Skip to content

Instantly share code, notes, and snippets.

@mbednarski

mbednarski/opt.py

Created July 19, 2021 10:32
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save mbednarski/caf1fe413ec16774dba9ce9b97c89ed8 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save mbednarski/caf1fe413ec16774dba9ce9b97c89ed8 to your computer and use it in GitHub Desktop.
Download ZIP

Revisions

  1. mbednarski created this gist Jul 19, 2021.
    30 changes: 30 additions & 0 deletions opt.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,30 @@
    from sklearn.datasets import load_iris
    from sklearn.model_selection import train_test_split
    from sklearn.tree import DecisionTreeClassifier
    import optuna


    X, y = load_iris(return_X_y=True)

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.20, stratify=y)

    def objective(trial: optuna.Trial):

    params = {
    'max_depth': trial.suggest_int('max_depth', 1, 20),
    'criterion': trial.suggest_categorical('crterion', ['gini', 'entropy']),
    'min_samples_split': trial.suggest_float('min_samples_split', 0.1, 1.0,log=True)
    }

    clf = DecisionTreeClassifier(**params)

    clf.fit(X_train, y_train)

    score = clf.score(X_test, y_test) # acc

    return score


    study = optuna.create_study(study_name='irysy', storage='sqlite:///irysy.db', direction='maximize', load_if_exists=True)
    study.optimize(objective, n_trials=20)

    42 changes: 42 additions & 0 deletions opt2.py
    View file
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,42 @@
    from sklearn.datasets import load_digits
    from sklearn.model_selection import train_test_split
    from sklearn.tree import DecisionTreeClassifier
    from sklearn.svm import SVR
    import optuna


    X, y = load_digits(return_X_y=True)

    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.20, stratify=y)

    def objective(trial: optuna.Trial):

    type_ = trial.suggest_categorical('type_', ['svr', 'rf'])

    if type_ == 'rf':
    params = {
    'max_depth': trial.suggest_int('max_depth', 1, 20),
    'criterion': trial.suggest_categorical('crterion', ['gini', 'entropy']),
    'min_samples_split': trial.suggest_float('min_samples_split', 0.1, 1.0,log=True),
    'max_features': trial.suggest_categorical('max_features', ["auto", "sqrt", "log2"])
    }
    clf = DecisionTreeClassifier(**params)
    clf.fit(X_train, y_train)
    score = clf.score(X_test, y_test) # acc
    return score
    elif type_ == 'svr':
    params = {
    'kernel': trial.suggest_categorical('kernel', ['linear', 'poly', 'rbf', 'sigmoid']),
    'degree': trial.suggest_int('degree', 1, 3),
    'C': trial.suggest_float('C', 0.01, 10, log=True)
    }
    clf = SVR(**params)
    clf.fit(X_train, y_train)
    score = clf.score(X_test, y_test) # acc
    return score



    study = optuna.create_study(study_name='digits2', storage='sqlite:///digits2.db', direction='maximize', load_if_exists=True)
    study.optimize(objective, n_trials=200)