---
title: "Scikit-Learn"
description: "Learn how to create, train, and evaluate machine learning models in the research environment in QuantConnect with Scikit-Learn library."
canonical: https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn
markdown: https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn.md
language: python
source: https://github.com/QuantConnect/Documentation/tree/master/04%20Research%20Environment/08%20Machine%20Learning/03%20Popular%20Libraries/06%20Scikit-Learn
modified: 2026-10-30
index: https://www.quantconnect.com/llms.txt
---

# Scikit-Learn

[Documentation](https://www.quantconnect.com/docs/v2.md) > [Research Environment](https://www.quantconnect.com/docs/v2/research-environment.md) > Machine Learning > [Popular Libraries](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries.md) > Scikit-Learn

> Code examples are shown in Python. Append `?lang=csharp` to this URL for the C# version of this page.

## Introduction

This page explains how to build, train, test, and store `Scikit-Learn`/`sklearn` models.

## Import Libraries

Import the `sklearn` libraries.

```python
from sklearn.svm import SVR
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
import joblib
```

You need the `joblib` library to store models.

## Get Historical Data

[Get some historical market data](https://www.quantconnect.com/docs/v2/research-environment/datasets/us-equity.md#04-Get-Historical-Data) to train and test the model. For example, to get data for the SPY ETF during 2020 and 2021, run:

```python
qb = QuantBook()
symbol = qb.add_equity("SPY", Resolution.DAILY).symbol
history = qb.history(symbol, datetime(2020, 1, 1), datetime(2022, 1, 1)).loc[symbol]
```

## Prepare Data

You need some [historical data](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn.md#03-Get-Historical-Data) to prepare the data for the model. If you have historical data, manipulate it to train and test the model. In this example, use the following features and labels:

| Data Category | Description |
| --- | --- |
| Features | Daily percent change of the open, high, low, close, and volume of the SPY over the last 5 days |
| Labels | Daily percent return of the SPY over the next day |

The following image shows the time difference between the features and labels:

![Features and labels for training](https://cdn.quantconnect.com/i/tu/ml-keras-function.png)

Follow these steps to prepare the data:

1. Call the `pct_change` method and then drop the first row.
   ```python
   daily_returns = history['close'].pct_change()[1:]
   ```
2. Loop through the `daily_returns` DataFrame and collect the features and labels.
   ```python
   n_steps = 5
   features = []
   labels = []
   for i in range(len(daily_returns)-n_steps):
       features.append(daily_returns.iloc[i:i+n_steps].values)
       labels.append(daily_returns.iloc[i+n_steps])
   ```
3. Convert the lists of features and labels into `numpy` arrays.
   ```python
   X = np.array(features)
   y = np.array(labels)
   ```
4. Split the data into training and testing periods.
   ```python
   X_train, X_test, y_train, y_test = train_test_split(X, y)
   ```

## Train Models

You need to [prepare the historical data](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn.md#04-Prepare-Data) for training before you train the model. If you have prepared the data, build and train the model. In this example, build a Support Vector Regressor model and optimize its hyperparameters with grid search cross-validation. Follow these steps to create the model:

1. Set the choices of hyperparameters used for grid search testing.
   ```python
   param_grid = {'C': [.05, .1, .5, 1, 5, 10],
                 'epsilon': [0.001, 0.005, 0.01, 0.05, 0.1],
                 'gamma': ['auto', 'scale']}
   ```
2. Call the `GridSearchCV` constructor with the SVR model, the parameter grid, a scoring method, the number of cross-validation folds.
   ```python
   gsc = GridSearchCV(SVR(), param_grid, scoring='neg_mean_squared_error', cv=5)
   ```
3. Call the `fit` method and then select the best estimator.
   ```python
   model = gsc.fit(X_train, y_train).best_estimator_
   ```

## Test Models

You need to [build and train the model](https://www.quantconnect.com/docs/v2/research-environment/machine-learning/popular-libraries/scikit-learn.md#05-Train-Models) before you test its performance. If you have trained the model, test it on the out-of-sample data. Follow these steps to test the model:

1. Call the `predict` method with the features of the testing period.
   ```python
   y_hat = model.predict(X_test)
   ```
2. Plot the actual and predicted labels of the testing period.
   ```python
   df = pd.DataFrame({'y': y_test.flatten(), 'y_hat': y_hat.flatten()})
   df.plot(title='Model Performance: predicted vs actual %change in closing price', figsize=(15, 10))
   ```

![Sklearn model performance](https://cdn.quantconnect.com/i/tu/sklearn-plot-2.png)

## Store Models

You can save and load `sklearn` models using the Object Store.

### Save Models

Follow these steps to save models in the Object Store:

1. Set the key name of the model to be stored in the Object Store.
   ```python
   model_key = "model"
   ```
2. Call the `get_file_path` method with the key.
   ```python
   file_name = qb.object_store.get_file_path(model_key)
   ```
   This method returns the file path where the model will be stored.
3. Call the `dump` method with the model and file path.
   ```python
   joblib.dump(model, file_name)
   ```
   If you dump the model using the `joblib` module before you save the model, you don't need to retrain the model.

### Load Models

You must save a model into the Object Store before you can load it from the Object Store. If you saved a model, follow these steps to load it:

1. Call the `contains_key` method with the model key.
   ```python
   qb.object_store.contains_key(model_key)
   ```
   This method returns a boolean that represents if the `model_key` is in the Object Store. If the Object Store does not contain the `model_key`, save the model using the `model_key` before you proceed.
2. Call `get_file_path` with the key.
   ```python
   file_name = qb.object_store.get_file_path(model_key)
   ```
   This method returns the path where the model is stored.
3. Call `load` with the file path.
   ```python
   loaded_model = joblib.load(file_name)
   ```
   This method returns the saved model.

## Examples

The following examples demonstrate some common practices for using the sklearn library.

### Example 1: Predict Next Return

The following research notebook uses `sklearn` machine learning model to predict the next day's return by the previous 5 days' daily returns.

```python
# Import the sklearn library and others.
from sklearn.svm import SVR
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import train_test_split
import joblib

# Instantiate the QuantBook for researching.
qb = QuantBook()
# Request the daily SPY history with the date range to be studied.
symbol = qb.add_equity("SPY", Resolution.DAILY).symbol
history = qb.history(symbol, datetime(2020, 1, 1), datetime(2022, 1, 1)).loc[symbol]

# Obtain the daily returns to be the features and labels.
daily_returns = history['close'].pct_change()[1:]
# We use the previous 5 day returns as the features to be studied.
# Get the 1-day forward return as the labels for the machine to learn.
n_steps = 5
features = []
labels = []
for i in range(len(daily_returns)-n_steps):
    features.append(daily_returns.iloc[i:i+n_steps].values)
    labels.append(daily_returns.iloc[i+n_steps])

# Split the data as a training set and test set for validation.
features = np.array(features)
labels = np.array(labels)
X_train, X_test, y_train, y_test = train_test_split(X, y)

# Set the choices of hyperparameters used for grid search testing.
param_grid = {'C': [.05, .1, .5, 1, 5, 10],
              'epsilon': [0.001, 0.005, 0.01, 0.05, 0.1],
              'gamma': ['auto', 'scale']}
# Call the GridSearchCV constructor with the SVR model, the parameter grid, a scoring method, the number of cross-validation folds.
gsc = GridSearchCV(SVR(), param_grid, scoring='neg_mean_squared_error', cv=5)
# Call the fit method and then select the best estimator.
model = gsc.fit(X_train, y_train).best_estimator_

# Call the predict method with the features of the testing period.
y_hat = model.predict(X_test)
# Plot the actual and predicted labels of the testing period.
df = pd.DataFrame({'y': y_test.flatten(), 'y_hat': y_hat.flatten()})
df.plot(title='Model Performance: predicted vs actual %change in closing price', figsize=(15, 10))

# Store the model in the object store to allow accessing the model in the next research session or in the algorithm for trading.
model_key = "model"
file_name = qb.object_store.get_file_path(model_key)
joblib.dump(model, file_name)
```