mirror of
https://github.com/webclinic017/drift.git
synced 2026-08-05 07:07:46 +00:00
Mark Aron Szulyovszky
3eb3ea94e3
* 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
59 lines
3.0 KiB
Python
59 lines
3.0 KiB
Python
import pandas as pd
|
|
from training.types import ModelOverTime, TransformationsOverTime, PredictionsSeries, ProbabilitiesDataFrame
|
|
from utils.helpers import get_first_valid_return_index
|
|
from tqdm import tqdm
|
|
from typing import Optional
|
|
from data_loader.types import XDataFrame
|
|
from utils.helpers import get_last_non_na_index
|
|
|
|
def walk_forward_inference(
|
|
model_name: str,
|
|
model_over_time: ModelOverTime,
|
|
transformations_over_time: TransformationsOverTime,
|
|
X: XDataFrame,
|
|
expanding_window: bool,
|
|
window_size: int,
|
|
retrain_every: int,
|
|
from_index: Optional[pd.Timestamp],
|
|
) -> tuple[PredictionsSeries, ProbabilitiesDataFrame]:
|
|
predictions = pd.Series(index=X.index).rename(model_name)
|
|
probabilities = pd.DataFrame(index=X.index)
|
|
|
|
inference_from = max(get_first_valid_return_index(model_over_time), get_first_valid_return_index(X.iloc[:,0])) if from_index is None else X.index.to_list().index(from_index)
|
|
inference_till = X.shape[0]
|
|
model_index_offset = get_last_non_na_index(model_over_time, inference_from) if pd.isna(model_over_time[inference_from]) else 0
|
|
first_model = model_over_time[inference_from - model_index_offset] if pd.isna(model_over_time[inference_from]) else model_over_time[inference_from]
|
|
|
|
if first_model.only_column is not None:
|
|
X = X[[column for column in X.columns if first_model.only_column in column]]
|
|
|
|
if first_model.data_transformation == 'original':
|
|
transformations_over_time = []
|
|
|
|
for index in tqdm(range(inference_from, inference_till)):
|
|
|
|
last_model_index = index - ((index - inference_from) % retrain_every) - model_index_offset
|
|
train_window_start = X.index[inference_from] if expanding_window else X.index[index - window_size - 1]
|
|
|
|
current_model = model_over_time[X.index[last_model_index]]
|
|
current_transformations = [transformation_over_time[X.index[last_model_index]] for transformation_over_time in transformations_over_time]
|
|
|
|
if current_model.predict_window_size == 'window_size':
|
|
next_timestep = X.loc[train_window_start:X.index[index]]
|
|
else:
|
|
# we need to get a Dataframe out of it, since the transformation step always expects a 2D array, but it's equivalent to X.iloc[index]
|
|
next_timestep = X.loc[X.index[index]:X.index[index]]
|
|
|
|
for transformation in current_transformations:
|
|
next_timestep = transformation.transform(next_timestep)
|
|
|
|
next_timestep = next_timestep.to_numpy()
|
|
|
|
prediction, probs = current_model.predict(next_timestep)
|
|
predictions[X.index[index]] = prediction
|
|
if inference_from == index and len(probabilities.columns) != len(probs):
|
|
probabilities = probabilities.reindex(columns = ["prob_" + str(num) for num in range(0, len(probs.T))])
|
|
probabilities.loc[X.index[index]] = probs
|
|
|
|
return predictions, probabilities
|