Added usage example

example/usage_example.ipynb

@@ -0,0 +1,254 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "from akin import MinHash, LSH"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "outputs": [],
+   "source": [
+    "content = [\n",
+    "    'Jupiter is primarily composed of hydrogen with a quarter of its mass being helium',\n",
+    "    'Jupiter moving out of the inner Solar System would have allowed the formation of inner planets.',\n",
+    "    'A helium atom has about four times as much mass as a hydrogen atom, so the composition changes '\n",
+    "    'when described as the proportion of mass contributed by different atoms.',\n",
+    "    'Jupiter is primarily composed of hydrogen and a quarter of its mass being helium',\n",
+    "    'A helium atom has about four times as much mass as a hydrogen atom and the composition changes '\n",
+    "    'when described as a proportion of mass contributed by different atoms.',\n",
+    "    'Theoretical models indicate that if Jupiter had much more mass than it does at present, it '\n",
+    "    'would shrink.',\n",
+    "    'This process causes Jupiter to shrink by about 2 cm each year.',\n",
+    "    'Jupiter is mostly composed of hydrogen with a quarter of its mass being helium',\n",
+    "    'The Great Red Spot is large enough to accommodate Earth within its boundaries.'\n",
+    "]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [],
+   "source": [
+    "# Labels for each text in content.\n",
+    "labels = [1, 2, 3, 4, 5, 6, 7, 8, 9]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "outputs": [],
+   "source": [
+    "# Create MinHash object.\n",
+    "minhash = MinHash(content, n_gram=9, permutations=100, hash_bits=64, seed=3)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [],
+   "source": [
+    "# Create LSH model.\n",
+    "lsh = LSH(minhash, labels, no_of_bands=50)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[8, 4]"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Query to find near duplicates for text 1.\n",
+    "lsh.query(1, min_jaccard=0.5)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "outputs": [],
+   "source": [
+    "# Generate minhash signature and add new texts to LSH model.\n",
+    "new_text = [\n",
+    "    'Jupiter is primarily composed of hydrogen with a quarter of its mass being helium',\n",
+    "    'Jupiter moving out of the inner Solar System would have allowed the formation of '\n",
+    "    'inner planets.'\n",
+    "]"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "outputs": [],
+   "source": [
+    "new_labels = ['doc1', 'doc2']"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "outputs": [],
+   "source": [
+    "new_minhash = MinHash(new_text, n_gram=9, permutations=100, hash_bits=64, seed=3)\n",
+    "lsh.update(new_minhash, new_labels)"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[1, 2, 3, 4, 5, 6, 7, 8, 9, 'doc1', 'doc2']"
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Check contents of documents.\n",
+    "lsh.contains()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[1, 2, 3, 4, 6, 7, 8, 9, 'doc1', 'doc2']"
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Remove text and label from model.\n",
+    "lsh.remove(5)\n",
+    "lsh.contains()"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "{1: ['doc1', 4],\n 2: ['doc2'],\n 3: [],\n 4: [1, 'doc1'],\n 6: [],\n 7: [],\n 8: [],\n 9: [],\n 'doc1': [1, 4],\n 'doc2': [2]}"
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Return adjacency list for all similar texts.\n",
+    "adjacency_list = lsh.adjacency_list(min_jaccard=0.55)\n",
+    "adjacency_list"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "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
+}