import numpy as np
from sklearn.linear_model import LogisticRegressionCV

from quapy.data import LabelledCollection
from quapy.method.non_aggregative import MaximumLikelihoodPrevalenceEstimation as MLPE
from quapy.method.aggregative import CC, PCC, ACC, PACC, EMQ
from commons import *
from table import Table
from tqdm import tqdm
import quapy as qp


np.set_printoptions(linewidth=np.inf)

def classifier():
    return LogisticRegressionCV()

def quantifiers():
    cls = classifier()
    yield 'MLPE', MLPE()
    yield 'CC', CC(cls)
    yield 'PCC', PCC(cls)
    yield 'ACC', ACC(cls)
    yield 'PACC', PACC(cls)
    yield 'SLD', EMQ(cls)


survey_y = './data/survey_y.csv'

Atr, Xtr, ytr = load_csv(survey_y, use_yhat=True)

preprocessor = Preprocessor()
Xtr = preprocessor.fit_transform(Xtr)

data = get_dataset_by_area(Atr, Xtr, ytr)
n_areas = len(data)

Madj = AdjMatrix('./data/matrice_adiacenza.csv')

areas = [Ai for Ai, _, _ in data]
q_names = [q_name for q_name, _ in quantifiers()]

# tables = []
text_outputs = []

benchmarks  = [f'te-{Ai}' for Ai in areas]  # areas used as test

# areas on which a quantifier is trained, e.g., 'PACC-w/o46' means a PACC quantifier
# has been trained on all areas but 46
methods     = [f'{q_name}-cat' for q_name in q_names]

table = Table(name='adjacentconcat', benchmarks=benchmarks, methods=methods, stat_test=None, color_mode='local')
table.format.mean_prec = 4
table.format.show_std = False
# table.format = False
table.format.remove_zero = True

for q_name, q in quantifiers():
    for i, (Ai, Xi, yi) in tqdm(enumerate(data), total=n_areas):
        #training
        trainings = [LabelledCollection(Xj, yj) for Aj, Xj, yj in data if Aj!=Ai and Aj in Madj.get_adjacent(Ai)]
        print(f'for test Ai={Ai} there should be {Madj.get_adjacent(Ai)}: len={len(trainings)}')
        tr = LabelledCollection.join(*trainings)
        q.fit(tr)

        #test
        te = LabelledCollection(Xi, yi)
        qp.environ["SAMPLE_SIZE"] = len(te)
        pred_prev = q.quantify(te.X)
        true_prev = te.prevalence()
        err = qp.error.mae(true_prev, pred_prev)

        method_name = f'{q_name}-cat'
        table.add(benchmark=f'te-{Ai}', method=method_name, v=err)

    # text_outputs.append(f'{q_name} got mean {table.all_mean():.5f}, best mean {table.get_method_values("Best").mean():.5f}')


Table.LatexPDF(f'./results/adjacentconcat/doc.pdf', [table])

# with open(f'./results/classifier/output.txt', 'tw') as foo:
#     foo.write('\n'.join(text_outputs))