Support Python 3.7 while reverting 3.10 (#37)

* remove walrus operator

* prepare for the new release with 3.7 support

* revert the support for python 3.10 to support 3.7

.github/workflows/build_all_os.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: ['3.8', '3.9', '3.10']
+        python-version: ['3.7', '3.8', '3.9']
     steps:
       - uses: actions/checkout@v2
       - name: Set up Python

README.md

@@ -3,7 +3,7 @@
 [![build](https://github.com/delftdata/valentine/actions/workflows/build.yml/badge.svg)](https://github.com/delftdata/valentine/actions/workflows/build.yml)
 [![codecov](https://codecov.io/gh/delftdata/valentine/branch/master/graph/badge.svg?token=4QR0X315CL)](https://codecov.io/gh/delftdata/valentine)
 [![PyPI version](https://badge.fury.io/py/valentine.svg)](https://badge.fury.io/py/valentine)
-[![Python 3.8+](https://img.shields.io/badge/python-3.8|3.9|3.10-blue.svg)](https://www.python.org/downloads/release/python-380/)
+[![Python 3.7+](https://img.shields.io/badge/python-3.7|3.8|3.9-blue.svg)](https://www.python.org/downloads/release/python-380/)
 
 A python package for capturing potential relationships among columns of different tabular datasets, which are given in the form of pandas DataFrames. Valentine is based on [Valentine: Evaluating Matching Techniques for Dataset Discovery](https://ieeexplore.ieee.org/abstract/document/9458921)
 
@@ -17,7 +17,7 @@ pip install valentine
 
 ## Installation requirements
 
-* Python>=3.8
+* Python>=3.7,<3.10
 
 
 

requirements.txt

@@ -1,5 +1,6 @@
 # algorithms
 numpy==1.21.2
+scipy==1.7.1
 pandas==1.3.4
 nltk==3.6.5
 snakecase==1.0.1

setup.py

@@ -6,18 +6,19 @@
 
 setuptools.setup(
     name='valentine',
-    version='0.1.2',
+    version='0.1.3',
     description='Valentine Matcher',
     license_files=('LICENSE',),
     author='Delft Data',
     author_email='delftdatasystems@gmail.com',
     maintainer='Delft Data',
     maintainer_email='delftdatasystems@gmail.com',
     url='https://delftdata.github.io/valentine/',
-    download_url='https://github.com/delftdata/valentine/archive/refs/tags/v0.1.2.tar.gz',
+    download_url='https://github.com/delftdata/valentine/archive/refs/tags/v0.1.3.tar.gz',
     packages=setuptools.find_packages(exclude=('tests*', 'examples*')),
     install_requires=[
         'numpy>=1.21,<2.0',
+        'scipy>=1.6,<2.0',
         'pandas>=1.3,<1.4',
         'nltk>=3.6,<3.7',
         'snakecase>=1.0,<2.0',
@@ -33,7 +34,7 @@
     ],
     keywords=['matching', 'valentine', 'schema matching', 'dataset discovery', 'coma', 'cupid', 'similarity flooding'],
     include_package_data=True,
-    python_requires='>=3.8',
+    python_requires='>=3.7,<3.10',
     long_description=long_description,
     long_description_content_type='text/markdown'
 )

valentine/algorithms/distribution_based/column_model.py

@@ -108,6 +108,6 @@ def get_global_ranks(column: list, tmp_folder_path: str):
         """
         with open(os.path.join(tmp_folder_path, 'ranks.pkl'), 'rb') as pkl_file:
             global_ranks: dict = pickle.load(pkl_file)
-            ranks = np.array(sorted([global_ranks[dt_x] for x in column
-                                     if (dt_x := convert_data_type(x)) in global_ranks]))
+            ranks = np.array(sorted([global_ranks[convert_data_type(x)] for x in column
+                                     if convert_data_type(x) in global_ranks]))
             return ranks

valentine/algorithms/distribution_based/quantile_histogram.py

@@ -1,4 +1,4 @@
-from statistics import quantiles
+import scipy.stats as ss
 from numpy import ndarray
 import numpy as np
 import math
@@ -73,7 +73,7 @@ def __init__(self,
         self.dist_matrix = self.calc_dist_matrix()
         if reference_hist is None:
             self.add_buckets(ranks.min(initial=math.inf),
-                             [round(q, 3) for q in quantiles(ranks, n=self.quantiles + 1, method='inclusive')])
+                             ss.mstats.mquantiles(ranks, np.array(list(range(1, self.quantiles + 1))) / self.quantiles))
             self.add_values(ranks)
         else:
             self.bucket_boundaries = reference_hist.bucket_boundaries