Add model test files

Author: Weichen Shen

.travis.yml

@@ -0,0 +1,47 @@
+sudo: required
+dist: trusty
+language: python
+
+python:
+  #- "3.4"
+  #- "3.5"
+  - "3.6"
+
+env:
+- TF_VERSION=1.4.0
+- TF_VERSION=1.5.0
+- TF_VERSION=1.5.1
+- TF_VERSION=1.6.0
+#- TF_VERSION=1.7.0
+
+matrix:
+  allow_failures:
+    - python: "3.4"
+    - python: "3.5"
+    - env: TF_VERSION=1.7.0
+    - env: TF_VERSION=1.5.0
+  fast_finish: true
+
+
+cache: pip
+# command to install dependencies
+install:
+    - pip install -q pytest-cov==2.4.0
+#>=2.4.0,<2.6
+    - pip install -q python-coveralls
+    - pip install -q h5py
+    - pip install -q tensorflow==$TF_VERSION
+    - pip install -e .
+# command to run tests
+script:
+    - pytest --cov=deepctr
+
+notifications:  
+    recipients:
+        - [email protected]
+
+    on_success: change
+    on_failure: always
+
+after_success:
+  coveralls

README.md

@@ -1,12 +1,16 @@
 # DeepCTR
 ![dep1](https://img.shields.io/badge/Tensorflow-1.4/1.5/1.6-blue.svg
 )
-[![Python Versions](https://img.shields.io/pypi/pyversions/deepctr.svg)](https://pypi.org/project/deepctr)
-[![Documentation Status](https://readthedocs.org/projects/deepctr-doc/badge/?version=latest)](https://deepctr-doc.readthedocs.io/)
+[![Python Versions](https://img.shields.io/badge/python-3.6-blue.svg)](https://pypi.org/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)
 [![License](https://img.shields.io/badge/license-MIT-brightgreen.svg)](https://github.com/shenweichen/deepctr/blob/master/LICENSE)
-[![PyPI Version](https://img.shields.io/pypi/v/deepctr.svg)](https://pypi.org/project/deepctr)
+
+[![Documentation Status](https://readthedocs.org/projects/deepctr-doc/badge/?version=latest)](https://deepctr-doc.readthedocs.io/)
+[![Build Status](https://travis-ci.com/shenweichen/DeepCTR.svg?branch=master)](https://travis-ci.com/shenweichen/DeepCTR)
+[![Coverage Status](https://coveralls.io/repos/github/shenweichen/DeepCTR/badge.svg)](https://coveralls.io/github/shenweichen/DeepCTR)
+[![Codacy Badge](https://api.codacy.com/project/badge/Grade/c5e1deb657a94e40aa1db080cb0df91e)](https://www.codacy.com/app/wcshen1994/DeepCTR?utm_source=github.com&utm_medium=referral&utm_content=shenweichen/DeepCTR&utm_campaign=Badge_Grade)
 
 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.You can use any complex model with `model.fit()`and`model.predict()` just like any other keras model.And the layers are compatible with tensorflow.Through  `pip install deepctr`  get the package and [**Get Started!**](https://deepctr-doc.readthedocs.io/en/latest/Quick-Start.html)
 

docs/source/Demo.rst

@@ -16,7 +16,7 @@ In this demo,we simply normailize the integer feature between 0 and 1,you
 can try other transformation technique like log normalization or discretization.
 
 This example shows how to use *DeepFM* to solve a simple binary classification task. You can get the demo data 
-`criteo_sample.txt <https://github.com/shenweichen/DeepCTR/tree/master/demo
+`criteo_sample.txt <https://github.com/shenweichen/DeepCTR/tree/master/examples
 /criteo_sample.txt>`_ and run the following codes.
 
 .. code-block:: python
@@ -73,7 +73,7 @@ Here is a small fraction of data include  only sparse field.
    :scale: 70 %
 
 This example shows how to use *DeepFM* to solve a simple binary regression task. You can get the demo data 
-`movielens_sample.txt <https://github.com/shenweichen/DeepCTR/tree/master/demo
+`movielens_sample.txt <https://github.com/shenweichen/DeepCTR/tree/master/examples
 /movielens_sample.txt>`_ and run the following codes.
 
 .. code-block:: python

demo/criteo_sample.txt examples/criteo_sample.txt

@@ -0,0 +1,23 @@
+[metadata]
+desciption-file = README.md
+
+#[coverage:run]
+#branch = True
+
+[coverage:report]
+exclude_lines =
+    # Have to re-enable the standard pragma
+    pragma: no cover
+    # Don't complain about missing debug-only code:
+    def __repr__
+    if self\.debug
+
+    # Don't complain if tests don't hit defensive assertion code:
+    raise ValueError
+    raise AssertionError
+    raise NotImplementedError
+
+    # Don't complain if non-runnable code isn't run:
+    if 0:
+    if False:
+    if __name__ == .__main__.:

demo/movielens_sample.txt examples/movielens_sample.txt

@@ -0,0 +1,36 @@
+import numpy as np
+from tensorflow.python.keras.models import save_model, load_model
+from deepctr.models import AFM
+from deepctr.utils import custom_objects
+
+
+def test_AFM():
+    name = "AFM"
+
+    sample_size = 64
+    feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
+                                   'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
+    sparse_input = [np.random.randint(0, dim, sample_size)
+                    for dim in feature_dim_dict['sparse'].values()]
+    dense_input = [np.random.random(sample_size)
+                   for name in feature_dim_dict['dense']]
+    y = np.random.randint(0, 2, sample_size)
+    x = sparse_input + dense_input
+
+    model = AFM(feature_dim_dict, use_attention=True, keep_prob=0.5,)
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+    save_model(model,  name + '.h5')
+    model = load_model(name + '.h5', custom_objects)
+    print(name + " test save load model pass!")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_AFM()

demo/run_classification_criteo.py examples/run_classification_criteo.py

@@ -0,0 +1,37 @@
+import numpy as np
+from deepctr.models import DCN
+from deepctr.utils import custom_objects
+from tensorflow.python.keras.models import save_model, load_model
+
+
+def test_DCN():
+    name = "DCN"
+
+    sample_size = 64
+    feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
+                                   'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
+    sparse_input = [np.random.randint(0, dim, sample_size)
+                    for dim in feature_dim_dict['sparse'].values()]
+    dense_input = [np.random.random(sample_size)
+                   for name in feature_dim_dict['dense']]
+    y = np.random.randint(0, 2, sample_size)
+    x = sparse_input + dense_input
+
+    model = DCN(feature_dim_dict, embedding_size=8,
+                hidden_size=[32, 32], keep_prob=0.5, )
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+    save_model(model, name + '.h5')
+    model = load_model(name + '.h5', custom_objects)
+    print(name + " test save load model pass!")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_DCN()

demo/run_regression_movielens.py examples/run_regression_movielens.py

@@ -0,0 +1,86 @@
+import numpy as np
+from deepctr.models import DIN
+from deepctr.activations import Dice
+from deepctr.utils import custom_objects
+
+from tensorflow.python.keras.layers import PReLU
+from tensorflow.python.keras.models import load_model, save_model
+
+
+def get_xy_fd():
+    feature_dim_dict = {"sparse": {'user': 4, 'gender': 2,
+                                   'item': 4, 'item_gender': 2}, "dense": []}
+    behavior_feature_list = ["item"]
+    uid = np.array([1, 2, 3])
+    ugender = np.array([0, 1, 0])
+    iid = np.array([0, 1, 2])
+    igender = np.array([0, 1, 0])
+
+    hist_iid = np.array([[0, 1, 2, 3], [0, 1, 2, 3], [0, 1, 2, 3]])
+    hist_igender = np.array([[0, 1, 0, 1], [0, 1, 1, 1], [0, 0, 1, 0]])
+    hist_length = np.array([4, 4, 4])
+
+    feature_dict = {'user': uid, 'gender': ugender, 'item': iid, 'item_gender': igender,
+                    'hist_item': hist_iid, 'hist_item_gender': hist_igender, }
+    x = [feature_dict[feat] for feat in feature_dim_dict["sparse"]] \
+        + [feature_dict['hist_'+feat] for feat in behavior_feature_list]\
+        + [hist_length]
+    y = [1, 0, 1]
+    return x, y, feature_dim_dict, behavior_feature_list
+
+
+def test_DIN_att():
+
+    name = "DIN_att"
+    x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
+
+    model = DIN(feature_dim_dict, behavior_feature_list, hist_len_max=4, embedding_size=8,
+                use_din=True, hidden_size=[4, 4, 4], keep_prob=0.6,)
+
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, verbose=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+
+    try:
+        save_model(model,  name + '.h5')
+        model = load_model(name + '.h5', custom_objects)
+        print(name + " test save load model pass!")
+    except:
+        print("【Error】There is a bug when save model use Dice or Prelu---------------------------------------------------")
+
+    print(name + " test pass!")
+
+
+def test_DIN_sum():
+
+    name = "DIN_sum"
+    x, y, feature_dim_dict, behavior_feature_list = get_xy_fd()
+
+    model = DIN(feature_dim_dict, behavior_feature_list, hist_len_max=4, embedding_size=8,
+                use_din=False, hidden_size=[4, 4, 4], keep_prob=0.6, activation="sigmoid")
+
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, verbose=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+
+    try:
+        save_model(model,  name + '.h5')
+        model = load_model(name + '.h5', custom_objects)
+        print(name + " test save load model pass!")
+    except:
+        print("There is a bug when save model use Dice or Prelu")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_DIN_att()
+    test_DIN_sum()

setup.cfg

@@ -0,0 +1,36 @@
+import numpy as np
+from deepctr.models import DeepFM
+from deepctr.utils import custom_objects
+from tensorflow.python.keras.models import save_model, load_model
+
+
+def test_DeepFM():
+    name = "DeepFM"
+    sample_size = 64
+    feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
+                                   'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
+    sparse_input = [np.random.randint(0, dim, sample_size)
+                    for dim in feature_dim_dict['sparse'].values()]
+    dense_input = [np.random.random(sample_size)
+                   for name in feature_dim_dict['dense']]
+    y = np.random.randint(0, 2, sample_size)
+    x = sparse_input + dense_input
+
+    model = DeepFM(feature_dim_dict,  use_fm=True,
+                   hidden_size=[32, 32], keep_prob=0.5, )
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+    save_model(model,  name + '.h5')
+    model = load_model(name + '.h5', custom_objects)
+    print(name + " test save load model pass!")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_DeepFM()

tests/AFM_test.py

@@ -0,0 +1,36 @@
+import numpy as np
+from deepctr.models import FNN
+from deepctr.utils import custom_objects
+from tensorflow.python.keras.models import save_model, load_model
+
+
+def test_FNN():
+    name = "FNN"
+
+    sample_size = 64
+    feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
+                                   'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
+    sparse_input = [np.random.randint(0, dim, sample_size)
+                    for dim in feature_dim_dict['sparse'].values()]
+    dense_input = [np.random.random(sample_size)
+                   for name in feature_dim_dict['dense']]
+    y = np.random.randint(0, 2, sample_size)
+    x = sparse_input + dense_input
+
+    model = FNN(feature_dim_dict,  hidden_size=[32, 32], keep_prob=0.5, )
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+    save_model(model, name + '.h5')
+    model = load_model(name + '.h5', custom_objects)
+    print(name + " test save load model pass!")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_FNN()

tests/DCN_test.py

@@ -0,0 +1,36 @@
+import numpy as np
+from deepctr.models import MLR
+from deepctr.utils import custom_objects
+from tensorflow.python.keras.models import save_model, load_model
+
+
+def test_MLR():
+    name = "MLR"
+
+    sample_size = 64
+    feature_dim_dict = {'sparse': {'sparse_1': 2, 'sparse_2': 5,
+                                   'sparse_3': 10}, 'dense': ['dense_1', 'dense_2', 'dense_3']}
+    sparse_input = [np.random.randint(0, dim, sample_size)
+                    for dim in feature_dim_dict['sparse'].values()]
+    dense_input = [np.random.random(sample_size)
+                   for name in feature_dim_dict['dense']]
+    y = np.random.randint(0, 2, sample_size)
+    x = sparse_input + dense_input
+
+    model = MLR(feature_dim_dict)
+    model.compile('adam', 'binary_crossentropy',
+                  metrics=['binary_crossentropy'])
+    model.fit(x, y, batch_size=100, epochs=1, validation_split=0.5)
+    print(name+" test train valid pass!")
+    model.save_weights(name + '_weights.h5')
+    model.load_weights(name + '_weights.h5')
+    print(name+" test save load weight pass!")
+    save_model(model, name + '.h5')
+    model = load_model(name + '.h5', custom_objects)
+    print(name + " test save load model pass!")
+
+    print(name + " test pass!")
+
+
+if __name__ == "__main__":
+    test_MLR()