Adds single sentence summarization (#3)

* Adds single sentence summarization

* Expand Python version compatibility

* Formatting

* Address flake

* [0.1.5] Adds single sentence summarization

* formatting

.gitignore

@@ -12,3 +12,4 @@ tfhub/
 notebooks/*_experiment.ipynb
 
 dist/
+bpe_summarizer.egg-info

notebooks/Evaluation Single Sentence.ipynb

@@ -0,0 +1,186 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "env: TFHUB_CACHE_DIR=tfhub/\n"
+     ]
+    }
+   ],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "%env TFHUB_CACHE_DIR=tfhub/"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import sys\n",
+    "module_path = os.path.abspath(os.path.join('..'))\n",
+    "if module_path not in sys.path:\n",
+    "    sys.path.append(module_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib\n",
+    "matplotlib.use(\"agg\")\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "\n",
+    "import numpy as np\n",
+    "import tensorflow as tf\n",
+    "from transformers import pipeline\n",
+    "import torch\n",
+    "from tqdm import tqdm\n",
+    "\n",
+    "from src.bpe_summarizer import bpe_summarize, sentencizer\n",
+    "from src.utils import remove_stopwords\n",
+    "from validation import scicummnet_validation, similarity_score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'notification repeated overdraft'"
+      ]
+     },
+     "execution_count": 39,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\"\"\"\n",
+    "The default percentile is 99, but the max percentile allowable for \n",
+    "a single sentence is derived from the mean of the token values\n",
+    "\"\"\"\n",
+    "bpe_summarize(\"I received a notification today about being subject to extended holds due to repeated overdrafts.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'notification subject extended holds repeated overdraft'"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "bpe_summarize(\n",
+    "    \"I received a notification today about being subject to extended holds due to repeated overdrafts.\", \n",
+    "    percentile=50\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'difference golden potatoes yellow potatoes'"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sample = \"what's the difference between golden potatoes and yellow potatoes?\"\n",
+    "result = bpe_summarize(\n",
+    "    sample, \n",
+    "    percentile=50\n",
+    ")\n",
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"what's difference golden potatoes yellow potatoes?\""
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "re.sub(r\"\\s{2,}\", \" \", remove_stopwords(sample))"
+   ]
+  },
+  {
+   "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": "3.8.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

notebooks/Evaluation.ipynb

@@ -47,15 +47,7 @@
    "cell_type": "code",
    "execution_count": 7,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:absl:Using tfhub/ to cache modules.\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import re\n",
     "\n",
@@ -66,7 +58,7 @@
     "from tqdm import tqdm\n",
     "\n",
     "from src.bpe_summarizer import bpe_summarize, sentencizer\n",
-    "from validation import scicummnet_validation, rouge_metric, similarity_score, mean_rouge_fscore"
+    "from validation import scicummnet_validation, similarity_score, mean_rouge_fscore"
    ]
   },
   {