Fix #117: Fix fill_na when copy from a column

CHANGELOG.md

@@ -4,6 +4,12 @@
 [Doing] Add support for saving pb file, exporting embeddings
 [Doing] Add support of multi-gpu training
 
+**FuxiCTR v2.3.3, 2024-10-14**
++ [Feature] Add EulerNet and DCNv3 models
++ [Feature] Add support to parquet as input, like csv format
++ [Fix] Add col_name as default args in feature_preprocess ([#105](https://github.com/reczoo/FuxiCTR/issues/105))
++ [Fix] Fix fill_na when copy from a column ([#117](https://github.com/reczoo/FuxiCTR/issues/117))
+
 **FuxiCTR v2.3.2, 2024-07-11**
 + [Feature] Add TransAct model
 + [Feature] Add new feature type `embedding`, supporting [`meta`, `numeric`, `embedding`, `categorical`, `sequence`]

CONTRIBUTORS.md

@@ -1,22 +1,3 @@
-## Contributing to FuxiCTR
-
-Contributions are always welcome. If you are interested in contributing to FuxiCTR, your contributions will likely fall into one of the following two categories:
-
-+ You want to implement a new feature:
-
-  In general, we accept any features that fit the scope of this package. A good starting place is [the project plan page](https://github.com/xue-pai/FuxiCTR/projects) that shows the current milestones. All contributions must go through pull requests and will be reviewed by the committers. **To avoid redudant efforts, please first open a feature request and propose your design if you want to implement a new feature. After discussing with the committers, you could start the implememntation and send out a PR.**
-
-+ You want to fix a bug:
-
-  Feel free to send a pull request for bug fix. Please provide a clear and concise description of what the bug was. If you are unsure about if this is a bug at all or how to fix, post an issue about this.
-
-Once your contribution is accepted and merged, you become a contributor to FuxiCTR. We will put your name in the contributor list.
-
-## Committers
-
-+ Jieming Zhu from Huawei Noah's Ark Lab
-+ Jinyang Liu from The Chinese University of Hong Kong
-
 ## Contributors 🤗
 
 <!-- readme: zhujiem,doubleQ2018,Da-Guo,kyriemao,contributors -start -->
@@ -122,3 +103,23 @@ Once your contribution is accepted and merged, you become a contributor to FuxiC
 	<tbody>
 </table>
 <!-- readme: zhujiem,doubleQ2018,Da-Guo,kyriemao,contributors -end -->
+
+## Committers
+
++ Jieming Zhu, Huawei Noah's Ark Lab
++ Jinyang Liu, The Chinese University of Hong Kong
+
+## How to Contribute
+
+Contributions are always welcome. If you are interested in contributing to FuxiCTR, your contributions will likely fall into one of the following two categories:
+
++ You want to implement a new feature:
+
+  In general, we accept any features that fit the scope of this package. A good starting place is [the project plan page](https://github.com/xue-pai/FuxiCTR/projects) that shows the current milestones. All contributions must go through pull requests and will be reviewed by the committers. **To avoid redudant efforts, please first open a feature request and propose your design if you want to implement a new feature. After discussing with the committers, you could start the implememntation and send out a PR.**
+
++ You want to fix a bug:
+
+  Feel free to send a pull request for bug fix. Please provide a clear and concise description of what the bug was. If you are unsure about if this is a bug at all or how to fix, post an issue about this.
+
+Once your contribution is accepted and merged, you become a contributor to FuxiCTR. We will put your name in the contributor list.
+

README.md

@@ -160,9 +160,3 @@ If you find our code or benchmarks helpful in your research, please cite the fol
 
 + Jieming Zhu, Jinyang Liu, Shuai Yang, Qi Zhang, Xiuqiang He. [Open Benchmarking for Click-Through Rate Prediction](https://arxiv.org/abs/2009.05794). *The 30th ACM International Conference on Information and Knowledge Management (CIKM)*, 2021. [[Bibtex](https://dblp.org/rec/conf/cikm/ZhuLYZH21.html?view=bibtex)]
 + Jieming Zhu, Quanyu Dai, Liangcai Su, Rong Ma, Jinyang Liu, Guohao Cai, Xi Xiao, Rui Zhang. [BARS: Towards Open Benchmarking for Recommender Systems](https://arxiv.org/abs/2205.09626). *The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)*, 2022. [[Bibtex](https://dblp.org/rec/conf/sigir/ZhuDSMLCXZ22.html?view=bibtex)]
-
-## Discussion
-
-Welcome to join our WeChat group for any question and discussion. We also have open positions for internships and full-time jobs. If you are interested in research and practice in recommender systems, please reach out via our WeChat group.
-
-![Scan QR code](https://openbenchmark.github.io/BARS/_images/wechat.jpg)

fuxictr/preprocess/feature_processor.py

@@ -102,9 +102,10 @@ def preprocess(self, ddf):
         all_cols = self.label_cols + self.feature_cols[::-1]
         for col in all_cols:
             name = col["name"]
-            if name in ddf.columns:
-                fill_na = "" if col["dtype"] in ["str", str] else 0
-                fill_na = col.get("fill_na", fill_na)
+            fill_na = col.get("fill_na", 
+                              "" if col["dtype"] in ["str", str] else 0)
+            col_exist = name in ddf.columns
+            if col_exist:
                 ddf = ddf.with_columns(pl.col(name).fill_null(fill_na))
             if col.get("preprocess"):
                 preprocess_args = re.split(r"\(|\)", col["preprocess"])
@@ -118,6 +119,8 @@ def preprocess(self, ddf):
                     .alias(name)
                     .cast(self.dtype_dict[name])
                 )
+            if not col_exist:
+                ddf = ddf.with_columns(pl.col(name).fill_null(fill_na))
         active_cols = [col["name"] for col in all_cols if col.get("active") != False]
         ddf = ddf.select(active_cols)
         return ddf

fuxictr/version.py

@@ -1 +1 @@
-__version__="2.3.2"
+__version__="2.3.3"

setup.py

@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="fuxictr",
-    version="2.3.2",
+    version="2.3.3",
     author="RECZOO",
     author_email="[email protected]",
     description="A configurable, tunable, and reproducible library for CTR prediction",