File size: 3,869 Bytes
af779a7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Similarity Score\n",
    "This Notebook imports the questions and answers from the QuestionGeneration.ipynb output and scores the similarity\n",
    "\n",
    "Heavy inspiration taken from:\n",
    "\n",
    "https://github.com/karndeepsingh/sentence_similarity/blob/main/Finding_Similar_Sentence.ipynb"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.metrics.pairwise import cosine_similarity\n",
    "import numpy as np\n",
    "from sentence_transformers import SentenceTransformer"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load the model\n",
    "Uncomment to store the model locally for easy retrieval, but delete the model before uploading to GitHub as too large"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = SentenceTransformer('nli-distilroberta-base-v2')\n",
    "# model.save(\"./Model/model\")\n",
    "# model = SentenceTransformer(\"./Model/model\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load in the questions and responses"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "Data = pd.read_csv(\"./Results/Compare.csv\", index_col=0)\n",
    "questions = Data.index.values\n",
    "company = Data['Company'].values\n",
    "gold = Data['Meta'].values\n",
    "sentences = np.concatenate((company, gold))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create the sentence embeddings and obtain scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "sentence_embeddings = model.encode(sentences)\n",
    "similarity_score = []\n",
    "for i in range(len(company)):\n",
    "    similarity_score.append(cosine_similarity(\n",
    "        [sentence_embeddings[i]],\n",
    "        [sentence_embeddings[len(company) + i]]\n",
    "    ).flatten()[0])\n",
    "Similarity = pd.DataFrame({'Score': similarity_score}, index=questions)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Print a few of the scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                               Score\n",
      "What is the file name of the document?      0.858884\n",
      "When was the document last modified?        0.565336\n",
      "What is the file path of the document?      0.755018\n",
      "When was the document last accessed?        0.553015\n",
      "What is the creation date of the document?  0.849555\n"
     ]
    }
   ],
   "source": [
    "print(Similarity.head())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save the scores to a .csv file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "Similarity.to_csv('./Results/Similarity_Scores.csv')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "docu_compare",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}