深度学习原理与TensorFlow实践3：数据读取

一、各种类型的数据形式及其对应使用的库

csv、pkl（cPickle、Pickle）、json、xsl、html、xml —— pandas

npy、npz（多个npy的压缩）——numpy

hdf —— 跨平台高校读写

二、TFRecord数据处理

1. 转化为tfrecords格式

# csv->tfrecords
def transform_to_tfrecord():
    data = pd.read_csv('data/train.csv')
    tfrecord_file = 'train.tfrecords'
    
    def int_feature(value):
        return tf.train_Feature(int64_list = tf.train.Int64List(value = [value]))
    
    def float_feature(value):
        return tf.train_Feature(float_list = tf.train.FloatList(value = [value]))
    
    writer = tf.python_io.TFRecordWriter(tfrecord_file)
    for i in range(len(data)):
        feature = tf.trian.Features(feature = {
            'Age':float_feature(data['Age'][i])
            ...
        })
    example = tf.train.Example(feature = features)
    writer.write(example.Seria