configs.py

# local imports
from models import *
from itertools import combinations

# Available feature extraction methods
features_methods = [
    'genre', 'movie_year', 'avg_rating', 
    'title_length'
]

# Available regression methods
regressor_methods = [
    'linear_regression','random_forest', 'lasso_regression','gradient_boosting',
    'ridge_regression', 'svr_regression'
]

# Generate all possible combinations of feature extraction methods
feature_combinations = []
for r in range(1, len(features_methods) + 1):
    feature_combinations.extend(combinations(features_methods, r))

# Generate all possible combinations of regression methods and feature extraction methods
model_combinations = []
for feature_set in feature_combinations:
    for regressor in regressor_methods:
        # Create a unique model name for the combination
        model_name = f"combination_{regressor}_{'_'.join(feature_set)}"
        # Define the arguments to be passed to the model
        arguments = {
            "features_method": list(feature_set),
            "regressor_method": regressor
        }
        # Append the combination to the list
        model_combinations.append((model_name, ContentBased, arguments))


class EvalConfig:
    """Configuration settings for evaluation."""
    
    # List of models to evaluate, each tuple containing model_name, model class, and model parameters (dict)
    models = [
        ("baseline_1", ModelBaseline1, {}),
        ("baseline_2", ModelBaseline2, {}),
        ("baseline_3", ModelBaseline3, {}),
        ("baseline_4", ModelBaseline4, {}),
<<<<<<< HEAD

        ("title_length_ContentBased_sample", ContentBased, {"title_length","random_sample"}),
        ("title_length_ContentBased_score", ContentBased, {"features_method" : ["title_length"], "regressor_method" : "random_score"}),
        ("title_length_ContentBased_Lr", ContentBased, {"features_method" : ["title_length"], "regressor_method" : "linear_regression"}),
        ("title_length_ContentBased_Lr", ContentBased, {"features_method" : ["title_length"], "regressor_method" : "svr_regression"}),
        ("title_length_ContentBased_Lr", ContentBased, {"features_method" : ["title_length"], "regressor_method" : "gradient_boosting"}),
        ("title_length_ContentBased_Lr", ContentBased, {"features_method" : ["title_length"], "regressor_method" : "random_forest"}),
        
        ("movie_year_ContentBased_sample", ContentBased, {"features_method" : "movie_year", "regressor_method" : "random_sample"}),
        ("movie_year_ContentBased_score", ContentBased, {"features_method" : "movie_year", "regressor_method" : "random_score"}),
        #("movie_year_ContentBased_Lr", ContentBased, {"features_method" : "movie_year", "regressor_method" : "linear_regression"}),
        #("movie_year_ContentBased_Lr", ContentBased, {"features_method" : "movie_year", "regressor_method" : "svr_regression"}),
        #("movie_year_ContentBased_Lr", ContentBased, {"features_method" : "movie_year", "regressor_method" : "gradient_boosting"}),
        #("movie_year_ContentBased_Lr", ContentBased, {"features_method" : "movie_year", "regressor_method" : "random_forest"}),


        ("genres_ContentBased_sample", ContentBased, {"features_method" : "genres", "regressor_method" : "random_sample"}),
        ("genres_ContentBased_score", ContentBased, {"features_method" : "genres", "regressor_method" : "random_score"}),
        #("genres_ContentBased_Lr", ContentBased, {"features_method" : "genres", "regressor_method" : "linear_regression"}),
        #("genres_ContentBased_Lr", ContentBased, {"features_method" : "genres", "regressor_method" : "svr_regression"}),
        #("genres_ContentBased_Lr", ContentBased, {"features_method" : "genres", "regressor_method" : "gradient_boosting"}),
        #("genres_ContentBased_Lr", ContentBased, {"features_method" : "genres", "regressor_method" : "random_forest"}),

        ("rating_ContentBased_sample", ContentBased, {"features_method" : "rating", "regressor_method" : "random_sample"}),
        ("rating_ContentBased_score", ContentBased, {"features_method" : "rating", "regressor_method" : "random_score"}),
        #("rating_ContentBased_Lr", ContentBased, {"features_method" : "rating", "regressor_method" : "linear_regression"}),
        #("rating_ContentBased_Lr", ContentBased, {"features_method" : "rating", "regressor_method" : "svr_regression"}),
        #("rating_ContentBased_Lr", ContentBased, {"features_method" : "rating", "regressor_method" : "gradient_boosting"}),
        #("rating_ContentBased_Lr", ContentBased, {"features_method" : "rating", "regressor_method" : "random_forest"}),
        

        ("tags_ContentBased_sample", ContentBased, {"features_method" : "tags", "regressor_method" : "random_sample"}),
        ("tags_ContentBased_score", ContentBased, {"features_method" : "tags", "regressor_method" : "random_score"}),
        #("tags_ContentBased_Lr", ContentBased, {"features_method" : "tags", "regressor_method" : "linear_regression"}),
        #("tags_ContentBased_Lr", ContentBased, {"features_method" : "tags", "regressor_method" : "svr_regression"}),
        #("tags_ContentBased_Lr", ContentBased, {"features_method" : "tags", "regressor_method" : "gradient_boosting"}),
        #("tags_ContentBased_Lr", ContentBased, {"features_method" : "tags", "regressor_method" : "random_forest"}),



        ("tags_length_ContentBased_sample", ContentBased, {"features_method" : "tags_length", "regressor_method" : "random_sample"}),
        ("tags_length_ContentBased_score", ContentBased, {"features_method" : "tags_length", "regressor_method" : "random_score"}),
        #("tags_length_ContentBased_Lr", ContentBased, {"features_method" : "tags_length", "regressor_method" : "linear_regression"}),
        #("tags_length_ContentBased_Lr", ContentBased, {"features_method" : "tags_length", "regressor_method" : "svr_regression"}),
        #("tags_length_ContentBased_Lr", ContentBased, {"features_method" : "tags_length", "regressor_method" : "gradient_boosting"}),
        #("tags_length_ContentBased_Lr", ContentBased, {"features_method" : "tags_length", "regressor_method" : "random_forest"}),


        ("timestamp_ContentBased_sample", ContentBased, {"features_method" : "timestamp", "regressor_method" : "random_sample"}),
        ("timestamp_ContentBased_score", ContentBased, {"features_method" : "timestamp", "regressor_method" : "random_score"}),
        #("timestamp_ContentBased_Lr", ContentBased, {"features_method" : "timestamp", "regressor_method" : "linear_regression"})
        #("timestamp_ContentBased_Lr", ContentBased, {"features_method" : "timestamp", "regressor_method" : "svr_regression"})
        #("timestamp_ContentBased_Lr", ContentBased, {"features_method" : "timestamp", "regressor_method" : "gradient_boosting"})
        #("timestamp_ContentBased_Lr", ContentBased, {"features_method" : "timestamp", "regressor_method" : "random_forest"})

        # model_name, model class, model parameters (dict)
=======
>>>>>>> 5385c4bc3a5802e1caec979d0d3a6bc7af3e970f
    ]

    # Add the combinations of ContentBased models to the list of models
    models.extend(model_combinations)

    # Print the models for verification
    for model in models:
          print(model)
    
    # Metrics to compute for split evaluation
    split_metrics = ["mae", "rmse"]

    # Metrics to compute for Leave-One-Out (LOO) evaluation
    loo_metrics = ["hit_rate"]

    # Metrics to compute for full dataset evaluation
    full_metrics = ["novelty"]

    # Split parameters
    test_size = 0.25  # Configure the test size (from 0 to 1)

    # Loo parameters
    top_n_value =  10 # -- configure the numer of recommendations (> 1) --