Skip to content
Projects
Groups
Snippets
Help
Loading...
Sign in
Toggle navigation
F
ffm-baseline
Project
Project
Details
Activity
Cycle Analytics
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Issues
0
Issues
0
List
Board
Labels
Milestones
Merge Requests
0
Merge Requests
0
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Charts
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Open sidebar
ML
ffm-baseline
Commits
1342e3ec
Commit
1342e3ec
authored
Jan 22, 2019
by
张彦钊
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
修改ctr_task_wgt参数
parent
044dc1f4
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
6 additions
and
9 deletions
+6
-9
EsmmData.scala
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
+2
-4
pipe.sh
tensnsorflow/pipe.sh
+3
-3
train.py
tensnsorflow/train.py
+1
-2
No files found.
eda/feededa/src/main/scala/com/gmei/EsmmData.scala
View file @
1342e3ec
...
@@ -332,10 +332,8 @@ object EsmmPredData {
...
@@ -332,10 +332,8 @@ object EsmmPredData {
val
native_data1
=
sc
.
sql
(
val
native_data1
=
sc
.
sql
(
s
"""
s
"""
|select device_id,city_id as ucity_id,
|select device_id,city_id as ucity_id,explode(split(native_queue,',')) as cid_id from native_data
|explode(native_queue) as cid_id
"""
.
stripMargin
|from native_data
"""
.
stripMargin
).
withColumn
(
"label"
,
lit
(
0
))
).
withColumn
(
"label"
,
lit
(
0
))
native_data1
.
createOrReplaceTempView
(
"native_data1"
)
native_data1
.
createOrReplaceTempView
(
"native_data1"
)
println
(
"native_explode_count"
,
native_data1
.
count
())
println
(
"native_explode_count"
,
native_data1
.
count
())
...
...
tensnsorflow/pipe.sh
View file @
1342e3ec
...
@@ -32,15 +32,15 @@ rm ${DATA_PATH}/nearby/nearby_*
...
@@ -32,15 +32,15 @@ rm ${DATA_PATH}/nearby/nearby_*
echo
"train..."
echo
"train..."
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
999
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
--task_type
=
train
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
3
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
--task_type
=
train
echo
"infer native..."
echo
"infer native..."
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
999
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
/native
--task_type
=
infer
>
${
DATA_PATH
}
/infer.log
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
3
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
/native
--task_type
=
infer
>
${
DATA_PATH
}
/infer.log
echo
"infer nearby..."
echo
"infer nearby..."
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
999
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
/nearby
--task_type
=
infer
>
${
DATA_PATH
}
/infer.log
${
PYTHON_PATH
}
${
MODEL_PATH
}
/train.py
--ctr_task_wgt
=
0.
3
--learning_rate
=
0.0001
--deep_layers
=
256,128
--dropout
=
0.8,0.5
--optimizer
=
Adam
--num_epochs
=
1
--embedding_size
=
16
--batch_size
=
1024
--field_size
=
12
--feature_size
=
260100
--l2_reg
=
0.005
--log_steps
=
100
--num_threads
=
36
--model_dir
=
${
DATA_PATH
}
/model_ckpt/DeepCvrMTL/
--data_dir
=
${
DATA_PATH
}
/nearby
--task_type
=
infer
>
${
DATA_PATH
}
/infer.log
echo
"sort and 2sql"
echo
"sort and 2sql"
${
PYTHON_PATH
}
${
MODEL_PATH
}
/sort_to_sql.py
${
PYTHON_PATH
}
${
MODEL_PATH
}
/sort_to_sql.py
...
...
tensnsorflow/train.py
View file @
1342e3ec
...
@@ -180,8 +180,7 @@ def model_fn(features, labels, mode, params):
...
@@ -180,8 +180,7 @@ def model_fn(features, labels, mode, params):
ctr_loss
=
tf
.
reduce_mean
(
tf
.
nn
.
sigmoid_cross_entropy_with_logits
(
logits
=
y_ctr
,
labels
=
y
))
ctr_loss
=
tf
.
reduce_mean
(
tf
.
nn
.
sigmoid_cross_entropy_with_logits
(
logits
=
y_ctr
,
labels
=
y
))
#cvr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctcvr, labels=z))
#cvr_loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(logits=y_ctcvr, labels=z))
cvr_loss
=
tf
.
reduce_mean
(
tf
.
losses
.
log_loss
(
predictions
=
pctcvr
,
labels
=
z
))
cvr_loss
=
tf
.
reduce_mean
(
tf
.
losses
.
log_loss
(
predictions
=
pctcvr
,
labels
=
z
))
# loss = ctr_task_wgt * ctr_loss + (1 -ctr_task_wgt) * cvr_loss + l2_reg * tf.nn.l2_loss(Feat_Emb)
loss
=
ctr_task_wgt
*
ctr_loss
+
(
1
-
ctr_task_wgt
)
*
cvr_loss
+
l2_reg
*
tf
.
nn
.
l2_loss
(
Feat_Emb
)
loss
=
ctr_loss
tf
.
summary
.
scalar
(
'ctr_loss'
,
ctr_loss
)
tf
.
summary
.
scalar
(
'ctr_loss'
,
ctr_loss
)
tf
.
summary
.
scalar
(
'cvr_loss'
,
cvr_loss
)
tf
.
summary
.
scalar
(
'cvr_loss'
,
cvr_loss
)
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment