Merge pull request #185 from jrzaurin/flash_attention

Flash attention

README.md

@@ -130,26 +130,33 @@ passed through a series of ResNet blocks built with dense layers.
 3. **TabNet**: details on TabNet can be found in
 [TabNet: Attentive Interpretable Tabular Learning](https://arxiv.org/abs/1908.07442)
 
+Two simpler attention based models that we call:
+
+4. **ContextAttentionMLP**: MLP with at attention mechanism "on top" that is based on
+    [Hierarchical Attention Networks for Document Classification](https://www.cs.cmu.edu/~./hovy/papers/16HLT-hierarchical-attention-networks.pd)
+5. **SelfAttentionMLP**: MLP with an attention mechanism that is a simplified
+    version of a transformer block that we refer as "query-key self-attention".
+
 The ``Tabformer`` family, i.e. Transformers for Tabular data:
 
-4. **TabTransformer**: details on the TabTransformer can be found in
+6. **TabTransformer**: details on the TabTransformer can be found in
 [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://arxiv.org/pdf/2012.06678.pdf).
-5. **SAINT**: Details on SAINT can be found in
+7. **SAINT**: Details on SAINT can be found in
 [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://arxiv.org/abs/2106.01342).
-6. **FT-Transformer**: details on the FT-Transformer can be found in
+8. **FT-Transformer**: details on the FT-Transformer can be found in
 [Revisiting Deep Learning Models for Tabular Data](https://arxiv.org/abs/2106.11959).
-7. **TabFastFormer**: adaptation of the FastFormer for tabular data. Details
+9. **TabFastFormer**: adaptation of the FastFormer for tabular data. Details
 on the Fasformer can be found in
 [FastFormers: Highly Efficient Transformer Models for Natural Language Understanding](https://arxiv.org/abs/2010.13382)
-8. **TabPerceiver**: adaptation of the Perceiver for tabular data. Details on
+10. **TabPerceiver**: adaptation of the Perceiver for tabular data. Details on
 the Perceiver can be found in
 [Perceiver: General Perception with Iterative Attention](https://arxiv.org/abs/2103.03206)
 
 And probabilistic DL models for tabular data based on
 [Weight Uncertainty in Neural Networks](https://arxiv.org/abs/1505.05424):
 
-9. **BayesianWide**: Probabilistic adaptation of the `Wide` model.
-10. **BayesianTabMlp**: Probabilistic adaptation of the `TabMlp` model
+11. **BayesianWide**: Probabilistic adaptation of the `Wide` model.
+12. **BayesianTabMlp**: Probabilistic adaptation of the `TabMlp` model
 
 Note that while there are scientific publications for the TabTransformer,
 SAINT and FT-Transformer, the TabFasfFormer and TabPerceiver are our own
@@ -196,7 +203,6 @@ using `Wide` and `DeepDense` and defaults settings.
 Building a wide (linear) and deep model with ``pytorch-widedeep``:
 
 ```python
-import pandas as pd
 import numpy as np
 import torch
 from sklearn.model_selection import train_test_split

VERSION

-1.3.1
+1.3.2

examples/scripts/adult_census_linear_and_flash_attention.py

+from time import time
+
+from sklearn.model_selection import train_test_split
+
+from pytorch_widedeep import Trainer
+from pytorch_widedeep.models import WideDeep, TabTransformer
+from pytorch_widedeep.metrics import Accuracy
+from pytorch_widedeep.datasets import load_adult
+from pytorch_widedeep.preprocessing import TabPreprocessor
+
+# use_cuda = torch.cuda.is_available()
+
+df = load_adult(as_frame=True)
+df.columns = [c.replace("-", "_") for c in df.columns]
+df["income_label"] = (df["income"].apply(lambda x: ">50K" in x)).astype(int)
+df.drop("income", axis=1, inplace=True)
+target_colname = "income_label"
+
+cat_embed_cols = []
+for col in df.columns:
+    if df[col].dtype == "O" or df[col].nunique() < 200 and col != target_colname:
+        cat_embed_cols.append(col)
+
+train, test = train_test_split(
+    df, test_size=0.1, random_state=1, stratify=df[[target_colname]]
+)
+
+with_cls_token = True
+tab_preprocessor = TabPreprocessor(
+    cat_embed_cols=cat_embed_cols, with_attention=True, with_cls_token=with_cls_token
+)
+
+X_tab_train = tab_preprocessor.fit_transform(train)
+X_tab_test = tab_preprocessor.transform(test)
+target = train[target_colname].values
+
+
+tab_transformer = TabTransformer(
+    column_idx=tab_preprocessor.column_idx,
+    cat_embed_input=tab_preprocessor.cat_embed_input,
+    input_dim=16,
+    n_heads=2,
+    n_blocks=2,
+)
+
+linear_tab_transformer = TabTransformer(
+    column_idx=tab_preprocessor.column_idx,
+    cat_embed_input=tab_preprocessor.cat_embed_input,
+    input_dim=16,
+    n_heads=2,
+    n_blocks=2,
+    use_linear_attention=True,
+)
+
+flash_tab_transformer = TabTransformer(
+    column_idx=tab_preprocessor.column_idx,
+    cat_embed_input=tab_preprocessor.cat_embed_input,
+    input_dim=16,
+    n_heads=2,
+    n_blocks=2,
+    use_flash_attention=True,
+)
+
+s_model = WideDeep(deeptabular=tab_transformer)
+l_model = WideDeep(deeptabular=linear_tab_transformer)
+f_model = WideDeep(deeptabular=flash_tab_transformer)
+
+for name, model in [("standard", s_model), ("linear", l_model), ("flash", f_model)]:
+    trainer = Trainer(
+        model,
+        objective="binary",
+        metrics=[Accuracy],
+    )
+
+    s = time()
+    trainer.fit(
+        X_tab=X_tab_train,
+        target=target,
+        n_epochs=1,
+        batch_size=64,
+        val_split=0.2,
+    )
+    e = time() - s
+    print(f"{name} attention time: {round(e, 3)} secs")

examples/scripts/wide_deep_for_recsys/ml100k_data_preparation.py

@@ -10,7 +10,7 @@ from sklearn.model_selection import train_test_split
 
 from pytorch_widedeep.datasets import load_movielens100k
 
-data, user, items = load_movielens100k(as_frame=True)
+data, users, items = load_movielens100k(as_frame=True)
 
 # Alternatively, as specified in the docs: 'The last 19 fields are the genres' so:
 # list_of_genres = items.columns.tolist()[-19:]
@@ -37,7 +37,7 @@ list_of_genres = [
 ]
 
 
-# adding a column with the number of movies watched per user
+# adding a column with the number of movies watched per users
 dataset = data.sort_values(["user_id", "timestamp"]).reset_index(drop=True)
 dataset["one"] = 1
 dataset["num_watched"] = dataset.groupby("user_id")["one"].cumsum()
@@ -61,6 +61,9 @@ dataset["prev_movies"] = (
 )
 dataset["prev_movies"] = dataset["prev_movies"].apply(lambda x: x.split())
 
+# Adding user feats
+dataset = dataset.merge(users, on="user_id", how="left")
+
 # Adding a genre_rate as the mean of all movies rated for a given genre per
 # user
 dataset = dataset.merge(items[["movie_id"] + list_of_genres], on="movie_id", how="left")

examples/scripts/wide_deep_for_recsys/pytorch_wide_deep_pt2.py

@@ -47,7 +47,7 @@ train_movies_sequences = df_train.prev_movies.apply(
 ).to_list()
 y_train = df_train.target.values.astype(int)
 
-df_test_user_item = df_train[["user_id", "movie_id", "rating"]]
+df_test_user_item = df_test[["user_id", "movie_id", "rating"]]
 test_movies_sequences = df_test.prev_movies.apply(
     lambda x: [int(el) for el in x]
 ).to_list()
@@ -89,7 +89,7 @@ X_test_text = np.array(
 tab_mlp = TabMlp(
     column_idx=tab_preprocessor.column_idx,
     cat_embed_input=tab_preprocessor.cat_embed_input,
-    mlp_hidden_dims=[1024, 512, 256],
+    mlp_hidden_dims=[512, 256],
     mlp_activation="relu",
 )
 
@@ -124,7 +124,7 @@ trainer.fit(
         "X_text": X_test_text,
         "target": y_test,
     },
-    n_epochs=10,
-    batch_size=521,
+    n_epochs=2,
+    batch_size=32,
     shuffle=False,
 )

mkdocs/mkdocs.yml

@@ -56,6 +56,9 @@ nav:
         - 16_Self-Supervised Pre-Training pt 1: examples/16_Self_Supervised_Pretraning_pt1.ipynb
         - 16_Self-Supervised Pre-Training pt 2: examples/16_Self_Supervised_Pretraning_pt2.ipynb
         - 17_Using_a_huggingface_model: examples/17_Usign_a_hugging_face_model.ipynb
+        - 18_feature_importance_via_attention_weights: examples/18_feature_importance_via_attention_weights.ipynb
+        - 19_wide_and_deep_for_recsys_pt1: examples/19_wide_and_deep_for_recsys_pt1.ipynb
+        - 19_wide_and_deep_for_recsys_pt2: examples/19_wide_and_deep_for_recsys_pt2.ipynb
     - Contributing: contributing.md
 
 theme:

mkdocs/site/404.html

@@ -739,6 +739,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1012,6 +1018,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="/examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="/examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="/examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/contributing.html

@@ -743,6 +743,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1016,6 +1022,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1095,7 +1143,7 @@
     <nav class="md-footer__inner md-grid" aria-label="Footer" >
       
         
-        <a href="examples/17_Usign_a_hugging_face_model.html" class="md-footer__link md-footer__link--prev" aria-label="Previous: 17_Using_a_huggingface_model" rel="prev">
+        <a href="examples/19_wide_and_deep_for_recsys_pt2.html" class="md-footer__link md-footer__link--prev" aria-label="Previous: 19_wide_and_deep_for_recsys_pt2" rel="prev">
           <div class="md-footer__button md-icon">
             <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11h12Z"/></svg>
           </div>
@@ -1104,7 +1152,7 @@
               <span class="md-footer__direction">
                 Previous
               </span>
-              17_Using_a_huggingface_model
+              19_wide_and_deep_for_recsys_pt2
             </div>
           </div>
         </a>

mkdocs/site/examples/01_Preprocessors_and_utils.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1092,6 +1098,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/02_model_components.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1085,6 +1091,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/03_Binary_Classification_with_Defaults.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1071,6 +1077,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/04_regression_with_images_and_text.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1085,6 +1091,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/05_save_and_load_model_and_artifacts.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1033,6 +1039,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/06_fineTune_and_warmup.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1071,6 +1077,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/07_Custom_Components.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1085,6 +1091,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/08_custom_dataLoader_imbalanced_dataset.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1064,6 +1070,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/09_extracting_embeddings.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1033,6 +1039,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/11_auc_multiclass.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1078,6 +1084,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/13_Model_Uncertainty_prediction.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1092,6 +1098,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/14_bayesian_models.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1071,6 +1077,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/15_DIR-LDS_and_FDS.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1064,6 +1070,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/16_Self_Supervised_Pretraning_pt1.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1080,6 +1086,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/examples/16_Self_Supervised_Pretraning_pt2.html

@@ -750,6 +750,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1073,6 +1079,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/index.md

@@ -3,21 +3,21 @@
   <img width="300" src="docs/figures/widedeep_logo.png">
 </p>
 
-[<img src="https://badge.fury.io/py/pytorch-widedeep.svg" alt="PyPI version">](https://pypi.org/project/pytorch-widedeep/)
-[<img src="https://img.shields.io/badge/python-3.7%20%7C%203.8%20%7C%203.9-blue.svg" alt="Python 3.7 3.8 3.9">](https://pypi.org/project/pytorch-widedeep/)
-[<img src="https://github.com/jrzaurin/pytorch-widedeep/actions/workflows/build.yml/badge.svg" alt="Build Status">](https://github.com/jrzaurin/pytorch-widedeep/actions)
-[<img src="https://readthedocs.org/projects/pytorch-widedeep/badge/?version=latest" alt="Documentation Status">](https://pytorch-widedeep.readthedocs.io/en/latest/?badge=latest)
-[<img src="https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg" alt="codecov">](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
-[<img src="https://img.shields.io/badge/code%20style-black-000000.svg" alt="Code style: black">](https://github.com/psf/black)
-[<img src="https://img.shields.io/badge/Maintained%3F-yes-green.svg" alt="Maintenance">](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
-[<img src="https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat" alt="contributions welcome">](https://github.com/jrzaurin/pytorch-widedeep/issues)
-[<img src="https://img.shields.io/badge/slack-chat-green.svg?logo=slack" alt="Slack">](https://join.slack.com/t/pytorch-widedeep/shared_invite/zt-soss7stf-iXpVuLeKZz8lGTnxxtHtTw)
+[![PyPI version](https://badge.fury.io/py/pytorch-widedeep.svg)](https://pypi.org/project/pytorch-widedeep/)
+[![Python 3.7 3.8 3.9 3.10](https://img.shields.io/badge/python-3.7%20%7C%203.8%20%7C%203.9%20%7C%203.10-blue.svg)](https://pypi.org/project/pytorch-widedeep/)
+[![Build Status](https://github.com/jrzaurin/pytorch-widedeep/actions/workflows/build.yml/badge.svg)](https://github.com/jrzaurin/pytorch-widedeep/actions)
+[![Documentation Status](https://readthedocs.org/projects/pytorch-widedeep/badge/?version=latest)](https://pytorch-widedeep.readthedocs.io/en/latest/?badge=latest)
+[![codecov](https://codecov.io/gh/jrzaurin/pytorch-widedeep/branch/master/graph/badge.svg)](https://codecov.io/gh/jrzaurin/pytorch-widedeep)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Maintenance](https://img.shields.io/badge/Maintained%3F-yes-green.svg)](https://github.com/jrzaurin/pytorch-widedeep/graphs/commit-activity)
+[![contributions welcome](https://img.shields.io/badge/contributions-welcome-brightgreen.svg?style=flat)](https://github.com/jrzaurin/pytorch-widedeep/issues)
+[![Slack](https://img.shields.io/badge/slack-chat-green.svg?logo=slack)](https://join.slack.com/t/pytorch-widedeep/shared_invite/zt-soss7stf-iXpVuLeKZz8lGTnxxtHtTw)
+[![DOI](https://joss.theoj.org/papers/10.21105/joss.05027/status.svg)](https://doi.org/10.21105/joss.05027)
 
 # **pytorch-widedeep**
 
 A flexible package for multimodal-deep-learning to combine tabular data with
-text and images using Wide and Deep models (or just "Deep" models) in
-Pytorch
+text and images using Wide and Deep models in Pytorch
 
 **Documentation:** [https://pytorch-widedeep.readthedocs.io](https://pytorch-widedeep.readthedocs.io/en/latest/index.html)
 
@@ -33,6 +33,11 @@ The content of this document is organized as follows:
     - [Introduction](#introduction)
     - [The ``deeptabular`` component](#the-deeptabular-component)
     - [Acknowledgments](#acknowledgments)
+    - [License](#license)
+    - [Cite](#cite)
+        - [BibTex](#bibtex)
+        - [APA](#apa)
+
 
 ### Introduction
 
@@ -131,6 +136,8 @@ The ``Tabformer`` family, i.e. Transformers for Tabular data:
 
 6. **TabTransformer**: details on the TabTransformer can be found in
 [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://arxiv.org/pdf/2012.06678.pdf).
+Note that this is an 'enhanced' implementation that allows for many options that can be set up via
+the `TabTransformer` params.
 7. **SAINT**: Details on SAINT can be found in
 [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://arxiv.org/abs/2106.01342).
 8. **FT-Transformer**: details on the FT-Transformer can be found in
@@ -159,152 +166,6 @@ encoder-decoder method and constrastive-denoising method. Please, see the
 documentation and the examples for details on this functionality, and all
 other options in the library.
 
-<!-- ###  Installation
-
-Install using pip:
-
-```bash
-pip install pytorch-widedeep
-```
-
-Or install directly from github
-
-```bash
-pip install git+https://github.com/jrzaurin/pytorch-widedeep.git
-```
-
-#### Developer Install
-
-```bash
-# Clone the repository
-git clone https://github.com/jrzaurin/pytorch-widedeep
-cd pytorch-widedeep
-
-# Install in dev mode
-pip install -e .
-```
-
-### Quick start
-
-Binary classification with the [adult
-dataset]([adult](https://www.kaggle.com/wenruliu/adult-income-dataset))
-using `Wide` and `DeepDense` and defaults settings.
-
-Building a wide (linear) and deep model with ``pytorch-widedeep``:
-
-```python
-import numpy as np
-import torch
-from sklearn.model_selection import train_test_split
-
-from pytorch_widedeep import Trainer
-from pytorch_widedeep.preprocessing import WidePreprocessor, TabPreprocessor
-from pytorch_widedeep.models import Wide, TabMlp, WideDeep
-from pytorch_widedeep.metrics import Accuracy
-from pytorch_widedeep.datasets import load_adult
-
-
-df = load_adult(as_frame=True)
-df["income_label"] = (df["income"].apply(lambda x: ">50K" in x)).astype(int)
-df.drop("income", axis=1, inplace=True)
-df_train, df_test = train_test_split(df, test_size=0.2, stratify=df.income_label)
-
-# Define the 'column set up'
-wide_cols = [
-    "education",
-    "relationship",
-    "workclass",
-    "occupation",
-    "native-country",
-    "gender",
-]
-crossed_cols = [("education", "occupation"), ("native-country", "occupation")]
-
-cat_embed_cols = [
-    "workclass",
-    "education",
-    "marital-status",
-    "occupation",
-    "relationship",
-    "race",
-    "gender",
-    "capital-gain",
-    "capital-loss",
-    "native-country",
-]
-continuous_cols = ["age", "hours-per-week"]
-target = "income_label"
-target = df_train[target].values
-
-# prepare the data
-wide_preprocessor = WidePreprocessor(wide_cols=wide_cols, crossed_cols=crossed_cols)
-X_wide = wide_preprocessor.fit_transform(df_train)
-
-tab_preprocessor = TabPreprocessor(
-    cat_embed_cols=cat_embed_cols, continuous_cols=continuous_cols  # type: ignore[arg-type]
-)
-X_tab = tab_preprocessor.fit_transform(df_train)
-
-# build the model
-wide = Wide(input_dim=np.unique(X_wide).shape[0], pred_dim=1)
-tab_mlp = TabMlp(
-    column_idx=tab_preprocessor.column_idx,
-    cat_embed_input=tab_preprocessor.cat_embed_input,
-    continuous_cols=continuous_cols,
-)
-model = WideDeep(wide=wide, deeptabular=tab_mlp)
-
-# train and validate
-trainer = Trainer(model, objective="binary", metrics=[Accuracy])
-trainer.fit(
-    X_wide=X_wide,
-    X_tab=X_tab,
-    target=target,
-    n_epochs=5,
-    batch_size=256,
-)
-
-# predict on test
-X_wide_te = wide_preprocessor.transform(df_test)
-X_tab_te = tab_preprocessor.transform(df_test)
-preds = trainer.predict(X_wide=X_wide_te, X_tab=X_tab_te)
-
-# Save and load
-
-# Option 1: this will also save training history and lr history if the
-# LRHistory callback is used
-trainer.save(path="model_weights", save_state_dict=True)
-
-# Option 2: save as any other torch model
-torch.save(model.state_dict(), "model_weights/wd_model.pt")
-
-# From here in advance, Option 1 or 2 are the same. I assume the user has
-# prepared the data and defined the new model components:
-# 1. Build the model
-model_new = WideDeep(wide=wide, deeptabular=tab_mlp)
-model_new.load_state_dict(torch.load("model_weights/wd_model.pt"))
-
-# 2. Instantiate the trainer
-trainer_new = Trainer(model_new, objective="binary")
-
-# 3. Either start the fit or directly predict
-preds = trainer_new.predict(X_wide=X_wide, X_tab=X_tab)
-```
-
-Of course, one can do **much more**. See the Examples folder, the
-documentation or the companion posts for a better understanding of the content
-of the package and its functionalities.
-
-### Testing
-
-```
-pytest tests
-```
-
-### How to Contribute
-
-Check [CONTRIBUTING](https://github.com/jrzaurin/pytorch-widedeep/CONTRIBUTING.MD) page.
- -->
 ### Acknowledgments
 
 This library takes from a series of other libraries, so I think it is just
@@ -325,3 +186,37 @@ The `ImageProcessor` class in this library uses code from the fantastic [Deep
 Learning for Computer
 Vision](https://www.pyimagesearch.com/deep-learning-computer-vision-python-book/)
 (DL4CV) book by Adrian Rosebrock.
+
+### License
+
+This work is dual-licensed under Apache 2.0 and MIT (or any later version).
+You can choose between one of them if you use this work.
+
+`SPDX-License-Identifier: Apache-2.0 AND MIT`
+
+### Cite
+
+#### BibTex
+
+```
+@article{Zaurin_pytorch-widedeep_A_flexible_2023,
+author = {Zaurin, Javier Rodriguez and Mulinka, Pavol},
+doi = {10.21105/joss.05027},
+journal = {Journal of Open Source Software},
+month = jun,
+number = {86},
+pages = {5027},
+title = {{pytorch-widedeep: A flexible package for multimodal deep learning}},
+url = {https://joss.theoj.org/papers/10.21105/joss.05027},
+volume = {8},
+year = {2023}
+}
+```
+
+#### APA
+
+```
+Zaurin, J. R., & Mulinka, P. (2023). pytorch-widedeep: A flexible package for
+multimodal deep learning. Journal of Open Source Software, 8(86), 5027.
+https://doi.org/10.21105/joss.05027
+```

mkdocs/site/installation.html

@@ -789,6 +789,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1062,6 +1068,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1121,10 +1169,10 @@ pip<span class="w"> </span>install<span class="w"> </span>-e<span class="w"> </s
 </code></pre></div>
 <h2 id="dependencies">Dependencies<a class="headerlink" href="#dependencies" title="Permanent link">&para;</a></h2>
 <ul>
-<li>pandas</li>
-<li>numpy</li>
-<li>scipy</li>
-<li>scikit-learn</li>
+<li>pandas&gt;=1.3.5</li>
+<li>numpy&gt;=1.21.6</li>
+<li>scipy&gt;=1.7.3</li>
+<li>scikit-learn&gt;=1.0.2</li>
 <li>gensim</li>
 <li>spacy</li>
 <li>opencv-contrib-python</li>
@@ -1135,6 +1183,8 @@ pip<span class="w"> </span>install<span class="w"> </span>-e<span class="w"> </s
 <li>einops</li>
 <li>wrapt</li>
 <li>torchmetrics</li>
+<li>pyarrow</li>
+<li>fastparquet&gt;=0.8.1</li>
 </ul>
 
 

mkdocs/site/installation.md

@@ -27,10 +27,10 @@ pip install -e .
 
 ## Dependencies
 
-* pandas
-* numpy
-* scipy
-* scikit-learn
+* pandas>=1.3.5
+* numpy>=1.21.6
+* scipy>=1.7.3
+* scikit-learn>=1.0.2
 * gensim
 * spacy
 * opencv-contrib-python
@@ -41,3 +41,5 @@ pip install -e .
 * einops
 * wrapt
 * torchmetrics
+* pyarrow
+* fastparquet>=0.8.1
\ No newline at end of file

mkdocs/site/pytorch-widedeep/bayesian_models.html

@@ -798,6 +798,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1071,6 +1077,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/pytorch-widedeep/bayesian_trainer.html

@@ -791,6 +791,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1064,6 +1070,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/pytorch-widedeep/callbacks.html

@@ -805,6 +805,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1078,6 +1084,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1174,9 +1222,9 @@ of the <code>Trainer</code>.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/callbacks.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">267</span>
-<span class="normal">268</span>
-<span class="normal">269</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n_epochs</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">268</span>
+<span class="normal">269</span>
+<span class="normal">270</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n_epochs</span><span class="p">:</span> <span class="nb">int</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">LRHistory</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">n_epochs</span> <span class="o">=</span> <span class="n">n_epochs</span>
 </code></pre></div></td></tr></table></div>
@@ -1214,6 +1262,7 @@ of the <code>Trainer</code>.</p>
 <div class="highlight"><pre><span></span><code><span class="n">ModelCheckpoint</span><span class="p">(</span>
     <span class="n">filepath</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
     <span class="n">monitor</span><span class="o">=</span><span class="s2">&quot;val_loss&quot;</span><span class="p">,</span>
+    <span class="n">min_delta</span><span class="o">=</span><span class="mf">0.0</span><span class="p">,</span>
     <span class="n">verbose</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
     <span class="n">save_best_only</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
     <span class="n">mode</span><span class="o">=</span><span class="s2">&quot;auto&quot;</span><span class="p">,</span>
@@ -1250,6 +1299,13 @@ class just report best metric and best_epoch.</p>
             (<code>str</code>)
         – <p>quantity to monitor. Typically <em>'val_loss'</em> or metric name
 (e.g. <em>'val_acc'</em>)</p>
+      </li>
+      <li class="field-body">
+        <b>min_delta</b>
+            (<code>float</code>)
+        – <p>minimum change in the monitored quantity to qualify as an
+improvement, i.e. an absolute change of less than min_delta, will
+count as no improvement.</p>
       </li>
       <li class="field-body">
         <b>verbose</b>
@@ -1323,12 +1379,7 @@ the repo or the Examples section in this documentation for details</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/callbacks.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">395</span>
-<span class="normal">396</span>
-<span class="normal">397</span>
-<span class="normal">398</span>
-<span class="normal">399</span>
-<span class="normal">400</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">400</span>
 <span class="normal">401</span>
 <span class="normal">402</span>
 <span class="normal">403</span>
@@ -1378,10 +1429,23 @@ the repo or the Examples section in this documentation for details</p>
 <span class="normal">447</span>
 <span class="normal">448</span>
 <span class="normal">449</span>
-<span class="normal">450</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
+<span class="normal">450</span>
+<span class="normal">451</span>
+<span class="normal">452</span>
+<span class="normal">453</span>
+<span class="normal">454</span>
+<span class="normal">455</span>
+<span class="normal">456</span>
+<span class="normal">457</span>
+<span class="normal">458</span>
+<span class="normal">459</span>
+<span class="normal">460</span>
+<span class="normal">461</span>
+<span class="normal">462</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span>
     <span class="n">filepath</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
     <span class="n">monitor</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;val_loss&quot;</span><span class="p">,</span>
+    <span class="n">min_delta</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>
     <span class="n">verbose</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span>
     <span class="n">save_best_only</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
     <span class="n">mode</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;auto&quot;</span><span class="p">,</span>
@@ -1392,6 +1456,7 @@ the repo or the Examples section in this documentation for details</p>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">filepath</span> <span class="o">=</span> <span class="n">filepath</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">monitor</span> <span class="o">=</span> <span class="n">monitor</span>
+    <span class="bp">self</span><span class="o">.</span><span class="n">min_delta</span> <span class="o">=</span> <span class="n">min_delta</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">verbose</span> <span class="o">=</span> <span class="n">verbose</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">save_best_only</span> <span class="o">=</span> <span class="n">save_best_only</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">mode</span> <span class="o">=</span> <span class="n">mode</span>
@@ -1434,6 +1499,11 @@ the repo or the Examples section in this documentation for details</p>
         <span class="k">else</span><span class="p">:</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">monitor_op</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">less</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">best</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">Inf</span>
+
+    <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">monitor_op</span> <span class="o">==</span> <span class="n">np</span><span class="o">.</span><span class="n">greater</span><span class="p">:</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">min_delta</span> <span class="o">*=</span> <span class="mi">1</span>
+    <span class="k">else</span><span class="p">:</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">min_delta</span> <span class="o">*=</span> <span class="o">-</span><span class="mi">1</span>
 </code></pre></div></td></tr></table></div>
           </details>
 
@@ -1568,7 +1638,8 @@ obtained at the last step of training are used.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/callbacks.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">593</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">592</span>
+<span class="normal">593</span>
 <span class="normal">594</span>
 <span class="normal">595</span>
 <span class="normal">596</span>
@@ -1612,8 +1683,7 @@ obtained at the last step of training are used.</p>
 <span class="normal">634</span>
 <span class="normal">635</span>
 <span class="normal">636</span>
-<span class="normal">637</span>
-<span class="normal">638</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
+<span class="normal">637</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span>
     <span class="n">monitor</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;val_loss&quot;</span><span class="p">,</span>
     <span class="n">min_delta</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.0</span><span class="p">,</span>

mkdocs/site/pytorch-widedeep/dataloaders.html

@@ -791,6 +791,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1064,6 +1070,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1190,12 +1238,14 @@ minority \space class \space count \times number \space of \space classes \times
 <span class="normal">93</span>
 <span class="normal">94</span>
 <span class="normal">95</span>
-<span class="normal">96</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
+<span class="normal">96</span>
+<span class="normal">97</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span> <span class="n">dataset</span><span class="p">:</span> <span class="n">WideDeepDataset</span><span class="p">,</span> <span class="n">batch_size</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">num_workers</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span>
 <span class="p">):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">with_lds</span> <span class="o">=</span> <span class="n">dataset</span><span class="o">.</span><span class="n">with_lds</span>
     <span class="k">if</span> <span class="s2">&quot;oversample_mul&quot;</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span>
         <span class="n">oversample_mul</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;oversample_mul&quot;</span><span class="p">]</span>
+        <span class="k">del</span> <span class="n">kwargs</span><span class="p">[</span><span class="s2">&quot;oversample_mul&quot;</span><span class="p">]</span>
     <span class="k">else</span><span class="p">:</span>
         <span class="n">oversample_mul</span> <span class="o">=</span> <span class="mi">1</span>
     <span class="n">weights</span><span class="p">,</span> <span class="n">minor_cls_cnt</span><span class="p">,</span> <span class="n">num_clss</span> <span class="o">=</span> <span class="n">get_class_weights</span><span class="p">(</span><span class="n">dataset</span><span class="p">)</span>

mkdocs/site/pytorch-widedeep/losses.html

@@ -903,6 +903,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1176,6 +1182,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -3851,9 +3899,7 @@ reduction: str, default = "mean"
 <span class="normal">823</span>
 <span class="normal">824</span>
 <span class="normal">825</span>
-<span class="normal">826</span>
-<span class="normal">827</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">temperature</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span> <span class="n">reduction</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;mean&quot;</span><span class="p">):</span>
-
+<span class="normal">826</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">temperature</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">0.1</span><span class="p">,</span> <span class="n">reduction</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;mean&quot;</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">InfoNCELoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">temperature</span> <span class="o">=</span> <span class="n">temperature</span>
@@ -3909,7 +3955,8 @@ for Tabular Data via Row Attention and Contrastive Pre-Training'.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/losses.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">829</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">828</span>
+<span class="normal">829</span>
 <span class="normal">830</span>
 <span class="normal">831</span>
 <span class="normal">832</span>
@@ -3939,8 +3986,7 @@ for Tabular Data via Row Attention and Contrastive Pre-Training'.</p>
 <span class="normal">856</span>
 <span class="normal">857</span>
 <span class="normal">858</span>
-<span class="normal">859</span>
-<span class="normal">860</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">g_projs</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Tensor</span><span class="p">:</span>
+<span class="normal">859</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">g_projs</span><span class="p">:</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">Tensor</span><span class="p">:</span>
 <span class="w">    </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Parameters</span>
 <span class="sd">    ----------</span>
@@ -4026,14 +4072,14 @@ reduction: str, default = "mean"
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/losses.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">887</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">886</span>
+<span class="normal">887</span>
 <span class="normal">888</span>
 <span class="normal">889</span>
 <span class="normal">890</span>
 <span class="normal">891</span>
 <span class="normal">892</span>
-<span class="normal">893</span>
-<span class="normal">894</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
+<span class="normal">893</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span> <span class="n">lambda_cat</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> <span class="n">lambda_cont</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1.0</span><span class="p">,</span> <span class="n">reduction</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s2">&quot;mean&quot;</span>
 <span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">DenoisingLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
@@ -4100,7 +4146,8 @@ categorical feature</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/losses.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">896</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">895</span>
+<span class="normal">896</span>
 <span class="normal">897</span>
 <span class="normal">898</span>
 <span class="normal">899</span>
@@ -4141,8 +4188,7 @@ categorical feature</p>
 <span class="normal">934</span>
 <span class="normal">935</span>
 <span class="normal">936</span>
-<span class="normal">937</span>
-<span class="normal">938</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span>
+<span class="normal">937</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span>
     <span class="n">x_cat_and_cat_</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span>
         <span class="n">Union</span><span class="p">[</span><span class="n">List</span><span class="p">[</span><span class="n">Tuple</span><span class="p">[</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">]],</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">Tensor</span><span class="p">,</span> <span class="n">Tensor</span><span class="p">]]</span>
@@ -4232,9 +4278,9 @@ Interpretable Tabular Learning</a>.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/losses.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">996</span>
-<span class="normal">997</span>
-<span class="normal">998</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-9</span><span class="p">):</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">993</span>
+<span class="normal">994</span>
+<span class="normal">995</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">eps</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">1e-9</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">EncoderDecoderLoss</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">eps</span> <span class="o">=</span> <span class="n">eps</span>
 </code></pre></div></td></tr></table></div>
@@ -4299,7 +4345,10 @@ loss, is based on those features.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/losses.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1000</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"> 997</span>
+<span class="normal"> 998</span>
+<span class="normal"> 999</span>
+<span class="normal">1000</span>
 <span class="normal">1001</span>
 <span class="normal">1002</span>
 <span class="normal">1003</span>
@@ -4335,10 +4384,7 @@ loss, is based on those features.</p>
 <span class="normal">1033</span>
 <span class="normal">1034</span>
 <span class="normal">1035</span>
-<span class="normal">1036</span>
-<span class="normal">1037</span>
-<span class="normal">1038</span>
-<span class="normal">1039</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x_true</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">x_pred</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">mask</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Tensor</span><span class="p">:</span>
+<span class="normal">1036</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">forward</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x_true</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">x_pred</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">,</span> <span class="n">mask</span><span class="p">:</span> <span class="n">Tensor</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Tensor</span><span class="p">:</span>
 <span class="w">    </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Parameters</span>
 <span class="sd">    ----------</span>

mkdocs/site/pytorch-widedeep/metrics.html

@@ -826,6 +826,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1099,6 +1105,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1217,13 +1265,13 @@ multiclass problems</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">76</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">75</span>
+<span class="normal">76</span>
 <span class="normal">77</span>
 <span class="normal">78</span>
 <span class="normal">79</span>
 <span class="normal">80</span>
-<span class="normal">81</span>
-<span class="normal">82</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">):</span>
+<span class="normal">81</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">top_k</span><span class="p">:</span> <span class="nb">int</span> <span class="o">=</span> <span class="mi">1</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">Accuracy</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">top_k</span> <span class="o">=</span> <span class="n">top_k</span>
@@ -1263,12 +1311,12 @@ multiclass problems</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">84</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">83</span>
+<span class="normal">84</span>
 <span class="normal">85</span>
 <span class="normal">86</span>
 <span class="normal">87</span>
-<span class="normal">88</span>
-<span class="normal">89</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">88</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets counters to 0</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -1338,14 +1386,14 @@ precision for each label, and finds their unweighted mean.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">135</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">134</span>
+<span class="normal">135</span>
 <span class="normal">136</span>
 <span class="normal">137</span>
 <span class="normal">138</span>
 <span class="normal">139</span>
 <span class="normal">140</span>
-<span class="normal">141</span>
-<span class="normal">142</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
+<span class="normal">141</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">Precision</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">average</span> <span class="o">=</span> <span class="n">average</span>
@@ -1386,12 +1434,12 @@ precision for each label, and finds their unweighted mean.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">144</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">143</span>
+<span class="normal">144</span>
 <span class="normal">145</span>
 <span class="normal">146</span>
 <span class="normal">147</span>
-<span class="normal">148</span>
-<span class="normal">149</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">148</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets counters to 0</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -1461,14 +1509,14 @@ for each label, and finds their unweighted mean.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">201</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">200</span>
+<span class="normal">201</span>
 <span class="normal">202</span>
 <span class="normal">203</span>
 <span class="normal">204</span>
 <span class="normal">205</span>
 <span class="normal">206</span>
-<span class="normal">207</span>
-<span class="normal">208</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
+<span class="normal">207</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">Recall</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">average</span> <span class="o">=</span> <span class="n">average</span>
@@ -1509,12 +1557,12 @@ for each label, and finds their unweighted mean.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">210</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">209</span>
+<span class="normal">210</span>
 <span class="normal">211</span>
 <span class="normal">212</span>
 <span class="normal">213</span>
-<span class="normal">214</span>
-<span class="normal">215</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">214</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets counters to 0</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -1592,15 +1640,15 @@ for each label, and find their unweighted mean.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">273</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">272</span>
+<span class="normal">273</span>
 <span class="normal">274</span>
 <span class="normal">275</span>
 <span class="normal">276</span>
 <span class="normal">277</span>
 <span class="normal">278</span>
 <span class="normal">279</span>
-<span class="normal">280</span>
-<span class="normal">281</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
+<span class="normal">280</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">beta</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">FBetaScore</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">beta</span> <span class="o">=</span> <span class="n">beta</span>
@@ -1642,12 +1690,12 @@ for each label, and find their unweighted mean.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">283</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">282</span>
+<span class="normal">283</span>
 <span class="normal">284</span>
 <span class="normal">285</span>
 <span class="normal">286</span>
-<span class="normal">287</span>
-<span class="normal">288</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">287</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets precision and recall</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -1717,12 +1765,12 @@ each label, and find their unweighted mean.</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">332</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">330</span>
+<span class="normal">331</span>
+<span class="normal">332</span>
 <span class="normal">333</span>
 <span class="normal">334</span>
-<span class="normal">335</span>
-<span class="normal">336</span>
-<span class="normal">337</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
+<span class="normal">335</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">average</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">):</span>
     <span class="nb">super</span><span class="p">(</span><span class="n">F1Score</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span>
 
     <span class="bp">self</span><span class="o">.</span><span class="n">average</span> <span class="o">=</span> <span class="n">average</span>
@@ -1761,11 +1809,11 @@ each label, and find their unweighted mean.</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">339</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">337</span>
+<span class="normal">338</span>
+<span class="normal">339</span>
 <span class="normal">340</span>
-<span class="normal">341</span>
-<span class="normal">342</span>
-<span class="normal">343</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">341</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets counters to 0</span>
 <span class="sd">    &quot;&quot;&quot;</span>
@@ -1824,13 +1872,13 @@ R^2 = 1 - \frac{\sum_{j=1}^n(y_j - \hat{y_j})^2}{\sum_{j=1}^n(y_j - \bar{y})^2}
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">374</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">372</span>
+<span class="normal">373</span>
+<span class="normal">374</span>
 <span class="normal">375</span>
 <span class="normal">376</span>
 <span class="normal">377</span>
-<span class="normal">378</span>
-<span class="normal">379</span>
-<span class="normal">380</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">378</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">numerator</span> <span class="o">=</span> <span class="mi">0</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">denominator</span> <span class="o">=</span> <span class="mi">0</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">num_examples</span> <span class="o">=</span> <span class="mi">0</span>
@@ -1870,14 +1918,14 @@ R^2 = 1 - \frac{\sum_{j=1}^n(y_j - \hat{y_j})^2}{\sum_{j=1}^n(y_j - \bar{y})^2}
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/metrics.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">382</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">380</span>
+<span class="normal">381</span>
+<span class="normal">382</span>
 <span class="normal">383</span>
 <span class="normal">384</span>
 <span class="normal">385</span>
 <span class="normal">386</span>
-<span class="normal">387</span>
-<span class="normal">388</span>
-<span class="normal">389</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="normal">387</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">reset</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    resets counters to 0</span>
 <span class="sd">    &quot;&quot;&quot;</span>

mkdocs/site/pytorch-widedeep/model_components.md

@@ -112,6 +112,12 @@ self-supervised pre-training with tabular data.
             - "!^_"  # exclude all members starting with _
             - "!^forward$"
 
+::: pytorch_widedeep.models.text.basic_transformer.Transformer
+    selection:
+        filters:
+            - "!^_"  # exclude all members starting with _
+            - "!^forward$"
+
 ::: pytorch_widedeep.models.image.vision.Vision
     selection:
         filters:

mkdocs/site/pytorch-widedeep/preprocessing.md

@@ -8,6 +8,8 @@ model component: ``wide``, ``deeptabular``, ``deepimage`` and ``deeptext``.
 
 ::: pytorch_widedeep.preprocessing.tab_preprocessor.TabPreprocessor
 
+::: pytorch_widedeep.preprocessing.tab_preprocessor.Quantizer
+
 ::: pytorch_widedeep.preprocessing.text_preprocessor.TextPreprocessor
 
 ::: pytorch_widedeep.preprocessing.image_preprocessor.ImagePreprocessor

mkdocs/site/pytorch-widedeep/self_supervised_pretraining.html

@@ -798,6 +798,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1071,6 +1077,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1620,7 +1668,8 @@ model's state dictionary</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/self_supervised_training/encoder_decoder_trainer.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">215</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">214</span>
+<span class="normal">215</span>
 <span class="normal">216</span>
 <span class="normal">217</span>
 <span class="normal">218</span>
@@ -1657,8 +1706,7 @@ model's state dictionary</p>
 <span class="normal">249</span>
 <span class="normal">250</span>
 <span class="normal">251</span>
-<span class="normal">252</span>
-<span class="normal">253</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span>
+<span class="normal">252</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span>
     <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">save_state_dict</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>
@@ -2276,7 +2324,8 @@ model's state dictionary</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/self_supervised_training/contrastive_denoising_trainer.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">263</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">262</span>
+<span class="normal">263</span>
 <span class="normal">264</span>
 <span class="normal">265</span>
 <span class="normal">266</span>
@@ -2313,8 +2362,7 @@ model's state dictionary</p>
 <span class="normal">297</span>
 <span class="normal">298</span>
 <span class="normal">299</span>
-<span class="normal">300</span>
-<span class="normal">301</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span>
+<span class="normal">300</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span>
     <span class="bp">self</span><span class="p">,</span>
     <span class="n">path</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
     <span class="n">save_state_dict</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">False</span><span class="p">,</span>

mkdocs/site/pytorch-widedeep/tab2vec.html

@@ -791,6 +791,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1064,6 +1070,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1550,7 +1598,7 @@ same applies to dataframes in case we choose to set
 <span class="sd">    &quot;&quot;&quot;</span>
 
     <span class="n">X_tab</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">tab_preprocessor</span><span class="o">.</span><span class="n">transform</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
-    <span class="n">X</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">X_tab</span><span class="p">)</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span>
+    <span class="n">X</span> <span class="o">=</span> <span class="n">torch</span><span class="o">.</span><span class="n">from_numpy</span><span class="p">(</span><span class="n">X_tab</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="s2">&quot;float&quot;</span><span class="p">))</span><span class="o">.</span><span class="n">to</span><span class="p">(</span><span class="n">device</span><span class="p">)</span>
 
     <span class="k">with</span> <span class="n">torch</span><span class="o">.</span><span class="n">no_grad</span><span class="p">():</span>
         <span class="n">x_cat</span><span class="p">,</span> <span class="n">x_cont</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">vectorizer</span><span class="p">(</span><span class="n">X</span><span class="p">)</span>  <span class="c1"># type: ignore[operator]</span>

mkdocs/site/pytorch-widedeep/utils/deeptabular_utils.html

@@ -793,6 +793,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1066,6 +1072,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/pytorch-widedeep/utils/fastai_transforms.html

@@ -800,6 +800,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1073,6 +1079,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>
@@ -1478,9 +1526,9 @@ their corresponding index</p>
 
           <details class="quote">
             <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">357</span>
-<span class="normal">358</span>
-<span class="normal">359</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">itos</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
+            <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">358</span>
+<span class="normal">359</span>
+<span class="normal">360</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">itos</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">str</span><span class="p">]):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">itos</span> <span class="o">=</span> <span class="n">itos</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">stoi</span> <span class="o">=</span> <span class="n">defaultdict</span><span class="p">(</span><span class="nb">int</span><span class="p">,</span> <span class="p">{</span><span class="n">v</span><span class="p">:</span> <span class="n">k</span> <span class="k">for</span> <span class="n">k</span><span class="p">,</span> <span class="n">v</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">itos</span><span class="p">)})</span>
 </code></pre></div></td></tr></table></div>
@@ -1524,15 +1572,15 @@ their corresponding index</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">361</span>
-<span class="normal">362</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">362</span>
 <span class="normal">363</span>
 <span class="normal">364</span>
 <span class="normal">365</span>
 <span class="normal">366</span>
 <span class="normal">367</span>
 <span class="normal">368</span>
-<span class="normal">369</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">numericalize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">t</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]:</span>
+<span class="normal">369</span>
+<span class="normal">370</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">numericalize</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">t</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">str</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">int</span><span class="p">]:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Convert a list of tokens ``t`` to their ids.</span>
 
 <span class="sd">    Returns</span>
@@ -1573,15 +1621,15 @@ their corresponding index</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">371</span>
-<span class="normal">372</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">372</span>
 <span class="normal">373</span>
 <span class="normal">374</span>
 <span class="normal">375</span>
 <span class="normal">376</span>
 <span class="normal">377</span>
 <span class="normal">378</span>
-<span class="normal">379</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">textify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">nums</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">sep</span><span class="o">=</span><span class="s2">&quot; &quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
+<span class="normal">379</span>
+<span class="normal">380</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">textify</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">nums</span><span class="p">:</span> <span class="n">Collection</span><span class="p">[</span><span class="nb">int</span><span class="p">],</span> <span class="n">sep</span><span class="o">=</span><span class="s2">&quot; &quot;</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">List</span><span class="p">[</span><span class="nb">str</span><span class="p">]:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Convert a list of ``nums`` (or indexes) to their tokens.</span>
 
 <span class="sd">    Returns</span>
@@ -1614,9 +1662,9 @@ their corresponding index</p>
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">388</span>
-<span class="normal">389</span>
-<span class="normal">390</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">389</span>
+<span class="normal">390</span>
+<span class="normal">391</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="k">def</span> <span class="nf">save</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Save the  attribute ``self.itos`` in ``path``&quot;&quot;&quot;</span>
     <span class="n">pickle</span><span class="o">.</span><span class="n">dump</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">itos</span><span class="p">,</span> <span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s2">&quot;wb&quot;</span><span class="p">))</span>
 </code></pre></div></td></tr></table></div>
@@ -1638,7 +1686,7 @@ their corresponding index</p>
   </span>
 
 <a href="#pytorch_widedeep.utils.fastai_transforms.Vocab.create" class="headerlink" title="Permanent link">&para;</a></h3>
-<div class="highlight"><pre><span></span><code><span class="n">create</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="n">max_vocab</span><span class="p">,</span> <span class="n">min_freq</span><span class="p">)</span>
+<div class="highlight"><pre><span></span><code><span class="n">create</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="n">max_vocab</span><span class="p">,</span> <span class="n">min_freq</span><span class="p">,</span> <span class="n">pad_idx</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span>
 </code></pre></div>
 
   <div class="doc doc-contents ">
@@ -1660,10 +1708,11 @@ strings (e.g. list of tokenized sentences)</p>
         – <p>maximum vocabulary size</p>
       </li>
       <li class="field-body">
-        <b>min_freq</b>
-            (<code>int</code>)
-        – <p>minimum frequency that a token has to appear to be part of the
-vocabulary</p>
+        <b>pad_idx</b>
+            (<code><span title="pytorch_widedeep.wdtypes.Optional">Optional</span>[int]</code>)
+        – <p>padding index. If <code>None</code>, Fastai's Tokenizer leaves the 0 index
+for the unknown token (<em>'xxunk'</em>) and defaults to 1 for the padding
+token (<em>'xxpad'</em>).</p>
       </li>
   </ul>
 
@@ -1692,8 +1741,7 @@ classification/Regression tasks. Please see the <a href="https://docs.fast.ai/te
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">392</span>
-<span class="normal">393</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">393</span>
 <span class="normal">394</span>
 <span class="normal">395</span>
 <span class="normal">396</span>
@@ -1741,8 +1789,28 @@ classification/Regression tasks. Please see the <a href="https://docs.fast.ai/te
 <span class="normal">438</span>
 <span class="normal">439</span>
 <span class="normal">440</span>
-<span class="normal">441</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="nd">@classmethod</span>
-<span class="k">def</span> <span class="nf">create</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">tokens</span><span class="p">:</span> <span class="n">Tokens</span><span class="p">,</span> <span class="n">max_vocab</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span> <span class="n">min_freq</span><span class="p">:</span> <span class="nb">int</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;Vocab&quot;</span><span class="p">:</span>
+<span class="normal">441</span>
+<span class="normal">442</span>
+<span class="normal">443</span>
+<span class="normal">444</span>
+<span class="normal">445</span>
+<span class="normal">446</span>
+<span class="normal">447</span>
+<span class="normal">448</span>
+<span class="normal">449</span>
+<span class="normal">450</span>
+<span class="normal">451</span>
+<span class="normal">452</span>
+<span class="normal">453</span>
+<span class="normal">454</span>
+<span class="normal">455</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="nd">@classmethod</span>
+<span class="k">def</span> <span class="nf">create</span><span class="p">(</span>
+    <span class="bp">cls</span><span class="p">,</span>
+    <span class="n">tokens</span><span class="p">:</span> <span class="n">Tokens</span><span class="p">,</span>
+    <span class="n">max_vocab</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
+    <span class="n">min_freq</span><span class="p">:</span> <span class="nb">int</span><span class="p">,</span>
+    <span class="n">pad_idx</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
+<span class="p">)</span> <span class="o">-&gt;</span> <span class="s2">&quot;Vocab&quot;</span><span class="p">:</span>
 <span class="w">    </span><span class="sa">r</span><span class="sd">&quot;&quot;&quot;Create a vocabulary object from a set of tokens.</span>
 
 <span class="sd">    Parameters</span>
@@ -1753,9 +1821,10 @@ classification/Regression tasks. Please see the <a href="https://docs.fast.ai/te
 <span class="sd">        strings (e.g. list of tokenized sentences)</span>
 <span class="sd">    max_vocab: int</span>
 <span class="sd">        maximum vocabulary size</span>
-<span class="sd">    min_freq: int</span>
-<span class="sd">        minimum frequency that a token has to appear to be part of the</span>
-<span class="sd">        vocabulary</span>
+<span class="sd">    pad_idx: int, Optional, default = None</span>
+<span class="sd">        padding index. If `None`, Fastai&#39;s Tokenizer leaves the 0 index</span>
+<span class="sd">        for the unknown token (_&#39;xxunk&#39;_) and defaults to 1 for the padding</span>
+<span class="sd">        token (_&#39;xxpad&#39;_).</span>
 
 <span class="sd">    Examples</span>
 <span class="sd">    --------</span>
@@ -1778,12 +1847,18 @@ classification/Regression tasks. Please see the <a href="https://docs.fast.ai/te
 <span class="sd">    Vocab</span>
 <span class="sd">        An instance of a `Vocab` object</span>
 <span class="sd">    &quot;&quot;&quot;</span>
+
     <span class="n">freq</span> <span class="o">=</span> <span class="n">Counter</span><span class="p">(</span><span class="n">p</span> <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">tokens</span> <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">o</span><span class="p">)</span>
     <span class="n">itos</span> <span class="o">=</span> <span class="p">[</span><span class="n">o</span> <span class="k">for</span> <span class="n">o</span><span class="p">,</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">freq</span><span class="o">.</span><span class="n">most_common</span><span class="p">(</span><span class="n">max_vocab</span><span class="p">)</span> <span class="k">if</span> <span class="n">c</span> <span class="o">&gt;=</span> <span class="n">min_freq</span><span class="p">]</span>
     <span class="k">for</span> <span class="n">o</span> <span class="ow">in</span> <span class="nb">reversed</span><span class="p">(</span><span class="n">defaults</span><span class="o">.</span><span class="n">text_spec_tok</span><span class="p">):</span>
         <span class="k">if</span> <span class="n">o</span> <span class="ow">in</span> <span class="n">itos</span><span class="p">:</span>
             <span class="n">itos</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">o</span><span class="p">)</span>
         <span class="n">itos</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">o</span><span class="p">)</span>
+
+    <span class="k">if</span> <span class="n">pad_idx</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
+        <span class="n">itos</span><span class="o">.</span><span class="n">remove</span><span class="p">(</span><span class="n">PAD</span><span class="p">)</span>
+        <span class="n">itos</span><span class="o">.</span><span class="n">insert</span><span class="p">(</span><span class="n">pad_idx</span><span class="p">,</span> <span class="n">PAD</span><span class="p">)</span>
+
     <span class="n">itos</span> <span class="o">=</span> <span class="n">itos</span><span class="p">[:</span><span class="n">max_vocab</span><span class="p">]</span>
     <span class="k">if</span> <span class="p">(</span>
         <span class="nb">len</span><span class="p">(</span><span class="n">itos</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">max_vocab</span>
@@ -1819,11 +1894,11 @@ classification/Regression tasks. Please see the <a href="https://docs.fast.ai/te
 
       <details class="quote">
         <summary>Source code in <code>pytorch_widedeep/utils/fastai_transforms.py</code></summary>
-        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">443</span>
-<span class="normal">444</span>
-<span class="normal">445</span>
-<span class="normal">446</span>
-<span class="normal">447</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="nd">@classmethod</span>
+        <div class="highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">457</span>
+<span class="normal">458</span>
+<span class="normal">459</span>
+<span class="normal">460</span>
+<span class="normal">461</span></pre></div></td><td class="code"><div><pre><span></span><code><span class="nd">@classmethod</span>
 <span class="k">def</span> <span class="nf">load</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">path</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Load an intance of :obj:`Vocab` contained in ``path``&quot;&quot;&quot;</span>
     <span class="n">itos</span> <span class="o">=</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="nb">open</span><span class="p">(</span><span class="n">path</span><span class="p">,</span> <span class="s2">&quot;rb&quot;</span><span class="p">))</span>

mkdocs/site/pytorch-widedeep/utils/image_utils.html

@@ -800,6 +800,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1073,6 +1079,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/pytorch-widedeep/utils/index.html

@@ -752,6 +752,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1025,6 +1031,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="../../examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>

mkdocs/site/quick_start.html

@@ -758,6 +758,12 @@
           
         
           
+        
+          
+        
+          
+        
+          
         
           
         
@@ -1031,6 +1037,48 @@
 
             
           
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/18_feature_importance_via_attention_weights.html" class="md-nav__link">
+        18_feature_importance_via_attention_weights
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt1.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt1
+      </a>
+    </li>
+  
+
+            
+          
+            
+              
+  
+  
+  
+    <li class="md-nav__item">
+      <a href="examples/19_wide_and_deep_for_recsys_pt2.html" class="md-nav__link">
+        19_wide_and_deep_for_recsys_pt2
+      </a>
+    </li>
+  
+
+            
+          
         </ul>
       </nav>
     </li>