Merge pull request #54 from anusii/develop

Updating master for initial public release

.github/workflows/python-package.yml

@@ -5,17 +5,18 @@ name: Python package
 
 on:
   push:
-    branches: [ master ]
+    branches: [ develop ]
   pull_request:
-    branches: [ master ]
+    branches: [ develop ]
+  workflow_dispatch:
 
 jobs:
   build:
 
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7]
+        python-version: [3.6, 3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v2
@@ -34,4 +35,4 @@ jobs:
     - name: Check formatting with black
       run: |
         pip install black
-        black --check relm tests
+        black --check relm tests

.github/workflows/release-workflow.yml

@@ -0,0 +1,39 @@
+# This workflow will install Python dependencies, run tests and lint with a variety of Python versions
+# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
+
+name: Python package
+
+"on":
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: [ master ]
+  schedule:
+    - cron: "0 0 * * *"
+
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.6, 3.7, 3.8, 3.9]
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v2
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Build
+      run: |
+        python -m pip install --upgrade pip
+        pip install .
+    - name: Test with pytest
+      run: |
+        pip install .[tests]
+        pytest tests
+    - name: Check formatting with black
+      run: |
+        pip install black
+        black --check relm tests

Cargo.toml

@@ -9,7 +9,9 @@ crate-type = ["cdylib"]
 
 [dependencies]
 pyo3 = { version = "0.11.1", features = ["extension-module"] }
-rand = "0.7.3"
+rand = "0.8.0"
+rand_distr = "0.4.0"
 rayon = "1.4.1"
 numpy = "0.11.0"
 rug = "1.11.0"
+ndarray = "0.13.1"

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2021 anusii
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

crisper_smalldb.ipynb

@@ -0,0 +1,159 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import pandas as pd\n",
+    "from relm.histogram import Histogram\n",
+    "from relm.mechanisms import SmallDB\n",
+    "import numpy as np\n",
+    "from itertools import product\n",
+    "import scipy.sparse as sps\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fp = 'examples/20200811_QLD_dummy_dataset_individual_v2.xlsx'\n",
+    "df = pd.read_excel(fp)\n",
+    "df.drop([\"NOTF_ID\", \"LGA\", \"HHS\"] + list(df.columns[12:]), axis=1, inplace=True)\n",
+    "\n",
+    "hist = Histogram(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_cols = [\"AGEGRP5\", \"SEX\", \"INDIG_STATUS\"]\n",
+    "queries = []\n",
+    "\n",
+    "# this creates the queries for:\n",
+    "# df.groupby([\"AGEGRP5\", \"SEX\", \"INDIG_STATUS\", col]).count()\n",
+    "# where col is in [\"HOSPITALISED\", \"VENTILATED\", \"ICU\", \"DIED_OF_CONDITION\"]\n",
+    "for col in [\"HOSPITALISED\", \"VENTILATED\", \"ICU\", \"DIED_OF_CONDITION\"]:\n",
+    "    cols = _cols + [col,]\n",
+    "    vals = product(*[list(hist.column_sets[hist.column_dict[c]]) for c in cols])\n",
+    "    queries.extend(dict(zip(cols, val)) for val in vals)\n",
+    "\n",
+    "# this creates the queries for:\n",
+    "# df.groupby([\"ONSET_DATE\", \"AGEGRP5\", \"INDIG_STATUS\", \"SEX\"]).count()\n",
+    "cols = [\"ONSET_DATE\", \"AGEGRP5\", \"INDIG_STATUS\", \"SEX\"]\n",
+    "vals = product(*[list(hist.column_sets[hist.column_dict[c]]) for c in cols])\n",
+    "queries.extend(dict(zip(cols, val)) for val in vals)\n",
+    "\n",
+    "# this creates the queries for:\n",
+    "# df.groupby([\"ONSET_DATE\", \"POSTCODE\"]).count()\n",
+    "cols = [\"ONSET_DATE\", \"POSTCODE\"]\n",
+    "vals = product(*[list(hist.column_sets[hist.column_dict[c]]) for c in cols])\n",
+    "queries.extend(dict(zip(cols, val)) for val in vals)\n",
+    "\n",
+    "queries = sps.vstack([hist.get_query_vector(q) for q in queries])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "smalldb = SmallDB(epsilon=4, data=hist.get_db(), alpha=0.1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 2min 1s, sys: 1.68 s, total: 2min 3s\n",
+      "Wall time: 2min 3s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%time x = smalldb.release(queries)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0, 0, 0, ..., 1, 0, 0], dtype=uint64)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "28554240"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs-source/conf.py

@@ -14,35 +14,37 @@
 import sys
 
 try:
-    build_folder = next(filter(lambda fn: "lib" in fn, os.listdir('../build')))
+    build_folder = next(filter(lambda fn: "lib" in fn, os.listdir("../build")))
 except StopIteration:
-    RuntimeError("Project must be built before building docs. Run 'python setup.py install'.")
+    RuntimeError(
+        "Project must be built before building docs. Run 'python setup.py install'."
+    )
 
-sys.path.insert(0, os.path.abspath(os.path.join('..', 'build', 'build_folder')))
+sys.path.insert(0, os.path.abspath(os.path.join("..", "build", "build_folder")))
 
 # -- Project information -----------------------------------------------------
 
-project = 'Differential Privacy'
-copyright = '2020, Kieran Ricardo, Michael Purcell'
-author = 'Kieran Ricardo, Michael Purcell'
+project = "Differential Privacy"
+copyright = "2020, Kieran Ricardo, Michael Purcell"
+author = "Kieran Ricardo, Michael Purcell"
 
 
 # -- General configuration ---------------------------------------------------
 
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['sphinx.ext.autodoc', 'sphinx.ext.coverage', 'sphinx.ext.napoleon']
+extensions = ["sphinx.ext.autodoc", "sphinx.ext.coverage", "sphinx.ext.napoleon"]
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
 #
 # This is also used if you do content translation via gettext catalogs.
 # Usually you set "language" from the command line for these cases.
-language = '[en]'
+language = "[en]"
 
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
@@ -66,4 +68,4 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]

docs-source/index.rst

@@ -14,7 +14,7 @@ Mechanisms
 ================================================
 
 .. automodule:: relm.mechanisms
-    :members: LaplaceMechanism, GeometricMechanism, SnappingMechanism, AboveThreshold, SparseIndicator, SparseNumeric
+    :members: LaplaceMechanism, GeometricMechanism, SnappingMechanism, AboveThreshold, SparseIndicator, SparseNumeric, ReportNoisyMax, ExponentialMechanism
 
 
 Indices and tables