sriharsha0806/skorch

A scikit-learn compatible neural network library that wraps pytorch

---

A scikit-learn compatible neural network library that wraps pytorch.

Example

To see a more elaborate example, look here.

import numpy as np
from sklearn.datasets import make_classification
import torch
from torch import nn
import torch.nn.functional as F

from skorch.net import NeuralNetClassifier


X, y = make_classification(1000, 20, n_informative=10, random_state=0)
X = X.astype(np.float32)


class MyModule(nn.Module):
    def __init__(self, num_units=10, nonlin=F.relu):
        super(MyModule, self).__init__()

        self.dense0 = nn.Linear(20, num_units)
        self.nonlin = nonlin
        self.dropout = nn.Dropout(0.5)
        self.dense1 = nn.Linear(num_units, 10)
        self.output = nn.Linear(10, 2)

    def forward(self, X, **kwargs):
        X = self.nonlin(self.dense0(X))
        X = self.dropout(X)
        X = F.relu(self.dense1(X))
        X = F.softmax(self.output(X))
        return X


net = NeuralNetClassifier(
    MyModule,
    max_epochs=10,
    lr=0.1,
)

net.fit(X, y)
y_proba = net.predict_proba(X)

In an sklearn Pipeline:

from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler


pipe = Pipeline([
    ('scale', StandardScaler()),
    ('net', net),
])

pipe.fit(X, y)
y_proba = pipe.predict_proba(X)

With grid search

from sklearn.model_selection import GridSearchCV


params = {
    'lr': [0.01, 0.02],
    'max_epochs': [10, 20],
    'module__num_units': [10, 20],
}
gs = GridSearchCV(net, params, refit=False, cv=3, scoring='accuracy')

gs.fit(X, y)
print(gs.best_score_, gs.best_params_)

Installation

pip installation

To install with pip, run:

pip install -U skorch

We recommend to use a virtual environment for this.

From source

If you would like to use the must recent additions to skorch or help development, you should install skorch from source.

Using conda

You need a working conda installation. Get the correct miniconda for your system from here.

If you just want to use skorch, use:

git clone https://github.com/dnouri/skorch.git
cd skorch
conda env create
source activate skorch
# install pytorch version for your system (see below)
python setup.py install

If you want to help developing, run:

git clone https://github.com/dnouri/skorch.git
cd skorch
conda env create
source activate skorch
# install pytorch version for your system (see below)
conda install --file requirements-dev.txt
python setup.py develop

py.test  # unit tests
pylint skorch  # static code checks

Using pip

If you just want to use skorch, use:

git clone https://github.com/dnouri/skorch.git
cd skorch
# create and activate a virtual environment
pip install -r requirements.txt
# install pytorch version for your system (see below)
python setup.py install

If you want to help developing, run:

git clone https://github.com/dnouri/skorch.git
cd skorch
# create and activate a virtual environment
pip install -r requirements.txt
# install pytorch version for your system (see below)
pip install -r requirements-dev.txt
python setup.py develop

py.test  # unit tests
pylint skorch  # static code checks

pytorch

pytorch is not covered by the dependencies, since the pytorch version you need is dependent on your system. For installation instructions for pytorch, visit the pytorch website.

In general, this should work:

# using conda:
conda install pytorch cuda80 -c soumith
# using pip
pip install http://download.pytorch.org/whl/cu80/torch-0.2.0.post3-cp36-cp36m-manylinux1_x86_64.whl