Pytorch Tabular Example

Note.py

# !pip install torch torchvision torchaudio
# !pip install pytorch_tabular[all]

## Prepare utility functions
from sklearn.datasets import make_classification
def make_mixed_classification(n_samples, n_features, n_categories):
    X,y = make_classification(n_samples=n_samples, n_features=n_features, random_state=42, n_informative=5)
    cat_cols = random.choices(list(range(X.shape[-1])),k=n_categories)
    num_cols = [i for i in range(X.shape[-1]) if i not in cat_cols]
    for col in cat_cols:
        X[:,col] = pd.qcut(X[:,col], q=4).codes.astype(int)
    col_names = [] 
    num_col_names=[]
    cat_col_names=[]
    for i in range(X.shape[-1]):
        if i in cat_cols:
            col_names.append(f"cat_col_{i}")
            cat_col_names.append(f"cat_col_{i}")
        if i in num_cols:
            col_names.append(f"num_col_{i}")
            num_col_names.append(f"num_col_{i}")
    X = pd.DataFrame(X, columns=col_names)
    y = pd.Series(y, name="target")
    data = X.join(y)
    return data, cat_col_names, num_col_names

## Obtain trainign data
from sklearn.model_selection import train_test_split
import random
import pandas as pd

data, cat_col_names, num_col_names = make_mixed_classification(n_samples=100, n_features=20, n_categories=4)
train, test = train_test_split(data, random_state=42)
train, val = train_test_split(train, random_state=42)

## Define a machine learning model using Pytorch Tabular
from pytorch_tabular import TabularModel
from pytorch_tabular.models import CategoryEmbeddingModelConfig
from pytorch_tabular.config import DataConfig, OptimizerConfig, TrainerConfig, ExperimentConfig

data_config = DataConfig(
    target=['target'], #target should always be a list. Multi-targets are only supported for regression. Multi-Task Classification is not implemented
    continuous_cols=num_col_names,
    categorical_cols=cat_col_names,
)
trainer_config = TrainerConfig(
    auto_lr_find=True, # Runs the LRFinder to automatically derive a learning rate
    batch_size=1024,
    max_epochs=100,
    gpus=1, #index of the GPU to use. 0, means CPU
)
optimizer_config = OptimizerConfig()

model_config = CategoryEmbeddingModelConfig(
    task="classification",
    layers="1024-512-512",  # Number of nodes in each layer
    activation="LeakyReLU", # Activation between each layers
    learning_rate = 1e-2
)

tabular_model = TabularModel(
    data_config=data_config,
    model_config=model_config,
    optimizer_config=optimizer_config,
    trainer_config=trainer_config,
)

## Start learning
# see https://stackoverflow.com/questions/43769068/jupyter-notebook-widget-javascript-not-detected if error occurs
tabular_model.fit(train=train, validation=val)
result = tabular_model.evaluate(test)
pred_df = tabular_model.predict(test)
tabular_model.save_model("examples/basic")