[英]HOWTO tf.estimator with continuous and categorical columns
I have a tf.estimator which works for continuous variables and I want to expand it to use categorical variables.我有一个适用于连续变量的 tf.estimator,我想将其扩展为使用分类变量。
Consider a pandas dataframe which looks like this:考虑一个看起来像这样的 pandas dataframe:
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
To build the estimator for just the label and the continuous variable column (con_col) I build the following feature_column variable.为了构建仅用于 label 和连续变量列 (con_col) 的估计器,我构建了以下 feature_column 变量。
feature_cols = [
tf.feature_column.numeric_column('con_col')
]
Then I pass it to the DNNClassifer like so.然后我像这样将它传递给 DNNClassifer。
tf.estimator.DNNClassifier(feature_columns=feature_cols ...)
Later I build a serving_input_fn().后来我建立了一个serving_input_fn()。 In this function I also specify the columns.
在此 function 中,我还指定了列。 This routine is quite small and looks like this:
这个例程非常小,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)
This works.这行得通。 However, when I try to use the categorical column I have a problem.
但是,当我尝试使用分类列时,我遇到了问题。
So using the categorical column, this part seems to work.所以使用分类列,这部分似乎工作。
feature_cols = [
tf.feature_column.sequence_categorical_column_with_identity('cat_col', num_buckets=4))
]
tf.estimator.DNNClassifier(feature_columns=feature_cols ...)
For the serving_input_fn() I get suggestions from the stack trace but both suggestions fail.:对于 serving_input_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)
This is the error message if try #0 is used.如果使用 try #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's answer implementation Lak的答案实现
Using Lak's answer as a guide, this works for both both feature columns.以 Lak 的回答为指导,这对两个特征列都有效。
# 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])
You need to wrap categorical columns before sending to DNN:您需要在发送到 DNN 之前包装分类列:
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]
Use indicator column to one-hot encode, or embedded column to embed.使用指示列进行 one-hot 编码,或使用嵌入列进行嵌入。
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.