mirror of
https://github.com/webclinic017/drift.git
synced 2026-07-28 11:17:47 +00:00
Mark Aron Szulyovszky
9488e92597
* feature(MetaLabeling): added hacky prototype * fix(MetaLabeling): drop index until first valid X & y * fix(MetaLabeling): transform both X & y before feature selection * fix(MetaLabeling): got feature selection to work * fix(MetaLabeling): correct values for meta_y * feat(MetaLabeling): created predictions multiplied by bet sizes * feat(Pipeline): print out averaged result * fix(Evaluation): correctly deal with non-discretized data * fix(Pipeline): use the right column names * refactor(Pipeline): move out meta-labeling * refactor(Pipeline): complete refactoring * feat(CI): post results to PR * fix(Pipeline): use the correct filename * chore(Config): removed now redundant feature_selection flag * feat(Models): added SVC * fix(Pipeline): accidentally switched two return values * feat(Sweep): prepared sweep_meta.yaml, moved report_results() into a separate file * fix(Pipeline): wrong function name * fix(Sweep): yaml + run_sweep * fix(Sweep): typo in name * fix(Reporting): only save averaged results * feat(MetaLabeling): use optional meta-labeling step for every lvl1 models, before averaging * feat(Reporting): print out sharpe improvement in meta-labeling step * fix(Sweep): adjusted config, defaulted to good defaults * fix(Sweep): adjusted sweep
93 lines
3.3 KiB
Python
93 lines
3.3 KiB
Python
import pandas as pd
|
|
from models.base import Model
|
|
import numpy as np
|
|
from utils.helpers import get_first_valid_return_index
|
|
from tqdm import tqdm
|
|
|
|
from sklearn.base import clone
|
|
|
|
def walk_forward_train_test(
|
|
model_name: str,
|
|
model: Model,
|
|
X: pd.DataFrame,
|
|
y: pd.Series,
|
|
target_returns: pd.Series,
|
|
expanding_window: bool,
|
|
window_size: int,
|
|
retrain_every: int,
|
|
scaler,
|
|
) -> tuple[pd.Series, pd.Series, pd.DataFrame]:
|
|
assert len(X) == len(y)
|
|
predictions = pd.Series(index=y.index).rename(model_name)
|
|
probabilities = pd.DataFrame(index=y.index)
|
|
models = pd.Series(index=y.index).rename(model_name)
|
|
|
|
first_nonzero_return = max(get_first_valid_return_index(target_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
|
|
train_from = first_nonzero_return + window_size + 1
|
|
train_till = len(y)
|
|
iterations_before_retrain = 0
|
|
|
|
if model.only_column is not None:
|
|
X = X[[column for column in X.columns if model.only_column in column]]
|
|
|
|
|
|
|
|
is_scaling_on = scaler is not None and model.data_scaling == 'scaled'
|
|
|
|
if is_scaling_on:
|
|
scaler = clone(scaler)
|
|
|
|
for index in tqdm(range(train_from, train_till)):
|
|
if expanding_window:
|
|
train_window_start = first_nonzero_return
|
|
else:
|
|
train_window_start = index - window_size - 1
|
|
|
|
if iterations_before_retrain <= 0 or pd.isna(models[index-1]):
|
|
|
|
train_window_end = index - 1
|
|
|
|
if is_scaling_on:
|
|
# We need to fit on the expanding window data slice
|
|
# This is our only way to avoid lookahead bias
|
|
X_expanding_window = X[first_nonzero_return:train_window_end]
|
|
scaler.fit(X_expanding_window.values)
|
|
|
|
X_slice = X[train_window_start:train_window_end]
|
|
y_slice = y[train_window_start:train_window_end]
|
|
|
|
if is_scaling_on:
|
|
X_slice = scaler.transform(X_slice.values)
|
|
else:
|
|
X_slice = X_slice.to_numpy()
|
|
|
|
|
|
current_model = model.clone()
|
|
|
|
current_model.initialize_network(input_dim = len(X_slice[0]), output_dim=1)
|
|
current_model.fit(X_slice, y_slice.to_numpy())
|
|
|
|
iterations_before_retrain = retrain_every
|
|
else:
|
|
current_model = models[index-1]
|
|
|
|
models[index] = current_model
|
|
|
|
if model.predict_window_size == 'window_size':
|
|
next_timestep = X.iloc[train_window_start:index].to_numpy()#.reshape(1, -1)
|
|
else:
|
|
next_timestep = X.iloc[index].to_numpy().reshape(1, -1)
|
|
|
|
if is_scaling_on:
|
|
next_timestep = scaler.transform(next_timestep)
|
|
|
|
prediction, probs = current_model.predict(next_timestep)
|
|
predictions[index] = prediction
|
|
if len(probabilities.columns) != len(probs):
|
|
probabilities = probabilities.reindex(columns = ["prob_" + str(num) for num in range(0, len(probs.T))])
|
|
probabilities.iloc[index] = probs
|
|
|
|
iterations_before_retrain -= 1
|
|
|
|
return models, predictions, probabilities
|