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])
在发送到DNN之前,需要包装分类列:
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
相关问题 更多 >
编程相关推荐