simplify input logic

Author: 浅梦

.github/workflows/ci.yml

@@ -18,7 +18,7 @@ jobs:
     strategy:
       matrix:
         python-version: [3.5,3.6,3.7]
-        tf-version: [1.4.0,1.14.0,2.0.0b1]
+        tf-version: [1.4.0,1.14.0,2.0.0]
 
         exclude:
           - python-version: 3.7

deepctr/__init__.py

@@ -2,5 +2,5 @@
 from . import models
 from .utils import check_version
 
-__version__ = '0.6.1'
+__version__ = '0.6.2'
 check_version(__version__)

deepctr/contrib/utils.py

@@ -87,7 +87,7 @@ def __init__(self,
 
             else:
 
-                total_arg_size += shape[1]#.value
+                total_arg_size += int(shape[1])#.value
 
         dtype = [a.dtype for a in args][0]
 

deepctr/inputs.py

@@ -42,39 +42,31 @@ def __new__(cls, name, dimension, maxlen, combiner="mean", use_hash=False, dtype
             embedding_name = name
         return super(VarLenSparseFeat, cls).__new__(cls, name, dimension, maxlen, combiner, use_hash, dtype, embedding_name,embedding)
 
-
-def get_fixlen_feature_names(feature_columns):
-    features = build_input_features(feature_columns, include_varlen=False,include_fixlen=True)
-    return list(features.keys())
-
-def get_varlen_feature_names(feature_columns):
-    features = build_input_features(feature_columns, include_varlen=True,include_fixlen=False)
+def get_feature_names(feature_columns):
+    features = build_input_features(feature_columns)
     return list(features.keys())
 
 def get_inputs_list(inputs):
     return list(chain(*list(map(lambda x: x.values(), filter(lambda x: x is not None, inputs)))))
 
-def build_input_features(feature_columns, include_varlen=True, mask_zero=True, prefix='',include_fixlen=True):
+def build_input_features(feature_columns, mask_zero=True, prefix=''):
     input_features = OrderedDict()
-    if include_fixlen:
-        for fc in feature_columns:
-            if isinstance(fc,SparseFeat):
-                input_features[fc.name] = Input(
-                    shape=(1,), name=prefix+fc.name, dtype=fc.dtype)
-            elif isinstance(fc,DenseFeat):
-                input_features[fc.name] = Input(
-                    shape=(fc.dimension,), name=prefix + fc.name, dtype=fc.dtype)
-    if include_varlen:
-        for fc in feature_columns:
-            if isinstance(fc,VarLenSparseFeat):
-                input_features[fc.name] = Input(shape=(fc.maxlen,), name=prefix + 'seq_' + fc.name,
-                                                      dtype=fc.dtype)
-        if not mask_zero:
-            for fc in feature_columns:
-                input_features[fc.name+"_seq_length"] = Input(shape=(
+    for fc in feature_columns:
+        if isinstance(fc,SparseFeat):
+            input_features[fc.name] = Input(
+                shape=(1,), name=prefix+fc.name, dtype=fc.dtype)
+        elif isinstance(fc,DenseFeat):
+            input_features[fc.name] = Input(
+                shape=(fc.dimension,), name=prefix + fc.name, dtype=fc.dtype)
+        elif isinstance(fc,VarLenSparseFeat):
+            input_features[fc.name] = Input(shape=(fc.maxlen,), name=prefix + fc.name,
+                                            dtype=fc.dtype)
+            if not mask_zero:
+                input_features[fc.name + "_seq_length"] = Input(shape=(
                     1,), name=prefix + 'seq_length_' + fc.name)
-                input_features[fc.name+"_seq_max_length"] = fc.maxlen
-
+                input_features[fc.name + "_seq_max_length"] = fc.maxlen
+        else:
+            raise TypeError("Invalid feature column type,got",type(fc))
 
     return input_features
 
@@ -119,8 +111,6 @@ def create_embedding_dict(sparse_feature_columns, varlen_sparse_feature_columns,
                                                             l2_reg),
                                                         name=prefix + '_seq_emb_' + feat.name,
                                                         mask_zero=seq_mask_zero)
-
-
     return sparse_embedding
 
 

deepctr/layers/sequence.py

@@ -708,7 +708,7 @@ def build(self, input_shape):
 
         if self.axis < 1 or self.axis > len(input_shape):
             raise ValueError("axis must be 1~%d,now is %d" %
-                             (len(input_shape), len(input_shape)))
+                             (len(input_shape), self.axis))
 
         if self.k < 1 or self.k > input_shape[self.axis]:
             raise ValueError("k must be in 1 ~ %d,now k is %d" %

deepctr/models/afm.py

@@ -37,7 +37,7 @@ def AFM(linear_feature_columns, dnn_feature_columns, embedding_size=8, use_atten
     """
 
 
-    features = build_input_features(linear_feature_columns+dnn_feature_columns)
+    features = build_input_features(linear_feature_columns + dnn_feature_columns)
 
     inputs_list = list(features.values())
 

deepctr/models/ccpm.py

@@ -42,7 +42,7 @@ def CCPM(linear_feature_columns, dnn_feature_columns, embedding_size=8, conv_ker
         raise ValueError(
             "conv_kernel_width must have same element with conv_filters")
 
-    features = build_input_features(linear_feature_columns+dnn_feature_columns)
+    features = build_input_features(linear_feature_columns + dnn_feature_columns)
     inputs_list = list(features.values())
 
     sparse_embedding_list, _ = input_from_feature_columns(features,dnn_feature_columns,embedding_size,

deepctr/models/fibinet.py

@@ -38,8 +38,7 @@ def FiBiNET(linear_feature_columns, dnn_feature_columns, embedding_size=8, bilin
     :return: A Keras model instance.
     """
 
-    features = build_input_features(
-        linear_feature_columns + dnn_feature_columns)
+    features = build_input_features(linear_feature_columns + dnn_feature_columns)
 
     inputs_list = list(features.values())
 

deepctr/models/mlr.py

@@ -40,7 +40,7 @@ def MLR(region_feature_columns, base_feature_columns=None, region_num=4,
     if bias_feature_columns is None:
         bias_feature_columns = []
 
-    features = build_input_features(region_feature_columns + base_feature_columns+bias_feature_columns)
+    features = build_input_features(region_feature_columns + base_feature_columns + bias_feature_columns)
 
     inputs_list = list(features.values())
 

docs/source/Examples.md

@@ -31,7 +31,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder, MinMaxScaler
 
 from deepctr.models import DeepFM
-from deepctr.inputs import  SparseFeat, DenseFeat,get_fixlen_feature_names
+from deepctr.inputs import  SparseFeat, DenseFeat, get_feature_names
 
 if __name__ == "__main__":
     data = pd.read_csv('./criteo_sample.txt')
@@ -59,14 +59,13 @@ if __name__ == "__main__":
     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)
+    feature_names = get_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]
+    train_model_input = {name:train[name] for name in feature_names}
+    test_model_input = {name:test[name] for name in feature_names}
 
     # 4.Define Model,train,predict and evaluate
     model = DeepFM(linear_feature_columns, dnn_feature_columns, task='binary')
@@ -91,7 +90,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MinMaxScaler
 
 from deepctr.models import DeepFM
-from deepctr.inputs import SparseFeat, DenseFeat,get_fixlen_feature_names
+from deepctr.inputs import SparseFeat, DenseFeat,get_feature_names
 
 if __name__ == "__main__":
     data = pd.read_csv('./criteo_sample.txt')
@@ -115,14 +114,14 @@ if __name__ == "__main__":
 
     linear_feature_columns = fixlen_feature_columns
     dnn_feature_columns = fixlen_feature_columns
-    fixlen_feature_names = get_fixlen_feature_names(linear_feature_columns + dnn_feature_columns, )
+    feature_names = get_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]
+    train_model_input = {name:train[name] for name in feature_names}
+    test_model_input = {name:test[name] for name in feature_names}
 
 
     # 4.Define Model,train,predict and evaluate
@@ -156,7 +155,7 @@ from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import LabelEncoder
 
 from deepctr.models import DeepFM
-from deepctr.inputs import SparseFeat,get_fixlen_feature_names
+from deepctr.inputs import SparseFeat,get_feature_names
 
 if __name__ == "__main__":
 
@@ -174,12 +173,13 @@ if __name__ == "__main__":
                               for feat in sparse_features]
     linear_feature_columns = fixlen_feature_columns
     dnn_feature_columns = fixlen_feature_columns
-    fixlen_feature_names = get_fixlen_feature_names(linear_feature_columns + dnn_feature_columns)
+    feature_names = get_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].values for name in fixlen_feature_names]
-    test_model_input = [test[name].values for name in fixlen_feature_names]
+    train_model_input = {name:train[name].values for name in feature_names}
+    test_model_input = {name:test[name].values for name in feature_names}
+
     # 4.Define Model,train,predict and evaluate
     model = DeepFM(linear_feature_columns, dnn_feature_columns, task='regression')
     model.compile("adam", "mse", metrics=['mse'], )
@@ -228,7 +228,7 @@ from sklearn.preprocessing import LabelEncoder
 from tensorflow.python.keras.preprocessing.sequence import pad_sequences
 
 from deepctr.models import DeepFM
-from deepctr.inputs import SparseFeat, VarLenSparseFeat,get_fixlen_feature_names,get_varlen_feature_names
+from deepctr.inputs import SparseFeat, VarLenSparseFeat,get_feature_names
 
 
 def split(x):
@@ -239,49 +239,49 @@ def split(x):
             key2index[key] = len(key2index) + 1
     return list(map(lambda x: key2index[x], key_ans))
 
+if __name__ == "__main__":
+    data = pd.read_csv("./movielens_sample.txt")
+    sparse_features = ["movie_id", "user_id",
+                       "gender", "age", "occupation", "zip", ]
+    target = ['rating']
 
-data = pd.read_csv("./movielens_sample.txt")
-sparse_features = ["movie_id", "user_id",
-                   "gender", "age", "occupation", "zip", ]
-target = ['rating']
+    # 1.Label Encoding for sparse features,and process sequence features
+    for feat in sparse_features:
+        lbe = LabelEncoder()
+        data[feat] = lbe.fit_transform(data[feat])
+    # preprocess the sequence feature
 
-# 1.Label Encoding for sparse features,and process sequence features
-for feat in sparse_features:
-    lbe = LabelEncoder()
-    data[feat] = lbe.fit_transform(data[feat])
-# preprocess the sequence feature
+    key2index = {}
+    genres_list = list(map(split, data['genres'].values))
+    genres_length = np.array(list(map(len, genres_list)))
+    max_len = max(genres_length)
+    # Notice : padding=`post`
+    genres_list = pad_sequences(genres_list, maxlen=max_len, padding='post', )
 
-key2index = {}
-genres_list = list(map(split, data['genres'].values))
-genres_length = np.array(list(map(len, genres_list)))
-max_len = max(genres_length)
-# Notice : padding=`post`
-genres_list = pad_sequences(genres_list, maxlen=max_len, padding='post', )
+    # 2.count #unique features for each sparse field and generate feature config for sequence feature
 
-# 2.count #unique features for each sparse field and generate feature config for sequence feature
+    fixlen_feature_columns = [SparseFeat(feat, data[feat].nunique())
+                        for feat in sparse_features]
+    varlen_feature_columns = [VarLenSparseFeat('genres', len(
+        key2index) + 1, max_len, 'mean')]  # Notice : value 0 is for padding for sequence input feature
 
-fixlen_feature_columns = [SparseFeat(feat, data[feat].nunique())
-                    for feat in sparse_features]
-varlen_feature_columns = [VarLenSparseFeat('genres', len(
-    key2index) + 1, max_len, 'mean')]  # Notice : value 0 is for padding for sequence input feature
+    linear_feature_columns = fixlen_feature_columns + varlen_feature_columns
+    dnn_feature_columns = fixlen_feature_columns + varlen_feature_columns
 
-linear_feature_columns = fixlen_feature_columns + varlen_feature_columns
-dnn_feature_columns = fixlen_feature_columns + varlen_feature_columns
-fixlen_feature_names = get_fixlen_feature_names(linear_feature_columns + dnn_feature_columns)
-varlen_feature_names = get_varlen_feature_names(linear_feature_columns+dnn_feature_columns)
+    feature_names = get_feature_names(linear_feature_columns+dnn_feature_columns)
 
 
-# 3.generate input data for model
-fixlen_input = [data[name].values for name in fixlen_feature_names]
-varlen_input = [genres_list]#varlen_feature_names[0]
-model_input = fixlen_input + varlen_input # make sure the order is right
+    # 3.generate input data for model
+    model_input = {name:data[name] for name in feature_names}#
+    model_input["genres"] = genres_list
 
-# 4.Define Model,compile and train
-model = DeepFM(linear_feature_columns,dnn_feature_columns,task='regression')
 
-model.compile("adam", "mse", metrics=['mse'], )
-history = model.fit(model_input, data[target].values,
-                    batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
+    # 4.Define Model,compile and train
+    model = DeepFM(linear_feature_columns,dnn_feature_columns,task='regression')
+
+    model.compile("adam", "mse", metrics=['mse'], )
+    history = model.fit(model_input, data[target].values,
+                        batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
 
 ```
 
@@ -293,44 +293,43 @@ import pandas as pd
 from tensorflow.python.keras.preprocessing.sequence import pad_sequences
 
 from deepctr.models import DeepFM
-from deepctr.inputs import SparseFeat, VarLenSparseFeat,get_fixlen_feature_names
-
-data = pd.read_csv("./movielens_sample.txt")
-sparse_features = ["movie_id", "user_id",
-                   "gender", "age", "occupation", "zip", ]
+from deepctr.inputs import SparseFeat, VarLenSparseFeat,get_feature_names
 
-data[sparse_features] = data[sparse_features].astype(str)
-target = ['rating']
+if __name__ == "__main__":
+    data = pd.read_csv("./movielens_sample.txt")
+    sparse_features = ["movie_id", "user_id",
+                       "gender", "age", "occupation", "zip", ]
 
-# 1.Use hashing encoding on the fly for sparse features,and process sequence features
+    data[sparse_features] = data[sparse_features].astype(str)
+    target = ['rating']
 
-genres_list = list(map(lambda x: x.split('|'), data['genres'].values))
-genres_length = np.array(list(map(len, genres_list)))
-max_len = max(genres_length)
+    # 1.Use hashing encoding on the fly for sparse features,and process sequence features
 
-# Notice : padding=`post`
-genres_list = pad_sequences(genres_list, maxlen=max_len, padding='post', dtype=str, value=0)
+    genres_list = list(map(lambda x: x.split('|'), data['genres'].values))
+    genres_length = np.array(list(map(len, genres_list)))
+    max_len = max(genres_length)
 
-# 2.set hashing space for each sparse field and generate feature config for sequence feature
+    # Notice : padding=`post`
+    genres_list = pad_sequences(genres_list, maxlen=max_len, padding='post', dtype=str, value=0)
 
-fixlen_feature_columns = [SparseFeat(feat, data[feat].nunique() * 5, use_hash=True, dtype='string')
-                          for feat in sparse_features]
-varlen_feature_columns = [VarLenSparseFeat('genres', 100, max_len, 'mean', use_hash=True,
-                                           dtype="string")]  # Notice : value 0 is for padding for sequence input feature
-linear_feature_columns = fixlen_feature_columns + varlen_feature_columns
-dnn_feature_columns = fixlen_feature_columns + varlen_feature_columns
-feature_names = get_fixlen_feature_names(linear_feature_columns + dnn_feature_columns)
+    # 2.set hashing space for each sparse field and generate feature config for sequence feature
 
-# 3.generate input data for model
-fixlen_input = [data[name].values for name in feature_names]
-varlen_input = [genres_list]
+    fixlen_feature_columns = [SparseFeat(feat, data[feat].nunique() * 5, use_hash=True, dtype='string')
+                              for feat in sparse_features]
+    varlen_feature_columns = [VarLenSparseFeat('genres', 100, max_len, 'mean', use_hash=True,
+                                               dtype="string")]  # Notice : value 0 is for padding for sequence input feature
+    linear_feature_columns = fixlen_feature_columns + varlen_feature_columns
+    dnn_feature_columns = fixlen_feature_columns + varlen_feature_columns
+    feature_names = get_feature_names(linear_feature_columns + dnn_feature_columns)
 
-model_input = fixlen_input + varlen_input # make sure the order is right
+    # 3.generate input data for model
+    model_input = {name:data[name] for name in feature_names}
+    model_input['genres'] = genres_list
 
-# 4.Define Model,compile and train
-model = DeepFM(linear_feature_columns,dnn_feature_columns, task='regression')
+    # 4.Define Model,compile and train
+    model = DeepFM(linear_feature_columns,dnn_feature_columns, task='regression')
 
-model.compile("adam", "mse", metrics=['mse'], )
-history = model.fit(model_input, data[target].values,
-                    batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
+    model.compile("adam", "mse", metrics=['mse'], )
+    history = model.fit(model_input, data[target].values,
+                        batch_size=256, epochs=10, verbose=2, validation_split=0.2, )
 ```