python setup.py install

# Installation with pip
pip install -e .

from omegaconf import OmegaConf

encoder_config = OmegaConf.create({
    "embedding": {
        "name": "FeatureEmbedding",
    },
    "backbone": {
        "name": "FTTransformerBackbone",
    }
})

model_config = OmegaConf.create({
    "name": "MLPHeadModel"
})

trainer_config = OmegaConf.create({
    "max_epochs": 1,
})

from deep_table.data.data_module import TabularDatamodule


datamodule = TabularDatamodule(
    train=train_df,
    validation=val_df,
    test=test_df,
    task="binary",
    dim_out=1,
    categorical_cols=["education", "occupation", ...],
    continuous_cols=["age", "hours-per-week", ...],
    target=["income"],
    num_categories=110,
)

>> {'accuracy': array([0.8553...]), 'AUC': array([0.9111...]), 'F1 score': array([0.9077...]), 'cross_entropy': array([0.3093...])} ">

from deep_table.estimators.base import Estimator
from deep_table.utils import get_scores


estimator = Estimator(
    encoder_config,      # Encoder architecture
    model_config,        # model settings (learning rate, scheduler...)
    trainer_config,      # training settings (epoch, gpu...)
)

estimator.fit(datamodule)
predict = estimator.predict(datamodule.dataloader(split="test"))
get_scores(predict, target, task="binary")
>>> {'accuracy': array([0.8553...]),
     'AUC': array([0.9111...]),
     'F1 score': array([0.9077...]),
     'cross_entropy': array([0.3093...])}

from deep_table.estimators.base import Estimator
from deep_table.utils import get_scores


pretrain_model_config = OmegaConf.create({
    "name": "SAINTPretrainModel"
})

pretrain_model = Estimator(encoder_config, pretrain_model_config, trainer_config)
pretrain_model.fit(datamodule)

estimator = Estimator(encoder_config, model_config, trainer_config)
estimator.fit(datamodule, from_pretrained=pretrain_model)

import pandas as pd

import os,sys; sys.path.append(os.path.abspath(".."))
from deep_table.data.data_module import TabularDatamodule
from deep_table.preprocess import CategoryPreprocessor


# 0. Prepare datasets and create DataFrame
iris = pd.read_csv('https://raw.githubusercontent.com/mwaskom/seaborn-data/master/iris.csv')

# 1. Preprocessing pd.DataFrame
category_preprocesser = CategoryPreprocessor(categorical_columns=["species"], use_unk=False)
iris = category_preprocesser.fit_transform(iris)

# 2. TabularDatamodule
datamodule = TabularDatamodule(
    train=iris.iloc[:20],
    val=iris.iloc[20:40],
    test=iris.iloc[40:],
    task="multiclass",
    dim_out=3,
    categorical_columns=[],
    continuous_columns=["sepal_length", "sepal_width", "petal_length", "petal_width"],
    target=["species"],
    num_categories=0,
)

estimator = Estimator(
    encoder_config, model_config, trainer_config,
    custom_embedding=YourEmbedding, custom_backbone=YourBackbone, custom_model=YourModel
)