From 1d58e3ccc4efbd62e6628efc5e21bf1627a9fc0a Mon Sep 17 00:00:00 2001 From: bernard-ng Date: Fri, 20 Jun 2025 16:38:48 +0200 Subject: [PATCH] feat: add gender base models architectures --- .gitignore | 1 + misc/__init__.py | 4 ++++ processing/__init__.py | 0 processing/gender/__init__.py | 0 requirements.txt | 44 +++++++++++++++++++++++++++++++++++ 5 files changed, 49 insertions(+) create mode 100644 processing/__init__.py create mode 100644 processing/gender/__init__.py create mode 100644 requirements.txt diff --git a/.gitignore b/.gitignore index c526c05..82cdb45 100644 --- a/.gitignore +++ b/.gitignore @@ -8,3 +8,4 @@ models/ .env.local var/ /dataset/ +.DS_Store diff --git a/misc/__init__.py b/misc/__init__.py index dbfc2d4..7ecd60b 100644 --- a/misc/__init__.py +++ b/misc/__init__.py @@ -8,6 +8,10 @@ from typing import Optional ROOT_DIR = os.getcwd() DATA_DIR = os.path.join(ROOT_DIR, 'dataset') +MODELS_DIR = os.path.join(ROOT_DIR, 'models') +GENDER_MODELS_DIR = os.path.join(MODELS_DIR, 'gender') +NER_MODELS_DIR = os.path.join(MODELS_DIR, 'ner') + # Training TRAINING_EPOCHS = 5 MODEL_NAME = f"./models/ners-{datetime.now().strftime('%Y%m%d%H%M%S')}" diff --git a/processing/__init__.py b/processing/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/processing/gender/__init__.py b/processing/gender/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..6fd140b --- /dev/null +++ b/requirements.txt @@ -0,0 +1,44 @@ +absl-py==2.3.0 +astunparse==1.6.3 +certifi==2025.6.15 +charset-normalizer==3.4.2 +flatbuffers==25.2.10 +gast==0.6.0 +google-pasta==0.2.0 +grpcio==1.73.0 +h5py==3.14.0 +idna==3.10 +joblib==1.5.1 +keras==3.10.0 +libclang==18.1.1 +Markdown==3.8.2 +markdown-it-py==3.0.0 +MarkupSafe==3.0.2 +mdurl==0.1.2 +ml-dtypes==0.3.2 +namex==0.1.0 +numpy==1.26.4 +opt_einsum==3.4.0 +optree==0.16.0 +packaging==25.0 +pandas==2.3.0 +protobuf==4.25.8 +Pygments==2.19.1 +python-dateutil==2.9.0.post0 +pytz==2025.2 +requests==2.32.4 +rich==14.0.0 +scikit-learn==1.7.0 +scipy==1.15.3 +six==1.17.0 +tensorboard==2.16.2 +tensorboard-data-server==0.7.2 +tensorflow==2.16.2 +tensorflow-io-gcs-filesystem==0.37.1 +termcolor==3.1.0 +threadpoolctl==3.6.0 +typing_extensions==4.14.0 +tzdata==2025.2 +urllib3==2.5.0 +Werkzeug==3.1.3 +wrapt==1.17.2