如何tf.估计量具有连续列和分类列

Question

我有一个tf.估计量它适用于连续变量，我想扩展它来使用分类变量。你知道吗

考虑一个如下所示的数据帧：

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

为了只为标签和连续变量列（con\u col）构建估计器，我构建了以下特征列变量。你知道吗

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

然后我像这样把它传给DNN分类员。你知道吗

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

后来我构建了一个服务输入\ u fn（）。在这个函数中，我还指定了列。此例程非常小，如下所示：

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

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

这很管用。但是，当我尝试使用分类列时，我遇到了一个问题。你知道吗

因此，使用分类列，这一部分似乎是可行的。你知道吗

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

对于服务\u input \u fn（），我从堆栈跟踪中得到建议，但两个建议都失败了：

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try#0，则这是错误消息。你知道吗

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的答案实施

以Lak的答案为指导，这两个专栏都适用。你知道吗

# 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

在发送到DNN之前，需要包装分类列：

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]

使用指示符列进行一次热编码，或使用嵌入列进行嵌入。你知道吗