wassname/prob_jsonformer
1
0
Fork 0
mirror of https://github.com/wassname/prob_jsonformer.git synced 2026-08-20 12:40:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

prob dist

Browse Source
This commit is contained in:
wassname
2024-05-12 14:31:14 +08:00
parent a5deeb89af
commit 63050bcc3e
4 changed files with 328 additions and 552 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+11
View File
@@ -9,6 +9,17 @@ I've also merged some of the recent PR's for enum, integer, null, union. They ar
pip install git+https://github.com/wassname/prob_jsonformer.git
~~~
| method | KL_div_loss | time |
| :---------------------------- | ----------: | -------: |
| method0: sampling | -0.147245 | 21.5937 |
| method1: hindsight | -0.145874 | 0.631365 |
| method3: gen tree (this work) | -0.147246 | 0.066084 |
KL_div_loss is the KL divergence between the true distribution and the generated distribution. Lower is better as it indicated a faithful sampling of the distribution. Time is in seconds.
## Example
```python
poetry.lock
Generated
+34 -81
View File
@@ -57,17 +57,6 @@ six = ">=1.12.0"
astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
[[package]]
name = "backcall"
version = "0.2.0"
description = "Specifications for callback functions passed in to an API"
optional = false
python-versions = "*"
files = [
{file = "backcall-0.2.0-py2.py3-none-any.whl", hash = "sha256:fbbce6a29f263178a1f7915c1940bde0ec2b2a967566fe1c65c1dfb7422bd255"},
{file = "backcall-0.2.0.tar.gz", hash = "sha256:5cbdbf27be5e7cfadb448baf0aa95508f91f2bbc6c6437cd9cd06e2a4c215e1e"},
]
[[package]]
name = "bitsandbytes"
version = "0.38.1"
@@ -323,6 +312,20 @@ files = [
{file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
]
[[package]]
name = "exceptiongroup"
version = "1.2.1"
description = "Backport of PEP 654 (exception groups)"
optional = false
python-versions = ">=3.7"
files = [
{file = "exceptiongroup-1.2.1-py3-none-any.whl", hash = "sha256:5258b9ed329c5bbdd31a309f53cbfb0b155341807f6ff7606a1e801a891b29ad"},
{file = "exceptiongroup-1.2.1.tar.gz", hash = "sha256:a4785e48b045528f5bfe627b6ad554ff32def154f42372786903b7abcfe1aa16"},
]
[package.extras]
test = ["pytest (>=6)"]
[[package]]
name = "executing"
version = "2.0.1"
@@ -501,42 +504,40 @@ test = ["flaky", "ipyparallel", "pre-commit", "pytest (>=7.0)", "pytest-asyncio
[[package]]
name = "ipython"
version = "8.12.3"
version = "8.18.1"
description = "IPython: Productive Interactive Computing"
optional = false
python-versions = ">=3.8"
python-versions = ">=3.9"
files = [
{file = "ipython-8.12.3-py3-none-any.whl", hash = "sha256:b0340d46a933d27c657b211a329d0be23793c36595acf9e6ef4164bc01a1804c"},
{file = "ipython-8.12.3.tar.gz", hash = "sha256:3910c4b54543c2ad73d06579aa771041b7d5707b033bd488669b4cf544e3b363"},
{file = "ipython-8.18.1-py3-none-any.whl", hash = "sha256:e8267419d72d81955ec1177f8a29aaa90ac80ad647499201119e2f05e99aa397"},
{file = "ipython-8.18.1.tar.gz", hash = "sha256:ca6f079bb33457c66e233e4580ebfc4128855b4cf6370dddd73842a9563e8a27"},
]
[package.dependencies]
appnope = {version = "*", markers = "sys_platform == \"darwin\""}
backcall = "*"
colorama = {version = "*", markers = "sys_platform == \"win32\""}
decorator = "*"
exceptiongroup = {version = "*", markers = "python_version < \"3.11\""}
jedi = ">=0.16"
matplotlib-inline = "*"
pexpect = {version = ">4.3", markers = "sys_platform != \"win32\""}
pickleshare = "*"
prompt-toolkit = ">=3.0.30,<3.0.37 || >3.0.37,<3.1.0"
prompt-toolkit = ">=3.0.41,<3.1.0"
pygments = ">=2.4.0"
stack-data = "*"
traitlets = ">=5"
typing-extensions = {version = "*", markers = "python_version < \"3.10\""}
[package.extras]
all = ["black", "curio", "docrepr", "ipykernel", "ipyparallel", "ipywidgets", "matplotlib", "matplotlib (!=3.2.0)", "nbconvert", "nbformat", "notebook", "numpy (>=1.21)", "pandas", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio", "qtconsole", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "trio", "typing-extensions"]
all = ["black", "curio", "docrepr", "exceptiongroup", "ipykernel", "ipyparallel", "ipywidgets", "matplotlib", "matplotlib (!=3.2.0)", "nbconvert", "nbformat", "notebook", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "qtconsole", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "trio", "typing-extensions"]
black = ["black"]
doc = ["docrepr", "ipykernel", "matplotlib", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "typing-extensions"]
doc = ["docrepr", "exceptiongroup", "ipykernel", "matplotlib", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "typing-extensions"]
kernel = ["ipykernel"]
nbconvert = ["nbconvert"]
nbformat = ["nbformat"]
notebook = ["ipywidgets", "notebook"]
parallel = ["ipyparallel"]
qtconsole = ["qtconsole"]
test = ["pytest (<7.1)", "pytest-asyncio", "testpath"]
test-extra = ["curio", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.21)", "pandas", "pytest (<7.1)", "pytest-asyncio", "testpath", "trio"]
test = ["pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath"]
test-extra = ["curio", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath", "trio"]
[[package]]
name = "jaxtyping"
@@ -763,58 +764,21 @@ files = [
[[package]]
name = "networkx"
version = "3.1"
version = "3.2.1"
description = "Python package for creating and manipulating graphs and networks"
optional = false
python-versions = ">=3.8"
python-versions = ">=3.9"
files = [
{file = "networkx-3.1-py3-none-any.whl", hash = "sha256:4f33f68cb2afcf86f28a45f43efc27a9386b535d567d2127f8f61d51dec58d36"},
{file = "networkx-3.1.tar.gz", hash = "sha256:de346335408f84de0eada6ff9fafafff9bcda11f0a0dfaa931133debb146ab61"},
{file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"},
{file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"},
]
[package.extras]
default = ["matplotlib (>=3.4)", "numpy (>=1.20)", "pandas (>=1.3)", "scipy (>=1.8)"]
developer = ["mypy (>=1.1)", "pre-commit (>=3.2)"]
doc = ["nb2plots (>=0.6)", "numpydoc (>=1.5)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.13)", "sphinx (>=6.1)", "sphinx-gallery (>=0.12)", "texext (>=0.6.7)"]
extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.10)", "sympy (>=1.10)"]
test = ["codecov (>=2.1)", "pytest (>=7.2)", "pytest-cov (>=4.0)"]
[[package]]
name = "numpy"
version = "1.24.4"
description = "Fundamental package for array computing in Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "numpy-1.24.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:c0bfb52d2169d58c1cdb8cc1f16989101639b34c7d3ce60ed70b19c63eba0b64"},
{file = "numpy-1.24.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ed094d4f0c177b1b8e7aa9cba7d6ceed51c0e569a5318ac0ca9a090680a6a1b1"},
{file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:79fc682a374c4a8ed08b331bef9c5f582585d1048fa6d80bc6c35bc384eee9b4"},
{file = "numpy-1.24.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7ffe43c74893dbf38c2b0a1f5428760a1a9c98285553c89e12d70a96a7f3a4d6"},
{file = "numpy-1.24.4-cp310-cp310-win32.whl", hash = "sha256:4c21decb6ea94057331e111a5bed9a79d335658c27ce2adb580fb4d54f2ad9bc"},
{file = "numpy-1.24.4-cp310-cp310-win_amd64.whl", hash = "sha256:b4bea75e47d9586d31e892a7401f76e909712a0fd510f58f5337bea9572c571e"},
{file = "numpy-1.24.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:f136bab9c2cfd8da131132c2cf6cc27331dd6fae65f95f69dcd4ae3c3639c810"},
{file = "numpy-1.24.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e2926dac25b313635e4d6cf4dc4e51c8c0ebfed60b801c799ffc4c32bf3d1254"},
{file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:222e40d0e2548690405b0b3c7b21d1169117391c2e82c378467ef9ab4c8f0da7"},
{file = "numpy-1.24.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7215847ce88a85ce39baf9e89070cb860c98fdddacbaa6c0da3ffb31b3350bd5"},
{file = "numpy-1.24.4-cp311-cp311-win32.whl", hash = "sha256:4979217d7de511a8d57f4b4b5b2b965f707768440c17cb70fbf254c4b225238d"},
{file = "numpy-1.24.4-cp311-cp311-win_amd64.whl", hash = "sha256:b7b1fc9864d7d39e28f41d089bfd6353cb5f27ecd9905348c24187a768c79694"},
{file = "numpy-1.24.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1452241c290f3e2a312c137a9999cdbf63f78864d63c79039bda65ee86943f61"},
{file = "numpy-1.24.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:04640dab83f7c6c85abf9cd729c5b65f1ebd0ccf9de90b270cd61935eef0197f"},
{file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5425b114831d1e77e4b5d812b69d11d962e104095a5b9c3b641a218abcc050e"},
{file = "numpy-1.24.4-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd80e219fd4c71fc3699fc1dadac5dcf4fd882bfc6f7ec53d30fa197b8ee22dc"},
{file = "numpy-1.24.4-cp38-cp38-win32.whl", hash = "sha256:4602244f345453db537be5314d3983dbf5834a9701b7723ec28923e2889e0bb2"},
{file = "numpy-1.24.4-cp38-cp38-win_amd64.whl", hash = "sha256:692f2e0f55794943c5bfff12b3f56f99af76f902fc47487bdfe97856de51a706"},
{file = "numpy-1.24.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:2541312fbf09977f3b3ad449c4e5f4bb55d0dbf79226d7724211acc905049400"},
{file = "numpy-1.24.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:9667575fb6d13c95f1b36aca12c5ee3356bf001b714fc354eb5465ce1609e62f"},
{file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f3a86ed21e4f87050382c7bc96571755193c4c1392490744ac73d660e8f564a9"},
{file = "numpy-1.24.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d11efb4dbecbdf22508d55e48d9c8384db795e1b7b51ea735289ff96613ff74d"},
{file = "numpy-1.24.4-cp39-cp39-win32.whl", hash = "sha256:6620c0acd41dbcb368610bb2f4d83145674040025e5536954782467100aa8835"},
{file = "numpy-1.24.4-cp39-cp39-win_amd64.whl", hash = "sha256:befe2bf740fd8373cf56149a5c23a0f601e82869598d41f8e188a0e9869926f8"},
{file = "numpy-1.24.4-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:31f13e25b4e304632a4619d0e0777662c2ffea99fcae2029556b17d8ff958aef"},
{file = "numpy-1.24.4-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95f7ac6540e95bc440ad77f56e520da5bf877f87dca58bd095288dce8940532a"},
{file = "numpy-1.24.4-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:e98f220aa76ca2a977fe435f5b04d7b3470c0a2e6312907b37ba6068f26787f2"},
{file = "numpy-1.24.4.tar.gz", hash = "sha256:80f5e3a4e498641401868df4208b74581206afbee7cf7b8329daae82676d9463"},
]
default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"]
developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"]
doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"]
extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"]
test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
[[package]]
name = "numpy"
@@ -1116,17 +1080,6 @@ files = [
[package.dependencies]
ptyprocess = ">=0.5"
[[package]]
name = "pickleshare"
version = "0.7.5"
description = "Tiny 'shelve'-like database with concurrency support"
optional = false
python-versions = "*"
files = [
{file = "pickleshare-0.7.5-py2.py3-none-any.whl", hash = "sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"},
{file = "pickleshare-0.7.5.tar.gz", hash = "sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca"},
]
[[package]]
name = "platformdirs"
version = "4.2.1"
@@ -2144,4 +2097,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
[metadata]
lock-version = "2.0"
python-versions = "^3.9,<4.0"
content-hash = "7dc5b5ce8859c474fbf5706b8b3729058bcb7a55d2201fa6aef6aa348587d5e2"
content-hash = "de9ff88e0262687eae944edc9546130665af3bf7b325daa50bdbd78b6a23381f"
prob_dist.ipynb
+282 -470
View File
File diff suppressed because one or more lines are too long
pyproject.toml
+1 -1
View File
@@ -9,9 +9,9 @@ readme = "README.md"
python = "^3.9,<4.0"
termcolor = "^2.3.0"
jaxtyping = "^0.2.28"
pandas = "^2.2.2"
[tool.poetry.group.dev.dependencies]
pandas = "^2.2.2"
ipykernel = "^6.22.0"
torch = "^2.0.0"
accelerate = "^0.18.0"