import matplotlib as mpl
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
import sklearn
import pandas as pd
import os
import sys
import time
import tensorflow as tf

from tensorflow import keras

print(tf.__version__)
print(sys.version_info)
for module in mpl, np, pd, sklearn, tf, keras:
    print(module.__name__, module.__version__)

fashion_mnist = keras.datasets.fashion_mnist
(x_train_all, y_train_all), (x_test, y_test) = fashion_mnist.load_data()
x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
y_valid, y_train = y_train_all[:5000], y_train_all[5000:]

# 查看维度
print(x_valid.shape, y_valid.shape)
print(x_train.shape, y_train.shape)
print(x_test.shape, y_test.shape)
# 第二种方案，建议采用
# import gzip
# # 定义加载数据的函数，data_folder为保存gz数据的文件夹，该文件夹下有4个文件
# # 'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
# # 't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'

# def load_data(data_folder):
#     files = [
#         'train-labels-idx1-ubyte.gz', 'train-images-idx3-ubyte.gz',
#         't10k-labels-idx1-ubyte.gz', 't10k-images-idx3-ubyte.gz'
#     ]
#     paths = []
#     for fname in files:
#         paths.append(os.path.join(data_folder,fname))

#     with gzip.open(paths[0], 'rb') as lbpath:
#         y_train = np.frombuffer(lbpath.read(), np.uint8, offset=8)

#     with gzip.open(paths[1], 'rb') as imgpath:
#         x_train = np.frombuffer(
#             imgpath.read(), np.uint8, offset=16).reshape(len(y_train), 28, 28)

#     with gzip.open(paths[2], 'rb') as lbpath:
#         y_test = np.frombuffer(lbpath.read(), np.uint8, offset=8)

#     with gzip.open(paths[3], 'rb') as imgpath:
#         x_test = np.frombuffer(
#             imgpath.read(), np.uint8, offset=16).reshape(len(y_test), 28, 28)
#         return (x_train, y_train), (x_test, y_test)
# (x_train_all, y_train_all), (x_test, y_test) = load_data('../keras/fashion/')
# x_valid, x_train = x_train_all[:5000], x_train_all[5000:]
# y_valid, y_train = y_train_all[:5000], y_train_all[5000:]
# print(x_valid.shape, x_train.shape, y_valid.shape, y_train.shape)

# 看效果图
def show_single_image(img_arr):
    plt.imshow(img_arr, cmap="binary")
    plt.show()
show_single_image(x_train[0])

def show_imgs(n_rows, n_cols, x_data, y_data, class_names):
    assert len(x_data) == len(y_data)
    assert n_rows * n_cols < len(x_data)
    plt.figure(figsize = (n_cols * 1.4, n_rows * 1.6))
    for row in range(n_rows):
        for col in range(n_cols):
            index = n_cols * row + col 
            plt.subplot(n_rows, n_cols, index+1)
            plt.imshow(x_data[index], cmap="binary",
                       interpolation = 'nearest')
            plt.axis('off')
            plt.title(class_names[y_data[index]])
    plt.show()

class_names = ['T-shirt', 'Trouser', 'Pullover', 'Dress',
               'Coat', 'Sandal', 'Shirt', 'Sneaker',
               'Bag', 'Ankle boot']
show_imgs(50, 50, x_train, y_train, class_names)

print(x_train.shape)

# tf.keras.models.Sequential()

# 第一种方式
"""
model = keras.models.Sequential()
model.add(keras.layers.Flatten(input_shape=[28, 28]))
model.add(keras.layers.Dense(300, activation="relu"))
model.add(keras.layers.Dense(100, activation="relu"))
model.add(keras.layers.Dense(10, activation="softmax"))
"""
# 第二种方式
model = keras.models.Sequential([
    keras.layers.Flatten(input_shape=[28, 28]),
    keras.layers.Dense(300, activation='relu'),
    keras.layers.Dense(100, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])
model.summary()

# relu: y = max(0, x)
# softmax: 将向量变成概率分布. x = [x1, x2, x3], 
#          y = [e^x1/sum, e^x2/sum, e^x3/sum], sum = e^x1 + e^x2 + e^x3

# reason for sparse: y->index. y->one_hot->[] 
model.compile(loss="sparse_categorical_crossentropy",
              optimizer = "sgd",
              metrics = ["accuracy"])

model.layers

model.summary()

# [None, 784] * W + b -> [None, 300] W.shape [784, 300], b = [300]

history = model.fit(x_train, y_train, epochs=10,
                    validation_data=(x_valid, y_valid))
save_model_name = './modelckpt/model.h5'
if not os.path.exists('modelckpt/'):
    os.mkdir('modelckpt/')
model.save(save_model_name)

type(history)

history.history

def plot_learning_curves(history):
    pd.DataFrame(history.history).plot(figsize=(8, 5))
    plt.grid(True)
    plt.gca().set_ylim(0, 1)
    plt.show()
plot_learning_curves(history)

# model.evaluate
# 输入数据和标签,输出损失和精确度.
#     # 评估模型,不输出预测结果
#   loss,accuracy = model.evaluate(X_test,Y_test)
#     print('\ntest loss',loss)
#     print('accuracy',accuracy)
# model.predict
# 输入测试数据,输出预测结果
# (通常用在需要得到预测结果的时候)
#     模型预测,输入测试集,输出预测结果
#   y_pred = model.predict(X_test,batch_size = 1)

test_loss, test_acc = model.evaluate(x_test, y_test)
print("准确率: %.4f，共测试了%d张图片 " % (test_acc, len(x_test)))