mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-06 23:57:49 +00:00
Refactor(Training): new outcome types, representative pipeline steps, bet-sizing (#187)
* refactor(Training): added InferenceResult & TrainedModel types * refactor(Pipeline): introduced TrainingOutcome, BetSizingWithMetaOutcome, etc. * fix(Pipeline): getting it to compile * refactor(WalkForward): separate preprocessing step * feat(Pipeline): separate out transformations processing step * refactor(Pipeline): use the Directional model terminology, put bet_sizing into pipeline instead of hiding it in a step * refactor(WalkForward): moved functions to separate folder * fix(WalkForward): use sparse array to store models, process transformations in parallel (lot faster) * fix(Tests): and evaluation * fix(Tests): for realz * fix(Inference): preloading everything now, renamed primary models to directional models * fix(BetSizing): was running transformations on the wrong data, oops * fix(BetSizing): concatenated on the wrong axis accidentally * fix(Reporting): able to use the new Stats type * fix(BetSizing): renamed int column names * fix(Portfolio): name the column properly * fix(Reporting): rename the correct Series, lol * fix(Inference): walk_forwad_inference() can deal with models not being aligned with the starting index * fix(WalkForward): accidentally using the wrong index * fix(WalkForward): use the correct indicies to fetch last model/transformations * fix(CI): changed the name of the results
This commit is contained in:
Mark Aron Szulyovszky
committed by
GitHub
GitHub
parent
42a1bc59cb
commit
3eb3ea94e3
@@ -1,32 +0,0 @@
|
||||
from __future__ import annotations
|
||||
from models.base import Model
|
||||
import numpy as np
|
||||
|
||||
class StaticAverageModel(Model):
|
||||
'''
|
||||
Model that averages .
|
||||
'''
|
||||
|
||||
data_transformation = 'original'
|
||||
only_column = 'model_'
|
||||
model_type = 'static'
|
||||
predict_window_size = 'single_timestamp'
|
||||
|
||||
def fit(self, X: np.ndarray, y: np.ndarray) -> None:
|
||||
# This is a static model, it can' learn anything
|
||||
pass
|
||||
|
||||
def predict(self, X) -> tuple[float, np.ndarray]:
|
||||
# Make sure there's data to average
|
||||
assert X.shape[1] > 0
|
||||
prediction = np.average(X[-1])
|
||||
return (prediction, np.array([]))
|
||||
|
||||
def clone(self) -> StaticAverageModel:
|
||||
return self
|
||||
|
||||
def get_name(self) -> str:
|
||||
return 'static_average'
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
+1
-4
@@ -5,6 +5,7 @@ import numpy as np
|
||||
|
||||
class Model(ABC):
|
||||
|
||||
name: str = ""
|
||||
method: Literal["regression", "classification"]
|
||||
data_transformation: Literal["transformed", "original"]
|
||||
only_column: Optional[str]
|
||||
@@ -22,10 +23,6 @@ class Model(ABC):
|
||||
@abstractmethod
|
||||
def clone(self) -> Model:
|
||||
raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
def get_name(self) -> str:
|
||||
raise NotImplementedError
|
||||
|
||||
@abstractmethod
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
|
||||
+29
-26
@@ -4,89 +4,92 @@ from sklearnex.ensemble import RandomForestRegressor
|
||||
from .base import Model
|
||||
|
||||
default_feature_selector_classification = SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1), 'classification')
|
||||
default_feature_selector_regression = SKLearnModel(RandomForestRegressor(n_jobs=-1, max_depth=20, random_state=1), 'regression')
|
||||
|
||||
def get_model(model_name: str) -> Model:
|
||||
|
||||
def set_name(model: Model) -> Model:
|
||||
model.name = model_name
|
||||
return model
|
||||
|
||||
if model_name == 'LinearRegression':
|
||||
from sklearn.linear_model import LinearRegression
|
||||
return SKLearnModel(LinearRegression(n_jobs=-1), 'regression')
|
||||
return set_name(SKLearnModel(LinearRegression(n_jobs=-1), 'regression'))
|
||||
elif model_name == 'Lasso':
|
||||
from sklearn.linear_model import Lasso
|
||||
return SKLearnModel(Lasso(alpha=100, random_state=1), 'regression')
|
||||
return set_name(SKLearnModel(Lasso(alpha=100, random_state=1), 'regression'))
|
||||
elif model_name == 'Ridge':
|
||||
from sklearn.linear_model import Ridge
|
||||
return SKLearnModel(Ridge(alpha=0.1), 'regression')
|
||||
return set_name(SKLearnModel(Ridge(alpha=0.1), 'regression'))
|
||||
elif model_name == 'BayesianRidge':
|
||||
from sklearn.linear_model import BayesianRidge
|
||||
return SKLearnModel(BayesianRidge(), 'regression')
|
||||
return set_name(SKLearnModel(BayesianRidge(), 'regression'))
|
||||
elif model_name == 'KNN':
|
||||
from sklearnex.neighbors import KNeighborsRegressor
|
||||
return SKLearnModel(KNeighborsRegressor(n_neighbors=25), 'regression')
|
||||
return set_name(SKLearnModel(KNeighborsRegressor(n_neighbors=25), 'regression'))
|
||||
elif model_name == 'AB':
|
||||
from sklearn.ensemble import AdaBoostRegressor
|
||||
return SKLearnModel(AdaBoostRegressor(random_state=1), 'regression')
|
||||
return set_name(SKLearnModel(AdaBoostRegressor(random_state=1), 'regression'))
|
||||
elif model_name == 'MLP':
|
||||
from sklearn.neural_network import MLPRegressor
|
||||
return SKLearnModel(MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000), 'regression')
|
||||
return set_name(SKLearnModel(MLPRegressor(hidden_layer_sizes=(100,20), max_iter=1000), 'regression'))
|
||||
elif model_name == 'RFR':
|
||||
return SKLearnModel(RandomForestRegressor(n_jobs=-1, max_depth=20, random_state=1), 'regression')
|
||||
return set_name(SKLearnModel(RandomForestRegressor(n_jobs=-1, max_depth=20, random_state=1), 'regression'))
|
||||
elif model_name == 'SVR':
|
||||
from sklearnex.svm import SVR
|
||||
return SKLearnModel(SVR(kernel='rbf', C=1e3, gamma=0.1), 'regression')
|
||||
return set_name(SKLearnModel(SVR(kernel='rbf', C=1e3, gamma=0.1), 'regression'))
|
||||
elif model_name == 'StaticNaive':
|
||||
from models.naive import StaticNaiveModel
|
||||
return StaticNaiveModel()
|
||||
return set_name(StaticNaiveModel())
|
||||
elif model_name == 'DNN':
|
||||
from models.neural import LightningNeuralNetModel
|
||||
from models.pytorch.neural_nets import MultiLayerPerceptron
|
||||
import torch.nn.functional as F
|
||||
return LightningNeuralNetModel(
|
||||
return set_name(LightningNeuralNetModel(
|
||||
MultiLayerPerceptron(
|
||||
hidden_layers_ratio = [1.0],
|
||||
probabilities = False,
|
||||
loss_function = F.mse_loss),
|
||||
max_epochs=15
|
||||
)
|
||||
))
|
||||
|
||||
elif model_name == 'LogisticRegression_two_class':
|
||||
from sklearn.linear_model import LogisticRegression
|
||||
return SKLearnModel(LogisticRegression(C=10, random_state=1, solver='liblinear', max_iter=1000), 'classification')
|
||||
return set_name(SKLearnModel(LogisticRegression(C=10, random_state=1, solver='liblinear', max_iter=1000), 'classification'))
|
||||
elif model_name == 'LogisticRegression_three_class':
|
||||
from sklearnex.linear_model import LogisticRegression as LogisticRegression_EX
|
||||
return SKLearnModel(LogisticRegression_EX(C=10, random_state=1, max_iter=1000, n_jobs=-1), 'classification')
|
||||
return set_name(SKLearnModel(LogisticRegression_EX(C=10, random_state=1, max_iter=1000, n_jobs=-1), 'classification'))
|
||||
elif model_name == 'LDA':
|
||||
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
|
||||
return SKLearnModel(LinearDiscriminantAnalysis(), 'classification')
|
||||
return set_name(SKLearnModel(LinearDiscriminantAnalysis(), 'classification'))
|
||||
elif model_name == 'KNN':
|
||||
from sklearn.neighbors import KNeighborsClassifier
|
||||
return SKLearnModel(KNeighborsClassifier(), 'classification')
|
||||
return set_name(SKLearnModel(KNeighborsClassifier(), 'classification'))
|
||||
elif model_name == 'CART':
|
||||
from sklearn.tree import DecisionTreeClassifier
|
||||
return SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1), 'classification')
|
||||
return set_name(SKLearnModel(DecisionTreeClassifier(max_depth=15, random_state=1), 'classification'))
|
||||
elif model_name == 'NB':
|
||||
from sklearn.naive_bayes import GaussianNB
|
||||
return SKLearnModel(GaussianNB(), 'classification')
|
||||
return set_name(SKLearnModel(GaussianNB(), 'classification'))
|
||||
elif model_name == 'AB':
|
||||
from sklearn.ensemble import AdaBoostClassifier
|
||||
return SKLearnModel(AdaBoostClassifier(n_estimators=15), 'classification')
|
||||
return set_name(SKLearnModel(AdaBoostClassifier(n_estimators=15), 'classification'))
|
||||
elif model_name == 'RFC':
|
||||
return SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1), 'classification')
|
||||
return set_name(SKLearnModel(RandomForestClassifier(n_jobs=-1, max_depth=20, random_state=1), 'classification'))
|
||||
elif model_name == 'SVC':
|
||||
from sklearn.svm import SVC
|
||||
return SKLearnModel(SVC(kernel='rbf', C=1e3, probability=True, random_state=1), 'classification')
|
||||
return set_name(SKLearnModel(SVC(kernel='rbf', C=1e3, probability=True, random_state=1), 'classification'))
|
||||
elif model_name == 'XGB_two_class':
|
||||
from xgboost import XGBClassifier
|
||||
from models.xgboost import XGBoostModel
|
||||
return XGBoostModel(XGBClassifier(n_jobs=-1, max_depth = 20, random_state=1, objective='binary:logistic', use_label_encoder= False, eval_metric='mlogloss'))
|
||||
return set_name(XGBoostModel(XGBClassifier(n_jobs=-1, max_depth = 20, random_state=1, objective='binary:logistic', use_label_encoder= False, eval_metric='mlogloss')))
|
||||
elif model_name == 'LGBM':
|
||||
from lightgbm import LGBMClassifier
|
||||
return SKLearnModel(LGBMClassifier(n_jobs=-1, max_depth=20, random_state=1), 'classification')
|
||||
return set_name(SKLearnModel(LGBMClassifier(n_jobs=-1, max_depth=20, random_state=1), 'classification'))
|
||||
elif model_name == 'StaticMom':
|
||||
from models.momentum import StaticMomentumModel
|
||||
return StaticMomentumModel(allow_short=True)
|
||||
return set_name(StaticMomentumModel(allow_short=True))
|
||||
elif model_name == 'Average':
|
||||
from models.average import StaticAverageModel
|
||||
return StaticAverageModel()
|
||||
return set_name(StaticAverageModel())
|
||||
else:
|
||||
raise Exception(f'Model {model_name} not found')
|
||||
@@ -28,9 +28,6 @@ class StaticMomentumModel(Model):
|
||||
|
||||
def clone(self) -> StaticMomentumModel:
|
||||
return self
|
||||
|
||||
def get_name(self) -> str:
|
||||
return 'static_mom'
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
@@ -23,8 +23,5 @@ class StaticNaiveModel(Model):
|
||||
def clone(self) -> StaticNaiveModel:
|
||||
return self
|
||||
|
||||
def get_name(self) -> str:
|
||||
return 'static_naive'
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
@@ -36,7 +36,3 @@ class LightningNeuralNetModel(Model):
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
self.model.initialize_network(input_dim, output_dim)
|
||||
|
||||
def get_name(self) -> str:
|
||||
return self.model.__class__.__name__
|
||||
|
||||
@@ -27,9 +27,6 @@ class SKLearnModel(Model):
|
||||
|
||||
def clone(self) -> SKLearnModel:
|
||||
return SKLearnModel(clone(self.model), self.method)
|
||||
|
||||
def get_name(self) -> str:
|
||||
return self.model.__class__.__name__
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
|
||||
@@ -25,9 +25,6 @@ class StatsModel(Model):
|
||||
|
||||
def clone(self) -> StatsModel:
|
||||
return StatsModel(deepcopy(self.model))
|
||||
|
||||
def get_name(self) -> str:
|
||||
return self.model.__class__.__name__
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
|
||||
@@ -27,9 +27,6 @@ class XGBoostModel(Model):
|
||||
|
||||
def clone(self) -> XGBoostModel:
|
||||
return XGBoostModel(clone(self.model))
|
||||
|
||||
def get_name(self) -> str:
|
||||
return self.model.__class__.__name__
|
||||
|
||||
def initialize_network(self, input_dim:int, output_dim:int):
|
||||
pass
|
||||
|
||||
Reference in New Issue
Block a user