【tensorflow2.0】特征列feature_column

摘要:
要创建要素列,请调用列模块的tf feature_ Function。该模块中常用的九个功能如下图所示。所有九个函数都将返回CategoryColumn或DenseColumn对象,但不会返回从这两个类继承的bucketized_Column。numeric_列是最常用的数字列。categorical_column_with_标识分类标识列,一个pot代码,相当于bucket列,其中每个bucket都是整数。categorical_ column_with_ vocabulary_List是一个带有一个pot代码的分类词汇列。字典由列表指定。categorical_column_with_hash_Bucket哈希列,当整数或字典较大时使用。indicator_列指示符列,由CategoricalColumn生成,一锅代码嵌入_列嵌入在列中,由CategorialColumn生成。需要学习嵌入的向量分布参数。crossed_Column交叉列,可按category_Column_with_hash_存储桶的任何类别列划分。

特征列 通常用于对结构化数据实施特征工程时候使用,图像或者文本数据一般不会用到特征列。

一,特征列用法概述

使用特征列可以将类别特征转换为one-hot编码特征,将连续特征构建分桶特征,以及对多个特征生成交叉特征等等。

要创建特征列,请调用 tf.feature_column 模块的函数。该模块中常用的九个函数如下图所示,所有九个函数都会返回一个 Categorical-Column 或一个 Dense-Column 对象,但却不会返回 bucketized_column,后者继承自这两个类。

注意:所有的Catogorical Column类型最终都要通过indicator_column转换成Dense Column类型才能传入模型!

【tensorflow2.0】特征列feature_column第1张

  • numeric_column 数值列,最常用。
  • bucketized_column 分桶列,由数值列生成,可以由一个数值列出多个特征,one-hot编码。
  • categorical_column_with_identity 分类标识列,one-hot编码,相当于分桶列每个桶为1个整数的情况。
  • categorical_column_with_vocabulary_list 分类词汇列,one-hot编码,由list指定词典。
  • categorical_column_with_vocabulary_file 分类词汇列,由文件file指定词典。
  • categorical_column_with_hash_bucket 哈希列,整数或词典较大时采用。
  • indicator_column 指标列,由Categorical Column生成,one-hot编码
  • embedding_column 嵌入列,由Categorical Column生成,嵌入矢量分布参数需要学习。嵌入矢量维数建议取类别数量的 4 次方根。
  • crossed_column 交叉列,可以由除categorical_column_with_hash_bucket的任意分类列构成。

二,特征列使用范例

以下是一个使用特征列解决Titanic生存问题的完整范例。

import datetime
import numpy as np
import pandas as pd
from matplotlib import pyplot as plt
import tensorflow as tf
from tensorflow.keras import layers,models
 
 
# 打印日志
def printlog(info):
    nowtime = datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    print("
"+"=========="*8 + "%s"%nowtime)
    print(info+'...

')
 
 
 
# ================================================================================
# 一,构建数据管道
# ================================================================================
printlog("step1: prepare dataset...")
 
 
dftrain_raw = pd.read_csv("./data/titanic/train.csv")
dftest_raw = pd.read_csv("./data/titanic/test.csv")
 
dfraw = pd.concat([dftrain_raw,dftest_raw])
 
def prepare_dfdata(dfraw):
    dfdata = dfraw.copy()
    dfdata.columns = [x.lower() for x in dfdata.columns]
    dfdata = dfdata.rename(columns={'survived':'label'})
    dfdata = dfdata.drop(['passengerid','name'],axis = 1)
    for col,dtype in dict(dfdata.dtypes).items():
        # 判断是否包含缺失值
        if dfdata[col].hasnans:
            # 添加标识是否缺失列
            dfdata[col + '_nan'] = pd.isna(dfdata[col]).astype('int32')
            # 填充
            if dtype not in [np.object,np.str,np.unicode]:
                dfdata[col].fillna(dfdata[col].mean(),inplace = True)
            else:
                dfdata[col].fillna('',inplace = True)
    return(dfdata)
 
dfdata = prepare_dfdata(dfraw)
dftrain = dfdata.iloc[0:len(dftrain_raw),:]
dftest = dfdata.iloc[len(dftrain_raw):,:]
 
 
 
# 从 dataframe 导入数据 
def df_to_dataset(df, shuffle=True, batch_size=32):
    dfdata = df.copy()
    if 'label' not in dfdata.columns:
        ds = tf.data.Dataset.from_tensor_slices(dfdata.to_dict(orient = 'list'))
    else: 
        labels = dfdata.pop('label')
        ds = tf.data.Dataset.from_tensor_slices((dfdata.to_dict(orient = 'list'), labels))  
    if shuffle:
        ds = ds.shuffle(buffer_size=len(dfdata))
    ds = ds.batch(batch_size)
    return ds
 
ds_train = df_to_dataset(dftrain)
ds_test = df_to_dataset(dftest)
# ================================================================================
# 二,定义特征列
# ================================================================================
printlog("step2: make feature columns...")
 
feature_columns = []
 
# 数值列
for col in ['age','fare','parch','sibsp'] + [
    c for c in dfdata.columns if c.endswith('_nan')]:
    feature_columns.append(tf.feature_column.numeric_column(col))
 
# 分桶列
age = tf.feature_column.numeric_column('age')
age_buckets = tf.feature_column.bucketized_column(age, 
             boundaries=[18, 25, 30, 35, 40, 45, 50, 55, 60, 65])
feature_columns.append(age_buckets)
 
# 类别列
# 注意:所有的Catogorical Column类型最终都要通过indicator_column转换成Dense Column类型才能传入模型!!
sex = tf.feature_column.indicator_column(
      tf.feature_column.categorical_column_with_vocabulary_list(
      key='sex',vocabulary_list=["male", "female"]))
feature_columns.append(sex)
 
pclass = tf.feature_column.indicator_column(
      tf.feature_column.categorical_column_with_vocabulary_list(
      key='pclass',vocabulary_list=[1,2,3]))
feature_columns.append(pclass)
 
ticket = tf.feature_column.indicator_column(
     tf.feature_column.categorical_column_with_hash_bucket('ticket',3))
feature_columns.append(ticket)
 
embarked = tf.feature_column.indicator_column(
      tf.feature_column.categorical_column_with_vocabulary_list(
      key='embarked',vocabulary_list=['S','C','B']))
feature_columns.append(embarked)
 
# 嵌入列
cabin = tf.feature_column.embedding_column(
    tf.feature_column.categorical_column_with_hash_bucket('cabin',32),2)
feature_columns.append(cabin)
 
# 交叉列
pclass_cate = tf.feature_column.categorical_column_with_vocabulary_list(
          key='pclass',vocabulary_list=[1,2,3])
 
crossed_feature = tf.feature_column.indicator_column(
    tf.feature_column.crossed_column([age_buckets, pclass_cate],hash_bucket_size=15))
 
feature_columns.append(crossed_feature)
 
# ================================================================================
# 三,定义模型
# ================================================================================
printlog("step3: define model...")
 
tf.keras.backend.clear_session()
model = tf.keras.Sequential([
  layers.DenseFeatures(feature_columns), #将特征列放入到tf.keras.layers.DenseFeatures中!!!
  layers.Dense(64, activation='relu'),
  layers.Dense(64, activation='relu'),
  layers.Dense(1, activation='sigmoid')
])
 
# ================================================================================
# 四,训练模型
# ================================================================================
printlog("step4: train model...")
 
model.compile(optimizer='adam',
              loss='binary_crossentropy',
              metrics=['accuracy'])
 
history = model.fit(ds_train,
          validation_data=ds_test,
          epochs=10)
# ================================================================================
# 五,评估模型
# ================================================================================
printlog("step5: eval model...")
 
model.summary()
 
 
%matplotlib inline
%config InlineBackend.figure_format = 'svg'
 
import matplotlib.pyplot as plt
 
def plot_metric(history, metric):
    train_metrics = history.history[metric]
    val_metrics = history.history['val_'+metric]
    epochs = range(1, len(train_metrics) + 1)
    plt.plot(epochs, train_metrics, 'bo--')
    plt.plot(epochs, val_metrics, 'ro-')
    plt.title('Training and validation '+ metric)
    plt.xlabel("Epochs")
    plt.ylabel(metric)
    plt.legend(["train_"+metric, 'val_'+metric])
    plt.show()
 
plot_metric(history,"accuracy")
================================================================================2020-04-13 02:29:07
step1: prepare dataset......



================================================================================2020-04-13 02:29:08
step2: make feature columns......



================================================================================2020-04-13 02:29:08
step3: define model......



================================================================================2020-04-13 02:29:08
step4: train model......


Epoch 1/10
23/23 [==============================] - 0s 21ms/step - loss: 0.7117 - accuracy: 0.6615 - val_loss: 0.5706 - val_accuracy: 0.7039
Epoch 2/10
23/23 [==============================] - 0s 3ms/step - loss: 0.5920 - accuracy: 0.7022 - val_loss: 0.6129 - val_accuracy: 0.6648
Epoch 3/10
23/23 [==============================] - 0s 3ms/step - loss: 0.6388 - accuracy: 0.7079 - val_loss: 0.5196 - val_accuracy: 0.7374
Epoch 4/10
23/23 [==============================] - 0s 3ms/step - loss: 0.5950 - accuracy: 0.7219 - val_loss: 0.5028 - val_accuracy: 0.7318
Epoch 5/10
23/23 [==============================] - 0s 3ms/step - loss: 0.5166 - accuracy: 0.7486 - val_loss: 0.4975 - val_accuracy: 0.7318
Epoch 6/10
23/23 [==============================] - 0s 3ms/step - loss: 0.5260 - accuracy: 0.7612 - val_loss: 0.5045 - val_accuracy: 0.7821
Epoch 7/10
23/23 [==============================] - 0s 3ms/step - loss: 0.4957 - accuracy: 0.7697 - val_loss: 0.4756 - val_accuracy: 0.7709
Epoch 8/10
23/23 [==============================] - 0s 3ms/step - loss: 0.4848 - accuracy: 0.7837 - val_loss: 0.4532 - val_accuracy: 0.8045
Epoch 9/10
23/23 [==============================] - 0s 3ms/step - loss: 0.4636 - accuracy: 0.8006 - val_loss: 0.4561 - val_accuracy: 0.7989
Epoch 10/10
23/23 [==============================] - 0s 3ms/step - loss: 0.4784 - accuracy: 0.7907 - val_loss: 0.4722 - val_accuracy: 0.7821

================================================================================2020-04-13 02:29:11
step5: eval model......


Model: "sequential"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_features (DenseFeature multiple                  64        
_________________________________________________________________
dense (Dense)                multiple                  3008      
_________________________________________________________________
dense_1 (Dense)              multiple                  4160      
_________________________________________________________________
dense_2 (Dense)              multiple                  65        
=================================================================
Total params: 7,297
Trainable params: 7,297
Non-trainable params: 0
_________________________________________________________________

【tensorflow2.0】特征列feature_column第2张

参考:

开源电子书地址:https://lyhue1991.github.io/eat_tensorflow2_in_30_days/

GitHub 项目地址:https://github.com/lyhue1991/eat_tensorflow2_in_30_days

免责声明:文章转载自《【tensorflow2.0】特征列feature_column》仅用于学习参考。如对内容有疑问,请及时联系本站处理。

上篇软件架构自学笔记----分享“去哪儿 Hadoop 集群 Federation 数据拷贝优化”使用deploy命令发布jar到私服仓库nexus下篇

宿迁高防,2C2G15M,22元/月;香港BGP,2C5G5M,25元/月 雨云优惠码:MjYwNzM=

随便看看

安装samba服务器实现Linux mint和Windows共享文件

安装samba服务器以实现Linuxmint和Windows共享文件。在Linuxmint普通用户下执行命令:sudoapt-geinstallsamba、installsamba和打开smb。conf配置文件,并执行命令gedit/etc/samba/smb-Coff,如果您想安装gedit(sudoapt-geinstallgedit),还可以使用Lin...

Google Drive 里的文件下载的方法

Google Drive不提供创建直接下载链接的选项,但您可以通过更改链接形式在本地保存共享内容。例如,通过Google Drive共享的文件链接是:https://drive.google.com/file/d/FILE_ID/edit?usp=sharing如果您将其更改为以下修改版本,然后通过浏览器打开,则将直接下载该文件:https://drive....

H3C交换机如何配置管理VLAN

1.输入“系统视图”(缩写为“sys”)进入系统配置模式[H3C]...

mac 安装git

gitconfig--globaluser.name"your_name"gitconfig--globaluser.email"your_email@gmail.com"配置信息可以更改,以后想要更改使用上面指令就可以。同时可以使用gitconfig--list指令查看Git的配置信息。gitconfigcore.ignorecasefalse生成密钥Gi...

等保2.0 二级安全要求

1.6.2管理体系本要求包括:a)针对安全管理活动的主要管理内容建立安全管理体系;b) 应为管理人员或操作员进行的日常管理操作制定操作程序。...