generate_lsh_seeds_and_features.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "import random\n",
    "import numpy as np\n",
    "\n",
    "SEEDS_COUNT = 20\n",
    "SAMPLES_COUNT = 300\n",
    "FEATURES_COUNT = 10\n",
    "\n",
    "BANDS_COUNT = 4\n",
    "HASH_FUNCTIONS_COUNT = 48\n",
    "\n",
    "P_VALUE = 15307\n",
    "R_VALUE = HASH_FUNCTIONS_COUNT / BANDS_COUNT\n",
    "\n",
    "def generate_features(feature_count, sample_count):\n",
    "    return [[int(round(random.random())) for i in range(feature_count)] for i in range(sample_count)]\n",
    "\n",
    "def generate_hash_function_seeds(p_value, hash_function_count):\n",
    "    return np.random.randint(0, p_value + 1, size=(hash_function_count,2))\n",
    "\n",
    "hash_function_seeds = generate_hash_function_seeds(P_VALUE, HASH_FUNCTIONS_COUNT)\n",
    "\n",
    "with open('/tmp/hash_function_seeds.json', 'w') as file:\n",
    "    hash_function_seeds_dict = dict(p_value=P_VALUE, seeds=hash_function_seeds.tolist())\n",
    "    file.write(json.dumps(hash_function_seeds_dict))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('/tmp/hash_function_seeds.json') as file:  \n",
    "    hash_function_seeds_dict_read = json.load(file)\n",
    "\n",
    "assert np.array_equal(np.array(hash_function_seeds_dict_read['seeds']), hash_function_seeds)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "features = generate_features(FEATURES_COUNT, SAMPLES_COUNT)\n",
    "\n",
    "with open('/tmp/features.json', 'w') as file:\n",
    "    file.write(json.dumps(features))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('/tmp/features.json') as file:  \n",
    "    features_read = json.load(file)\n",
    "\n",
    "assert features_read == features"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "SEEDS_COUNT = 20\n",
    "\n",
    "seeds = generate_features(FEATURES_COUNT, SEEDS_COUNT)\n",
    "\n",
    "with open('/tmp/seeds.json', 'w') as file:\n",
    "    file.write(json.dumps(seeds))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}