grid_search_usage.py

"""
This module describes how to use the GridSearchCV() class for finding the best
parameter combination of a given algorithm.
"""

from __future__ import (absolute_import, division, print_function,
                        unicode_literals)

from surprise import SVD
from surprise import Dataset
from surprise.model_selection import GridSearchCV

# Use movielens-100K
data = Dataset.load_builtin('ml-100k')

param_grid = {'n_epochs': [5, 10], 'lr_all': [0.002, 0.005],
              'reg_all': [0.4, 0.6]}
gs = GridSearchCV(SVD, param_grid, measures=['rmse', 'mae'], cv=3)

gs.fit(data)

# best RMSE score
print(gs.best_score['rmse'])

# combination of parameters that gave the best RMSE score
print(gs.best_params['rmse'])

# We can now use the algorithm that yields the best rmse:
algo = gs.best_estimator['rmse']
algo.fit(data.build_full_trainset())

import pandas as pd  # noqa
results_df = pd.DataFrame.from_dict(gs.cv_results)