代码如下:
def read_data(file_queue):
'''
the function is to get features and label (即样本特征和样本的标签)
数据来源是csv的文件,采用tensorflow 自带的对csv文件的处理方式
:param file_queue:
:return: features,label
'''
# 读取的时候需要跳过第一行
reader = tf.TextLineReader(skip_header_lines=1)
key, value = reader.read(file_queue)
# 对于数据源中空的值设置默认值
record_defaults = [[''], [''], [''], [''], [0.], [0.], [0.], [0.], [''],[0], [''], [0.], [''], [''], [0]]
# 定义decoder,每次读取的执行都从文件中读取一行。然后,decode_csv 操作将结果解析为张量列表
province, city, address, postCode, longitude,latitude, price, buildingTypeId, buildingTypeName, tradeTypeId, tradeTypeName, expectedDealPrice, listingDate, delislingDate, daysOnMarket = tf.decode_csv(value, record_defaults)
#对非数值数据进行编码:buildingTypeName
preprocess_buildingTypeName_op = tf.case({
tf.equal(buildingTypeName, tf.constant('Residential')): lambda: tf.constant(0.00),
tf.equal(buildingTypeName, tf.constant('Condo')): lambda: tf.constant(1.00),
tf.equal(buildingTypeName, tf.constant('Mobile Home')): lambda: tf.constant(2.00),
tf.equal(buildingTypeName, tf.constant('No Building')): lambda: tf.constant(3.00),
tf.equal(buildingTypeName, tf.constant('Row / Townhouse')): lambda: tf.constant(4.00),
tf.equal(buildingTypeName, tf.constant('Duplex')): lambda: tf.constant(5.00),
tf.equal(buildingTypeName, tf.constant('Manufactured Home')): lambda: tf.constant(6.00),
tf.equal(buildingTypeName, tf.constant('Commercial')): lambda: tf.constant(7.00),
tf.equal(buildingTypeName, tf.constant('Other')): lambda: tf.constant(8.00),
}, lambda: tf.constant(-1.00), exclusive=True)
# 对tradeTypeName 进行编码 Sale,Lease
preprocess_tradeTypeName_op = tf.case({
tf.equal(tradeTypeName, tf.constant('Sale')): lambda: tf.constant(0.00),
tf.equal(tradeTypeName, tf.constant('Lease')): lambda: tf.constant(1.00),
}, lambda: tf.constant(-1.00), exclusive=True)
features = tf.stack([latitude,longitude,price, preprocess_buildingTypeName_op, preprocess_tradeTypeName_op,expectedDealPrice])
return features, daysOnMarket
也就是通过:tf.case ,tf.equal和lambda 函数来实现