pytorch-widedeep 0.4.1

Combine tabular data with text and images using Wide and Deep models in Pytorch

pytorch-widedeep

A flexible package to combine tabular data with text and images using wide and deep models.

Documentation: https://pytorch-widedeep.readthedocs.io

Introduction

pytorch-widedeep is based on Google's Wide and Deep Algorithm. Details of the original algorithm can be found here, and the nice research paper can be found here.

In general terms, pytorch-widedeep is a package to use deep learning with tabular data. In particular, is intended to facilitate the combination of text and images with corresponding tabular data using wide and deep models. With that in mind there are two architectures that can be implemented with just a few lines of code. For details on these architectures please visit the repo.

Installation

Install using pip:

pip install pytorch-widedeep

Or install directly from github

pip install git+https://github.com/jrzaurin/pytorch-widedeep.git

Developer Install

# Clone the repository
git clone https://github.com/jrzaurin/pytorch-widedeep
cd pytorch-widedeep

# Install in dev mode
pip install -e .

Examples

There are a number of notebooks in the examples folder plus some additional files. These notebooks cover most of the utilities of this package and can also act as documentation. In the case that github does not render the notebooks, or it renders them missing some parts, they are saved as markdown files in the docs folder.

Quick start

Binary classification with the adult dataset using Wide and DeepDense and defaults settings.

import pandas as pd
from sklearn.model_selection import train_test_split

from pytorch_widedeep.preprocessing import WidePreprocessor, DeepPreprocessor
from pytorch_widedeep.models import Wide, DeepDense, WideDeep
from pytorch_widedeep.metrics import BinaryAccuracy

# these next 4 lines are not directly related to pytorch-widedeep. I assume
# you have downloaded the dataset and place it in a dir called data/adult/
df = pd.read_csv("data/adult/adult.csv.zip")
df["income_label"] = (df["income"].apply(lambda x: ">50K" in x)).astype(int)
df.drop("income", axis=1, inplace=True)
df_train, df_test = train_test_split(df, test_size=0.2, stratify=df.income_label)

# prepare wide, crossed, embedding and continuous columns
wide_cols = [
    "education",
    "relationship",
    "workclass",
    "occupation",
    "native-country",
    "gender",
]
cross_cols = [("education", "occupation"), ("native-country", "occupation")]
embed_cols = [
    ("education", 16),
    ("workclass", 16),
    ("occupation", 16),
    ("native-country", 32),
]
cont_cols = ["age", "hours-per-week"]
target_col = "income_label"

# target
target = df_train[target_col].values

# wide
preprocess_wide = WidePreprocessor(wide_cols=wide_cols, crossed_cols=cross_cols)
X_wide = preprocess_wide.fit_transform(df_train)
wide = Wide(wide_dim=X_wide.shape[1], output_dim=1)

# deepdense
preprocess_deep = DeepPreprocessor(embed_cols=embed_cols, continuous_cols=cont_cols)
X_deep = preprocess_deep.fit_transform(df_train)
deepdense = DeepDense(
    hidden_layers=[64, 32],
    deep_column_idx=preprocess_deep.deep_column_idx,
    embed_input=preprocess_deep.embeddings_input,
    continuous_cols=cont_cols,
)

# build, compile and fit
model = WideDeep(wide=wide, deepdense=deepdense)
model.compile(method="binary", metrics=[BinaryAccuracy])
model.fit(
    X_wide=X_wide,
    X_deep=X_deep,
    target=target,
    n_epochs=5,
    batch_size=256,
    val_split=0.1,
)

# predict
X_wide_te = preprocess_wide.transform(df_test)
X_deep_te = preprocess_deep.transform(df_test)
preds = model.predict(X_wide=X_wide_te, X_deep=X_deep_te)

Of course, one can do much more, such as using different initializations, optimizers or learning rate schedulers for each component of the overall model. Adding FC-Heads to the Text and Image components. Using the Focal Loss, warming up individual components before joined training, etc. See the examples or the docs folders for a better understanding of the content of the package and its functionalities.

Testing

pytest tests

Acknowledgments

This library takes from a series of other libraries, so I think it is just fair to mention them here in the README (specific mentions are also included in the code).

The Callbacks and Initializers structure and code is inspired by the torchsample library, which in itself partially inspired by Keras.

The TextProcessor class in this library uses the fastai's Tokenizer and Vocab. The code at utils.fastai_transforms is a minor adaptation of their code so it functions within this library. To my experience their Tokenizer is the best in class.

The ImageProcessor class in this library uses code from the fantastic Deep Learning for Computer Vision (DL4CV) book by Adrian Rosebrock.