Merge pull request #7 from shimo-lab/peform_pred

Add  code for model performance prediction

Author: momoseoyama

resampling-texts/README.md

@@ -32,7 +32,14 @@ Using only texts selected through LS sampling allows new models to be efficientl
 <img src="figures/fig3.png" alt="fig3" style="width:90%">
 </p>
 
+### Prediction of Model's Performance (Figure4)
 
+Using model coordinates from unique texts, we predict the average performance across six downstream tasks with ridge regression.
+See [`code_for_prediction/`](./code_for_prediction/) for details.
+
+<p align="center">
+<img src="figures/fig4.png" alt="fig4" style="width:50%">
+</p>
 
 ## 🦉 Misc.
 

resampling-texts/code_for_prediction/.gitignore

@@ -0,0 +1,226 @@
+### Generated by gibo (https://github.com/simonwhitaker/gibo)
+### https://raw.github.com/github/gitignore/d0b80a469983a7beece8fa1f5c48a8242318b531/Global/Vim.gitignore
+
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg  # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+*~
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+
+### https://raw.github.com/github/gitignore/d0b80a469983a7beece8fa1f5c48a8242318b531/Python.gitignore
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+### https://raw.github.com/github/gitignore/d0b80a469983a7beece8fa1f5c48a8242318b531/C++.gitignore
+
+# Prerequisites
+*.d
+
+# Compiled Object files
+*.slo
+*.lo
+*.o
+*.obj
+
+# Precompiled Headers
+*.gch
+*.pch
+
+# Compiled Dynamic libraries
+*.so
+*.dylib
+*.dll
+
+# Fortran module files
+*.mod
+*.smod
+
+# Compiled Static libraries
+*.lai
+*.la
+*.a
+*.lib
+
+# Executables
+*.exe
+*.out
+*.app
+
+# Added manually
+.DS_Store
+output/

resampling-texts/code_for_prediction/.python-version

@@ -0,0 +1 @@
+3.13

resampling-texts/code_for_prediction/README.md

@@ -0,0 +1,59 @@
+## Model Performance Prediction (Section 4.3 and Appendix F)
+
+We use [`uv`](https://docs.astral.sh/uv/) for the experiment environment in this directory. See the official site for installation.
+
+### Setup
+
+With `uv` available, install the required packages:
+
+```bash
+$ uv sync
+```
+
+The experiments use [`../data/modeldata_1018.pkl`](../data/modeldata_1018.pkl) and [`../data/uniq-idx-weight/`](../data/uniq-idx-weight/). See [`../README.md`](../README.md) for details of these data.
+
+### Data Preparation
+
+Prepare training and prediction splits for ridge regression with `GroupKFold`:
+
+```bash
+$ uv run src/split_data.py
+```
+
+Five-fold splits with five seeds are saved to `output/split_data/groupkfold/`.
+
+### Train and Predict with Ridge Regression
+
+Train the ridge regression models and generate predictions (**This step takes about half a day !**) :
+
+```bash
+$ uv run src/train_and_pred.py
+```
+
+Predictions for each method (Uniform, KL, LS) are saved to `output/train_and_pred/groupkfold/`.
+
+### Plot Figures
+
+Draw Figure 4 from the predictions:
+
+```bash
+$ uv run src/figure4.py
+```
+
+Figure 4 is saved to `output/images/`.
+
+<p align="center">
+<img src="figures/fig4.png" alt="fig4" style="width:50%">
+</p>
+
+Draw Figure 6 from the predictions:
+
+```bash
+$ uv run src/figure6_and_table2.py
+```
+
+<p align="center">
+<img src="figures/fig6.png" alt="fig6" style="width:90%">
+</p>
+
+Figure 6 is saved to `output/images/`. This script also saves the results for Table 2 to `output/summary/`.

resampling-texts/code_for_prediction/figures/fig4.png

@@ -0,0 +1,14 @@
+[project]
+name = "code-for-prediction"
+version = "0.1.0"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "numpy",
+    "pandas",
+    "scikit-learn",
+    "fire",
+    "matplotlib",
+    "tqdm",
+    "jinja2>=3.1.6",
+]