K-fold cross-validation is a model evaluation technique. This technique divides the data set into 'k' equally sized subsets (or 'folds'). The model is then trained 'k' times and each time a different fold is used as the test set while the remaining folds are used as the training set.
In each iteration, the performance of the model is evaluated and eventually 'k' different performance measurements are obtained. The average of these measurements is often used to determine overall model performance.
The advantage of k-fold cross-validation is that the entire data set can be used for both training and testing. This allows a more accurate estimate of the model's generalization ability because each data point appears in the test set at least once.
Below is an example of how k-fold cross-validation can be implemented in Python:
from sklearn.model_selection import cross_val_score
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
# Load iris dataset
data = load_iris()
X = data.data
y = data.target
# Create your model
model = RandomForestClassifier()
# Apply K-fold cross-validation
scores = cross_val_score(model, X, y, cv=5)
# Print performance scores
print("Cross-validation scores: ", scores)
print("Average cross-validation score: ", scores.mean())
In this example, 5-fold cross-validation is used (i.e. cv=5). This means that the data set is divided into five equal parts and the model is trained and tested five times. As a result, we obtain five different performance scores and estimate the overall model performance by averaging them.
Top comments (0)