Merge pull request #234 from jrzaurin/ffm

The `rec` module

.github/workflows/build.yml

@@ -24,11 +24,8 @@ jobs:
         python -m pip install black flake8
     - name: Code Style (Black/Flake8)
       run: |
-        # Black code style
         black --check --diff pytorch_widedeep tests examples setup.py
-        # Stop the build if there are Python syntax errors or undefined names
         flake8 . --count --select=E901,E999,F821,F822,F823 --ignore=E266 --show-source --statistics
-        # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
         flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --ignore=E203,E266,E501,E721,E722,F401,F403,F405,F811,W503,C901 --statistics
 
   test:
@@ -47,41 +44,16 @@ jobs:
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
-        python -m pip install pytest-cov codecov faker
+        python -m pip install pytest pytest-cov codecov faker
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-    - name: Test with pytest
+    - name: Test with pytest and generate coverage
       run: |
-        pytest --doctest-modules pytorch_widedeep --cov-report xml --cov-report term --disable-pytest-warnings --cov=pytorch_widedeep tests/
-    - name: Upload coverage
-      uses: actions/upload-artifact@v4
-      with:
-        name: coverage${{ matrix.python-version }}
-        path: .coverage
-
-  finish: 
-    needs: test
-    runs-on: ubuntu-latest
-    if: ${{ github.event_name == 'push' || !github.event.pull_request.draft }}
-    steps:
-    - uses: actions/checkout@v4
-    - name: Set up Python 3.10
-      uses: actions/setup-python@v5
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        python -m pip install coverage
-    - name: Download all artifacts
-      # Downloads coverage1, coverage2, etc.
-      uses: actions/download-artifact@v4
-    - name: Convert coverage
-      run: |
-        coverage combine coverage*/.coverage*
-        coverage report --fail-under=90
-        coverage xml
-    - name: upload coverage to Codecov
+        pytest --doctest-modules pytorch_widedeep --cov=pytorch_widedeep --cov-report=xml --cov-report=term --disable-pytest-warnings tests
+    - name: Upload coverage to Codecov
       uses: codecov/codecov-action@v4
       with:
         token: ${{ secrets.CODECOV_TOKEN }}
-        fail_ci_if_error: true
+        file: ./coverage.xml
+        flags: unittests
+        name: codecov-${{ matrix.python-version }}
+        fail_ci_if_error: true

.isort.cfg

@@ -1,4 +1,4 @@
 [settings]
+profile=black
 multi_line_output=3
-include_trailing_comma=True
 length_sort=1

README.md

@@ -33,6 +33,7 @@ The content of this document is organized as follows:
     - [Introduction](#introduction)
     - [Architectures](#architectures)
     - [The ``deeptabular`` component](#the-deeptabular-component)
+    - [The ``rec`` module](#the-rec-module)
     - [Text and Images](#text-and-images)
     - [Installation](#installation)
       - [Developer Install](#developer-install)
@@ -795,6 +796,28 @@ 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.
 
+### The ``rec`` module
+
+This module was introduced as an extension to the existing components in the
+library, addressing questions and issues related to recommendation systems.
+While still under active development, it currently includes a select number
+of powerful recommendation models.
+
+It's worth noting that this library already supported the implementation of
+various recommendation algorithms using existing components. For example,
+models like Wide and Deep, Two-Tower, or Neural Collaborative Filtering could
+be constructed using the library's core functionalities.
+
+The recommendation algorithms in the `rec` module are:
+
+1. [DeepFM: A Factorization-Machine based Neural Network for CTR Prediction](https://arxiv.org/abs/1703.04247)
+2. (Deep) Field Aware Factorization Machine (FFM): a Deep Learning version of the algorithm presented in [Field-aware Factorization Machines in a Real-world Online Advertising System](https://arxiv.org/abs/1701.04099)
+3. [xDeepFM: Combining Explicit and Implicit Feature Interactions for Recommender Systems](https://arxiv.org/pdf/1803.05170)
+4. [Deep Interest Network for Click-Through Rate Prediction](https://arxiv.org/abs/1706.06978)
+
+These can all be used as the `deeptabular` component in the `WideDeep` model.
+See the examples for more details.
+
 ### Text and Images
 For the text component, `deeptext`, the library offers the following models:
 

VERSION

@@ -1 +1 @@
-1.6.3
+1.6.4

examples/scripts/adult_census.py

@@ -3,19 +3,10 @@
 import pandas as pd
 
 from pytorch_widedeep import Trainer
-from pytorch_widedeep.models import (  # noqa: F401
-    Wide,
-    TabMlp,
-    WideDeep,
-    TabResnet,
-)
+from pytorch_widedeep.models import Wide, TabMlp, WideDeep, TabResnet  # noqa: F401
 from pytorch_widedeep.metrics import Accuracy, Precision
 from pytorch_widedeep.datasets import load_adult
-from pytorch_widedeep.callbacks import (
-    LRHistory,
-    EarlyStopping,
-    ModelCheckpoint,
-)
+from pytorch_widedeep.callbacks import LRHistory, EarlyStopping, ModelCheckpoint
 from pytorch_widedeep.initializers import XavierNormal, KaimingNormal
 from pytorch_widedeep.preprocessing import TabPreprocessor, WidePreprocessor
 

examples/scripts/adult_census_attention_mlp.py

@@ -3,11 +3,7 @@
 import pandas as pd
 
 from pytorch_widedeep import Trainer
-from pytorch_widedeep.models import (
-    WideDeep,
-    SelfAttentionMLP,
-    ContextAttentionMLP,
-)
+from pytorch_widedeep.models import WideDeep, SelfAttentionMLP, ContextAttentionMLP
 from pytorch_widedeep.metrics import Accuracy
 from pytorch_widedeep.datasets import load_adult
 from pytorch_widedeep.preprocessing import TabPreprocessor

examples/scripts/adult_census_cont_den_full_example.py

@@ -8,9 +8,7 @@
 from pytorch_widedeep.metrics import Accuracy
 from pytorch_widedeep.datasets import load_adult
 from pytorch_widedeep.preprocessing import TabPreprocessor
-from pytorch_widedeep.self_supervised_training import (
-    ContrastiveDenoisingTrainer,
-)
+from pytorch_widedeep.self_supervised_training import ContrastiveDenoisingTrainer
 
 use_cuda = torch.cuda.is_available()
 

examples/scripts/adult_census_cont_den_run_all_models.py

@@ -14,9 +14,7 @@
 )
 from pytorch_widedeep.datasets import load_adult
 from pytorch_widedeep.preprocessing import TabPreprocessor
-from pytorch_widedeep.self_supervised_training import (
-    ContrastiveDenoisingTrainer,
-)
+from pytorch_widedeep.self_supervised_training import ContrastiveDenoisingTrainer
 
 use_cuda = torch.cuda.is_available()
 

examples/scripts/adult_census_enc_dec_run_all_models.py

@@ -5,11 +5,7 @@
 from pytorch_widedeep.models import TabMlp as TabMlpEncoder
 from pytorch_widedeep.models import TabNet as TabNetEncoder
 from pytorch_widedeep.models import TabResnet as TabResnetEncoder
-from pytorch_widedeep.models import (
-    TabMlpDecoder,
-    TabNetDecoder,
-    TabResnetDecoder,
-)
+from pytorch_widedeep.models import TabMlpDecoder, TabNetDecoder, TabResnetDecoder
 from pytorch_widedeep.datasets import load_adult
 from pytorch_widedeep.preprocessing import TabPreprocessor
 from pytorch_widedeep.self_supervised_training import EncoderDecoderTrainer

examples/scripts/adult_census_tabnet.py

@@ -6,11 +6,7 @@
 from pytorch_widedeep.models import TabNet, WideDeep
 from pytorch_widedeep.metrics import Accuracy, Precision
 from pytorch_widedeep.datasets import load_adult
-from pytorch_widedeep.callbacks import (
-    LRHistory,
-    EarlyStopping,
-    ModelCheckpoint,
-)
+from pytorch_widedeep.callbacks import LRHistory, EarlyStopping, ModelCheckpoint
 from pytorch_widedeep.preprocessing import TabPreprocessor
 
 use_cuda = torch.cuda.is_available()

examples/scripts/adult_census_transformers.py

@@ -14,11 +14,7 @@
 )
 from pytorch_widedeep.metrics import Accuracy
 from pytorch_widedeep.datasets import load_adult
-from pytorch_widedeep.callbacks import (
-    LRHistory,
-    EarlyStopping,
-    ModelCheckpoint,
-)
+from pytorch_widedeep.callbacks import LRHistory, EarlyStopping, ModelCheckpoint
 from pytorch_widedeep.initializers import XavierNormal, KaimingNormal
 from pytorch_widedeep.preprocessing import TabPreprocessor, WidePreprocessor