具有连续列和分类列的HOWTO tf.estimator

Question

我有一个tf.estimator，它适用于连续变量，我想将其扩展为使用分类变量。

考虑如下所示的熊猫数据框：

label           |  con_col          |  cat_col
(float 0 or 1)  |  (float -1 to 1)  |  (int 0-3)
----------------+-------------------+---------------
0               |   0.123           |  2
0               |   0.456           |  1
1               |  -0.123           |  3
1               |  -0.123           |  3
0               |   0.123           |  2

[仅为标签和连续变量列（con_col）构建估算器，我构建以下feature_column变量。

feature_cols = [
                   tf.feature_column.numeric_column('con_col')
               ]

然后我像这样将其传递给DNNClassifer。

tf.estimator.DNNClassifier(feature_columns=feature_cols ...)

稍后，我将创建一个serving_input_fn（）。在此函数中，我还指定了列。这个例程很小，看起来像这样：

def serving_input_fn(): 
    feat_placeholders['con_col'] = tf.placeholder(tf.float32, [None])

    return tf.estimator.export.ServingInputReceiver(feat_placeholders.copy(), feat_placeholders)

这有效。但是，当我尝试使用分类列时，我遇到了问题。

因此使用分类列，这部分似乎正常工作。

feature_cols = [
    tf.feature_column.sequence_categorical_column_with_identity('cat_col', num_buckets=4))
               ]
tf.estimator.DNNClassifier(feature_columns=feature_cols ...)

对于serving_input_fn（），我从堆栈跟踪中获得了建议，但是两个建议都失败了。：

def serving_input_fn(): 
    # try #2
    # this fails
    feat_placeholders['cat_col'] = tf.SequenceCategoricalColumn(categorical_column=tf.IdentityCategoricalColumn(key='cat_col', number_buckets=4,default_value=None))

    # try #1
    # this also fails
    # feat_placeholders['cat_col'] = tf.feature_column.indicator_column(tf.feature_column.sequence_categorical_column_with_identity(column, num_buckets=4))

    # try #0
    # this fails. Its using the same form for the con_col
    # the resulting error gave hints for the above code.
    # Note, i'm using this url as a guide.  My cat_col is
    # is similar to that code samples 'dayofweek' except it
    # is not a string.
    # https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/machine_learning/feateng/taxifare_tft/trainer/model.py
    #feat_placeholders['cat_col'] = tf.placeholder(tf.float32, [None])


    return tf.estimator.export.ServingInputReceiver(feat_placeholders.copy(), feat_placeholders)

如果使用尝试＃0，这是错误消息。

ValueError: Items of feature_columns must be a <class 'tensorflow.python.feature_column.feature_column_v2.DenseColumn'>. You can wrap a categorical column with an embedding_column or indicator_column. Given: SequenceCategoricalColumn(categorical_column=IdentityCategoricalColumn(key='cat_col', number_buckets=4, default_value=None))

Lak的答案实现

使用Lak的答案作为指导，这对两个要素列均适用。

# This is the list of features we pass as an argument to DNNClassifier
feature_cols = []

# Add the continuous column first
feature_cols.append(tf.feature_column.numeric_column('con_col'))                  

# Add the categorical column which is wrapped?
# This creates new columns from a single column?
category_feature_cols = [tf.feature_column.categorical_column_with_identity('cat_col', num_buckets=4)]
for c in category_feature_cols:
    feat_cols.append(tf.feature_column.indicator_column(c))

# now pass this list to the DNN
tf.estimator.DNNClassifier(feature_columns=feature_cols ...)


def serving_input_fn(): 
    feat_placeholders['con_col'] = tf.placeholder(tf.float32, [None])
    feat_placeholders['cat_col'] = tf.placeholder(tf.int64, [None])

Answer 1

发送到DNN之前，您需要包装类别列：

cat_feature_cols = [ tf.feature_column.sequence_categorical_column_with_identity('cat_col', num_buckets=4)) ]
feature_cols = [tf.feature_column.indicator_column(c) for c in cat_feature_cols]

使用指示器列进行一次热编码，或使用嵌入列进行嵌入。