Python hp.choice方法代碼示例

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_compilefn_train_test_split(tmpdir):
    db_name = "test"
    exp_name = "test2"
    fn = CompileFN(db_name, exp_name,
                   data_fn=data.data,
                   model_fn=model.build_model,
                   optim_metric="acc",
                   optim_metric_mode="max",
                   # eval
                   valid_split=.5,
                   stratified=False,
                   random_state=True,
                   save_dir="/tmp/")
    hyper_params = {
        "data": {},
        "shared": {"max_features": 100, "maxlen": 20},
        "model": {"filters": hp.choice("m_filters", (2, 5)),
                  "hidden_dims": 3,
                  },
        "fit": {"epochs": 1}
    }
    fn_test(fn, hyper_params, tmp_dir=str(tmpdir))
    trials = Trials()
    best = fmin(fn, hyper_params, trials=trials, algo=tpe.suggest, max_evals=2)
    assert isinstance(best, dict) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def __init__(self, estimator=None, max_evals=50, cv=5, handle_cv_failure=False, 
                scoring='accuracy', best_score=0.0, max_opt_time=None, max_eval_time=None, 
                pgo:Optional[PGO]=None, show_progressbar=True, args_to_scorer=None,
                verbose=False):
        self.max_evals = max_evals
        if estimator is None:
            self.estimator = LogisticRegression()
        else:
            self.estimator = estimator
        self.search_space = hp.choice('meta_model', [hyperopt_search_space(self.estimator, pgo=pgo)])
        self.scoring = scoring
        self.best_score = best_score
        self.handle_cv_failure = handle_cv_failure
        self.cv = cv
        self._trials = Trials()
        self.max_opt_time = max_opt_time
        self.max_eval_time = max_eval_time
        self.show_progressbar = show_progressbar
        if args_to_scorer is not None:
            self.args_to_scorer = args_to_scorer
        else:
            self.args_to_scorer = {}
        self.verbose = verbose 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_convert_conditional_space(self):
        a_or_b = configuration_space.CategoricalHyperparameter("a_or_b", ["a", "b"])
        cond_a = configuration_space.UniformFloatHyperparameter(
            'cond_a', 0, 1, conditions=[['a_or_b == a']])
        cond_b = configuration_space.UniformFloatHyperparameter(
            'cond_b', 0, 3, q=0.1, conditions=[['a_or_b == b']])
        conditional_space = {"a_or_b": a_or_b, "cond_a": cond_a, "cond_b": cond_b}
        cs = self.pyll_writer.write(conditional_space)
        expected = StringIO.StringIO()
        expected.write('from hyperopt import hp\nimport hyperopt.pyll as pyll')
        expected.write('\n\n')
        expected.write('param_0 = hp.uniform("cond_a", 0.0, 1.0)\n')
        expected.write('param_1 = hp.quniform("cond_b", -0.0499, 3.05, 0.1)\n')
        expected.write('param_2 = hp.choice("a_or_b", [\n')
        expected.write('    {"a_or_b": "a", "cond_a": param_0, },\n')
        expected.write('    {"a_or_b": "b", "cond_b": param_1, },\n')
        expected.write('    ])\n\n')
        expected.write('space = {"a_or_b": param_2}\n')
        self.assertEqual(expected.getvalue(), cs) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_operator_in(self):
        a_or_b = configuration_space.CategoricalHyperparameter("a_or_b", ["a", "b"])
        cond_a = configuration_space.UniformFloatHyperparameter(
            'cond_a', 0, 1, conditions=[['a_or_b == a']])
        cond_b = configuration_space.UniformFloatHyperparameter(
            'cond_b', 0, 3, q=0.1, conditions=[['a_or_b == b']])
        e = configuration_space.UniformFloatHyperparameter("e", 0, 5,
                                     conditions=[['a_or_b in {a,b}']])
        conditional_space_operator_in = {"a_or_b": a_or_b, "cond_a": cond_a,
                                 "cond_b": cond_b, "e": e}
        cs = self.pyll_writer.write(conditional_space_operator_in)
        expected = StringIO.StringIO()
        expected.write('from hyperopt import hp\nimport hyperopt.pyll as pyll')
        expected.write('\n\n')
        expected.write('param_0 = hp.uniform("cond_a", 0.0, 1.0)\n')
        expected.write('param_1 = hp.quniform("cond_b", -0.0499, 3.05, 0.1)\n')
        expected.write('param_2 = hp.uniform("e", 0.0, 5.0)\n')
        expected.write('param_3 = hp.choice("a_or_b", [\n')
        expected.write('    {"a_or_b": "a", "cond_a": param_0, "e": param_2, '
                       '},\n')
        expected.write('    {"a_or_b": "b", "cond_b": param_1, "e": param_2, '
                       '},\n')
        expected.write('    ])\n\n')
        expected.write('space = {"a_or_b": param_3}\n')
        self.assertEqual(expected.getvalue(), cs) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def set_default_hyperparameters(self):
        """
        Set default hyperparameter space. If none is provided, default is used.
        """
        self.hyperparameter_space = {
                                    'scale_X': hp.choice('scale_X', ['std', 'mm01', 'mm11', None]),
                                    'scale_y': hp.choice('scale_y', ['std', 'mm01', 'mm11', None]),
                                    }

        if self.input_obj.keywords['pes_format'] == 'interatomics':
            self.set_hyperparameter('morse_transform', hp.choice('morse_transform',[{'morse': True,'morse_alpha': hp.quniform('morse_alpha', 1, 2, 0.1)},{'morse': False}]))
        else:
            self.set_hyperparameter('morse_transform', hp.choice('morse_transform',[{'morse': False}]))
        if self.pip:
            val =  hp.choice('pip',[{'pip': True,'degree_reduction': hp.choice('degree_reduction', [True,False])}])
            self.set_hyperparameter('pip', val)
        else:
            self.set_hyperparameter('pip', hp.choice('pip', [{'pip': False}]))

        if self.input_obj.keywords['gp_ard'] == 'opt': # auto relevancy determination (independant length scales for each feature)
            self.set_hyperparameter('ARD', hp.choice('ARD', [True,False]))
         #TODO add optional space inclusions, something like: if option: self.hyperparameter_space['newoption'] = hp.choice(..) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_compilefn_cross_val(tmpdir):
    db_name = "test"
    exp_name = "test2"
    fn = CompileFN(db_name, exp_name,
                   cv_n_folds=3,
                   stratified=False,
                   random_state=True,
                   data_fn=data.data,
                   model_fn=model.build_model,
                   optim_metric="loss",
                   optim_metric_mode="min",
                   save_dir="/tmp/")
    hyper_params = {
        "data": {},
        "shared": {"max_features": 100, "maxlen": 20},
        "model": {"filters": hp.choice("m_filters", (2, 5)),
                  "hidden_dims": 3,
                  },
        "fit": {"epochs": 1}
    }
    fn_test(fn, hyper_params, tmp_dir=str(tmpdir))
    trials = Trials()
    best = fmin(fn, hyper_params, trials=trials, algo=tpe.suggest, max_evals=2)
    assert isinstance(best, dict) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def train_and_predict_with_time_control_basic(X_train: pd.DataFrame, X_test:pd.DataFrame, y:pd.Series, config:Config, random_state, test=False):
    if test:
        X_train, X_test, y, y_test = data_split_by_time(X_train, y, test_size=0.2)

    params = {
        "objective": "binary",
        "metric": "auc",
        "verbosity": -1,
        "seed": 1,
        "num_threads": 4
    }
    result = None

    ##-------------Generate random index--------------
    #index = random_state.choice(X_train.shape[0], 30000, replace=False)
    #index.sort()
    ### If assign the n_p_ratio, the HPO process will become very slow, which
    ### indicates low convergence speed.
    #index = sample(X_train, y, sample_size=30000, n_p_ratio=20, is_sort=True)
    index = sample(X_train, y, sample_size=30000, is_sort=True, random_state=random_state, same_ratio=False)
    X_sample = X_train.iloc[index]
    y_sample = y.iloc[index]

    hyperparams = hyperopt_lightgbm_basic(X_sample, y_sample, params, config)

    X_train, X_val, y, y_val = data_split_by_time(X_train, y, test_size=0.1)
    train_data = lgb.Dataset(X_train, y)
    val_data = lgb.Dataset(X_val, y_val)

    model = lgb.train({**params, **hyperparams}, train_data, 10000,
                          val_data, early_stopping_rounds=30, verbose_eval=100)


    result = model.predict(X_test)

    return result 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def hyperopt_lightgbm_basic(X, y, params, config, max_evals=50):
    X_train, X_test, y_train, y_test = data_split_by_time(X, y, test_size=0.2)
    X_train, X_val, y_train, y_val = data_split_by_time(X, y, test_size=0.3)
    train_data = lgb.Dataset(X_train, label=y_train)
    val_data = lgb.Dataset(X_val, label=y_val)

    space = {
        "learning_rate": hp.loguniform("learning_rate", np.log(0.01), np.log(0.5)),
        #"forgetting_factor": hp.loguniform("forgetting_factor", 0.01, 0.1)
        #"max_depth": hp.choice("max_depth", [-1, 2, 3, 4, 5, 6]),
        "max_depth": hp.choice("max_depth", [1, 2, 3, 4, 5, 6]),
        "num_leaves": hp.choice("num_leaves", np.linspace(10, 200, 50, dtype=int)),
        "feature_fraction": hp.quniform("feature_fraction", 0.5, 1.0, 0.1),
        "bagging_fraction": hp.quniform("bagging_fraction", 0.5, 1.0, 0.1),
        "bagging_freq": hp.choice("bagging_freq", np.linspace(0, 50, 10, dtype=int)),
        "reg_alpha": hp.uniform("reg_alpha", 0, 2),
        "reg_lambda": hp.uniform("reg_lambda", 0, 2),
        "min_child_weight": hp.uniform('min_child_weight', 0.5, 10),
    }

    def objective(hyperparams):
        model = lgb.train({**params, **hyperparams}, train_data, 100,
                        val_data, early_stopping_rounds=30, verbose_eval=0)
        pred = model.predict(X_test)
        score = roc_auc_score(y_test, pred)
        return {'loss': -score, 'status': STATUS_OK}

    trials = Trials()
    best = hyperopt.fmin(fn=objective, space=space, trials=trials,
                         algo=tpe.suggest, max_evals=max_evals, verbose=1,
                         rstate=np.random.RandomState(1))

    hyperparams = space_eval(space, best)
    log(f"auc = {-trials.best_trial['result']['loss']:0.4f} {hyperparams}")
    return hyperparams 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def hyperopt_lightgbm(X_train: pd.DataFrame, y_train: pd.Series, params: Dict, config: Config, max_evals=10):
    X_train, X_test, y_train, y_test = data_split_by_time(X_train, y_train, test_size=0.2)
    X_train, X_val, y_train, y_val = data_split_by_time(X_train, y_train, test_size=0.3)
    train_data = lgb.Dataset(X_train, label=y_train)
    valid_data = lgb.Dataset(X_val, label=y_val)

    space = {
        "learning_rate": hp.loguniform("learning_rate", np.log(0.01), np.log(0.5)),
        #"max_depth": hp.choice("max_depth", [-1, 2, 3, 4, 5, 6]),
        "max_depth": hp.choice("max_depth", [1, 2, 3, 4, 5, 6]),
        "num_leaves": hp.choice("num_leaves", np.linspace(10, 200, 50, dtype=int)),
        "feature_fraction": hp.quniform("feature_fraction", 0.5, 1.0, 0.1),
        "bagging_fraction": hp.quniform("bagging_fraction", 0.5, 1.0, 0.1),
        "bagging_freq": hp.choice("bagging_freq", np.linspace(0, 50, 10, dtype=int)),
        "reg_alpha": hp.uniform("reg_alpha", 0, 2),
        "reg_lambda": hp.uniform("reg_lambda", 0, 2),
        "min_child_weight": hp.uniform('min_child_weight', 0.5, 10),
    }

    def objective(hyperparams):
        if config.time_left() < 50:
            return {'status': STATUS_FAIL}
        else:
            model = lgb.train({**params, **hyperparams}, train_data, 100,
                          valid_data, early_stopping_rounds=10, verbose_eval=0)
            pred = model.predict(X_test)
            score = roc_auc_score(y_test, pred)

            #score = model.best_score["valid_0"][params["metric"]]

            # in classification, less is better
            return {'loss': -score, 'status': STATUS_OK}

    trials = Trials()
    best = hyperopt.fmin(fn=objective, space=space, trials=trials,
                         algo=tpe.suggest, max_evals=max_evals, verbose=1,
                         rstate=np.random.RandomState(1))

    hyperparams = space_eval(space, best)
    log(f"auc = {-trials.best_trial['result']['loss']:0.4f} {hyperparams}")
    return hyperparams 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def __init__(self):
        self.search_space = {
          'learning_rate': hp.loguniform('learning_rate', np.log(0.00001), np.log(0.1)),
          'L1_flag': hp.choice('L1_flag', [True, False]),
          'hidden_size': scope.int(hp.qloguniform('hidden_size', np.log(8), np.log(256),1)),
          'batch_size': scope.int(hp.qloguniform('batch_size', np.log(8), np.log(4096),1)),
          'margin': hp.uniform('margin', 0.0, 10.0),
          'optimizer': hp.choice('optimizer', ["adam", "sgd", 'rms']),
          'epochs': hp.choice('epochs', [500]) # always choose 10 training epochs.
        } 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def hyperopt_lightgbm(X: pd.DataFrame, y: pd.Series, params: Dict, config: Config):
    X_train, X_val, y_train, y_val = data_split(X, y, test_size=0.5)
    train_data = lgb.Dataset(X_train, label=y_train)
    valid_data = lgb.Dataset(X_val, label=y_val)

    space = {
        "max_depth": hp.choice("max_depth", np.arange(2, 10, 1, dtype=int)),
        # smaller than 2^(max_depth)
        "num_leaves": hp.choice("num_leaves", np.arange(4, 200, 4, dtype=int)),
        "feature_fraction": hp.quniform("feature_fraction", 0.2, 0.8, 0.1),
        # "bagging_fraction": hp.quniform("bagging_fraction", 0.2, 0.8, 0.1),
        # "bagging_freq": hp.choice("bagging_freq", np.linspace(0, 10, 2, dtype=int)),
        # "scale_pos_weight":hp.uniform('scale_pos_weight',1.0, 10.0),
        # "colsample_by_tree":hp.uniform("colsample_bytree",0.5,1.0),
        "min_child_weight": hp.quniform('min_child_weight', 2, 50, 2),
        "reg_alpha": hp.uniform("reg_alpha", 2.0, 8.0),
        "reg_lambda": hp.uniform("reg_lambda", 2.0, 8.0),
        "learning_rate": hp.quniform("learning_rate", 0.05, 0.4, 0.01),
        # "learning_rate": hp.loguniform("learning_rate", np.log(0.04), np.log(0.5)),
        #
        "min_data_in_leaf": hp.choice('min_data_in_leaf', np.arange(200, 2000, 100, dtype=int)),
        #"is_unbalance": hp.choice("is_unbalance", [True])
    }

    def objective(hyperparams):
        model = lgb.train({**params, **hyperparams}, train_data, 300,
                          valid_data, early_stopping_rounds=45, verbose_eval=0)

        score = model.best_score["valid_0"][params["metric"]]

        # in classification, less is better
        return {'loss': -score, 'status': STATUS_OK}

    trials = Trials()
    best = hyperopt.fmin(fn=objective, space=space, trials=trials,
                         algo=tpe.suggest, max_evals=150, verbose=1,
                         rstate=np.random.RandomState(1))

    hyperparams = space_eval(space, best)
    log(f"auc = {-trials.best_trial['result']['loss']:0.4f} {hyperparams}")
    return hyperparams 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def predict(self, x):
        data = xgb.DMatrix(x)
        pred = self.model.predict(data)
        return pred


# -----------------------------------
# 探索するパラメータの空間の指定
# -----------------------------------
# hp.choiceでは、複數の選択肢から選ぶ
# hp.uniformでは、下限・上限を指定した一様分布から抽出する。引數は下限・上限
# hp.quniformでは、下限・上限を指定した一様分布のうち一定の間隔ごとの點から抽出する。引數は下限・上限・間隔
# hp.loguniformでは、下限・上限を指定した対數が一様分布に従う分布から抽出する。引數は下限・上限の対數をとった値 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_read_switch(self):
        # 0 switch
        # 1   hyperopt_param
        # 2     Literal{dist1}
        # 3     randint
        # 4       Literal{2}
        # 5   Literal{uniform}
        # 6   Literal{normal}
        dist = hp.choice('dist1', ['uniform', 'normal'])
        ret = self.pyll_reader.read_switch(dist)
        expected = configuration_space.CategoricalHyperparameter(
            'dist1', ['uniform', 'normal'])
        self.assertEqual(expected, ret)

        bigger_choice = hp.choice('choice', [
            {'choice': "zero", 'a': 0, 'b': hp.uniform('b', 0, 10)},
            {'choice': "other", 'a': 1, 'b': hp.uniform('b', 0, 10)}])
        ret = self.pyll_reader.read_switch(bigger_choice)
        expected = configuration_space.CategoricalHyperparameter(
            'choice', ['zero', 'other'])
        self.assertEqual(expected, ret)
        self.assertEqual(2, len(self.pyll_reader.constants))
        # Only the hyperparameter b is put into pyll_reader.hyperparameters
        self.assertEqual(1, len(self.pyll_reader.hyperparameters))

    # TODO: duplicate these tests for Integer/care about integers + test if
    # the warning of non-uniform parameters is actually printed 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def test_convert_complex_space(self):
        cs = self.pyll_writer.write(config_space)
        expected = StringIO.StringIO()
        expected.write('from hyperopt import hp\nimport hyperopt.pyll as pyll')
        expected.write('\n\n')
        expected.write('param_0 = hp.uniform("LOG2_C", -5.0, 15.0)\n')
        expected.write('param_1 = hp.uniform("LOG2_gamma", -14.9999800563, '
                       '3.0)\n')
        expected.write('param_2 = hp.choice("kernel", [\n')
        expected.write('    {"kernel": "linear", },\n')
        expected.write('    {"kernel": "rbf", "LOG2_gamma": param_1, },\n')
        expected.write('    ])\n')
        expected.write('param_3 = hp.uniform("lr", 0.0001, 1.0)\n')
        expected.write('param_4 = pyll.scope.int(hp.quniform('
                       '"neurons", 15.50001, 1024.5, 16.0))\n')
        expected.write('param_5 = hp.choice("classifier", [\n')
        expected.write('    {"classifier": "nn", "lr": param_3, "neurons": '
                       'param_4, },\n')
        expected.write('    {"classifier": "svm", "LOG2_C": param_0, '
                       '"kernel": param_2, },\n')
        expected.write('    ])\n')
        expected.write('param_6 = hp.choice("preprocessing", [\n')
        expected.write('    {"preprocessing": "None", },\n')
        expected.write('    {"preprocessing": "pca", },\n')
        expected.write('    ])\n\n')
        expected.write('space = {"classifier": param_5, '
                       '"preprocessing": param_6}\n')
        self.assertEqual(expected.getvalue(), cs)

        self.pyll_writer.reset_hyperparameter_countr()
        expected.seek(0)
        cs = self.pyll_writer.write(config_space_2)
        self.assertEqual(expected.getvalue().replace("gamma", "gamma_2"), cs) 

# 需要導入模塊: from hyperopt import hp [as 別名]
# 或者: from hyperopt.hp import choice [as 別名]
def set_default_hyperparameters(self, nn_search_space=1):
        """
        Set default hyperparameter space. If none is provided, default is used.

        Parameters
        ----------
        nn_search_space : int
            Which tier of default hyperparameter search spaces to use. Neural networks have too many hyperparameter configurations to search across, 
            so this option reduces the number of variable hyperparameters to search over. Generally, larger integer => more hyperparameters, and more iterations of hp_maxit are recommended.
        """
        if nn_search_space == 1:
            self.hyperparameter_space = {
            'scale_X': hp.choice('scale_X',
                     [
                     {'scale_X': 'mm11',
                          'activation': hp.choice('activ2', ['tanh'])},
                     {'scale_X': 'std',
                          'activation': hp.choice('activ3', ['tanh'])},
                     ]),
            'scale_y': hp.choice('scale_y', ['std', 'mm01', 'mm11']),}
        # TODO make more expansive search spaces, benchmark them, expose them as input options
        #elif nn_search_space == 2:
        #elif nn_search_space == 3:
        else:
            raise Exception("Invalid search space specification")

        # Standard geometry transformations, always use these.
        if self.input_obj.keywords['pes_format'] == 'interatomics':
            self.set_hyperparameter('morse_transform', hp.choice('morse_transform',[{'morse': True,'morse_alpha': hp.quniform('morse_alpha', 1, 2, 0.1)},{'morse': False}]))
        else:
            self.set_hyperparameter('morse_transform', hp.choice('morse_transform',[{'morse': False}]))
        if self.pip:
            val =  hp.choice('pip',[{'pip': True,'degree_reduction': hp.choice('degree_reduction', [True,False])}])
            self.set_hyperparameter('pip', val)
        else:
            self.set_hyperparameter('pip', hp.choice('pip', [{'pip': False}]))