Tensorflow 中的分类和连续交叉特征列

Question

在使用 Tensorflow 的估计器和feature_column可以交叉分类列和分桶连续列交叉列，但不能交叉分类和数字交叉。是否可以从 https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/feature_column/feature_column.py#L704 实现此功能？

在 Tensforflow 图中看到任何实现相同结果的替代方法也会很棒。

import numpy as np
cont = np.array([1,2,3])
cat = np.array(['cat', 'dog', 'cat'])
cross_function(cat, cont) = np.array([[1,0],[0,2],[3,0]])

Answer 1

在这里回答我自己的问题。涉及的步骤包括：

1. 对分类特征进行数字编码
   • 在图表内，因此可以在训练和服务中
2. 一个热编码数值结果
3. 将其乘以连续变量

法典：

import numpy as np
import tensorflow as tf
cont = np.array([1,2,3])
cat = np.array(['cat', 'dog', 'cat'])
categories = np.unique(cat)
def categorical_continuous_interaction(categorical_onehot, continuous):
cont = tf.expand_dims(continuous, 0)
return tf.transpose(tf.multiply(tf.transpose(categorical_onehot), cont))
def transformation_function(feature_dictionary, mapping_table):
continuous_feature = feature_dictionary['cont']
categorical_feature = mapping_table.lookup(feature_dictionary['cat'])
onehot = tf.one_hot(categorical_feature, categories.shape[0])
cross_feature = categorical_continuous_interaction(onehot, continuous_feature)
return {'feature_name': cross_feature}
def input_function(dataframe, label_key, ...):
# categorical mapping tables, these must be generated outside of the dataset 
# transformation function but within the input function
mapping_table = tf.contrib.lookup.index_table_from_tensor(
mapping=tf.constant(categories),
num_oov_buckets=0, 
default_value=-1
)
# Generate the dataset of a dictionary of all of the dataframes columns
dataset = tf.data.Dataset.from_tensor_slices(dict(dataframe))
# Convert to a dataset of tuples of dicts with the labels as one tuple
dataset = dataset.map(lambda x: split_label(x, label_key))
# Transform the features dict within the dataset
dataset = dataset.map(lambda features, labels: (transformation_function(
features, mapping_table=mapping_table), labels))
...
return dataset
def serving_input_fn():
# categorical mapping tables, these must be generated outside of the dataset 
# transformation function but within the input function
mapping_table=tf.contrib.lookup.index_table_from_tensor(
mapping=tf.constant(categories),
num_oov_buckets=0, 
default_value=-1
)
numeric_receiver_tensors = {
name: tf.placeholder(dtype=tf.float32, shape=[1], name=name+"_placeholder")
for name in numeric_feature_column_names
}
categorical_receiver_tensors = {
name: tf.placeholder(dtype=tf.string, shape=[1], name=name+"_placeholder")
for name in categorical_feature_column_names
}
receiver_tensors = {**numeric_receiver_tensors, **categorical_receiver_tensors}
features = transformation_function(receiver_tensors, 
country_mapping_table=country_mapping_table)
return tf.estimator.export.ServingInputReceiver(features, receiver_tensors)