import os
import numpy as np
import pandas as pd
import cv2
import matplotlib.pyplot as plt
import seaborn as sns
# imgaug 圖片數(shù)據(jù)增強(qiáng)
import imgaug.augmenters as iaa
import tensorflow as tf
# Conv2D MaxPooling2D Dropout Flatten Dense BN  GAP
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Layer, BatchNormalization, GlobalAveragePooling2D 
from tensorflow.keras.optimizers import Adam
from tensorflow.keras import Model, Input 
from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau
# 圖片處理器
from tensorflow.keras.preprocessing.image import ImageDataGenerator
import plotly.express as px
import plotly.graph_objects as go
import plotly.offline as pyo
pyo.init_notebook_mode()

# 數(shù)據(jù)路徑
DIR = '../input/captcha-version-2-images/samples/samples'
# 存儲(chǔ)驗(yàn)證碼的標(biāo)簽
captcha_list = []
characters = {}
for captcha in os.listdir(DIR):
    captcha_list.append(captcha)
    # 每張驗(yàn)證碼的captcha_code
    captcha_code = captcha.split(".")[0]
    for i in captcha_code:
        # 遍歷captcha_code 
        characters[i] = characters.get(i, 0) +1
symbols = list(characters.keys())
len_symbols = len(symbols)
print(f'圖像中只使用了{(lán)len_symbols}符號(hào)')

plt.bar(*zip(*characters.items()))
plt.title('Frequency of symbols')
plt.show()

# 如何提取圖像 建立 model  X 的shape  1070 * 50 * 200 * 1 
# y的shape 5 * 1070 * 19
 
for i, captcha in enumerate(captcha_list):
    captcha_code = captcha.split('.')[0]
    # cv2.IMREAD_GRAYSCALE 灰度圖
    captcha_cv2 = cv2.imread(os.path.join(DIR, captcha),cv2.IMREAD_GRAYSCALE)
    # 縮放
    captcha_cv2 = captcha_cv2 / 255.0
    # print(captcha_cv2.shape) (50, 200) 
    # 將captcha_cv2的(50, 200) 切換成(50, 200, 1)
    captcha_cv2 = np.reshape(captcha_cv2, img_shape)
    # (5,19)
    targs = np.zeros((len_captcha, len_symbols))
    
    for a, b in enumerate(captcha_code):
        targs[a, symbols.index(b)] = 1
    X[i] = captcha_cv2
    y[:, i] = targs

print("shape of X:", X.shape)
print("shape of y:", y.shape)

# 生成隨機(jī)數(shù)
from numpy.random import default_rng

rng = default_rng(seed=1)
test_numbers = rng.choice(1070, size=int(1070*0.3), replace=False)
X_test = X[test_numbers]
X_full = np.delete(X, test_numbers,0)
y_test = y[:,test_numbers]
y_full = np.delete(y, test_numbers,1)

val_numbers = rng.choice(int(1070*0.7), size=int(1070*0.3), replace=False)

X_val = X_full[val_numbers]
X_train = np.delete(X_full, val_numbers,0)
y_val = y_full[:,val_numbers]
y_train = np.delete(y_full, val_numbers,1)

# Sequential(C, R)	 尺寸增加了5倍，
# 選取一系列子增強(qiáng)器C作用于每張圖片的位置,第二個(gè)參數(shù)表示是否對(duì)每個(gè)batch的圖片應(yīng)用不同順序的Augmenter list     # rotate=(-8, 8)  旋轉(zhuǎn)
# iaa.CropAndPad  截取(crop)或者填充(pad),填充時(shí),被填充區(qū)域?yàn)楹谏?
# px: 想要crop(negative values)的或者pad(positive values)的像素點(diǎn)。
# (top, right, bottom, left)
# 當(dāng)pad_mode=constant的時(shí)候選擇填充的值
aug =iaa.Sequential([iaa.CropAndPad(
    px=((0, 10), (0, 35), (0, 10), (0, 35)),
    pad_mode=['edge'],
    pad_cval=1
),iaa.Rotate(rotate=(-8,8))])

X_aug_train = None
y_aug_train = y_train
for i in range(40):
    X_aug = aug(images = X_train)
    if X_aug_train is not None:
        X_aug_train = np.concatenate([X_aug_train, X_aug], axis = 0)
        y_aug_train = np.concatenate([y_aug_train, y_train], axis = 1)
    else:
        X_aug_train = X_aug

fig, ax = plt.subplots(nrows=2, ncols =5, figsize = (16,16))
for i in range(10):
    index = np.random.randint(X_aug_train.shape[0])
    ax[i//5][i%5].imshow(X_aug_train[index],cmap='gray')

#函數(shù)式API模型創(chuàng)建
captcha = Input(shape=(50,200,channels))
x = Conv2D(32, (5,5),padding='valid',activation='relu')(captcha)
x = MaxPooling2D((2,2),padding='same')(x)
x = Conv2D(64, (3,3),padding='same',activation='relu')(x)
x = MaxPooling2D((2,2),padding='same')(x)
x = Conv2D(128, (3,3),padding='same',activation='relu')(x)
maxpool = MaxPooling2D((2,2),padding='same')(x)
outputs = []
for i in range(5):
    x = Conv2D(256, (3,3),padding='same',activation='relu')(maxpool)
    x = MaxPooling2D((2,2),padding='same')(x)
    x = Flatten()(x)
    x = Dropout(0.5)(x)
    x = BatchNormalization()(x)
    x = Dense(64, activation='relu')(x)
    x = Dropout(0.5)(x)
    x = BatchNormalization()(x)
    x = Dense(len_symbols , activation='softmax' , name=f'char_{i+1}')(x)
    outputs.append(x)
    
model = Model(inputs = captcha , outputs=outputs)
# ReduceLROnPlateau更新學(xué)習(xí)率
reduce_lr = ReduceLROnPlateau(patience =3, factor = 0.5,verbose = 1)
model.compile(loss='categorical_crossentropy', optimizer=Adam(learning_rate=0.0005), metrics=["accuracy"])
# EarlyStopping用于提前停止訓(xùn)練的callbacks。具體地,可以達(dá)到當(dāng)訓(xùn)練集上的loss不在減小
earlystopping = EarlyStopping(monitor ="val_loss",  
                             mode ="min", patience = 10,
                              min_delta = 1e-4,
                             restore_best_weights = True) 

history = model.fit(X_train, [y_train[i] for i in range(5)], batch_size=32, epochs=30, verbose=1, validation_data = (X_val, [y_val[i] for i in range(5)]), callbacks =[earlystopping,reduce_lr])

score = model.evaluate(X_test,[y_test[0], y_test[1], y_test[2], y_test[3], y_test[4]],verbose=1)
metrics = ['loss','char_1_loss', 'char_2_loss', 'char_3_loss', 'char_4_loss', 'char_5_loss', 'char_1_acc', 'char_2_acc', 'char_3_acc', 'char_4_acc', 'char_5_acc']

for i,j in zip(metrics, score):
    print(f'{i}: {j}')

metrics_df = pd.DataFrame(history.history)

columns = [col for col in metrics_df.columns if 'loss' in col and len(col)>8]

fig = px.line(metrics_df, y = columns)
fig.show()

plt.figure(figsize=(15,8))
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'val'], loc='upper right',prop={'size': 10})
plt.show()

# 預(yù)測(cè)數(shù)據(jù)
def predict(captcha):
    captcha = np.reshape(captcha , (1, 50,200,channels))
    result = model.predict(captcha)
    result = np.reshape(result ,(5,len_symbols))
    # 取出最大預(yù)測(cè)中的輸出
    label = ''.join([symbols[np.argmax(i)] for i in result])
    return label
    
predict(X_test[2])
# 25277

actual_pred = []

for i in range(X_test.shape[0]):
    actual = ''.join([symbols[i] for i in (np.argmax(y_test[:, i],axis=1))])
    pred =  predict(X_test[i])
    actual_pred.append((actual, pred))
print(actal_pred[:10])

sameCount = 0
diffCount = 0
letterDiff = {i:0 for i in range(5)}
incorrectness = {i:0 for i in range(1,6)}
for real, pred in actual_pred:
    # 預(yù)測(cè)和輸出相同
    if real == pred:
        sameCount += 1
    else:
        # 失敗
        diffCount += 1
        # 遍歷
        incorrectnessPoint = 0
        for i in range(5):
            if real[i] != pred[i]:
                letterDiff[i] += 1
                incorrectnessPoint += 1
        incorrectness[incorrectnessPoint] += 1


x = ['True predicted', 'False predicted']
y = [sameCount, diffCount]

fig = go.Figure(data=[go.Bar(x = x, y = y)])
fig.show()

x1 = ["Character " + str(x) for x in range(1, 6)]
    
fig = go.Figure(data=[go.Bar(x = x1, y = list(letterDiff.values()))])
fig.show()

x2 = [str(x) + " incorrect" for x in incorrectness.keys()]
y2 = list(incorrectness.values())

fig = go.Figure(data=[go.Bar(x = x2, y = y2)])
fig.show()

fig, ax = plt.subplots(nrows = 8, ncols=4,figsize = (16,20))
count = 0
for i, (actual , pred) in enumerate(actual_pred):
    if actual != pred:
        img = X_test[i]
        try:
            ax[count//4][count%4].imshow(img, cmap = 'gray')
            ax[count//4][count%4].title.set_text(pred + ' - ' + actual)
            count += 1
        except:
            pass