# Рисует график обучения
def tr_plot(tr_data, start_epoch):
    #Plot the training and validation data
    tacc = tr_data.history['accuracy']
    tloss = tr_data.history['loss']
    vacc = tr_data.history['val_accuracy']
    vloss = tr_data.history['val_loss']
    Epoch_count = len(tacc) + start_epoch
    Epochs = []
    for i in range (start_epoch, Epoch_count):
        Epochs.append(i + 1)
    index_loss  = np.argmin(vloss)#  this is the epoch with the lowest validation loss
    val_lowest  = vloss[index_loss]
    index_acc   = np.argmax(vacc)
    acc_highest = vacc[index_acc]
    plt.style.use('fivethirtyeight')
    sc_label = 'Лучшая эпоха= '+ str(index_loss + 1 + start_epoch)
    vc_label = 'Лучшая эпоха= '+ str(index_acc  + 1 + start_epoch)
    fig,axes=plt.subplots(nrows=1, ncols = 2, figsize = (20,8))
    axes[0].plot (Epochs,tloss, 'r', label = 'Потери при обучении')
    axes[0].plot (Epochs,vloss,'g',label='Потери при валидации' )
    axes[0].scatter (index_loss + 1 + start_epoch,val_lowest, s = 150, c = 'blue', label = sc_label)
    axes[0].set_title('Потери при валидации и обучении')
    axes[0].set_xlabel('Эпохи')
    axes[0].set_ylabel('Потери')
    axes[0].legend()
    axes[1].plot (Epochs,tacc,'r', label = 'Точность при обучении')
    axes[1].plot (Epochs,vacc,'g', label = 'Точность при валидации')
    axes[1].scatter(index_acc + 1 + start_epoch, acc_highest, s = 150, c = 'blue', label = vc_label)
    axes[1].set_title  ('Точность при валидации и обучении')
    axes[1].set_xlabel ('Эпохи')
    axes[1].set_ylabel ('Точность')
    axes[1].legend()
    plt.tight_layout
    #plt.style.use('fivethirtyeight')
    plt.show()
# Создаем data_frame, в котором название папки является меткой класса изображений (коты и собаки в нашем случае)
# Каждому элементу data_frame будет присвоена метка (DX) и название файла (image)
# Функция возвращает объект frame
def load_data_frame(sdir):
    classlist = os.listdir(sdir)
    filepaths = []
    labels = []
    for klass in classlist:
        classpath=os.path.join(sdir, klass)
        flist=os.listdir(classpath)
        for f in flist:
            fpath = os.path.join(classpath, f)
            filepaths.append( fpath.replace('\\', '/') )
            labels.append(klass)

    Fseries=pd.Series( filepaths, name = 'image' )
    Lseries=pd.Series(labels, name = 'dx')
    return pd.concat([Fseries, Lseries], axis=1)

# -*- coding: utf-8 -*-
"""
Created on Tue Dec 20 02:45:02 2022

@author: Heigrast
"""
import tensorflow as tf
from tensorflow import keras

import numpy as np
import pandas as pd

import matplotlib.pyplot as plt
import os
import seaborn as sns
from sklearn.metrics import confusion_matrix, classification_report

import time


# Выводит информацию о процессе обучения
def print_info( test_gen, preds, print_code, save_dir, subject ):
    class_dict = test_gen.class_indices
    labels = test_gen.labels
    file_names = test_gen.filenames
    error_list = []
    true_class = []
    pred_class = []
    prob_list  = []
    new_dict   = {}
    error_indices = []
    y_pred = []
    for key,value in class_dict.items():
        new_dict[value] = key             # dictionary {integer of class number: string of class name}
    # store new_dict as a text fine in the save_dir
    classes = list(new_dict.values())     # list of string of class names
    errors = 0
    for i, p in enumerate(preds):
        pred_index = np.argmax(p)
        true_index = labels[i]  # labels are integer values
        if pred_index != true_index: # a misclassification has occurred
            error_list.append(file_names[i])
            true_class.append(new_dict[true_index])
            pred_class.append(new_dict[pred_index])
            prob_list.append(p[pred_index])
            error_indices.append(true_index)
            errors = errors + 1
        y_pred.append(pred_index)
    if print_code != 0:
        if errors > 0:
            if print_code>errors:
                r = errors
            else:
                r = print_code
            msg ='{0:^28s}{1:^28s}{2:^28s}{3:^16s}'.format('Filename', 'Predicted Class' , 'True Class', 'Probability')
            print_in_color(msg, (0,255,0),(55,65,80))
            for i in range(r):
                split1 = os.path.split(error_list[i])
                split2 = os.path.split(split1[0])
                fname  = split2[1] + '/' + split1[1]
                msg    = '{0:^28s}{1:^28s}{2:^28s}{3:4s}{4:^6.4f}'.format(fname, pred_class[i],true_class[i], ' ', prob_list[i])
                print_in_color(msg, (255,255,255), (55,65,60))
                #print(error_list[i]  , pred_class[i], true_class[i], prob_list[i])
        else:
            msg = 'With accuracy of 100 % there are no errors to print'
            print_in_color(msg, (0,255,0),(55,65,80))
    if errors > 0:
        plot_bar   = []
        plot_class = []
        for  key, value in new_dict.items():
            count = error_indices.count(key)
            if count != 0:
                plot_bar.append(count) # list containg how many times a class c had an error
                plot_class.append(value)   # stores the class
        fig=plt.figure()
        fig.set_figheight(len(plot_class)/3)
        fig.set_figwidth(10)
        plt.style.use('fivethirtyeight')
        for i in range(0, len(plot_class)):
            c = plot_class[i]
            x = plot_bar[i]
            plt.barh(c, x, )
            plt.title( ' Errors by Class on Test Set')
    y_true = np.array(labels)
    y_pred = np.array(y_pred)
    if len(classes)<= 30:
        # create a confusion matrix
        cm = confusion_matrix(y_true, y_pred )
        length = len(classes)
        if length < 8:
            fig_width  = 8
            fig_height = 8
        else:
            fig_width = int(length * .5)
            fig_height = int(length * .5)
        plt.figure(figsize = (fig_width, fig_height))
        sns.heatmap(cm, annot = True, vmin = 0, fmt = 'g', cmap = 'Blues', cbar = False)
        plt.xticks(np.arange(length) + .5, classes, rotation = 90)
        plt.yticks(np.arange(length) + .5, classes, rotation =0)
        plt.xlabel("Predicted")
        plt.ylabel("Actual")
        plt.title("Confusion Matrix")
        plt.show()
    clr = classification_report(y_true, y_pred, target_names=classes)
    print("Classification Report:\n----------------------\n", clr)

# Сохраняет результаты обучения в файл
def saver(save_path, model, model_name, subject, accuracy, img_size, scalar, generator):
    # first save the model
    save_id = str (model_name +  '-' + subject +'-'+ str(accuracy)[:str(accuracy).rfind('.')+3] + '.h5')
    model_save_loc = os.path.join(save_path, save_id)
    model.save(model_save_loc)
    print_in_color ('model was saved as ' + model_save_loc, (0,255,0),(55,65,80))
    # now create the class_df and convert to csv file
    class_dict = generator.class_indices
    height = []
    width = []
    scale = []
    for i in range(len(class_dict)):
        height.append(img_size[0])
        width.append(img_size[1])
        scale.append(scalar)
    Index_series  = pd.Series(list(class_dict.values()), name='class_index')
    Class_series  = pd.Series(list(class_dict.keys()), name='class')
    Height_series = pd.Series(height, name='height')
    Width_series  = pd.Series(width, name='width')
    Scale_series  = pd.Series(scale, name='scale by')

    class_df = pd.concat([Index_series, Class_series, Height_series, Width_series, Scale_series], axis=1)
    csv_name ='class_dict.csv'
    csv_save_loc = os.path.join(save_path, csv_name)
    class_df.to_csv(csv_save_loc, index=False)
    print_in_color ('class csv file was saved as ' + csv_save_loc, (0,255,0),(55,65,80))

    return model_save_loc, csv_save_loc

def print_in_color(txt_msg, fore_tupple, back_tupple,):
    #prints the text_msg in the foreground color specified by fore_tupple with the background specified by back_tupple
    #text_msg is the text, fore_tupple is foreground color tupple (r,g,b), back_tupple is background tupple (r,g,b)
    rf,gf,bf = fore_tupple
    rb,gb,bb = back_tupple
    msg = '{0}' + txt_msg
    mat = '\33[38;2;' + str(rf) +';' + str(gf) + ';' + str(bf) + ';48;2;' + str(rb) + ';' +str(gb) + ';' + str(bb) +'m'
    print(msg.format(mat), flush = True)
    print('\33[0m', flush = True) # returns default print color to back to black
    return

# Класс колбеков, он дает возможность выводить доп информацию во время обучения через переопределение методов родителя
class LRA(keras.callbacks.Callback):
    def __init__(self,model, base_model, patience, stop_patience, threshold, factor, dwell, batches, initial_epoch, epochs, ask_epoch):
        super(LRA, self).__init__()
        self.model=model
        self.base_model = base_model
        self.patience = patience # specifies how many epochs without improvement before learning rate is adjusted
        self.stop_patience = stop_patience # specifies how many times to adjust lr without improvement to stop training
        self.threshold = threshold # specifies training accuracy threshold when lr will be adjusted based on validation loss
        self.factor = factor # factor by which to reduce the learning rate
        self.dwell = dwell
        self.batches = batches # number of training batch to run per epoch
        self.initial_epoch = initial_epoch
        self.epochs = epochs
        self.ask_epoch = ask_epoch
        self.ask_epoch_initial = ask_epoch # save this value to restore if restarting training
        # callback variables
        self.count = 0 # how many times lr has been reduced without improvement
        self.stop_count = 0
        self.best_epoch = 1   # epoch with the lowest loss
        self.initial_lr = float(tf.keras.backend.get_value(model.optimizer.lr)) # get the initial learning rate and save it
        self.highest_tracc = 0.0 # set highest training accuracy to 0 initially
        self.lowest_vloss = np.inf # set lowest validation loss to infinity initially
        self.best_weights = self.model.get_weights() # set best weights to model's initial weights
        self.initial_weights = self.model.get_weights()   # save initial weights if they have to get restored

    def on_train_begin(self, logs = None):
        if self.base_model != None:
            status=self.base_model.trainable
            if status:
                msg = 'initializing callback starting train with base_model trainable'
            else:
                msg = 'initializing callback starting training with base_model not trainable'
        else:
            msg = 'initialing callback and starting training'
        print_in_color (msg, (244, 252, 3), (55,65,80))
        msg = '{0:^8s}{1:^10s}{2:^9s}{3:^9s}{4:^9s}{5:^9s}{6:^9s}{7:^10s}{8:^8s}'.format('Epoch', 'Loss', 'Accuracy',
                                                                                              'V_loss','V_acc', 'LR', 'Next LR', 'Monitor', 'Duration')
        print_in_color(msg, (244,252,3), (55,65,80))
        self.start_time = time.time()

    def on_train_end(self, logs = None):
        stop_time = time.time()
        tr_duration = stop_time- self.start_time
        hours = tr_duration // 3600
        minutes = (tr_duration - (hours * 3600)) // 60
        seconds = tr_duration - ((hours * 3600) + (minutes * 60))

        self.model.set_weights(self.best_weights) # set the weights of the model to the best weights
        msg=f'Training is completed - model is set with weights from epoch {self.best_epoch} '
        print_in_color(msg, (0,255,0), (55,65,80))
        msg = f'training elapsed time was {str(hours)} hours, {minutes:4.1f} minutes, {seconds:4.2f} seconds)'
        print_in_color(msg, (0,255,0), (55,65,80))

    def on_train_batch_end(self, batch, logs=None):
        acc = logs.get('accuracy')* 100  # get training accuracy
        loss = logs.get('loss')
        msg = '{0:20s}processing batch {1:4s} of {2:5s} accuracy= {3:8.3f}  loss: {4:8.5f}'.format(' ', str(batch), str(self.batches), acc, loss)
        print(msg, '\r', end='') # prints over on the same line to show running batch count

    def on_epoch_begin(self,epoch, logs = None):
        self.now = time.time()

    def on_epoch_end(self, epoch, logs = None):  # method runs on the end of each epoch
        later = time.time()
        duration = later-self.now
        lr=float(tf.keras.backend.get_value(self.model.optimizer.lr)) # get the current learning rate
        current_lr = lr
        v_loss = logs.get('val_loss')  # get the validation loss for this epoch
        acc = logs.get('accuracy')  # get training accuracy
        v_acc = logs.get('val_accuracy')
        loss = logs.get('loss')
        # if training accuracy is below threshold adjust lr based on training accuracy
        if acc < self.threshold:
            monitor = 'accuracy'
            if acc > self.highest_tracc: # training accuracy improved in the epoch
                self.highest_tracc = acc # set new highest training accuracy
                self.best_weights = self.model.get_weights() # traing accuracy improved so save the weights
                self.count = 0 # set count to 0 since training accuracy improved
                self.stop_count = 0 # set stop counter to 0
                if v_loss < self.lowest_vloss:
                    self.lowest_vloss = v_loss
                color = (0,255,0)
                self.best_epoch=epoch + 1  # set the value of best epoch for this epoch
            else:
                # training accuracy did not improve check if this has happened for patience number of epochs
                # if so adjust learning rate
                if self.count >= self.patience -1: # lr should be adjusted
                    color = (245, 170, 66)
                    lr = lr * self.factor # adjust the learning by factor
                    tf.keras.backend.set_value(self.model.optimizer.lr, lr) # set the learning rate in the optimizer
                    self.count = 0 # reset the count to 0
                    self.stop_count = self.stop_count + 1 # count the number of consecutive lr adjustments
                    self.count = 0 # reset counter
                    if self.dwell:
                        self.model.set_weights(self.best_weights) # return to better point in N space
                    else:
                        if v_loss < self.lowest_vloss:
                            self.lowest_vloss = v_loss
                else:
                    self.count=self.count +1 # increment patience counter
        else: # training accuracy is above threshold so adjust learning rate based on validation loss
            monitor = 'val_loss'
            if v_loss < self.lowest_vloss: # check if the validation loss improved
                self.lowest_vloss = v_loss # replace lowest validation loss with new validation loss
                self.best_weights = self.model.get_weights() # validation loss improved so save the weights
                self.count = 0 # reset count since validation loss improved
                self.stop_count = 0
                color=(0,255,0)
                self.best_epoch = epoch + 1 # set the value of the best epoch to this epoch
            else: # validation loss did not improve
                if self.count >= self.patience-1: # need to adjust lr
                    color = (245, 170, 66)
                    lr = lr * self.factor # adjust the learning rate
                    self.stop_count = self.stop_count + 1 # increment stop counter because lr was adjusted
                    self.count = 0 # reset counter
                    tf.keras.backend.set_value(self.model.optimizer.lr, lr) # set the learning rate in the optimizer
                    if self.dwell:
                        self.model.set_weights(self.best_weights) # return to better point in N space
                else:
                    self.count = self.count + 1 # increment the patience counter
                if acc > self.highest_tracc:
                    self.highest_tracc = acc
        msg=f'{str(epoch+1):^3s}/{str(self.epochs):4s} {loss:^9.3f}{acc*100:^9.3f}{v_loss:^9.5f}{v_acc*100:^9.3f}{current_lr:^9.5f}{lr:^9.5f}{monitor:^11s}{duration:^8.2f}'
        print_in_color (msg,color, (55,65,80))

        with open('epoch statistics.txt', 'a') as epoch_stats:
            epoch_stats.write(msg + '\n')

        if self.stop_count > self.stop_patience - 1: # check if learning rate has been adjusted stop_count times with no improvement
            msg = f' training has been halted at epoch {epoch + 1} after {self.stop_patience} adjustments of learning rate with no improvement'
            print_in_color(msg, (0,255,255), (55,65,80))
            self.model.stop_training = True # stop training
        else:
            if self.ask_epoch != None:
                if epoch + 1 >= self.ask_epoch:
                    msg ='enter H to halt ,F to fine tune model, or an integer for number of epochs to run then ask again'
                    print_in_color(msg, (0,255,255), (55,65,80))
                    ans=input('')
                    if ans =='H' or ans=='h':
                        msg =f'training has been halted at epoch {epoch + 1} due to user input'
                        print_in_color(msg, (0,255,255), (55,65,80))
                        self.model.stop_training = True # stop training
                    elif ans == 'F' or ans=='f':
                        msg ='setting base_model as trainable for fine tuning of model'
                        self.base_model.trainable = True
                        print_in_color(msg, (0, 255,255), (55,65,80))
                        msg='{0:^8s}{1:^10s}{2:^9s}{3:^9s}{4:^9s}{5:^9s}{6:^9s}{7:^10s}{8:^8s}'.format('Epoch', 'Loss', 'Accuracy',
                                                                                              'V_loss','V_acc', 'LR', 'Next LR', 'Monitor', 'Duration')
                        print_in_color(msg, (244,252,3), (55,65,80))
                        self.count = 0
                        self.stop_count = 0
                        self.ask_epoch = epoch + 1 + self.ask_epoch_initial

                    else:
                        ans=int(ans)
                        self.ask_epoch += ans
                        msg = f' training will continue until epoch ' + str(self.ask_epoch)
                        print_in_color(msg, (0, 255,255), (55,65,80))
                        msg = '{0:^8s}{1:^10s}{2:^9s}{3:^9s}{4:^9s}{5:^9s}{6:^9s}{7:^10s}{8:^8s}'.format('Epoch', 'Loss', 'Accuracy',
                                                                                              'V_loss','V_acc', 'LR', 'Next LR', 'Monitor', 'Duration')
                        print_in_color(msg, (244,252,3), (55,65,80))