Trying to understand rust divergence

notebooks/rust-validation.ipynb

@@ -0,0 +1,219 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import scipy\n",
+    "from glob import glob\n"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def read_xy(path: str):\n",
+    "    df = pd.read_csv(path)\n",
+    "    df['N'] = df.index + 1\n",
+    "    df['r'] = (df.x ** 2 + df.y ** 2) ** 0.5\n",
+    "    df['cr'] = df.r.cummax()\n",
+    "    df['fd'] = np.log(df.N) / np.log(df.cr)\n",
+    "\n",
+    "    return df\n",
+    "\n",
+    "\n",
+    "def convergent_tail_index(series, tol):\n",
+    "    diffs = np.abs(np.ediff1d(series))\n",
+    "    for i in range(0, len(diffs)):\n",
+    "        if np.max(diffs[i:]) <= tol:\n",
+    "            return i\n",
+    "\n",
+    "    # No convergence found\n",
+    "    return None\n",
+    "\n",
+    "\n",
+    "def mean_of_tail(series, tol=0.05):\n",
+    "    tail_index = convergent_tail_index(series, tol)\n",
+    "    return np.mean(series[tail_index:])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/joshuacoles/Library/Caches/pypoetry/virtualenvs/data-analysis-B4Au_hWl-py3.10/lib/python3.10/site-packages/pandas/core/arraylike.py:402: RuntimeWarning: divide by zero encountered in log\n",
+      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n",
+      "/Users/joshuacoles/Library/Caches/pypoetry/virtualenvs/data-analysis-B4Au_hWl-py3.10/lib/python3.10/site-packages/pandas/core/arraylike.py:402: RuntimeWarning: divide by zero encountered in log\n",
+      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n",
+      "/Users/joshuacoles/Library/Caches/pypoetry/virtualenvs/data-analysis-B4Au_hWl-py3.10/lib/python3.10/site-packages/pandas/core/arraylike.py:402: RuntimeWarning: divide by zero encountered in log\n",
+      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n",
+      "/Users/joshuacoles/Library/Caches/pypoetry/virtualenvs/data-analysis-B4Au_hWl-py3.10/lib/python3.10/site-packages/pandas/core/arraylike.py:402: RuntimeWarning: divide by zero encountered in log\n",
+      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n"
+     ]
+    }
+   ],
+   "source": [
+    "a = read_xy(\"/Users/joshuacoles/Developer/checkouts/jc3091/CompB DLA/c-codebase/a.csv\")\n",
+    "b = read_xy(\"/Users/joshuacoles/Developer/checkouts/jc3091/CompB DLA/c-codebase/b.csv\")\n",
+    "c = read_xy(\"/Users/joshuacoles/Developer/checkouts/jc3091/CompB DLA/c-codebase/c.csv\")\n",
+    "d = read_xy(\"/Users/joshuacoles/Developer/checkouts/jc3091/CompB DLA/c-codebase/d.csv\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1.7271570214996996"
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_of_tail(a.fd)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1.7271570214996996"
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_of_tail(b.fd)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1.7634427392486482"
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_of_tail(c.fd)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "1.7634427392486482"
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mean_of_tail(d.fd)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/joshuacoles/Library/Caches/pypoetry/virtualenvs/data-analysis-B4Au_hWl-py3.10/lib/python3.10/site-packages/pandas/core/arraylike.py:402: RuntimeWarning: divide by zero encountered in log\n",
+      "  result = getattr(ufunc, method)(*inputs, **kwargs)\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "20769"
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "convergent_tail_index(read_xy(\"../fucking_massive.csv\").fd, 0.001)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

tools/rust-sp-harness.bash

@@ -0,0 +1,16 @@
+#!/usr/bin/env bash
+
+# NOTE: Requires GNU parallel
+
+MODEL="models/rust-sp"
+#MODEL=echo
+mkdir -p data/rust-sp
+PROBABILITIES=$@
+
+for i in $PROBABILITIES; do
+  mkdir data/rust-sp/"$i"
+done
+
+MAX_PARTICLES=2000
+
+parallel "$MODEL" '{1}' $MAX_PARTICLES '{2}' 'data/rust-sp/{2}/{1}.csv' ::: {1..100} ::: $PROBABILITIES

tools/sp-harness.bash

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+
+# NOTE: Requires GNU parallel
+# USAGE: MAX_PARTICLES=... sp-harness.bash <model> <run_id> <probabilities...>
+
+# Run ID
+MODEL="$1"
+ID="$2"
+
+shift
+shift
+
+ROOT="data/$ID"
+mkdir -p "$ROOT"
+
+PROBABILITIES=$@
+
+for i in $PROBABILITIES; do
+  mkdir -p "$ROOT/$i"
+done
+
+MAX_PARTICLES="${MAX_PARTICLES:=2000}"
+
+parallel "'$MODEL'" '{1}' $MAX_PARTICLES '{2}' "$ROOT/{2}/{1}.csv" ::: {1..100} ::: $PROBABILITIES