bandwidth tuning via classification

Author: alartum

.pre-commit-config.yaml

@@ -8,13 +8,18 @@ repos:
       - id: requirements-txt-fixer
       - id: trailing-whitespace
 
+  - repo: https://github.com/PyCQA/flake8
+    rev: 3.9.2
+    hooks:
+    - id: flake8
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.6.4
+    hooks:
+      - id: isort
+
   - repo: https://github.com/ambv/black
     rev: 21.9b0
     hooks:
     - id: black
       language_version: python3.8
-
-  - repo: https://github.com/PyCQA/flake8
-    rev: 3.9.2
-    hooks:
-    - id: flake8

AUTHORS

@@ -0,0 +1,3 @@
+Aleksandr Artemenkov <[email protected]>
+Nikita Kotelevskii <[email protected]>
+mephody-bro <[email protected]>

ChangeLog

@@ -0,0 +1,21 @@
+CHANGES
+=======
+
+* hnsw without parallel
+* n\_jobs parameter
+* parallelize
+* local variant
+* refactor: initial commit
+* Fix the typo
+* Make the packcage
+* Cleaner example and little bit more compatible
+* Rename to nuq
+* Initial commit
+* Minor stuff with batch formation is fixed
+* Refined minibatches for uncertainty
+* Added minibatch for uncertainties
+* Added 3 types of uncertainty
+* Minor changes
+* Added small value for numerical stability in uncertainty
+* Added logsumexp computation of the conditional
+* Nadaraya-Watson method for uncertainty quantification

environment.yaml

@@ -0,0 +1,38 @@
+name: ray-env
+channels:
+  - conda-forge
+  - defaults
+dependencies:
+  - python=3.8
+  - pip
+
+  # Computations
+  - numpy
+  - matplotlib
+  - scikit-learn
+  - scipy
+  - pandas
+  - seaborn
+
+  # Jupyter Lab
+  - ipykernel
+  - ipywidgets
+  - nb_black # black formatter
+  - wurlitzer # C level output
+
+  # Parallelism
+  - ray-dashboard
+
+  # Utilities
+  - tqdm # progress bar
+  - black # formatter
+  - isort # import sorter
+  - flake8 # linter
+  - pre_commit # git pre-commit hooks
+  - pytest # code testing
+  - pybind11 # hnswlib build
+  - cython # KDEpy build
+
+  - pip:
+    - hnswlib
+    - KDEpy

example.ipynb

@@ -1,6 +1,8 @@
+import re
+
+import matplotlib.pyplot as plt
 import numpy as np
 from sklearn.datasets import make_blobs
-import matplotlib.pyplot as plt
 
 
 def plot_data(X, y, title=None):
@@ -16,3 +18,13 @@ def plot_data(X, y, title=None):
 def make_data(total_size=5000, centers=np.array([[-4.0, -4.0], [0.0, 4.0]])):
     X, y = make_blobs(n_samples=total_size, n_features=2, centers=centers)
     return X, y
+
+
+def parse_param(param_string):
+    res = param_string.split(":", maxsplit=1)
+    if len(res) == 1:
+        return res[0], {}
+    name, vals_string = res
+    vals_strings = filter(None, vals_string.split(";"))
+    vals = [v.split("=", maxsplit=1) for v in vals_strings]
+    return name, dict(vals)