Feature/update python versions

README.md

@@ -1,7 +1,7 @@
 # PyMASq
 
 <p align="center">
-    <img src="./assets/images/masq_logo_light.svg" width="150px"/>
+    <img src="./assets/images/masq_logo_light.svg" width="150px" alt="MASq Logo"/>
 </p>
 
 ## Python-based Mitigation Application and Assessment (MASq)
@@ -32,9 +32,9 @@ cd pymasq
 ### Installing into a Conda Environment
 
 ```sh
-conda create -n masq python=3.8 -y
+conda create -n masq python=3.10 -y
 conda activate masq
-pip install .
+pip install -e .
 ```
 
 To generate the docs
@@ -44,7 +44,7 @@ python -m pip install -r ./doc-requirements.txt
 ```
 
 <p align="center">
-    <img src="./assets/images/Lincoln_Lab_icon.png" width="150px"/>
+    <img src="./assets/images/Lincoln_Lab_icon.png" width="150px" alt="MIT Lincoln Lab Logo"/>
 </p>
 
 ## Distribution Statement

docs/source/conf.py

@@ -2,7 +2,7 @@
 import sys
 import sphinx_rtd_theme
 
-sys.path.insert(0, os.path.abspath(os.path.join('..','..')))
+sys.path.insert(0, os.path.abspath(os.path.join("..", "..")))
 # Configuration file for the Sphinx documentation builder.
 #
 # This file only contains a selection of the most common options. For a full
@@ -22,12 +22,12 @@
 
 # -- Project information -----------------------------------------------------
 
-project = 'pymasq'
-copyright = '2022, MITLL'
-author = 'MITLL'
+project = "pymasq"
+copyright = "2022, MITLL"
+author = "MITLL"
 
 # The full version, including alpha/beta/rc tags
-release = '1.0'
+release = "1.1"
 
 
 # -- General configuration ---------------------------------------------------
@@ -36,14 +36,14 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.napoleon',  # NumPy & Google style docstring support
+    "sphinx.ext.napoleon",  # NumPy & Google style docstring support
     "sphinx_rtd_theme",
 ]
 
 napoleon_google_docstring = False
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -56,9 +56,9 @@
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]

setup.cfg

@@ -11,27 +11,25 @@ author = Cuyler OBrien, Jaime Pena, Evan Young, Brian Levine, Eric Wybenga
 author_email = [email protected], [email protected], [email protected]
 
 [options]
-python_requires = >= 3.8
+python_requires = >= 3.10
 packages = find:
 package_dir =
        = src
 install_requires =
-       boruta>=0.3
-       bpemb>=0.3.3
-       matplotlib>=3.4.2
-       numpy>=1.19.3
-       pandas>=1.1.3
+       bpemb~=0.3
+       matplotlib~=3.5
+       numpy~=1.26
+       pandas~=1.4
        plotly>=4.11.0
-       scikit-learn>=0.23
-       scipy>=1.5.4
-       statsmodels>=0.12
-       SALib>=1.4.5
-       tensorflow>=2.4.0
-       tpot[dask]>=0.11
+       SALib~=1.4
+       scikit-learn~=1.1
+       scipy~=1.8
+       statsmodels~=0.13
+       tensorflow~=2.9
+       tpot[dask]~=0.11
 tests_require = 
-       pytest>=3.8
-       hypothesis>=4.53.2
-       beartype>=0.5.1
+       beartype>=0.5.1  
+       pytest~=7.4
 
 [options.packages.find]
 where = src
@@ -43,7 +41,7 @@ python_files=test_*.py
 testpaths=tests
 
 [tox:tox]
-envlist = py38, py39, coverage, bandit, owasp-depcheck
+envlist = py3{10,11}, coverage, bandit, owasp-depcheck
 toxworkdir = build/tox
 
 [testenv]
@@ -54,24 +52,24 @@ commands = pytest tests --junitxml={toxworkdir}/xunit-tests-{envname}.xml -o jun
 
 [testenv:coverage]
 usedevelop = true
-basepython = python3.8
+basepython = python3.10
 deps = {[testenv]deps}
        coverage
        pytest-cov
 commands = pytest --cov-report xml:{toxworkdir}/xunit-coverage.xml --cov-config=setup.cfg --cov=pymasq tests -o junit_suite_name=pytest-{envname}
 
 [testenv:localcoverage]
 usedevelop = true
-basepython = python3.8
+basepython = python3.10
 deps = {[testenv]deps}
        coverage
        pytest-cov
 commands = pytest --cov-report term-missing --cov-config=setup.cfg --cov=pymasq tests
 
 [testenv:bandit]
-basepython = python3.8
+basepython = python3.10
 deps = bandit
 commands = bandit -f json -o {toxworkdir}/security-bandit.json -r {envsitepackagesdir}/pymasq
 
 [testenv:owasp-depcheck]
-basepython = python3.8
+basepython = python3.10

src/pymasq/__init__.py

@@ -1,6 +1,6 @@
 from os import path
 
-__version__ = "0.6.5"
+__version__ = "0.6.6"
 
 
 try:

src/pymasq/config.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 from typing import Tuple
-from pymasq import ROOT_DIR
+
+import numpy as np
 
 # Directory where all embeddings and models will be cached
 CACHE_LOCATION: Path = Path("~/.cache/pymasq").expanduser()
@@ -27,6 +28,7 @@
 CLASSIFIER_MODELS: Tuple[str] = ("logreg", "rfclass", "tpotclass")
 
 DEFAULT_LOGISITIC_REGRESSION_SOLVER: str = "saga"
+DEFAULT_MODEL_ITERATIONS: int = 1000
 
 # Byte Pair Encoding default language and dimensionality for vectors
 BPE_LANG: str = "en"
@@ -40,3 +42,5 @@
 
 # Default number of parallel processors, set to -1 for all processors
 DEFAULT_N_JOBS: int = -1
+
+rg = np.random.default_rng(DEFAULT_SEED)

src/pymasq/datasets/__init__.py

@@ -2,7 +2,13 @@
 The :mod:`pymasq.datasets` module includes utilities to load tabular datasets.
 """
 
-from ._base import load_data, load_census, load_loan, load_prestige, load_bank_attrition_rates
+from ._base import (
+    load_data,
+    load_census,
+    load_loan,
+    load_prestige,
+    load_bank_attrition_rates,
+)
 from .data_generator import gen_geom_seq, gen_bin_df, gen_num_df
 from .utils import rand_cat_change
 

src/pymasq/datasets/_base.py

@@ -77,11 +77,12 @@ def load_loan():
     """
     return load_data("loan.csv")
 
+
 def load_bank_attrition_rates():
     """Load and return the Bank Attrition Rates dataset.
 
-    A manager at the bank is disturbed with more and more customers leaving their credit card services. 
-    They would really appreciate if one could predict for them who is gonna get churned so 
+    A manager at the bank is disturbed with more and more customers leaving their credit card services.
+    They would really appreciate if one could predict for them who is gonna get churned so
     they can proactively go to the customer to provide them better services and turn customers' decisions in the opposite direction.
 
     ==============   ==============

src/pymasq/datasets/data_generator.py

@@ -7,7 +7,9 @@
 from .utils import rand_cat_change
 
 from pymasq import BEARTYPE
+from pymasq.config import DEFAULT_SEED
 
+rg = np.random.default_rng(DEFAULT_SEED)
 
 @BEARTYPE
 def gen_geom_seq(start: float = 0.5, n: int = 6, rate: float = 2.0) -> List[float]:
@@ -117,12 +119,12 @@ def gen_num_df(n: int = 1000, seed: int = 1234) -> pd.DataFrame:
 
 
 @BEARTYPE
-def _l_div_sensitive_gen(l: int, n: int) -> List:
+def _l_div_sensitive_gen(l_div: int, n: int) -> List[int]:
     """
     Generates the sensitive variable for generate_l_diverse_table for each equivalence class
     Parameters
     ----------
-    l : int
+    l_div : int
         The specified diversity that the equivalence class needs to be
     n : int
         The size of the equivalence class (i.e. the lenght of the list returned)
@@ -132,17 +134,17 @@ def _l_div_sensitive_gen(l: int, n: int) -> List:
         List of integer values for the sensitive column
     """
 
-    unique_entries = np.random.choice(range(n), l)
+    unique_entries = rg.choice(range(n), l_div)
     while len(unique_entries) != len(set(unique_entries)):
-        unique_entries = np.random.choice(range(n), l)
+        unique_entries = rg.choice(range(n), l_div)
 
-    non_unique = np.random.choice(unique_entries, n - l)
+    non_unique = rg.choice(unique_entries, n - l_div)
     return list(unique_entries) + list(non_unique)
 
 
 @BEARTYPE
 def generate_l_diverse_table(
-    l: Union[int, List[int]],
+    l_div: Union[int, List[int]],
     num_col: int = 5,
     num_q_blocks: int = 5,
     q_block_sizes: Union[int, List[int]] = 5,
@@ -151,7 +153,7 @@ def generate_l_diverse_table(
     Used for testing l-diversity. Creates a data set that is l-diverse for given l.
     Parameters
     ----------
-    l : Union[int, List[int]]
+    l_div : Union[int, List[int]]
         The specified diversity that the data set needs to be TODO: need to expand this to allow float l parameters for entropy
     num_col : int, optional
         The number of columns (in addition to the sensitive column) the data set should have
@@ -178,10 +180,10 @@ def generate_l_diverse_table(
         if isinstance(q_block_sizes, int)
         else q_block_sizes
     )
-    l = [l] * num_q_blocks if not isinstance(l, list) else l
+    l_div: List[int] = [l_div] * num_q_blocks if not isinstance(l_div, list) else l_div
 
     for n in range(num_q_blocks):
-        senn = _l_div_sensitive_gen(l[n], q_block_sizes[n])
+        senn = _l_div_sensitive_gen(l_div[n], q_block_sizes[n])
         col_names["sensitive"] += senn
         for cn in col_names:
             if cn != "sensitive":

src/pymasq/errors/__init__.py

@@ -1,34 +1,34 @@
-
 """
 Expose public exceptions & warnings
 """
 
+
 class InputError(Exception):
-    """ Exception raised for errors in the input value. """
+    """Exception raised for errors in the input value."""
 
 
 class DataTypeError(Exception):
-    """ Exception raised for errors in the data type. """
-    
-    
+    """Exception raised for errors in the data type."""
+
+
 class SumNotEqualToOneError(ValueError):
-    """ Exception for sum of values not equal to 1. """
-    
+    """Exception for sum of values not equal to 1."""
+
 
 class NotInRangeError(ValueError):
-    """ Exception for values not in specified interval. """
+    """Exception for values not in specified interval."""
 
 
 class LessThanZeroError(ValueError):
-    """ Exceptions for values < 0. """
+    """Exceptions for values < 0."""
 
 
 class LessThanOrEqualToZeroError(ValueError):
-    """ Exceptions for values <= 0. """
+    """Exceptions for values <= 0."""
 
 
 class NoMutationAvailableError(ValueError):
-    """ Exception when all mutations have been discarded and not replaced """
+    """Exception when all mutations have been discarded and not replaced"""
 
 
 __all__ = [
@@ -38,5 +38,5 @@ class NoMutationAvailableError(ValueError):
     "NotInRangeError",
     "LessThanZeroError",
     "LessThanOrEqualToZeroError",
-    "NoMutationAvailableError"
-]
+    "NoMutationAvailableError",
+]