import logging

import pandas as pd
from sklearn import metrics
from sklearn.cluster import AffinityPropagation
from sklearn.metrics import davies_bouldin_score

from ..plot_metrics import draw_graphs

logging.getLogger().setLevel(logging.INFO)


def run_algo(training_set, fan_ids, modelling_config, algo_params):

    X = training_set
    if isinstance(fan_ids, pd.Series):
        fan_ids = fan_ids.to_frame()

    damping = algo_params['damping']
    hyperparams = algo_params['hyperparams']

    hyperparams['damping'] = damping
    hyperparams['random_state'] = 0  # For consistency over multiple runs, we want this to always remain the same
    #hyperparams['n_jobs'] = -1  # This algo doesn't utilize n_jobs and multiple cores

    clustering = AffinityPropagation(**hyperparams).fit(X)
    labels = clustering.labels_
    cluster_centers_indices = clustering.cluster_centers_indices_
    centers = clustering.cluster_centers_
    n_clusters = len(cluster_centers_indices)

    cluster_output = fan_ids.join(pd.DataFrame(labels)).rename(columns={0: 'cluster', '0': 'cluster'})
    X = pd.DataFrame(X).join(pd.DataFrame(labels), lsuffix='left_').rename(columns={0: 'cluster', '0': 'cluster'})
    graph_locations = draw_graphs(X, labels, modelling_config, n_clusters, centers)

    eval_metrics = {'clusters': n_clusters,
                    'n_iter': clustering.n_iter_,
                    'silhouette_coefficient': metrics.silhouette_score(X, labels),
                    'davies_bouldin_index': davies_bouldin_score(X, labels),
                    'calinski_harabasz_index': metrics.calinski_harabasz_score(X, labels)
                    }

    return clustering, eval_metrics, hyperparams, cluster_output, graph_locations


if __name__ == '__main__':
    """ Instead of generating df, perhaps load your own dataframe from csv. We need a dataframe with
    training cols only (preprocessed, and standardscaled) and a fan_id. """
    training_set = pd.DataFrame({
        'fan_id': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14],
        'a': [1,2,3,4,5,6,4,3,1,5,5,6,7,9],
        'b': [2,3,4,5,6,7,8,9,2,3,4,5,6,9]
    })
    fan_ids = training_set['fan_id']

    modelling_config = {
        'plot_2d': True,
        'plot_3d': True,
        'plot_silhouette': True,
        'boxplot': True,
    }
    algo_params = {'damping': 0.5, 'hyperparams': {'affinity': 'euclidean', 'max_iter': 2000, 'convergence_iter': 15}}

    print(run_algo(training_set, fan_ids, modelling_config, algo_params)[1])