Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add hyperparameter tuning with keras-tuning and RandomSearch #6

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Add hyperparameter tuning with keras-tuning and RandomSearch #6

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d93cc0a
Update config.py
josarago Feb 20, 2023
4bda02f
remove optuna
josarago Feb 20, 2023
1590903
install `keras-tuner`
josarago Feb 20, 2023
f07c47f
Update .gitignore
josarago Feb 20, 2023
08564a0
implement RandomSearch
josarago Feb 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,10 +156,12 @@ cython_debug/

# tensorflow
**/logs/*
**/tuner/*

#vscode
*.code-workspace

# plot_model
*.png
draft.py

18 changes: 18 additions & 0 deletions config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
import os
import logging
from dataclasses import dataclass

# logging
LOGGING_FORMAT = "%(asctime)s %(levelname)-8s [%(filename)s:%(lineno)d] %(message)s"
Expand All @@ -25,3 +26,20 @@ def get_logger(name):
# SizeManager config
SIZING_DIR_NAME = "sizing_systems"
SIZING_SYSTEM_DIR_PATH = os.path.join(DATA_DIR_PATH, SIZING_DIR_NAME)


@dataclass
class ModelConfig:
test_size: float = 0.3
embedding_dim: int = 4
learning_rate: float = 0.005
batch_size: int = 256
checkpoint_path: str = os.path.join(os.getcwd(), "model_checkpoints")
validation_split: float = 0.2
epochs: int = 2_000
fit_verbose: int = 0
asym_loss_gamma: float = 0.5
classification_loss: str = "categorical_crossentropy"
embedding_func: str = "subtract"
early_stopping__patience: int = 50
early_stopping__restore_best_weights: bool = True
7 changes: 0 additions & 7 deletions pipelines.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -106,11 +106,4 @@
]
)

USED_COLUMNS = (
EMBEDDING_COLUMNS
+ USER_CATEGORICAL_COLUMNS
+ SKU_NUMERICAL_COLUMNS
+ [TARGET_COLUMN]
)

target_pipe = LabelBinarizer()
Loading