# -*- coding: utf-8 -*-
__author__ = 106360


import numpy
import pandas as pd
import seaborn as sns
from sklearn.metrics import mean_squared_error
import scipy
import matplotlib.pyplot as plt


def train_model(trainX, trainY, testX, testY, model, epochs=200, batch_size=16,show_plot=True):
    history = model.fit(trainX, trainY, validation_data=(testX, testY),
                        epochs=epochs, batch_size=batch_size)

    if show_plot:
        acc = history.history['mean_absolute_percentage_error']
        val_acc = history.history['val_mean_absolute_percentage_error']
        loss = history.history['loss']
        val_loss = history.history['val_loss']

        epochs_range = range(epochs)

        plt.figure(figsize=(8, 8))
        plt.subplot(1, 2, 1)
        plt.plot(epochs_range, acc, label='Training mean_absolute_percentage_error')
        plt.plot(epochs_range, val_acc, label='Validation mean_absolute_percentage_error')
        plt.legend(loc='upper right')
        plt.title('Training and Validation \% error')

        plt.subplot(1, 2, 2)
        plt.plot(epochs_range, loss, label='Training Loss')
        plt.plot(epochs_range, val_loss, label='Validation Loss')
        plt.legend(loc='upper right')
        plt.title('Training and Validation Loss')
        plt.show()

    return model

def evaluate_regression_model(model,testX, testY,normalizer,show_plot=True):
    predicted_Y = model.predict(testX)
    test_Y_unnormalized = normalizer[-1].inverse_transform(testY)
    predicted_Y_unnormalized = normalizer[-1].inverse_transform(predicted_Y)

    if show_plot:
        plot_regression(test_Y_unnormalized,predicted_Y_unnormalized)

def plot_regression(gt_array, pred_array, filename='',show_plot=True):
    # fig, ax = plt.subplots(1, 1)
    x, y = pd.Series(numpy.squeeze(gt_array), name="ground_truth_val"), pd.Series(numpy.squeeze(pred_array), name="predicted_val")
    g= sns.jointplot(x=x, y=y,  marker='.')
    # sns.regplot(x=x, y=y, ax=ax, marker=None, scatter=None)

    # g = sns.jointplot(x, y, kind="hex", color="#5d5d60", joint_kws={'gridsize': 40, 'bins': 'log'}, xlim=(0, 1), ylim=(0, 1), stat_func=None)
    sns.regplot(pd.Series(numpy.arange(0, 1.001, 0.01)), pd.Series(numpy.arange(0, 1.001, 0.01)), ax=g.ax_joint, scatter=True)
    sns.regplot(x, y, ax=g.ax_joint, scatter=True)

    slope, intercept, r_value, p_value, std_err = scipy.stats.linregress(numpy.squeeze(gt_array), numpy.squeeze(pred_array))
    rms = numpy.sqrt(mean_squared_error(pred_array, gt_array))
    if show_plot:
        figure_title = 'rms=%.2f, r_value = %.2f, p_value = %.2f, y=%.2f*x + %.2f ' % (rms, r_value, p_value, slope, intercept)
        g.fig.suptitle(figure_title)
        # fig.suptitle(figure_title)
        print(figure_title)
        plt.tight_layout()
        plt.show()
    if filename!='':
        g.fig.savefig(filename, dpi=600)
    return slope, intercept, r_value, p_value, std_err



if __name__ == "__main__":
    pass