versioneer fix

README.md

@@ -42,8 +42,35 @@ However, this graph does not mean to imply the trend goes on forever, as current
 GPU = colab T4 + 15gb mem and colab CPU + 12gb memory
 
 
-
-## Startup Code:
+## Startup Code demonstrating speedup:
+
+    ! pip install cu-cat dirty-cat
+    from time import time
+    from cu_cat._table_vectorizer import TableVectorizer as cu_TableVectorizer
+    from dirty_cat._table_vectorizer import TableVectorizer as dirty_TableVectorizer
+    from sklearn.datasets import fetch_20newsgroups
+    n_samples = 2000  # speed boost improves as n_samples increases, to the limit of gpu mem
+
+    news, _ = fetch_20newsgroups(
+        shuffle=True,
+        random_state=1,
+        remove=("headers", "footers", "quotes"),
+        return_X_y=True,
+    )
+
+    news = news[:n_samples]
+    news=pd.DataFrame(news)
+    table_vec = cu_TableVectorizer()
+    t = time()
+    aa = table_vec.fit_transform((news))
+    ct = time() - t
+    # if deps.dirty_cat:
+    t = time()
+    bb = dirty_TableVectorizer().fit_transform(news)
+    dt = time() - t
+    print(f"cu_cat: {ct:.2f}s, dirty_cat: {dt:.2f}s, speedup: {dt/ct:.2f}x")
+    >>> cu_cat: 58.76s, dirty_cat: 84.54s, speedup: 1.44x
+## Enhanced Code using Graphistry:
 
     # !pip install graphistry[ai] ## future releases will have this by default
     !pip install git+https://github.com/graphistry/pygraphistry.git@dev/depman_gpufeat

cu_cat/__init__.py

@@ -20,9 +20,10 @@
 from ._gap_encoder import GapEncoder  # type: ignore
 from ._table_vectorizer import SuperVectorizer, TableVectorizer
 
-with open(_Path(__file__).parent / "VERSION.txt") as _fh:
-    __version__ = _fh.read().strip()
+from ._version import get_versions
 
+__version__ = get_versions()["version"]
+del get_versions
 
 __all__ = [
     "DatetimeEncoder",

cu_cat/_version.py

@@ -43,8 +43,8 @@ def get_config():
     cfg.VCS = "git"
     cfg.style = "pep440"
     cfg.tag_prefix = ""
-    cfg.parentdir_prefix = "graphistry-"
-    cfg.versionfile_source = "graphistry/_version.py"
+    cfg.parentdir_prefix = "cu_cat-"
+    cfg.versionfile_source = "cu_cat/_version.py"
     cfg.verbose = False
     return cfg
 

docs/source/conf.py

@@ -21,7 +21,7 @@
 # -- Project information -----------------------------------------------------
 
 project = "CU_CAT"
-copyright = "2023, Graphistry, Inc."
+copyright = "2024, Graphistry, Inc."
 author = "Graphistry, Inc."
 
 # The full version, including alpha/beta/rc tags

docs/source/cu_cat.rst

@@ -25,7 +25,7 @@ Table_Vectorizer
 Versioneer
 ==================
 
-.. automodule:: graphistry._version
+.. automodule:: cu_cat._version
     :members:
     :undoc-members:
     :show-inheritance:

docs/source/versioneer.rst

@@ -3,4 +3,4 @@
 .. toctree:: 
    :maxdepth: 2
 
-   graphistry.plugins_types
+   cu_cat.plugins_types

setup.py

@@ -2,7 +2,7 @@
 
 from setuptools import setup, find_packages
 import versioneer
-# # #github
+
 def unique_flatten_dict(d):
   return list(set(sum( d.values(), [] )))
 
@@ -16,9 +16,8 @@ def unique_flatten_dict(d):
   'flake8>=5.0',
   'psutil',
   'build',
-  'versioneer',
-  'dirty-cat',
-#   'cuml', ## cannot test on github actions
+  'dirty-cat',  # only for pytest speed comparison
+#   'cuml', # cannot test on github actions
 #   'cudf',
 #   'cupy'
 ]