Merge pull request #86 from shenweichen/dev-din

add din&dien

README.md

@@ -33,7 +33,9 @@ Let's [**Get Started!**](https://deepctr-torch.readthedocs.io/en/latest/Quick-St
 |   Attentional Factorization Machine    | [IJCAI 2017][Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks](http://www.ijcai.org/proceedings/2017/435) |
 |      Neural Factorization Machine      | [SIGIR 2017][Neural Factorization Machines for Sparse Predictive Analytics](https://arxiv.org/pdf/1708.05027.pdf)                                               |
 |                xDeepFM                 | [KDD 2018][xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://arxiv.org/pdf/1803.05170.pdf)                         |
-|                AutoInt                 | [arxiv 2018][AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/abs/1810.11921)                              |
+|         Deep Interest Network          | [KDD 2018][Deep Interest Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1706.06978.pdf)                                                       |
+|    Deep Interest Evolution Network     | [AAAI 2019][Deep Interest Evolution Network for Click-Through Rate Prediction](https://arxiv.org/pdf/1809.03672.pdf)                                            |
+|                AutoInt                 | [CIKM 2019][AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks](https://arxiv.org/abs/1810.11921)                              |
 |                  ONN                   | [arxiv 2019][Operation-aware Neural Networks for User Response Prediction](https://arxiv.org/pdf/1904.12579.pdf)                                                |
 |                FiBiNET                 | [RecSys 2019][FiBiNET: Combining Feature Importance and Bilinear feature Interaction for Click-Through Rate Prediction](https://arxiv.org/pdf/1905.09433.pdf)   |
 
@@ -45,25 +47,69 @@ Please follow our wechat to join group:
 - wechat ID: **deepctrbot**
 ![wechat](./docs/pics/weichennote.png)
 
+
 ## Contributors([welcome to join us!](./CONTRIBUTING.md))
-<a href="https://github.com/shenweichen">
-    <img src="https://avatars.githubusercontent.com/shenweichen " width=70 height="70" alt="pic" >
-</a>
-<a href="https://github.com/wutongzhang">
-    <img src="https://avatars.githubusercontent.com/wutongzhang " width=70 height="70" alt="pic" >
-</a>
-<a href="https://github.com/JyiHUO">
-    <img src="https://avatars.githubusercontent.com/JyiHUO " width=70 height="70" alt="pic" >
-</a>
-<a href="https://github.com/Zengai">
-    <img src="https://avatars.githubusercontent.com/Zengai " width=70 height="70" alt="pic" >
-</a>
-<a href="https://github.com/chenkkkk">
-    <img src="https://avatars.githubusercontent.com/chenkkkk " width=70 height="70" alt="pic" >
-</a>
-<a href="https://github.com/tangaqi">
-    <img src="https://avatars.githubusercontent.com/tangaqi " width=70 height=70" alt="pic" >
-</a>
-<a href="https://github.com/uestc7d">
-    <img src="https://avatars.githubusercontent.com/uestc7d " width=70 height="70" alt="pic" >
-</a>
+
+<table border="0">
+  <tbody>
+    <tr align="center" >
+      <td>
+        ​ <a href="https://github.com/shenweichen"><img width="70" height="70" src="https://github.com/shenweichen.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/shenweichen">Shen Weichen</a> ​
+        <p>Founder<br>
+        Zhejiang Unversity <br> <br>  </p>​
+      </td>
+      <td>
+         <a href="https://github.com/weberrr"><img width="70" height="70" src="https://github.com/weberrr.png?s=40" alt="pic"></a><br>
+         <a href="https://github.com/weberrr">Wang Ze</a> ​
+        <p>Core Dev<br> Beihang University <br> <br>  </p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/wutongzhang"><img width="70" height="70" src="https://github.com/wutongzhang.png?s=40" alt="pic"></a><br>
+         <a href="https://github.com/wutongzhang">Zhang Wutong</a>
+         <p>Core Dev<br> Beijing University <br> of  Posts and <br> Telecommunications</p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/ZhangYuef"><img width="70" height="70" src="https://github.com/ZhangYuef.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/ZhangYuef">Zhang Yuefeng</a>
+        <p>Core Dev<br>
+        Peking University <br>  <br>  </p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/JyiHUO"><img width="70" height="70" src="https://github.com/JyiHUO.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/JyiHUO">Huo Junyi</a>
+        <p>Core Dev<br>
+        University of Southampton <br> <br>  </p>​
+      </td>
+    </tr>
+    <tr align="center">
+      <td>
+        ​ <a href="https://github.com/Zengai"><img width="70" height="70" src="https://github.com/Zengai.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/Zengai">Zeng Kai</a> ​
+        <p>Dev<br>
+        SenseTime <br> <br>  </p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/chenkkkk"><img width="70" height="70" src="https://github.com/chenkkkk.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/chenkkkk">Chen K</a> ​
+        <p>Dev<br>
+        NetEase <br>  <br>  </p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/tangaqi"><img width="70" height="70" src="https://github.com/tangaqi.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/tangaqi">Tang</a>
+        <p>Test<br>
+        Tongji University <br> <br>  </p>​
+      </td>
+      <td>
+        ​ <a href="https://github.com/uestc7d"><img width="70" height="70" src="https://github.com/uestc7d.png?s=40" alt="pic"></a><br>
+        ​ <a href="https://github.com/uestc7d">Xu Qidi</a> ​
+        <p>Dev<br>
+        University of <br> Electronic  Science  and <br> Technology of China</p>​
+      </td>
+      <td>
+      <a href="https://github.com/shenweichen/DeepCTR-Torch/blob/master/CONTRIBUTING.md"> Welcome you !!</a>
+      </td>
+    </tr>
+  </tbody>
+</table>

deepctr_torch/__init__.py

@@ -2,5 +2,5 @@
 from . import models
 from .utils import check_version
 
-__version__ = '0.2.0'
+__version__ = '0.2.1'
 check_version(__version__)

deepctr_torch/inputs.py

@@ -4,10 +4,12 @@
     Weichen Shen,wcshen1994@163.com
 """
 
-from collections import OrderedDict, namedtuple
+from collections import OrderedDict, namedtuple, defaultdict
+from itertools import chain
 
 import torch
 import torch.nn as nn
+import numpy as np
 
 from .layers.sequence import SequencePoolingLayer
 from .layers.utils import concat_fun
@@ -27,7 +29,8 @@ def __new__(cls, name, vocabulary_size, embedding_dim=4, use_hash=False, dtype="
         if embedding_dim == "auto":
             embedding_dim = 6 * int(pow(vocabulary_size, 0.25))
         if use_hash:
-            print("Notice! Feature Hashing on the fly currently is not supported in torch version,you can use tensorflow version!")
+            print(
+                "Notice! Feature Hashing on the fly currently is not supported in torch version,you can use tensorflow version!")
         return super(SparseFeat, cls).__new__(cls, name, vocabulary_size, embedding_dim, use_hash, dtype,
                                               embedding_name, group_name)
 
@@ -108,23 +111,14 @@ def build_input_features(feature_columns):
         elif isinstance(feat, VarLenSparseFeat):
             features[feat_name] = (start, start + feat.maxlen)
             start += feat.maxlen
-            if feat.length_name is not None:
+            if feat.length_name is not None and feat.length_name not in features:
                 features[feat.length_name] = (start, start + 1)
                 start += 1
         else:
             raise TypeError("Invalid feature column type,got", type(feat))
     return features
 
 
-# def get_dense_input(features, feature_columns):
-#     dense_feature_columns = list(filter(lambda x: isinstance(
-#         x, DenseFeat), feature_columns)) if feature_columns else []
-#     dense_input_list = []
-#     for fc in dense_feature_columns:
-#         dense_input_list.append(features[fc.name])
-#     return dense_input_list
-
-
 def combined_dnn_input(sparse_embedding_list, dense_value_list):
     if len(sparse_embedding_list) > 0 and len(dense_value_list) > 0:
         sparse_dnn_input = torch.flatten(
@@ -139,72 +133,6 @@ def combined_dnn_input(sparse_embedding_list, dense_value_list):
     else:
         raise NotImplementedError
 
-    #
-    # def embedding_lookup(sparse_embedding_dict, sparse_input_dict, sparse_feature_columns, return_feat_list=(),
-    #                      mask_feat_list=(), to_list=False):
-    #     """
-    #         Args:
-    #             sparse_embedding_dict: nn.ModuleDict, {embedding_name: nn.Embedding}
-    #             sparse_input_dict: OrderedDict, {feature_name:(start, start+dimension)}
-    #             sparse_feature_columns: list, sparse features
-    #             return_feat_list: list, names of feature to be returned, defualt () -> return all features
-    #             mask_feat_list, list, names of feature to be masked in hash transform
-    #         Return:
-    #             group_embedding_dict: defaultdict(list)
-    #     """
-    #     group_embedding_dict = defaultdict(list)
-    #     for fc in sparse_feature_columns:
-    #         feature_name = fc.name
-    #         embedding_name = fc.embedding_name
-    #         if (len(return_feat_list) == 0 or feature_name in return_feat_list):
-    #             if fc.use_hash:
-    #                 # lookup_idx = Hash(fc.vocabulary_size, mask_zero=(feature_name in mask_feat_list))(
-    #                 #     sparse_input_dict[feature_name])
-    #                 # TODO: add hash function
-    #                 lookup_idx = sparse_input_dict[feature_name]
-    #             else:
-    #                 lookup_idx = sparse_input_dict[feature_name]
-    #
-    #             group_embedding_dict[fc.group_name].append(sparse_embedding_dict[embedding_name](lookup_idx))
-    #     if to_list:
-    #         return list(chain.from_iterable(group_embedding_dict.values()))
-    #     return group_embedding_dict
-    #
-    #
-    # def varlen_embedding_lookup(embedding_dict, sequence_input_dict, varlen_sparse_feature_columns):
-    #     varlen_embedding_vec_dict = {}
-    #     for fc in varlen_sparse_feature_columns:
-    #         feature_name = fc.name
-    #         embedding_name = fc.embedding_name
-    #         if fc.use_hash:
-    #             # lookup_idx = Hash(fc.vocabulary_size, mask_zero=True)(sequence_input_dict[feature_name])
-    #             # TODO: add hash function
-    #             lookup_idx = sequence_input_dict[feature_name]
-    #         else:
-    #             lookup_idx = sequence_input_dict[feature_name]
-    #         varlen_embedding_vec_dict[feature_name] = embedding_dict[embedding_name](lookup_idx)
-    #     return varlen_embedding_vec_dict
-    #
-    #
-    # def get_varlen_pooling_list(embedding_dict, features, varlen_sparse_feature_columns, to_list=False):
-    #     pooling_vec_list = defaultdict(list)
-    #     for fc in varlen_sparse_feature_columns:
-    #         feature_name = fc.name
-    #         combiner = fc.combiner
-    #         feature_length_name = fc.length_name
-    #         if feature_length_name is not None:
-    #             seq_input = embedding_dict[feature_name]
-    #             vec = SequencePoolingLayer(combiner)([seq_input, features[feature_length_name]])
-    #         else:
-    #             seq_input = embedding_dict[feature_name]
-    #             vec = SequencePoolingLayer(combiner)(seq_input)
-    #         pooling_vec_list[fc.group_name].append(vec)
-    #
-    #         if to_list:
-    #             return chain.from_iterable(pooling_vec_list.values())
-    #
-    #     return pooling_vec_list
-
 
 def get_varlen_pooling_list(embedding_dict, features, feature_index, varlen_sparse_feature_columns, device):
     varlen_sparse_embedding_list = []
@@ -249,3 +177,95 @@ def create_embedding_matrix(feature_columns, init_std=0.0001, linear=False, spar
         nn.init.normal_(tensor.weight, mean=0, std=init_std)
 
     return embedding_dict.to(device)
+
+
+def input_from_feature_columns(self, X, feature_columns, embedding_dict, support_dense=True):
+    sparse_feature_columns = list(
+        filter(lambda x: isinstance(x, SparseFeat), feature_columns)) if len(feature_columns) else []
+    dense_feature_columns = list(
+        filter(lambda x: isinstance(x, DenseFeat), feature_columns)) if len(feature_columns) else []
+
+    varlen_sparse_feature_columns = list(
+        filter(lambda x: isinstance(x, VarLenSparseFeat), feature_columns)) if feature_columns else []
+
+    if not support_dense and len(dense_feature_columns) > 0:
+        raise ValueError(
+            "DenseFeat is not supported in dnn_feature_columns")
+
+    sparse_embedding_list = [embedding_dict[feat.embedding_name](
+        X[:, self.feature_index[feat.name][0]:self.feature_index[feat.name][1]].long()) for
+        feat in sparse_feature_columns]
+
+    varlen_sparse_embedding_list = get_varlen_pooling_list(self.embedding_dict, X, self.feature_index,
+                                                           varlen_sparse_feature_columns, self.device)
+
+    dense_value_list = [X[:, self.feature_index[feat.name][0]:self.feature_index[feat.name][1]] for feat in
+                        dense_feature_columns]
+
+    return sparse_embedding_list + varlen_sparse_embedding_list, dense_value_list
+
+
+
+def embedding_lookup(X, sparse_embedding_dict, sparse_input_dict, sparse_feature_columns, return_feat_list=(),
+                     mask_feat_list=(), to_list=False):
+    """
+        Args:
+            X: input Tensor [batch_size x hidden_dim]
+            sparse_embedding_dict: nn.ModuleDict, {embedding_name: nn.Embedding}
+            sparse_input_dict: OrderedDict, {feature_name:(start, start+dimension)}
+            sparse_feature_columns: list, sparse features
+            return_feat_list: list, names of feature to be returned, defualt () -> return all features
+            mask_feat_list, list, names of feature to be masked in hash transform
+        Return:
+            group_embedding_dict: defaultdict(list)
+    """
+    group_embedding_dict = defaultdict(list)
+    for fc in sparse_feature_columns:
+        feature_name = fc.name
+        embedding_name = fc.embedding_name
+        if (len(return_feat_list) == 0 or feature_name in return_feat_list):
+            # TODO: add hash function
+            # if fc.use_hash:
+            #     raise NotImplementedError("hash function is not implemented in this version!")
+            lookup_idx = np.array(sparse_input_dict[feature_name])
+            input_tensor = X[:, lookup_idx[0]:lookup_idx[1]].long()
+            emb = sparse_embedding_dict[embedding_name](input_tensor)
+            group_embedding_dict[fc.group_name].append(emb)
+    if to_list:
+        return list(chain.from_iterable(group_embedding_dict.values()))
+    return group_embedding_dict
+
+
+def varlen_embedding_lookup(X, embedding_dict, sequence_input_dict, varlen_sparse_feature_columns):
+    varlen_embedding_vec_dict = {}
+    for fc in varlen_sparse_feature_columns:
+        feature_name = fc.name
+        embedding_name = fc.embedding_name
+        if fc.use_hash:
+            # lookup_idx = Hash(fc.vocabulary_size, mask_zero=True)(sequence_input_dict[feature_name])
+            # TODO: add hash function
+            lookup_idx = sequence_input_dict[feature_name]
+        else:
+            lookup_idx = sequence_input_dict[feature_name]
+        varlen_embedding_vec_dict[feature_name] = embedding_dict[embedding_name](
+            X[:, lookup_idx[0]:lookup_idx[1]].long())  # (lookup_idx)
+
+    return varlen_embedding_vec_dict
+
+
+def get_dense_input(X, features, feature_columns):
+    dense_feature_columns = list(filter(lambda x: isinstance(
+        x, DenseFeat), feature_columns)) if feature_columns else []
+    dense_input_list = []
+    for fc in dense_feature_columns:
+        lookup_idx = np.array(features[fc.name])
+        input_tensor = X[:, lookup_idx[0]:lookup_idx[1]].float()
+        dense_input_list.append(input_tensor)
+    return dense_input_list
+
+
+def maxlen_lookup(X, sparse_input_dict, maxlen_column):
+    if maxlen_column is None or len(maxlen_column)==0:
+        raise ValueError('please add max length column for VarLenSparseFeat of DIEN input')
+    lookup_idx = np.array(sparse_input_dict[maxlen_column[0]])
+    return X[:, lookup_idx[0]:lookup_idx[1]].long()

deepctr_torch/layers/__init__.py

@@ -1,4 +1,4 @@
 from .interaction import *
 from .core import *
 from .utils import concat_fun
-from .sequence import KMaxPooling, SequencePoolingLayer
+from .sequence import *