import numpy as np
import pandas as pd

from quapy.method.aggregative import EMQ, KDEyML, PACC
from sklearn.linear_model import LogisticRegression

METHODS = ['PACC',
           'EMQ',
           'KDEy-ML',
           'KDEy-MLA'
           ]


# common hyperparameterss
hyper_LR = {
    'classifier__C': np.logspace(-3, 3, 7),
    'classifier__class_weight': ['balanced', None]
}

hyper_kde = {
    'bandwidth': np.linspace(0.001, 0.5, 100)
}

hyper_kde_aitchison = {
    'bandwidth': np.linspace(0.01, 2, 100)
}

# instances a new quantifier based on a string name
def new_method(method, **lr_kwargs):
    lr = LogisticRegression(**lr_kwargs)

    if method == 'KDEy-ML':
        param_grid = {**hyper_kde, **hyper_LR}
        quantifier = KDEyML(lr, kernel='gaussian')
    elif method == 'KDEy-MLA':
        param_grid = {**hyper_kde_aitchison, **hyper_LR}
        quantifier = KDEyML(lr, kernel='aitchison')
    elif method == 'EMQ':
        param_grid = hyper_LR
        quantifier = EMQ(lr)
    elif method == 'PACC':
        param_grid = hyper_LR
        quantifier = PACC(lr)
    else:
        raise NotImplementedError('unknown method', method)

    return param_grid, quantifier


def show_results(result_path):
    df = pd.read_csv(result_path+'.csv', sep='\t')

    pd.set_option('display.max_columns', None)
    pd.set_option('display.max_rows', None)
    pv = df.pivot_table(index='Dataset', columns="Method", values=["MAE", "MRAE"])
    print(pv)