change package to src layout; fixed warning messages from changes in …

…pandas

.github/workflows/python-package.yml

@@ -18,7 +18,7 @@ jobs:
       matrix:
         # os: [ubuntu-latest, macOS-latest, windows-latest]
         os: [ubuntu-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11"]
+        python-version: ["3.8", "3.8", "3.9", "3.10", "3.11", "3.12"]
 
     steps:
     - uses: actions/checkout@v1

MANIFEST.in

@@ -1,5 +1,5 @@
 include README.md
 include LICENSE
-include interva/data/*.csv
-include interva/data/*.xls
-include interva/data/*.py
+include src/interva/data/*.csv
+include src/interva/data/*.xls
+include src/interva/data/*.py

pyproject.toml

@@ -1,3 +1,51 @@
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"
+
+[project]
+name = "interva"
+version = "0.0.7"
+authors = [
+    {name = "Sherry Zhao", email = "[email protected]"},
+    {name = "Jason Thomas", email = "[email protected]"},
+]
+maintainers = [
+    {name = "Jason Thomas", email = "[email protected]"},
+]
+description = "Python implementation of the InterVA Algorithm."
+readme = "README.md"
+requires-python = ">=3.8"
+keywords = ["verbal autopsy",]
+license = {text = "GPLv3"}
+classifiers=[
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
+        "Operating System :: OS Independent",
+]
+dependencies = [
+        "pandas",
+        "numpy",
+	"vacheck",
+	"xlrd",
+]
+
+[project.urls]
+"Homepage" = "https://github.com/verbal-autopsy-software/interva"
+"Bug Tracker" = "https://github.com/verbal-autopsy-software/interva/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.setuptools.package-data]
+"interva.data" = ["*.csv"]
+
+[tool.pytest.ini_options]
+addopts = [
+    "--import-mode=importlib",
+    ]
+

setup.py

@@ -1,47 +1,3 @@
-import os
-from codecs import open
-from setuptools import setup, find_namespace_packages
+from setuptools import setup
 
-here = os.path.abspath(os.path.dirname(__file__))
-
-about = {}
-with open(os.path.join(here, "interva", "__version__.py"), "r", "utf-8") as f:
-    exec(f.read(), about)
-
-with open("README.md", "r", "utf-8") as f:
-    readme = f.read()
-
-
-setup(
-    name=about["__title__"],
-    version=about["__version__"],
-    author=about["__author__"],
-    author_email=about["__author_email__"],
-    description=about["__description__"],
-    long_description=readme,
-    long_description_content_type="text/markdown",
-    url=about["__url__"],
-    license=about["__license__"],
-    packages=find_namespace_packages(),
-    include_package_data=True,
-    package_dir={"": "."},
-    package_data={
-        "interva.data": ["*.csv", "*.xls"],
-    },
-    install_requires=[
-        "pandas",
-        "xlrd",
-        "numpy",
-        "vacheck",
-        ],
-    classifiers=[
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-        "Programming Language :: Python :: 3.10",
-        "Programming Language :: Python :: 3.11",
-        "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
-        "Operating System :: OS Independent",
-    ],
-)
+setup()

interva/interva5.py → src/interva/interva5.py

@@ -553,7 +553,7 @@ def run(self) -> None:
                 comcat = "Multiple"
                 comnum = " "
             if nanmax(prob_C) >= 0.5:
-                comcat = prob_C_names[where(prob_C == nanmax(prob_C))[0][0]]
+                comcat = prob_C_names.iloc[where(prob_C == nanmax(prob_C))[0][0]]
                 comnum = round(nanmax(prob_C) * 100)
 
             ID_list[i] = index_current
@@ -827,11 +827,11 @@ def get_csmf(self, top: int = 10,
         dist_cod_sorted.sort_values(ascending=False, inplace=True)
         # show causes with top non-zero values
         show_top = 0
-        while dist_cod_sorted[show_top] > 0 and show_top < top:
+        while dist_cod_sorted.iloc[show_top] > 0 and show_top < top:
             show_top = show_top + 1
         if show_top == top:
-            a = dist_cod_sorted[show_top]
-            b = dist_cod_sorted[show_top-1]
+            a = dist_cod_sorted.iloc[show_top]
+            b = dist_cod_sorted.iloc[show_top-1]
             while show_top < len(dist_cod_sorted) and \
                     (abs(a-b) < (a+b) * 1e-5):
                 show_top = show_top + 1

interva/utils.py → src/interva/utils.py

@@ -195,15 +195,15 @@ def csmf(iva5: interva.interva5.InterVA5,
 
     # show causes with top non-zero values
     show_top = 0
-    while dist_cod[show_top] > 0 and show_top < top:
+    while dist_cod.iloc[show_top] > 0 and show_top < top:
         show_top = show_top + 1
     if show_top == top:
-        a = dist_cod[show_top]
-        b = dist_cod[show_top - 1]
+        a = dist_cod.iloc[show_top]
+        b = dist_cod.iloc[show_top - 1]
         while show_top < len(dist_cod) and (abs(a - b) < (a + b) * 1e-5):
             show_top = show_top + 1
-            a = dist_cod[show_top]
-            b = dist_cod[show_top - 1]
+            a = dist_cod.iloc[show_top]
+            b = dist_cod.iloc[show_top - 1]
     top_csmf = dist_cod.head(show_top)
 
     return top_csmf

tests/test_compare_r.py

@@ -57,7 +57,7 @@ def test_r_va5_comparison():
     for i in range(r_prob_check.shape[0]):
         for j in range(r_prob_check.shape[1]):
             a = round(r_prob_check.iloc[i, j], 10)
-            b = round(py_prob_check[i][j], 10)
+            b = round(py_prob_check.iloc[i].iloc[j], 10)
             assert a == b
 
 
@@ -67,7 +67,7 @@ def test_r_csmf_top15_comparison():
     r_csmf_top15 = r_csmf_top15_check.to_numpy()
     for i in range(len(r_csmf_top15_check)):
         a = round(float(py_csmf_top15[i]), 10)
-        b = round(float(r_csmf_top15[i]), 10)
+        b = round(float(r_csmf_top15[i][0]), 10)
         assert a == b
 
 
@@ -80,7 +80,7 @@ def tests_utils_csmf_1():
     r_csmf5_1_top15 = r_csmf5_1_top15.to_numpy()
     for i in range(len(r_csmf5_1_top15)):
         a = round(float(py_csmf5_1_top15[i]), 10)
-        b = round(float(r_csmf5_1_top15[i]), 10)
+        b = round(float(r_csmf5_1_top15[i][0]), 10)
         assert a == b
 
 
@@ -93,5 +93,5 @@ def tests_utils_csmf_2():
     r_csmf5_2_top15 = r_csmf5_2_top15.to_numpy()
     for i in range(len(r_csmf5_2_top15)):
         a = round(float(py_csmf5_2_top15[i]), 4)
-        b = round(float(r_csmf5_2_top15[i]), 4)
+        b = round(float(r_csmf5_2_top15[i][0]), 4)
         assert a == b

tests/test_utils.py

@@ -27,7 +27,7 @@
 
 def make_age_test_data(age_group, yes, no):
     sex_groups = Series({"ID": "d1", "i019a": "y", "i019b": "n"})
-    age_groups = Series({f"i022{i}": no for i in age_letters})
+    age_groups = Series({f"i022{i}": no for i in age_letters}).astype(object)
     age_groups[age_group] = yes
     va_record = concat([sex_groups, age_groups])
     age_all, age = all_age_groups[age_group]

tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = py37, py38, py39, py310, py311
+envlist = py38, py38, py39, py310, py311, py312
 
 [testenv]
 deps =