Configure LogisticRegression "fit_intercept" Parameter

The fit_intercept parameter in scikit-learn’s LogisticRegression controls whether a constant (bias or intercept) should be added to the decision function.

LogisticRegression is a linear model for binary classification that predicts the probability of a binary outcome using a logistic function. The fit_intercept parameter determines whether a constant should be included in the model.

Including the intercept (setting fit_intercept=True) adjusts the decision boundary by adding a constant term, while excluding it (setting fit_intercept=False) forces the model to pass through the origin.

The default value for fit_intercept is True. Common values are True and False.

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

# Generate synthetic dataset
X, y = make_classification(n_samples=1000, n_features=10, n_informative=5,
                           n_redundant=0, random_state=42)

# Split into train and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Train with fit_intercept=True
model_with_intercept = LogisticRegression(fit_intercept=True, random_state=42)
model_with_intercept.fit(X_train, y_train)
y_pred_with_intercept = model_with_intercept.predict(X_test)
accuracy_with_intercept = accuracy_score(y_test, y_pred_with_intercept)
print(f"fit_intercept=True, Accuracy: {accuracy_with_intercept:.3f}")

# Train with fit_intercept=False
model_without_intercept = LogisticRegression(fit_intercept=False, random_state=42)
model_without_intercept.fit(X_train, y_train)
y_pred_without_intercept = model_without_intercept.predict(X_test)
accuracy_without_intercept = accuracy_score(y_test, y_pred_without_intercept)
print(f"fit_intercept=False, Accuracy: {accuracy_without_intercept:.3f}")

Running the example gives an output like:

fit_intercept=True, Accuracy: 0.770
fit_intercept=False, Accuracy: 0.750

The key steps in this example are:

Generate a synthetic binary classification dataset.
Split the data into train and test sets.
Train LogisticRegression models with fit_intercept=True and fit_intercept=False.
Evaluate the accuracy of each model on the test set.

Some tips and heuristics for setting fit_intercept:

Use fit_intercept=True if your data does not include the intercept term already.
Use fit_intercept=False if your data is already centered around zero or includes the intercept term.

Issues to consider:

Not including an intercept when necessary can lead to biased models.
Always verify the data preprocessing steps to ensure they align with the fit_intercept setting.

See Also