Python Trials.statuses方法代码示例

# 需要导入模块: from hyperopt import Trials [as 别名]
# 或者: from hyperopt.Trials import statuses [as 别名]
def optimize_model_parameter_split(x, y, model_name=None, loss_function="accuracy", parameter=None, max_evals=100, n_folds=5, isWrite=True, times=1, problem_pattern="classification"):
    """
    hyperopt model turning
    """
    if model_name == None and parameter == None:
        print "you must set parameter or model_name"
        return None
    elif parameter != None:
        param = parameter
    elif model_name != None:
        param = parameter_dictionary[model_name]
    else:
        return None

    x_trains = []
    x_tests = []
    y_trains = []
    y_tests = []

    for time in xrange(times):
        x_train, x_test, y_train, y_test = cross_validation.train_test_split(
            x, y, test_size=0.0125)
        x_trains.append(x_train)
        x_tests.append(x_test)
        y_trains.append(y_train)
        y_tests.append(y_test)

    trials = Trials()
    function = lambda param: optimize_model_function_split(
        param, x_trains, x_tests, y_trains, y_tests, loss_function)
    print param
    print "========================================================================"
    best_param = fmin(function, param,
                      algo=tpe.suggest, max_evals=max_evals, trials=trials)
    print "========================================================================"
    print "write result to csv files"

    # write the csv file
    if isWrite:
        datas = []
        for trial_data in trials.trials:
            print trial_data
            trial_parameter_dictionary = {}
            trial_parameter_dictionary['model'] = model_name
            trial_parameter_dictionary['tid'] = trial_data['misc']['tid']
            for key, value in trial_data['misc']['vals'].items():
                print key, value[0]
                trial_parameter_dictionary[key] = value[0]
            trial_parameter_dictionary['loss'] = trial_data['result']['loss']
            trial_parameter_dictionary[
                'status'] = trial_data['result']['status']
            datas.append(trial_parameter_dictionary)
        filename = str(time.time()) + ".csv"
        dictionary_in_list_convert_to_csv(datas, filename)

    print trials.statuses()
    return best_param

# 需要导入模块: from hyperopt import Trials [as 别名]
# 或者: from hyperopt.Trials import statuses [as 别名]
def optimize_model_parameter_validation(x, y, model_name=None, loss_function="accuracy", parameter=None, max_evals=100, n_folds=5, isWrite=True, problem_pattern="classification"):
    """
    hyperopt model turning
    """
    if model_name == None and parameter == None:
        print "you must set parameter or model_name"
        return None
    elif parameter != None:
        param = parameter
    elif model_name != None:
        param = parameter_dictionary[model_name]
    else:
        return None

    validation_indexs = []

    if problem_pattern == "classification":
        for train_index, test_index in cross_validation.StratifiedKFold(y, n_folds=n_folds):
            validation_indexs.append((train_index, test_index))
    else:
        for train_index, test_index in cross_validation.KFold(len(y), n_folds=n_folds):
            validation_indexs.append((train_index, test_index))

    trials = Trials()
    function = lambda param: optimize_model_function(
        param, x, y, validation_indexs, loss_function)
    print param
    print "========================================================================"
    best_param = fmin(function, param,
                      algo=tpe.suggest, max_evals=max_evals, trials=trials)
    print "========================================================================"
    print "write result to csv files"

    # write the csv file
    if isWrite:
        datas = []
        for trial_data in trials.trials:
            print trial_data
            trial_parameter_dictionary = {}
            trial_parameter_dictionary['model'] = model_name
            trial_parameter_dictionary['tid'] = trial_data['misc']['tid']
            for key, value in trial_data['misc']['vals'].items():
                print key, value[0]
                trial_parameter_dictionary[key] = value[0]
            trial_parameter_dictionary['loss'] = trial_data['result']['loss']
            trial_parameter_dictionary[
                'status'] = trial_data['result']['status']
            datas.append(trial_parameter_dictionary)
        filename = str(time.time()) + ".csv"
        dictionary_in_list_convert_to_csv(datas, filename)

    print trials.statuses()
    return best_param

    def model_evaluation(clf, x, y, evaluate_function_name, labeled_type, label_convert_type="normal"):
        if evaluate_function_name == "accuracy":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
            score = -score
        elif evaluate_function_name == "logloss":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
            train_score = -score
        elif evaluate_function_name == "mean_squared_error":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
        elif evaluate_function_name == "gini":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
            score = -score
            train_score = -train_score
        elif evaluate_function_name == "rmsle":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
        elif evaluate_function_name == "auc":
            if params['model'] == "XGBREGLOGISTIC":
                y_pred = clf.predict_proba(x_test)
            else:
                y_pred = clf.predict_proba(x_test)[:, 1]

            train_score = evaluate_function(
                y_train, train_y_pred, evaluate_function_name)
            score = evaluate_function(y_test, y_pred, evaluate_function_name)
            score = -score
            train_score = -train_score
        elif evaluate_function_name == "rmspe":
            y_pred = clf.predict(x)
            score = evaluate_function(
                y, y_pred, evaluate_function_name)
            score = score
        return score

# 需要导入模块: from hyperopt import Trials [as 别名]
# 或者: from hyperopt.Trials import statuses [as 别名]
# why does hp.randint('x', 10) always return same number?
# works without space=____
trials = Trials()
best = fmin(objective,
            space=space,
            # space=hp.quniform('x', -10, 10, .00001),
            algo=tpe.suggest,
            max_evals=10,
            trials=trials)

# why is this red? where is the syntax error?
print best
print hyperopt.space_eval(space, best)
# always prints all the floats, regardless of status
print trials.losses()
print trials.statuses()
print trials.results
# here it's not red..
print best

# msg = trials.trial_attachments(trials.trials[5])['time_module']
# time_module = pickle.loads(msg)

# print time_module
# print msg

space = hp.choice('a',
        [
            ('case 1', 1 + hp.randint('c1', 10)),
            ('case 2', hp.uniform('c2', -10, 10))
        ]),