bug fix (#134)

shenweichen · web-flow · commit 2705f05b6753 · 2019-09-08T12:54:03.000+08:00
diff --git a/.gitignore b/.gitignore
@@ -1,6 +1,7 @@
 *.h5
 *.ipynb
 .pytest_cache/
+.vscode/
 tests/unused/*
 # Byte-compiled / optimized / DLL files
 __pycache__/
diff --git a/.travis.yml b/.travis.yml
@@ -51,6 +51,7 @@ install:
   - pip install -q codacy-coverage
   - pip install -q tensorflow==$TF_VERSION
   - pip install -q pandas
+  - pip install -q packaging
   - pip install -e .
 # command to run tests
 script:
diff --git a/LICENSE b/LICENSE
@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 2017-2019 Weichen Shen
+   Copyright 2017-present Weichen Shen
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.
diff --git a/README.md b/README.md
@@ -1,20 +1,23 @@
 # DeepCTR
 
 [![Python Versions](https://img.shields.io/pypi/pyversions/deepctr.svg)](https://pypi.org/project/deepctr)
+[![TensorFlow Versions](https://img.shields.io/badge/TensorFlow-1.4+/2.0+-blue.svg)](https://pypi.org/project/deepctr)
 [![Downloads](https://pepy.tech/badge/deepctr)](https://pepy.tech/project/deepctr)
 [![PyPI Version](https://img.shields.io/pypi/v/deepctr.svg)](https://pypi.org/project/deepctr)
 [![GitHub Issues](https://img.shields.io/github/issues/shenweichen/deepctr.svg
 )](https://github.com/shenweichen/deepctr/issues)
-[![Activity](https://img.shields.io/github/last-commit/shenweichen/deepctr.svg)](https://github.com/shenweichen/DeepCTR/commits/master)
+<!-- [![Activity](https://img.shields.io/github/last-commit/shenweichen/deepctr.svg)](https://github.com/shenweichen/DeepCTR/commits/master) -->
 
 
 [![Documentation Status](https://readthedocs.org/projects/deepctr-doc/badge/?version=latest)](https://deepctr-doc.readthedocs.io/)
 [![Build Status](https://travis-ci.org/shenweichen/DeepCTR.svg?branch=master)](https://travis-ci.org/shenweichen/DeepCTR)
 [![Coverage Status](https://coveralls.io/repos/github/shenweichen/DeepCTR/badge.svg?branch=master)](https://coveralls.io/github/shenweichen/DeepCTR?branch=master)
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/d4099734dc0e4bab91d332ead8c0bdd0)](https://www.codacy.com/app/wcshen1994/DeepCTR?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=shenweichen/DeepCTR&amp;utm_campaign=Badge_Grade)
+[![Gitter](https://badges.gitter.im/DeepCTR/community.svg)](https://gitter.im/DeepCTR/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge)
 [![License](https://img.shields.io/github/license/shenweichen/deepctr.svg)](https://github.com/shenweichen/deepctr/blob/master/LICENSE)
 
-DeepCTR is a **Easy-to-use**,**Modular** and **Extendible** package of deep-learning based CTR models along with lots of core components layers which can be used to build your own custom model easily.It is implemented by tensorflow.You can use any complex model with `model.fit()`and `model.predict()` .
+
+DeepCTR is a **Easy-to-use**,**Modular** and **Extendible** package of deep-learning based CTR models along with lots of core components layers which can be used to build your own custom model easily.It is compatible with **tensorflow 1.4+ and 2.0+**.You can use any complex model with `model.fit()`and `model.predict()` .
 
 Let's [**Get Started!**](https://deepctr-doc.readthedocs.io/en/latest/Quick-Start.html)([Chinese Introduction](https://zhuanlan.zhihu.com/p/53231955))
 
diff --git a/deepctr/__init__.py b/deepctr/__init__.py
@@ -2,5 +2,5 @@
 from . import models
 from .utils import check_version
 
-__version__ = '0.6.0'
+__version__ = '0.6.1'
 check_version(__version__)
diff --git a/deepctr/models/ccpm.py b/deepctr/models/ccpm.py
@@ -45,7 +45,7 @@ def CCPM(linear_feature_columns, dnn_feature_columns, embedding_size=8, conv_ker
     features = build_input_features(linear_feature_columns+dnn_feature_columns)
     inputs_list = list(features.values())
 
-    sparse_embedding_list, _ = input_from_feature_columns(features,linear_feature_columns,embedding_size,
+    sparse_embedding_list, _ = input_from_feature_columns(features,dnn_feature_columns,embedding_size,
                                                                                                l2_reg_embedding, init_std,
                                                                                                seed,support_dense=False)
     linear_logit = get_linear_logit(features, linear_feature_columns, l2_reg=l2_reg_linear, init_std=init_std,
diff --git a/deepctr/models/dien.py b/deepctr/models/dien.py
@@ -103,8 +103,8 @@ def interest_evolution(concat_behavior, deep_input_item, user_behavior_length, g
     if gru_type not in ["GRU", "AIGRU", "AGRU", "AUGRU"]:
         raise ValueError("gru_type error ")
     aux_loss_1 = None
-
-    rnn_outputs = DynamicGRU(embedding_size * 2, return_sequence=True,
+    embedding_size = None
+    rnn_outputs = DynamicGRU(embedding_size, return_sequence=True,
                              name="gru1")([concat_behavior, user_behavior_length])
 
     if gru_type == "AUGRU" and use_neg:
@@ -115,7 +115,7 @@ def interest_evolution(concat_behavior, deep_input_item, user_behavior_length, g
                                     tf.subtract(user_behavior_length, 1), stag="gru")  # [:, 1:]
 
     if gru_type == "GRU":
-        rnn_outputs2 = DynamicGRU(embedding_size * 2, return_sequence=True,
+        rnn_outputs2 = DynamicGRU(embedding_size, return_sequence=True,
                                   name="gru2")([rnn_outputs, user_behavior_length])
         # attention_score = AttentionSequencePoolingLayer(hidden_size=att_hidden_size, activation=att_activation, weight_normalization=att_weight_normalization, return_score=True)([
         #     deep_input_item, rnn_outputs2, user_behavior_length])
@@ -134,10 +134,10 @@ def interest_evolution(concat_behavior, deep_input_item, user_behavior_length, g
 
         if gru_type == "AIGRU":
             hist = multiply([rnn_outputs, Permute([2, 1])(scores)])
-            final_state2 = DynamicGRU(embedding_size * 2, gru_type="GRU", return_sequence=False, name='gru2')(
+            final_state2 = DynamicGRU(embedding_size, gru_type="GRU", return_sequence=False, name='gru2')(
                 [hist, user_behavior_length])
         else:  # AGRU AUGRU
-            final_state2 = DynamicGRU(embedding_size * 2, gru_type=gru_type, return_sequence=False,
+            final_state2 = DynamicGRU(embedding_size, gru_type=gru_type, return_sequence=False,
                                       name='gru2')([rnn_outputs, user_behavior_length, Permute([2, 1])(scores)])
         hist = final_state2
     return hist, aux_loss_1
diff --git a/docs/source/FAQ.md b/docs/source/FAQ.md
@@ -112,5 +112,5 @@ just install deepctr with
 $ pip install deepctr[gpu]
 ```
 
-## 7. Could not find a version that satisfies the requirement deepctr (from versions)
-please install with `pip3 install` instead of `pip install`
+## 7. How to run the demo with multiple GPUs
+you can use multiple gpus with tensorflow version higher than ``1.4``,see [run_classification_criteo_multi_gpu.py](https://github.com/shenweichen/DeepCTR/blob/master/examples/run_classification_criteo_multi_gpu.py)
diff --git a/docs/source/History.md b/docs/source/History.md
@@ -1,4 +1,5 @@
 # History
+- 09/07/2019 : [v0.6.1](https://github.com/shenweichen/DeepCTR/releases/tag/v0.6.1) released.Fix bugs in `CCPM` and `DynamicGRU`.
 - 08/02/2019 : [v0.6.0](https://github.com/shenweichen/DeepCTR/releases/tag/v0.6.0) released.Now DeepCTR is compatible with tensorflow `1.14` and `2.0.0`. 
 - 07/21/2019 : [v0.5.2](https://github.com/shenweichen/DeepCTR/releases/tag/v0.5.2) released.Refactor `Linear` Layer.
 - 07/10/2019 : [v0.5.1](https://github.com/shenweichen/DeepCTR/releases/tag/v0.5.1) released.Add [FiBiNET](./Features.html#fibinet-feature-importance-and-bilinear-feature-interaction-network).  
diff --git a/docs/source/Quick-Start.md b/docs/source/Quick-Start.md
@@ -1,7 +1,7 @@
 # Quick-Start
 
 ## Installation Guide
-Now `deepctr` is available for python `2.7 `and `3.4,  3.5, 3.6`.  
+Now `deepctr` is available for python `2.7 `and `3.5, 3.6, 3.7`.  
 `deepctr` depends on tensorflow, you can specify to install the cpu version or gpu version through `pip`.
 
 ### CPU version
@@ -57,7 +57,7 @@ Usually there are two simple way to encode the sparse categorical feature for em
         lbe = HashEncoder()
         data[feat] = lbe.transform(data[feat])
     ```
-  - Do feature hashing on the flay in training process 
+  - Do feature hashing on the fly in training process 
 
     We can do feature hasing throug setting `use_hash=True` in `SparseFeat` or `VarlenSparseFeat` in Step3.
 
diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -20,13 +20,13 @@
 # -- Project information -----------------------------------------------------
 
 project = 'DeepCTR'
-copyright = '2018-2019, Weichen Shen'
+copyright = '2017-present, Weichen Shen'
 author = 'Weichen Shen'
 
 # The short X.Y version
 version = ''
 # The full version, including alpha/beta/rc tags
-release = '0.6.0'
+release = '0.6.1'
 
 
 # -- General configuration ---------------------------------------------------
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -6,7 +6,7 @@
 Welcome to DeepCTR's documentation!
 ===================================
 
-|Downloads|_ |Stars|_ |Forks|_ |PyPi|_ |Issues|_ |Activity|_
+|Downloads|_ |Stars|_ |Forks|_ |PyPi|_ |Issues|_ |Gitter|_
 
 .. |Downloads| image:: https://pepy.tech/badge/deepctr
 .. _Downloads: https://pepy.tech/project/deepctr
@@ -23,11 +23,10 @@ Welcome to DeepCTR's documentation!
 .. |Issues| image:: https://img.shields.io/github/issues/shenweichen/deepctr.svg
 .. _Issues: https://github.com/shenweichen/deepctr/issues
 
-.. |Activity| image:: https://img.shields.io/github/last-commit/shenweichen/deepctr.svg
-.. _Activity: https://github.com/shenweichen/DeepCTR
+.. |Gitter| image:: https://badges.gitter.im/DeepCTR/community.svg
+.. _Gitter: https://gitter.im/DeepCTR/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge
 
-
-DeepCTR is a **Easy-to-use** , **Modular** and **Extendible** package of deep-learning based CTR models along with lots of core components layer  which can be used to build your own custom model easily.It is implemented by tensorflow.You can use any complex model with ``model.fit()`` and ``model.predict()``.
+DeepCTR is a **Easy-to-use** , **Modular** and **Extendible** package of deep-learning based CTR models along with lots of core components layer  which can be used to build your own custom model easily.It is compatible with **tensorflow 1.4+ and 2.0+**.You can use any complex model with ``model.fit()`` and ``model.predict()``.
 
 Let's `Get Started! <./Quick-Start.html>`_ (`Chinese Introduction <https://zhuanlan.zhihu.com/p/53231955>`_)
 
diff --git a/examples/run_all.sh b/examples/run_all.sh
@@ -23,14 +23,15 @@ function run_py(){
 
 ## python3
 python_version=python3
-source activate py36
+source activate base
 cd ..
 python setup.py install
 cd ./examples
 run_py
 
 #python2
 python_version=python2
+source activate py27
 cd ..
 python setup.py install
 cd ./examples
diff --git a/examples/run_classification_criteo_multi_gpu.py b/examples/run_classification_criteo_multi_gpu.py
@@ -0,0 +1,56 @@
+import pandas as pd
+from sklearn.metrics import log_loss, roc_auc_score
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import LabelEncoder, MinMaxScaler
+from tensorflow.python.keras.utils import multi_gpu_model
+
+from deepctr.models import DeepFM
+from deepctr.inputs import  SparseFeat, DenseFeat,get_fixlen_feature_names
+
+if __name__ == "__main__":
+    data = pd.read_csv('./criteo_sample.txt')
+
+    sparse_features = ['C' + str(i) for i in range(1, 27)]
+    dense_features = ['I' + str(i) for i in range(1, 14)]
+
+    data[sparse_features] = data[sparse_features].fillna('-1', )
+    data[dense_features] = data[dense_features].fillna(0, )
+    target = ['label']
+
+    # 1.Label Encoding for sparse features,and do simple Transformation for dense features
+    for feat in sparse_features:
+        lbe = LabelEncoder()
+        data[feat] = lbe.fit_transform(data[feat])
+    mms = MinMaxScaler(feature_range=(0, 1))
+    data[dense_features] = mms.fit_transform(data[dense_features])
+
+    # 2.count #unique features for each sparse field,and record dense feature field name
+
+    fixlen_feature_columns = [SparseFeat(feat, data[feat].nunique())
+                           for feat in sparse_features] + [DenseFeat(feat, 1,)
+                          for feat in dense_features]
+
+    dnn_feature_columns = fixlen_feature_columns
+    linear_feature_columns = fixlen_feature_columns
+
+    fixlen_feature_names = get_fixlen_feature_names(linear_feature_columns + dnn_feature_columns)
+
+    # 3.generate input data for model
+
+    train, test = train_test_split(data, test_size=0.2)
+    train_model_input = [train[name] for name in fixlen_feature_names]
+
+    test_model_input = [test[name] for name in fixlen_feature_names]
+
+    # 4.Define Model,train,predict and evaluate
+    model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')
+    #model = multi_gpu_model(model, gpus=2)
+
+    model.compile("adam", "binary_crossentropy",
+                  metrics=['binary_crossentropy'], )
+
+    history = model.fit(train_model_input, train[target].values,
+                        batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
+    pred_ans = model.predict(test_model_input, batch_size=256)
+    print("test LogLoss", round(log_loss(test[target].values, pred_ans), 4))
+    print("test AUC", round(roc_auc_score(test[target].values, pred_ans), 4))
diff --git a/setup.py b/setup.py
@@ -4,48 +4,47 @@
     long_description = fh.read()
 
 REQUIRED_PACKAGES = [
-    #'tensorflow>=1.4.0,!=1.7.*,!=1.8.*,<=1.13.1',
-    'h5py'
+    'h5py','requests'
 ]
 
 setuptools.setup(
     name="deepctr",
-    version="0.6.0",
+    version="0.6.1",
     author="Weichen Shen",
     author_email="wcshen1994@163.com",
-    description="Easy-to-use,Modular and Extendible package of deep learning based CTR(Click Through Rate) prediction models with tensorflow.",
+    description="Easy-to-use,Modular and Extendible package of deep learning based CTR(Click Through Rate) prediction models with tensorflow 1.x and 2.x .",
     long_description=long_description,
     long_description_content_type="text/markdown",
     url="https://github.com/shenweichen/deepctr",
     download_url='https://github.com/shenweichen/deepctr/tags',
     packages=setuptools.find_packages(
         exclude=["tests", "tests.models", "tests.layers"]),
-    python_requires=">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*",  # '>=3.4',  # 3.4.6
+    python_requires=">=2.7,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*",  # '>=3.4',  # 3.4.6
     install_requires=REQUIRED_PACKAGES,
     extras_require={
-        "cpu": ["tensorflow>=1.4.0,!=1.7.*,!=1.8.*"],#,<=1.13.1
-        "gpu": ["tensorflow-gpu>=1.4.0,!=1.7.*,!=1.8.*"],#,<=1.13.1
+        "cpu": ["tensorflow>=1.4.0,!=1.7.*,!=1.8.*"],
+        "gpu": ["tensorflow-gpu>=1.4.0,!=1.7.*,!=1.8.*"],
     },
     entry_points={
     },
     classifiers=(
-        "License :: OSI Approved :: MIT License",
+        "License :: OSI Approved :: Apache Software License",
         "Operating System :: OS Independent",
         'Intended Audience :: Developers',
         'Intended Audience :: Education',
         'Intended Audience :: Science/Research',
         'Programming Language :: Python :: 3',
         'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: 3.7',
         'Topic :: Scientific/Engineering',
         'Topic :: Scientific/Engineering :: Artificial Intelligence',
         'Topic :: Software Development',
         'Topic :: Software Development :: Libraries',
         'Topic :: Software Development :: Libraries :: Python Modules',
     ),
-    license="MIT license",
+    license="Apache-2.0",
     keywords=['ctr', 'click through rate',
               'deep learning', 'tensorflow', 'tensor', 'keras'],
 )
diff --git a/tests/layers/sequence_test.py b/tests/layers/sequence_test.py
@@ -1,4 +1,5 @@
 import pytest
+from packaging import version
 from tensorflow.python.keras.utils import CustomObjectScope
 import tensorflow as tf
 from deepctr.layers import sequence
@@ -34,7 +35,7 @@ def test_AttentionSequencePoolingLayer(weight_normalization):
 
 )
 def test_SequencePoolingLayer(mode, supports_masking, input_shape):
-    if tf.__version__ >='2.0.0' and mode!='sum': #todo check further version
+    if version.parse(tf.__version__) >= version.parse('1.14.0') and mode!='sum': #todo check further version
        return
     with CustomObjectScope({'SequencePoolingLayer': sequence.SequencePoolingLayer}):
         layer_test(sequence.SequencePoolingLayer, kwargs={'mode': mode, 'supports_masking': supports_masking},
diff --git a/tests/models/AutoInt_test.py b/tests/models/AutoInt_test.py
@@ -1,15 +1,16 @@
 import pytest
+from packaging import version
+import tensorflow as tf
 from deepctr.models import AutoInt
 from ..utils import check_model, get_test_data,SAMPLE_SIZE
-import tensorflow as tf
 
 
 @pytest.mark.parametrize(
     'att_layer_num,dnn_hidden_units,sparse_feature_num',
     [(1, (), 1), (1, (4,), 1)]#(0, (4,), 2), (2, (4, 4,), 2)
 )
 def test_AutoInt(att_layer_num, dnn_hidden_units, sparse_feature_num):
-    if tf.__version__ >= "2.0.0" and len(dnn_hidden_units)==0:#todo check version
+    if version.parse(tf.__version__) >= version.parse("1.14.0") and len(dnn_hidden_units)==0:#todo check version
         return
     model_name = "AutoInt"
     sample_size = SAMPLE_SIZE
diff --git a/tests/models/DIEN_test.py b/tests/models/DIEN_test.py
@@ -1,6 +1,7 @@
 import numpy as np
 import pytest
 import tensorflow as tf
+from packaging import version
 from deepctr.models import DIEN
 from deepctr.inputs import SparseFeat,DenseFeat,VarLenSparseFeat,get_fixlen_feature_names,get_varlen_feature_names
 from ..utils import check_model
@@ -60,7 +61,7 @@ def get_xy_fd(use_neg=False, hash_flag=False):
      ]
 )
 def test_DIEN(gru_type):
-    if tf.__version__ >= '2.0.0':
+    if version.parse(tf.__version__) >= version.parse('2.0.0'):
         tf.compat.v1.disable_eager_execution() #todo
     model_name = "DIEN_"+gru_type
 
@@ -74,7 +75,7 @@ def test_DIEN(gru_type):
 
 def test_DIEN_neg():
     model_name = "DIEN_neg"
-    if tf.__version__ >= "2.0.0":
+    if version.parse(tf.__version__) >= version.parse("1.14.0"):
         return
 
     x, y, feature_dim_dict, behavior_feature_list = get_xy_fd(use_neg=True)
diff --git a/tests/utils.py b/tests/utils.py
@@ -2,6 +2,7 @@
 
 import inspect
 import sys
+import os
 
 import numpy as np
 import  tensorflow as tf
@@ -347,10 +348,12 @@ def check_model(model, model_name, x, y,check_model_io=True):
     print(model_name+" test train valid pass!")
     model.save_weights(model_name + '_weights.h5')
     model.load_weights(model_name + '_weights.h5')
+    os.remove(model_name + '_weights.h5') 
     print(model_name+" test save load weight pass!")
     if check_model_io:
         save_model(model, model_name + '.h5')
         model = load_model(model_name + '.h5', custom_objects)
+        os.remove(model_name + '.h5') 
         print(model_name + " test save load model pass!")
 
     print(model_name + " test pass!")

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,5 @@`
`1`	`1`	`# History`
	`2`	+- 09/07/2019 : [v0.6.1](https://github.com/shenweichen/DeepCTR/releases/tag/v0.6.1) released.Fix bugs in `CCPM` and `DynamicGRU`.
`2`	`3`	- 08/02/2019 : [v0.6.0](https://github.com/shenweichen/DeepCTR/releases/tag/v0.6.0) released.Now DeepCTR is compatible with tensorflow `1.14` and `2.0.0`.
`3`	`4`	- 07/21/2019 : [v0.5.2](https://github.com/shenweichen/DeepCTR/releases/tag/v0.5.2) released.Refactor `Linear` Layer.
`4`	`5`	`- 07/10/2019 : [v0.5.1](https://github.com/shenweichen/DeepCTR/releases/tag/v0.5.1) released.Add [FiBiNET](./Features.html#fibinet-feature-importance-and-bilinear-feature-interaction-network).`