["h_value"].mean()
weights = pd.Series(np.zeros(N, dtype=float))
for i_b, b in enumerate(h_avg.index):
weights[h["bins"] == b] = 1.0 / (self.decay**k_th * h_avg[i_b] + 0.1)
for b in h_avg.index:
weights[h["bins"] == b] = 1.0 / (self.decay**k_th * h_avg[b] + 0.1)
return weights
def feature_selection(self, df_train, loss_values):
@@ -246,6 +248,7 @@ class DEnsembleModel(Model, FeatureInt):
pd.Series(submodel.predict(x_test.loc[:, feat_sub].values), index=x_test.index)
* self.sub_weights[i_sub]
)
pred = pred / np.sum(self.sub_weights)
return pred
def predict_sub(self, submodel, df_data, features):