Added markdown

justinbt1 · Apr 24, 2022 · 942acd1 · 942acd1
1 parent 7dcf216
commit 942acd1
Showing 1 changed file with 106 additions and 14 deletions.
diff --git a/example/usage_example.ipynb b/example/usage_example.ipynb
@@ -1,15 +1,30 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### Akin - Example Usage"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {
-    "collapsed": true
-   },
    "outputs": [],
    "source": [
     "from akin import MinHash, LSH"
-   ]
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
   },
   {
    "cell_type": "code",
@@ -43,8 +58,7 @@
    "execution_count": 3,
    "outputs": [],
    "source": [
-    "# Labels for each text in content.\n",
-    "labels = [1, 2, 3, 4, 5, 6, 7, 8, 9]"
+    "content_labels = [1, 2, 3, 4, 5, 6, 7, 8, 9]"
    ],
    "metadata": {
     "collapsed": false,
@@ -53,12 +67,23 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Create MinHash object:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\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": {
@@ -68,13 +93,24 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Create LSH object:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
    "outputs": [],
    "source": [
-    "# Create LSH model.\n",
-    "lsh = LSH(minhash, labels, no_of_bands=50)"
+    "lsh = LSH(minhash, content_labels, no_of_bands=50)"
    ],
    "metadata": {
     "collapsed": false,
@@ -83,6 +119,18 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Query to find near duplicates for text 1:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 6,
@@ -97,7 +145,6 @@
     }
    ],
    "source": [
-    "# Query to find near duplicates for text 1.\n",
     "lsh.query(1, min_jaccard=0.5)"
    ],
    "metadata": {
@@ -107,12 +154,23 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Generate minhash signature and add new texts to LSH model:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 14,
    "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",
@@ -155,6 +213,18 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Check contents of documents:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 10,
@@ -169,7 +239,6 @@
     }
    ],
    "source": [
-    "# Check contents of documents.\n",
     "lsh.contains()"
    ],
    "metadata": {
@@ -179,6 +248,18 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Remove text and label from model:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 11,
@@ -204,6 +285,18 @@
     }
    }
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "**Return adjacency list for all similar texts:**"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
   {
    "cell_type": "code",
    "execution_count": 12,
@@ -218,7 +311,6 @@
     }
    ],
    "source": [
-    "# Return adjacency list for all similar texts.\n",
     "adjacency_list = lsh.adjacency_list(min_jaccard=0.55)\n",
     "adjacency_list"
    ],