Fix dataset issue in v2.2.2

reczoo · Apr 19, 2024 · a3a33f1 · a3a33f1
1 parent 95fa81c
commit a3a33f1
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 3 deletions.
diff --git a/fuxictr/preprocess/build_dataset.py b/fuxictr/preprocess/build_dataset.py
@@ -60,13 +60,14 @@ def transform_block(feature_encoder, df_block, filename):
 
 
 def transform(feature_encoder, ddf, filename, block_size=0):
+    ddf = ddf.collect().to_pandas()
     if block_size > 0:
         pool = mp.Pool(mp.cpu_count() // 2)
         block_id = 0
         for idx in range(0, len(ddf), block_size):
             df_block = ddf.iloc[idx:(idx + block_size)]
             pool.apply_async(
-                transform_block, 
+                transform_block,
                 args=(feature_encoder,
                       df_block,
                       '{}/part_{:05d}.npz'.format(filename, block_id))

diff --git a/fuxictr/version.py b/fuxictr/version.py
@@ -1 +1 @@
-__version__="2.2.2"
+__version__="2.2.3"
diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setuptools.setup(
     name="fuxictr",
-    version="2.2.2",
+    version="2.2.3",
     author="RECZOO",
     author_email="[email protected]",
     description="A configurable, tunable, and reproducible library for CTR prediction",