feat(proportion.independent.ci): add more solvers and algorithms

[Snoopy1866]

新增下列置信区间算法：

• newcombe_wilson
• newcombe_wilson_cc
• farrington_manning
• miettinen_nurminen

[read-the-docs-community]

Documentation build overview

📚 pystatpower | 🛠️ Build #33051480 | 📁 Comparing 023b76f against latest (2d848bb)

  🔍 Preview build  

2 files changed

± api/proportion/independent/ci/index.html
± models/proportion/independent/ci/index.html

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 100.00%. Comparing base (2d848bb) to head (023b76f).

Additional details and impacted files

@@            Coverage Diff             @@
##              main      #394    +/-   ##
==========================================
  Coverage   100.00%   100.00%            
==========================================
  Files           25        25            
  Lines         1363      1573   +210     
==========================================
+ Hits          1363      1573   +210     

Flag	Coverage Δ
test-core-macos-latest-py3.10	100.00% <100.00%> (?)
test-core-macos-latest-py3.11	100.00% <100.00%> (?)
test-core-macos-latest-py3.12	100.00% <100.00%> (?)
test-core-macos-latest-py3.13	100.00% <100.00%> (?)
test-core-macos-latest-py3.14	100.00% <100.00%> (?)
test-core-ubuntu-latest-py3.10	100.00% <100.00%> (?)
test-core-ubuntu-latest-py3.11	100.00% <100.00%> (?)
test-core-ubuntu-latest-py3.12	100.00% <100.00%> (?)
test-core-ubuntu-latest-py3.13	100.00% <100.00%> (?)
test-core-ubuntu-latest-py3.14	100.00% <100.00%> (?)
test-core-windows-latest-py3.10	100.00% <100.00%> (?)
test-core-windows-latest-py3.11	100.00% <100.00%> (?)
test-core-windows-latest-py3.12	100.00% <100.00%> (?)
test-core-windows-latest-py3.13	100.00% <100.00%> (?)
test-core-windows-latest-py3.14	100.00% <100.00%> (?)
test-full-py3.10-scipy1.10	?
test-full-py3.10-scipy1.11	?
test-full-py3.10-scipy1.12	?
test-full-py3.10-scipy1.13	?
test-full-py3.10-scipy1.14	?
test-full-py3.10-scipy1.15	?
test-full-py3.10-scipy1.7	?
test-full-py3.10-scipy1.8	?
test-full-py3.10-scipy1.9	?
test-full-py3.11-scipy1.10	?
test-full-py3.11-scipy1.11	?
test-full-py3.11-scipy1.12	?
test-full-py3.11-scipy1.13	?
test-full-py3.11-scipy1.14	?
test-full-py3.11-scipy1.15	?
test-full-py3.11-scipy1.16	?
test-full-py3.11-scipy1.17	?
test-full-py3.12-scipy1.11	?
test-full-py3.12-scipy1.12	?
test-full-py3.12-scipy1.13	?
test-full-py3.12-scipy1.14	?
test-full-py3.12-scipy1.15	?
test-full-py3.12-scipy1.16	?
test-full-py3.12-scipy1.17	?
test-full-py3.13-scipy1.15	?
test-full-py3.13-scipy1.16	?
test-full-py3.13-scipy1.17	?
test-full-py3.14-scipy1.16	?
test-full-py3.14-scipy1.17	?
test-minimum-scipy-ubuntu-latest-py3.10-scipy1.7.2	100.00% <100.00%> (?)
test-minimum-scipy-ubuntu-latest-py3.11-scipy1.10.1	100.00% <100.00%> (?)
test-minimum-scipy-ubuntu-latest-py3.12-scipy1.11.3	100.00% <100.00%> (?)
test-minimum-scipy-ubuntu-latest-py3.13-scipy1.15.0	100.00% <100.00%> (?)
test-minimum-scipy-ubuntu-latest-py3.14-scipy1.16.1	100.00% <100.00%> (?)

Flags with carried forward coverage won't be shown. Click here to find out more.

Files with missing lines	Coverage Δ
...rc/pystatpower/models/proportion/independent/ci.py	100.00% <100.00%> (ø)

[codacy-production]

Pull Request Overview

While the PR successfully adds Newcombe-Wilson algorithms and standardizes one-sided terminology, there is a significant discrepancy between the PR's stated goals and the implementation: the farrington_manning algorithm is completely missing from the code despite being listed in the description.

Additionally, the _distance_newcombe_wilson_cc implementation is susceptible to ValueError: math domain error for certain edge cases (small sample sizes or low confidence levels). Several documentation and type-hint mismatches were also identified, particularly in the test suite and function docstrings. Although Codacy analysis indicates the code is otherwise up to standards, these issues should be addressed before merging.

About this PR

• The PR description explicitly states that the 'farrington_manning' algorithm is added, but no implementation or test cases appear in the code changes. Please either implement the missing algorithm or update the PR description to match the actual scope.

Test suggestions

• Calculate confidence interval distance using Newcombe-Wilson method for two-sided, lower one-sided, and upper one-sided types.
• Calculate confidence interval distance using Newcombe-Wilson with continuity correction for two-sided, lower one-sided, and upper one-sided types.
• Calculate confidence interval distance using Farrington-Manning method.

Prompt proposal for missing tests

Consider implementing these tests if applicable:
1. Calculate confidence interval distance using Farrington-Manning method.

_{TIP Improve review quality by adding custom instructions
TIP How was this review? Give us feedback}

[codacy-production]

Not up to standards ⛔

🔴 Issues 6 high

Alerts:
⚠ 6 issues (≤ 0 issues of at least minor severity)

Results:
6 new issues

Category	Results
Security	6 high

View in Codacy

🟢 Metrics 31 complexity

Metric	Results
Complexity	31

View in Codacy

AI Reviewer: first review requested successfully. AI can make mistakes. Always validate suggestions.

_{TIP This summary will be updated as you push new changes.}