gavindiaz/drift
1
0
Fork 0
mirror of https://github.com/webclinic017/drift.git synced 2026-08-14 03:18:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(Linter): reformatted code with black (#211)

Browse Source 
* chore(Linter): reformatted code with black

* Create black.yaml
This commit is contained in:
Mark Aron Szulyovszky
2022-02-17 19:22:17 +01:00
committed by GitHub
parent f3fee4a4e1
commit 8dd2d88740
101 changed files with 2595 additions and 2319 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/bet_sizing.py
+63 -46
View File
@@ -13,75 +13,92 @@ from transformations.scaler import get_scaler
from transformations.rfe import RFETransformation
from transformations.pca import PCATransformation
def bet_sizing_with_meta_model(
X: XDataFrame,
input_predictions: pd.Series,
y: ySeries,
forward_returns: ForwardReturnSeries,
model: Model,
config: Config,
model_suffix: str,
from_index: Optional[pd.Timestamp],
transformations_over_time: Optional[TransformationsOverTime] = None,
preloaded_models: Optional[ModelOverTime] = None
) -> BetSizingWithMetaOutcome:
X: XDataFrame,
input_predictions: pd.Series,
y: ySeries,
forward_returns: ForwardReturnSeries,
model: Model,
config: Config,
model_suffix: str,
from_index: Optional[pd.Timestamp],
transformations_over_time: Optional[TransformationsOverTime] = None,
preloaded_models: Optional[ModelOverTime] = None,
) -> BetSizingWithMetaOutcome:
input_predictions.name = "model_predictions"
discretized_predictions = input_predictions.apply(discretize_threeway_threshold(0.33))
discretized_predictions = input_predictions.apply(
discretize_threeway_threshold(0.33)
)
discretized_predictions.name = "model_discretized_predictions"
meta_y: pd.Series = pd.concat([discretized_predictions, y], axis=1).apply(equal_except_nan, axis = 1)
meta_X = pd.concat([X, input_predictions, discretized_predictions], axis = 1)
meta_y: pd.Series = pd.concat([discretized_predictions, y], axis=1).apply(
equal_except_nan, axis=1
)
meta_X = pd.concat([X, input_predictions, discretized_predictions], axis=1)
if transformations_over_time is None:
print("Preprocess transformations")
transformations_over_time = walk_forward_process_transformations(
X = meta_X,
y = meta_y,
forward_returns = forward_returns,
expanding_window = config.expanding_window_meta,
window_size = config.sliding_window_size_meta,
retrain_every = config.retrain_every,
from_index = from_index,
transformations= [
X=meta_X,
y=meta_y,
forward_returns=forward_returns,
expanding_window=config.expanding_window_meta,
window_size=config.sliding_window_size_meta,
retrain_every=config.retrain_every,
from_index=from_index,
transformations=[
get_scaler(config.scaler),
PCATransformation(ratio_components_to_keep=0.5, sliding_window_size=config.sliding_window_size_meta),
RFETransformation(n_feature_to_select=40, model=default_feature_selector_classification)
PCATransformation(
ratio_components_to_keep=0.5,
sliding_window_size=config.sliding_window_size_meta,
),
RFETransformation(
n_feature_to_select=40,
model=default_feature_selector_classification,
),
],
)
meta_outcome = train_model(
ticker_to_predict = "prediction_correct",
X = meta_X,
y = meta_y,
forward_returns = forward_returns,
model = model,
expanding_window = config.expanding_window_meta,
sliding_window_size = config.sliding_window_size_meta,
retrain_every = config.retrain_every,
from_index = from_index,
no_of_classes = 'two',
level = 'meta',
output_stats = config.mode == 'training',
transformations_over_time = transformations_over_time,
model_over_time = preloaded_models,
ticker_to_predict="prediction_correct",
X=meta_X,
y=meta_y,
forward_returns=forward_returns,
model=model,
expanding_window=config.expanding_window_meta,
sliding_window_size=config.sliding_window_size_meta,
retrain_every=config.retrain_every,
from_index=from_index,
no_of_classes="two",
level="meta",
output_stats=config.mode == "training",
transformations_over_time=transformations_over_time,
model_over_time=preloaded_models,
)
meta_predictions = meta_outcome.predictions
bet_size = meta_outcome.probabilities.iloc[:,1]
bet_size = meta_outcome.probabilities.iloc[:, 1]
avg_predictions_with_sizing = input_predictions * meta_predictions * bet_size
if config.mode == 'training':
if config.mode == "training":
stats = evaluate_predictions(
forward_returns = forward_returns,
y_pred = avg_predictions_with_sizing,
y_true = y,
no_of_classes = 'three-balanced',
discretize=False
forward_returns=forward_returns,
y_pred=avg_predictions_with_sizing,
y_true=y,
no_of_classes="three-balanced",
discretize=False,
)
print(stats)
else:
stats = None
model_id = "model_" + config.target_asset[1] + "_" + model_suffix
return BetSizingWithMetaOutcome(model_id, meta_outcome, transformations_over_time, avg_predictions_with_sizing, stats)
return BetSizingWithMetaOutcome(
model_id,
meta_outcome,
transformations_over_time,
avg_predictions_with_sizing,
stats,
)
training/directional_training.py
+43 -35
View File
@@ -5,7 +5,7 @@ from training.train_model import train_model
from training.walk_forward import walk_forward_process_transformations
from typing import Optional
from config.types import Config
from config.types import Config
from models.base import Model
from models.model_map import default_feature_selector_classification
@@ -13,53 +13,61 @@ from transformations.scaler import get_scaler
from transformations.rfe import RFETransformation
from transformations.pca import PCATransformation
def train_directional_model(
X: pd.DataFrame,
y: pd.Series,
forward_returns: pd.Series,
config: Config,
model: Model,
from_index: Optional[pd.Timestamp],
preloaded_training_step: Optional[DirectionalTrainingOutcome] = None,
) -> DirectionalTrainingOutcome:
X: pd.DataFrame,
y: pd.Series,
forward_returns: pd.Series,
config: Config,
model: Model,
from_index: Optional[pd.Timestamp],
preloaded_training_step: Optional[DirectionalTrainingOutcome] = None,
) -> DirectionalTrainingOutcome:
if preloaded_training_step is None:
print("Preprocess transformations")
transformations_over_time = walk_forward_process_transformations(
X = X,
y = y,
forward_returns = forward_returns,
expanding_window = config.expanding_window_base,
window_size = config.sliding_window_size_base,
retrain_every = config.retrain_every,
from_index = from_index,
transformations= [
X=X,
y=y,
forward_returns=forward_returns,
expanding_window=config.expanding_window_base,
window_size=config.sliding_window_size_base,
retrain_every=config.retrain_every,
from_index=from_index,
transformations=[
get_scaler(config.scaler),
PCATransformation(ratio_components_to_keep=0.5, sliding_window_size=config.sliding_window_size_base),
RFETransformation(n_feature_to_select=40, model=default_feature_selector_classification)
PCATransformation(
ratio_components_to_keep=0.5,
sliding_window_size=config.sliding_window_size_base,
),
RFETransformation(
n_feature_to_select=40,
model=default_feature_selector_classification,
),
],
)
else:
transformations_over_time = preloaded_training_step.transformations
training_outcome = train_model(
ticker_to_predict = config.target_asset[1],
X = X,
y = y,
forward_returns = forward_returns,
model = model,
expanding_window = config.expanding_window_base,
sliding_window_size = config.sliding_window_size_base,
retrain_every = config.retrain_every,
from_index = from_index,
no_of_classes = config.no_of_classes,
level = 'primary',
output_stats= config.mode == 'training',
transformations_over_time = transformations_over_time,
model_over_time = preloaded_training_step.training.model_over_time if preloaded_training_step else None
ticker_to_predict=config.target_asset[1],
X=X,
y=y,
forward_returns=forward_returns,
model=model,
expanding_window=config.expanding_window_base,
sliding_window_size=config.sliding_window_size_base,
retrain_every=config.retrain_every,
from_index=from_index,
no_of_classes=config.no_of_classes,
level="primary",
output_stats=config.mode == "training",
transformations_over_time=transformations_over_time,
model_over_time=preloaded_training_step.training.model_over_time
if preloaded_training_step
else None,
)
if config.mode == 'training':
if config.mode == "training":
print(training_outcome.stats)
return DirectionalTrainingOutcome(training_outcome, transformations_over_time)
training/train_model.py
+52 -43
View File
@@ -1,69 +1,78 @@
import pandas as pd
from typing import Literal, Optional
from training.walk_forward import walk_forward_train, walk_forward_inference, walk_forward_inference_batched
from training.walk_forward import (
walk_forward_train,
walk_forward_inference,
walk_forward_inference_batched,
)
from utils.evaluate import evaluate_predictions
from models.base import Model
from .types import ModelOverTime, TransformationsOverTime, TrainingOutcome
def train_model(
ticker_to_predict: str,
X: pd.DataFrame,
y: pd.Series,
forward_returns: pd.Series,
model: Model,
expanding_window: bool,
sliding_window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
no_of_classes: Literal['two', 'three-balanced', 'three-imbalanced'],
level: str,
output_stats: bool,
transformations_over_time: TransformationsOverTime,
model_over_time: Optional[ModelOverTime]
) -> TrainingOutcome:
ticker_to_predict: str,
X: pd.DataFrame,
y: pd.Series,
forward_returns: pd.Series,
model: Model,
expanding_window: bool,
sliding_window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
no_of_classes: Literal["two", "three-balanced", "three-imbalanced"],
level: str,
output_stats: bool,
transformations_over_time: TransformationsOverTime,
model_over_time: Optional[ModelOverTime],
) -> TrainingOutcome:
if model_over_time is None:
print("Train model")
model_over_time = walk_forward_train(
model = model,
X = X,
y = y,
forward_returns = forward_returns,
expanding_window = expanding_window,
window_size = sliding_window_size,
retrain_every = retrain_every,
from_index = from_index,
transformations_over_time = transformations_over_time,
model=model,
X=X,
y=y,
forward_returns=forward_returns,
expanding_window=expanding_window,
window_size=sliding_window_size,
retrain_every=retrain_every,
from_index=from_index,
transformations_over_time=transformations_over_time,
)
levelname = ("_" + level) if level == 'meta' else ""
levelname = ("_" + level) if level == "meta" else ""
if model_over_time is None:
model_id = "model_" + model.name + "_" + ticker_to_predict + levelname
model_id = "model_" + model.name + "_" + ticker_to_predict + levelname
else:
model_id = model_over_time.name
inference_function = walk_forward_inference if from_index is not None else walk_forward_inference_batched
predictions, probabilities = inference_function(
model_name = model_id,
model_over_time= model_over_time,
transformations_over_time = transformations_over_time,
X = X,
expanding_window = expanding_window,
window_size = sliding_window_size,
retrain_every = retrain_every,
from_index = from_index,
inference_function = (
walk_forward_inference
if from_index is not None
else walk_forward_inference_batched
)
predictions, probabilities = inference_function(
model_name=model_id,
model_over_time=model_over_time,
transformations_over_time=transformations_over_time,
X=X,
expanding_window=expanding_window,
window_size=sliding_window_size,
retrain_every=retrain_every,
from_index=from_index,
)
assert len(predictions) == len(y)
if output_stats:
stats = evaluate_predictions(
forward_returns = forward_returns,
y_pred = predictions,
y_true = y,
forward_returns=forward_returns,
y_pred=predictions,
y_true=y,
no_of_classes=no_of_classes,
discretize=True
discretize=True,
)
else:
stats = None
return TrainingOutcome(model_id, predictions, probabilities, stats, model_over_time)
return TrainingOutcome(model_id, predictions, probabilities, stats, model_over_time)
training/types.py
+5 -2
View File
@@ -19,6 +19,7 @@ class TrainingOutcome:
stats: Optional[Stats]
model_over_time: ModelOverTime
@dataclass
class BetSizingWithMetaOutcome:
model_id: str
@@ -27,11 +28,13 @@ class BetSizingWithMetaOutcome:
weights: WeightsSeries
stats: Optional[Stats]
@dataclass
class DirectionalTrainingOutcome:
training: TrainingOutcome
transformations: TransformationsOverTime
@dataclass
class PipelineOutcome:
directional_training: DirectionalTrainingOutcome
@@ -41,4 +44,4 @@ class PipelineOutcome:
return self.bet_sizing.weights
def get_output_stats(self) -> Stats:
return self.bet_sizing.stats
return self.bet_sizing.stats
training/walk_forward/__init__.py
+1 -1
View File
@@ -1,4 +1,4 @@
from .inference_batched import walk_forward_inference_batched
from .inference import walk_forward_inference
from .train import walk_forward_train
from .process_transformations import walk_forward_process_transformations
from .process_transformations import walk_forward_process_transformations
training/walk_forward/inference.py
+58 -26
View File
@@ -1,49 +1,79 @@
import pandas as pd
from training.types import ModelOverTime, TransformationsOverTime, PredictionsSeries, ProbabilitiesDataFrame
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, dtype='object').rename(model_name)
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, dtype="object").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_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]
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':
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]
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]
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:
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]]
next_timestep = X.loc[X.index[index] : X.index[index]]
for transformation in current_transformations:
next_timestep = transformation.transform(next_timestep)
@@ -54,7 +84,9 @@ def walk_forward_inference(
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 = probabilities.reindex(
columns=["prob_" + str(num) for num in range(0, len(probs.T))]
)
probabilities.loc[X.index[index]] = probs
return predictions, probabilities
training/walk_forward/inference_batched.py
+67 -24
View File
@@ -1,36 +1,64 @@
import pandas as pd
from training.types import ModelOverTime, TransformationsOverTime, PredictionsSeries, ProbabilitiesDataFrame
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 tqdm import tqdm
def walk_forward_inference_batched(
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, dtype='object').rename(model_name)
probabilities = pd.DataFrame(index=X.index, columns=['0', '1'])
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)
def walk_forward_inference_batched(
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, dtype="object").rename(model_name)
probabilities = pd.DataFrame(index=X.index, columns=["0", "1"])
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]
first_model = 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':
if first_model.data_transformation == "original":
transformations_over_time = []
batch_indices = range(inference_from, inference_till, retrain_every) if inference_till - inference_from > retrain_every else [inference_from]
batched_results = [__inference_from_window(index, index + retrain_every, X, model_over_time, transformations_over_time, expanding_window, window_size) for index in tqdm(batch_indices)]
batch_indices = (
range(inference_from, inference_till, retrain_every)
if inference_till - inference_from > retrain_every
else [inference_from]
)
batched_results = [
__inference_from_window(
index,
index + retrain_every,
X,
model_over_time,
transformations_over_time,
expanding_window,
window_size,
)
for index in tqdm(batch_indices)
]
for batch in batched_results:
for index, prediction, probs in batch:
predictions[X.index[index]] = prediction
@@ -38,12 +66,24 @@ def walk_forward_inference_batched(
return predictions, probabilities
def __inference_from_window(index_start: int, index_end: int, X: XDataFrame, model_over_time: ModelOverTime, transformations_over_time: TransformationsOverTime, expanding_window: bool, window_size: int) -> list[tuple[int, float, pd.Series]]:
def __inference_from_window(
index_start: int,
index_end: int,
X: XDataFrame,
model_over_time: ModelOverTime,
transformations_over_time: TransformationsOverTime,
expanding_window: bool,
window_size: int,
) -> list[tuple[int, float, pd.Series]]:
current_model = model_over_time[X.index[index_start]]
current_transformations = [transformation_over_time[X.index[index_start]] for transformation_over_time in transformations_over_time]
current_transformations = [
transformation_over_time[X.index[index_start]]
for transformation_over_time in transformations_over_time
]
input_data = X.iloc[index_start:index_end]
for transformation in current_transformations:
input_data = transformation.transform(input_data)
@@ -51,6 +91,9 @@ def __inference_from_window(index_start: int, index_end: int, X: XDataFrame, mod
predictions = current_model.predict(input_data)
probs = current_model.predict_proba(input_data)
results = [(index_start + index, predictions[index], probs[index]) for index in range(len(predictions))]
return results
results = [
(index_start + index, predictions[index], probs[index])
for index in range(len(predictions))
]
return results
training/walk_forward/inference_parallel.py
+72 -26
View File
@@ -1,6 +1,11 @@
import pandas as pd
from models.base import Model
from training.types import ModelOverTime, TransformationsOverTime, PredictionsSeries, ProbabilitiesDataFrame
from training.types import (
ModelOverTime,
TransformationsOverTime,
PredictionsSeries,
ProbabilitiesDataFrame,
)
from transformations.base import Transformation
from utils.helpers import get_first_valid_return_index
from tqdm import tqdm
@@ -8,31 +13,54 @@ from typing import Optional
from data_loader.types import XDataFrame
import ray
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, dtype='object').rename(model_name)
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, dtype="object").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_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]
first_model = 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':
if first_model.data_transformation == "original":
transformations_over_time = []
batch_size = int((inference_till - inference_from) / 10)
batched_results = ray.get([__inference_from_window.remote(index, index + batch_size, inference_from, retrain_every, X, model_over_time, transformations_over_time, expanding_window, window_size) for index in range(inference_from, inference_till)])
batched_results = ray.get(
[
__inference_from_window.remote(
index,
index + batch_size,
inference_from,
retrain_every,
X,
model_over_time,
transformations_over_time,
expanding_window,
window_size,
)
for index in range(inference_from, inference_till)
]
)
for batch in batched_results:
for index, prediction, probs in batch:
predictions[X.index[index]] = prediction
@@ -40,23 +68,41 @@ def walk_forward_inference(
return predictions, probabilities
@ray.remote
def __inference_from_window(index_start: int, index_end: int, inference_from: int, retrain_every: int, X: XDataFrame, model_over_time: ModelOverTime, transformations_over_time: TransformationsOverTime, expanding_window: bool, window_size: int) -> list[tuple[int, float, pd.Series]]:
def __inference_from_window(
index_start: int,
index_end: int,
inference_from: int,
retrain_every: int,
X: XDataFrame,
model_over_time: ModelOverTime,
transformations_over_time: TransformationsOverTime,
expanding_window: bool,
window_size: int,
) -> list[tuple[int, float, pd.Series]]:
results = []
for index in range(index_start, index_end):
last_model_index = index - ((index - inference_from) % retrain_every)
train_window_start = X.index[inference_from] if expanding_window else X.index[index - window_size - 1]
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]
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:
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]]
next_timestep = X.loc[X.index[index] : X.index[index]]
for transformation in current_transformations:
next_timestep = transformation.transform(next_timestep)
@@ -64,5 +110,5 @@ def __inference_from_window(index_start: int, index_end: int, inference_from: in
prediction, probs = current_model.predict(next_timestep)
results.append((index, prediction, probs))
return results
return results
training/walk_forward/process_transformations.py
+43 -20
View File
@@ -8,40 +8,63 @@ from data_loader.types import ForwardReturnSeries, XDataFrame, ySeries
def walk_forward_process_transformations(
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations: list[Transformation],
) -> TransformationsOverTime:
transformations_over_time = [pd.Series(index=y.index, dtype='object').rename(t.get_name()) for t in transformations]
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations: list[Transformation],
) -> TransformationsOverTime:
transformations_over_time = [
pd.Series(index=y.index, dtype="object").rename(t.get_name())
for t in transformations
]
first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
first_nonzero_return = max(
get_first_valid_return_index(forward_returns),
get_first_valid_return_index(X.iloc[:, 0]),
get_first_valid_return_index(y),
)
train_from = (
first_nonzero_return + window_size + 1
if from_index is None
else X.index.to_list().index(from_index)
)
train_till = len(y)
iterations_before_retrain = 0
for index in tqdm(range(train_from, train_till)):
train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
if iterations_before_retrain <= 0 or pd.isna(transformations_over_time[0][index-1]):
for index in tqdm(range(train_from, train_till)):
train_window_start = (
X.index[first_nonzero_return]
if expanding_window
else X.index[index - window_size - 1]
)
if iterations_before_retrain <= 0 or pd.isna(
transformations_over_time[0][index - 1]
):
train_window_end = X.index[index - 1]
X_expanding_window = X[train_window_start:train_window_end]
y_expanding_window = y[train_window_start:train_window_end]
current_transformations = [t.clone() for t in transformations]
for transformation_index, transformation in enumerate(current_transformations):
X_expanding_window = transformation.fit_transform(X_expanding_window, y_expanding_window)
for transformation_index, transformation in enumerate(
current_transformations
):
X_expanding_window = transformation.fit_transform(
X_expanding_window, y_expanding_window
)
iterations_before_retrain = retrain_every
for transformation_index, transformation in enumerate(current_transformations):
transformations_over_time[transformation_index][X.index[index]] = transformation
transformations_over_time[transformation_index][
X.index[index]
] = transformation
iterations_before_retrain -= 1
training/walk_forward/process_transformations_parallel.py
+62 -21
View File
@@ -8,33 +8,72 @@ from data_loader.types import ForwardReturnSeries, XDataFrame, ySeries
import ray
from utils.parallel import parallel_compute_with_bar
def walk_forward_process_transformations(
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations: list[Transformation],
) -> TransformationsOverTime:
transformations_over_time = [pd.Series(index=y.index).rename(t.get_name()) for t in transformations]
first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
def walk_forward_process_transformations(
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations: list[Transformation],
) -> TransformationsOverTime:
transformations_over_time = [
pd.Series(index=y.index).rename(t.get_name()) for t in transformations
]
first_nonzero_return = max(
get_first_valid_return_index(forward_returns),
get_first_valid_return_index(X.iloc[:, 0]),
get_first_valid_return_index(y),
)
train_from = (
first_nonzero_return + window_size + 1
if from_index is None
else X.index.to_list().index(from_index)
)
train_till = len(y)
processed_transformations = parallel_compute_with_bar([preprocess_transformations_window.remote(X, y, expanding_window, window_size, transformations, first_nonzero_return, index) for index in range(train_from, train_till, retrain_every)])
processed_transformations = parallel_compute_with_bar(
[
preprocess_transformations_window.remote(
X,
y,
expanding_window,
window_size,
transformations,
first_nonzero_return,
index,
)
for index in range(train_from, train_till, retrain_every)
]
)
for transformation, index_time in processed_transformations:
for transformation_index, transformation in enumerate(transformation):
transformations_over_time[transformation_index][X.index[index_time]] = transformation
transformations_over_time[transformation_index][
X.index[index_time]
] = transformation
return transformations_over_time
@ray.remote
def preprocess_transformations_window(X: XDataFrame, y: ySeries, expanding_window: bool, window_size: int, transformations: list[Transformation], first_nonzero_return: int, index: int) -> tuple[list[Transformation], int]:
train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
def preprocess_transformations_window(
X: XDataFrame,
y: ySeries,
expanding_window: bool,
window_size: int,
transformations: list[Transformation],
first_nonzero_return: int,
index: int,
) -> tuple[list[Transformation], int]:
train_window_start = (
X.index[first_nonzero_return]
if expanding_window
else X.index[index - window_size - 1]
)
train_window_end = X.index[index - 1]
X_expanding_window = X[train_window_start:train_window_end]
@@ -42,6 +81,8 @@ def preprocess_transformations_window(X: XDataFrame, y: ySeries, expanding_windo
current_transformations = [t.clone() for t in transformations]
for transformation in current_transformations:
X_expanding_window = transformation.fit_transform(X_expanding_window, y_expanding_window)
X_expanding_window = transformation.fit_transform(
X_expanding_window, y_expanding_window
)
return (current_transformations, index)
return (current_transformations, index)
training/walk_forward/train.py
+37 -21
View File
@@ -7,39 +7,55 @@ from typing import Optional
from data_loader.types import ForwardReturnSeries, XDataFrame, ySeries
from copy import deepcopy
def walk_forward_train(
model: Model,
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations_over_time: TransformationsOverTime,
) -> ModelOverTime:
models_over_time = pd.Series(index=y.index, dtype='object').rename(model.name)
first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
def walk_forward_train(
model: Model,
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations_over_time: TransformationsOverTime,
) -> ModelOverTime:
models_over_time = pd.Series(index=y.index, dtype="object").rename(model.name)
first_nonzero_return = max(
get_first_valid_return_index(forward_returns),
get_first_valid_return_index(X.iloc[:, 0]),
get_first_valid_return_index(y),
)
train_from = (
first_nonzero_return + window_size + 1
if from_index is None
else X.index.to_list().index(from_index)
)
train_till = len(y)
if model.only_column is not None:
X = X[[column for column in X.columns if model.only_column in column]]
if model.data_transformation == 'original':
if model.data_transformation == "original":
transformations_over_time = []
for index in tqdm(range(train_from, train_till, retrain_every)):
train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
train_window_start = (
X.index[first_nonzero_return]
if expanding_window
else X.index[index - window_size - 1]
)
train_window_end = X.index[index - 1]
current_transformations = [transformation_over_time[index] for transformation_over_time in transformations_over_time]
current_transformations = [
transformation_over_time[index]
for transformation_over_time in transformations_over_time
]
X_slice = X[train_window_start:train_window_end]
for transformation in current_transformations:
X_slice = transformation.transform(X_slice)
X_slice = X_slice.to_numpy()
y_slice = y[train_window_start:train_window_end].to_numpy()
@@ -48,4 +64,4 @@ def walk_forward_train(
models_over_time[X.index[index]] = current_model
return models_over_time
return models_over_time
training/walk_forward/train_parallel.py
+61 -21
View File
@@ -9,46 +9,86 @@ import ray
from utils.parallel import parallel_compute_with_bar
from copy import deepcopy
def walk_forward_train(
model: Model,
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations_over_time: TransformationsOverTime,
) -> ModelOverTime:
model: Model,
X: XDataFrame,
y: ySeries,
forward_returns: ForwardReturnSeries,
expanding_window: bool,
window_size: int,
retrain_every: int,
from_index: Optional[pd.Timestamp],
transformations_over_time: TransformationsOverTime,
) -> ModelOverTime:
models_over_time = pd.Series(index=y.index).rename(model.name)
first_nonzero_return = max(get_first_valid_return_index(forward_returns), get_first_valid_return_index(X.iloc[:,0]), get_first_valid_return_index(y))
train_from = first_nonzero_return + window_size + 1 if from_index is None else X.index.to_list().index(from_index)
first_nonzero_return = max(
get_first_valid_return_index(forward_returns),
get_first_valid_return_index(X.iloc[:, 0]),
get_first_valid_return_index(y),
)
train_from = (
first_nonzero_return + window_size + 1
if from_index is None
else X.index.to_list().index(from_index)
)
train_till = len(y)
if model.only_column is not None:
X = X[[column for column in X.columns if model.only_column in column]]
if model.data_transformation == 'original':
if model.data_transformation == "original":
transformations_over_time = []
models = parallel_compute_with_bar([train_on_window.remote(index, first_nonzero_return, window_size, X, y, model, expanding_window, transformations_over_time) for index in tqdm(range(train_from, train_till, retrain_every))])
for index, current_model in models:
models = parallel_compute_with_bar(
[
train_on_window.remote(
index,
first_nonzero_return,
window_size,
X,
y,
model,
expanding_window,
transformations_over_time,
)
for index in tqdm(range(train_from, train_till, retrain_every))
]
)
for index, current_model in models:
models_over_time[X.index[index]] = current_model
return models_over_time
@ray.remote
def train_on_window(index: int, first_nonzero_return: int, window_size: int, X: XDataFrame, y: ySeries, model: Model, expanding_window: bool, transformations_over_time: TransformationsOverTime) -> tuple[int, Model]:
train_window_start = X.index[first_nonzero_return] if expanding_window else X.index[index - window_size - 1]
def train_on_window(
index: int,
first_nonzero_return: int,
window_size: int,
X: XDataFrame,
y: ySeries,
model: Model,
expanding_window: bool,
transformations_over_time: TransformationsOverTime,
) -> tuple[int, Model]:
train_window_start = (
X.index[first_nonzero_return]
if expanding_window
else X.index[index - window_size - 1]
)
train_window_end = X.index[index - 1]
current_transformations = [transformation_over_time[index] for transformation_over_time in transformations_over_time]
current_transformations = [
transformation_over_time[index]
for transformation_over_time in transformations_over_time
]
X_slice = X[train_window_start:train_window_end]
for transformation in current_transformations:
X_slice = transformation.transform(X_slice)
X_slice = X_slice.to_numpy()
y_slice = y[train_window_start:train_window_end].to_numpy()