Performance may be degraded by the initialization scheme #90
Description
System information
- OS Platform and Distribution: MacOS 14.2.1
- Python version: 3.11.7
- DeepTables version: 0.2.6
- Other Python packages(run
pip list):
Package Version
---------------------------- ------------
absl-py 2.0.0
asttokens 2.4.1
astunparse 1.6.3
attrs 23.2.0
bcrypt 4.1.2
cachetools 5.3.2
category-encoders 2.6.3
certifi 2023.11.17
cffi 1.16.0
charset-normalizer 3.3.2
cryptography 41.0.7
decorator 5.1.1
deeptables 0.2.6
eli5 0.13.0
executing 2.0.1
flatbuffers 23.5.26
fsspec 2023.12.2
gast 0.5.4
google-auth 2.26.1
google-auth-oauthlib 1.2.0
google-pasta 0.2.0
graphviz 0.20.1
grpcio 1.60.0
h5py 3.10.0
hypernets 0.3.1
idna 3.6
ipython 8.19.0
jedi 0.19.1
Jinja2 3.1.2
joblib 1.3.2
keras 2.15.0
libclang 16.0.6
lightgbm 4.2.0
Markdown 3.5.1
MarkupSafe 2.1.3
matplotlib-inline 0.1.6
ml-dtypes 0.2.0
numpy 1.26.3
oauthlib 3.2.2
opt-einsum 3.3.0
packaging 23.2
pandas 2.1.4
paramiko 3.4.0
parso 0.8.3
patsy 0.5.6
pexpect 4.9.0
pip 23.3.2
prettytable 3.9.0
prompt-toolkit 3.0.43
protobuf 4.23.4
psutil 5.9.7
ptyprocess 0.7.0
pure-eval 0.2.2
pyasn1 0.5.1
pyasn1-modules 0.3.0
pycparser 2.21
Pygments 2.17.2
PyNaCl 1.5.0
python-dateutil 2.8.2
pytz 2023.3.post1
PyYAML 6.0.1
requests 2.31.0
requests-oauthlib 1.3.1
rsa 4.9
scikit-learn 1.3.2
scipy 1.11.4
setuptools 69.0.3
six 1.16.0
stack-data 0.6.3
statsmodels 0.14.1
tabulate 0.9.0
tensorboard 2.15.1
tensorboard-data-server 0.7.2
tensorflow 2.15.0
tensorflow-estimator 2.15.0
tensorflow-io-gcs-filesystem 0.34.0
tensorflow-macos 2.15.0
termcolor 2.4.0
threadpoolctl 3.2.0
tornado 6.4
tqdm 4.66.1
traitlets 5.14.1
typing_extensions 4.9.0
tzdata 2023.4
urllib3 2.1.0
wcwidth 0.2.12
Werkzeug 3.0.1
wheel 0.42.0
wrapt 1.14.1
XlsxWriter 3.1.9
Describe the current behavior
I run sample classification code from the documentation:
During execution, I see the following message in the logs:
01-04 14:38:13 I deeptables.m.deepmodel.py 231 - Building model...
./miniforge3/envs/sample_deeptable/lib/python3.11/site-packages/keras/src/initializers/initializers.py:120: UserWarning: The initializer RandomUniform is unseeded and being called multiple times, which will return identical values each time (even if the initializer is unseeded). Please update your code to provide a seed to the initializer, or avoid using the same initializer instance more than once.
Describe the expected behavior
There seems to be a need to modify the initialization schema of the WideDeep layer to improve performance and eliminate the warning.
Standalone code to reproduce the issue
# sample code from https://deeptables.readthedocs.io/en/latest/examples.html
from deeptables.models.deeptable import DeepTable, ModelConfig
from deeptables.models.deepnets import WideDeep
from deeptables.datasets import dsutils
from sklearn.model_selection import train_test_split
# Adult Data Set from UCI Machine Learning Repository: https://archive.ics.uci.edu/ml/datasets/Adult
df_train = dsutils.load_adult()
y = df_train.pop(14)
X = df_train
conf = ModelConfig(nets=WideDeep, metrics=["AUC", "accuracy"], auto_discrete=True)
dt = DeepTable(config=conf)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
model, history = dt.fit(X_train, y_train, epochs=100)