pybhatlib 0.3.0__tar.gz → 0.3.1__tar.gz

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/.gitignore

@@ -33,6 +33,11 @@ results/
 # Original GAUSS source
 chandra_code/
 
+# Project-local docs (not for repo)
+CLAUDE.md
+GAUSS_INTEGRATION_PLAN.md
+IMPLEMENTATION_PLAN.md
+
 # OS
 .DS_Store
 Thumbs.db

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: pybhatlib
-Version: 0.3.0
+Version: 0.3.1
 Summary: Python implementation of BHATLIB: matrix-based inference for advanced econometric models
 Project-URL: Homepage, https://github.com/UMN-Choi-Lab/pybhatlib
 Project-URL: Repository, https://github.com/UMN-Choi-Lab/pybhatlib

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t00_quickstart.py

@@ -11,6 +11,8 @@ What you will learn:
   - How to interpret the output
 
 Prerequisites: None (this is the first tutorial).
+
+Expected runtime: ~1 min
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t01a_vectorization.py

@@ -13,6 +13,8 @@ What you will learn:
   - nondiag: extract all non-diagonal elements
 
 Prerequisites: None.
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t01b_ldlt.py

@@ -10,6 +10,8 @@ What you will learn:
   - Why this matters for MVNCD sequential conditioning
 
 Prerequisites: t01a (vectorization basics).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t01c_truncated_mvn.py

@@ -10,6 +10,8 @@ What you will learn:
   - Different truncation scenarios and their effects
 
 Prerequisites: t01a (vectorization), t01b (LDLT).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t02a_gradcovcor.py

@@ -15,6 +15,8 @@ What you will learn:
   - Why this decomposition matters for unconstrained optimization
 
 Prerequisites: t01a (vectorization).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t02b_spherical.py

@@ -11,6 +11,8 @@ What you will learn:
   - Why this is better than direct correlation parameterization
 
 Prerequisites: t02a (gradcovcor).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t02c_chain_rules.py

@@ -12,6 +12,8 @@ What you will learn:
   - Numerical verification of every link
 
 Prerequisites: t02a (gradcovcor), t02b (spherical).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t03a_mvncd_methods.py

@@ -11,6 +11,8 @@ What you will learn:
   - Recommended method for different problem sizes
 
 Prerequisites: t03d (univariate CDFs) recommended.
+
+Expected runtime: ~15 sec
 """
 import os, sys, time
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t03b_mvncd_gradients.py

@@ -11,6 +11,8 @@ What you will learn:
   - Numerical verification via finite differences
 
 Prerequisites: t03a (MVNCD methods).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t03c_mvncd_rect.py

@@ -11,6 +11,8 @@ What you will learn:
   - Connection to ordered probit threshold bounds
 
 Prerequisites: t03a (MVNCD methods).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np

{pybhatlib-0.3.0 → pybhatlib-0.3.1}/examples/tutorials/python_scripts/t03d_univariate_cdfs.py

@@ -11,6 +11,8 @@ What you will learn:
   - How these building blocks compose into MVNCD methods
 
 Prerequisites: None (standalone reference).
+
+Expected runtime: <5 sec
 """
 import os, sys
 import numpy as np