Scribd
Upload
62 views

Grid Search Steps and Example

Uploaded by

realmex7max5g
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
62 views

Grid Search Steps and Example

Uploaded by

realmex7max5g
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Grid Search: Steps and Example

Grid search is a hyperparameter tuning technique used in machine learning to identify the best combination of
hyperparameters for a model. It systematically evaluates all possible combinations of hyperparameter values to
find the optimal set based on a scoring metric.

Steps in Grid Search


• Define the Hyperparameters and Their Ranges: Identify the hyperparameters to tune and their possible
values. For example:
- For a support vector machine (SVM), you might tune:
- C (regularization parameter): [0.1, 1, 10]
- kernel: ['linear', 'rbf']
- gamma (kernel coefficient): [0.001, 0.01, 0.1]
• Split the Dataset: Divide the dataset into training and validation sets (or use cross-validation).
• Construct the Grid: Create a grid of all possible hyperparameter combinations. For the above example:
- Total combinations: 3 (C values) × 2 (kernels) × 3 (gamma values) = 18.
• Train Models for Each Combination: For each combination of hyperparameters, train the model on the
training data and evaluate it on the validation data using a predefined scoring metric (e.g., accuracy, F1-
score).
• Select the Best Combination: Identify the combination that yields the best performance on the validation
set.
• Test the Best Model: Evaluate the selected model on the test set to estimate its performance.

Example: Grid Search for SVM


**Dataset**: Iris dataset (predicting flower species)
**Hyperparameters**:
- C: [0.1, 1, 10]
- kernel: ['linear', 'rbf']
- gamma: [0.001, 0.01, 0.1]

Process**:

Split the data into training and test sets.

Define the hyperparameter grid:

```python
param_grid = {
'C': [0.1, 1, 10],
'kernel': ['linear', 'rbf'],
'gamma': [0.001, 0.01, 0.1]
}

Use `GridSearchCV` (from `scikit-learn`) to automate the search:

python
from sklearn.model_selection import GridSearchCV
from sklearn.svm import SVC
grid_search = GridSearchCV(SVC(), param_grid, cv=5, scoring='accuracy')
grid_search.fit(X_train, y_train)
Retrieve the best parameters:

python code:
print("Best parameters:", grid_search.best_params_)
Output might be:
Best parameters: {'C': 10, 'gamma': 0.01, 'kernel': 'rbf'}

Evaluate the model with the best parameters on the test set.

This approach ensures that the model is fine-tuned to achieve the best performance for the given task.

You might also like