Function plot_learning_curve

src/visualizations.py:198–231

Plots the learning curve of a model. Args: model: A scikit-learn compatible model. X (pd.DataFrame or np.ndarray): Feature matrix. y (pd.Series or np.ndarray): Target values. cv (int): Number of cross-validation folds. train_sizes (array-like): Propo

(model, X, y, cv=5, train_sizes=np.linspace(0.1, 1.0, 10), scoring="accuracy")

    plt.show()

def plot_learning_curve(model, X, y, cv=5, train_sizes=np.linspace(0.1, 1.0, 10), scoring="accuracy"):
    """
    Plots the learning curve of a model.

    Args:
        model: A scikit-learn compatible model.
        X (pd.DataFrame or np.ndarray): Feature matrix.
        y (pd.Series or np.ndarray): Target values.
        cv (int): Number of cross-validation folds.
        train_sizes (array-like): Proportions of training data to evaluate.
        scoring (str): Scoring metric to evaluate model performance.

    Returns:
        None
    """
    train_sizes, train_scores, val_scores = learning_curve(model, X, y, cv=cv, train_sizes=train_sizes, scoring=scoring, n_jobs=-1)

    train_mean = np.mean(train_scores, axis=1)
    train_std = np.std(train_scores, axis=1)
    val_mean = np.mean(val_scores, axis=1)
    val_std = np.std(val_scores, axis=1)

    plt.figure(figsize=(8, 6))
    plt.plot(train_sizes, train_mean, label="Training Score", marker="o", color="blue")
    plt.fill_between(train_sizes, train_mean - train_std, train_mean + train_std, alpha=0.2, color="blue")
    plt.plot(train_sizes, val_mean, label="Validation Score", marker="o", color="red")
    plt.fill_between(train_sizes, val_mean - val_std, val_mean + val_std, alpha=0.2, color="red")

    plt.xlabel("Training Set Size")
    plt.ylabel(scoring.capitalize())
    plt.title("Learning Curve")
    plt.legend(loc="lower right")
    plt.grid(alpha=0.5)
    plt.show()


def plot_feature_distribution(df, feature, bins=30):