File size: 4,733 Bytes
5eaaba5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
165
166
167
168
169
170
171
172
173
174
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "42aaa537-ab3b-46d2-a12b-d0355669bf26",
   "metadata": {},
   "source": [
    "# ZeroShotClassification\n",
    "\n",
    "Experimenting with a ZeroShotClassification Pipeline.\n",
    "\n",
    "This works very good. Even \"login id\" was tagged as \"username\" at 20% confidence. Based on testing we will not consider below 18%."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c8e72fc9-198e-43c6-8045-aaf811145e1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import pipeline\n",
    "from faker import Faker"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "620682d6-fd51-47b7-b99b-a32434c28044",
   "metadata": {},
   "outputs": [],
   "source": [
    "fake = Faker()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "0c5d29b2-2d9f-4009-9f55-690af4be7ea7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a dictionary of Faker functions with descriptive labels\n",
    "faker_functions = {\n",
    "    \"person name\": fake.name,\n",
    "    \"first name\": fake.first_name,\n",
    "    \"last name\": fake.last_name,\n",
    "    \"email address\": fake.email,\n",
    "    \"phone number\": fake.phone_number,\n",
    "    \"street address\": fake.street_address,\n",
    "    \"city name\": fake.city,\n",
    "    \"state name\": fake.state,\n",
    "    \"country name\": fake.country,\n",
    "    \"zip code\": fake.zipcode,\n",
    "    \"job title\": fake.job,\n",
    "    \"company name\": fake.company,\n",
    "    \"credit card number\": fake.credit_card_number,\n",
    "    \"date of birth\": fake.date_of_birth,\n",
    "    \"username\": fake.user_name,\n",
    "    \"website url\": fake.url,\n",
    "    \"paragraph text\": fake.paragraph,\n",
    "    \"sentence text\": fake.sentence\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "998e0fa8-0ed5-4b39-8f5e-732628ace900",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Device set to use mps:0\n"
     ]
    }
   ],
   "source": [
    "pipe = pipeline(model=\"facebook/bart-large-mnli\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1a1d7010-1291-4e31-b525-83327b5e7c01",
   "metadata": {},
   "outputs": [],
   "source": [
    "result = pipe(\n",
    "    [\"The first name of a user\", \"login id\", \"full name of member\"],\n",
    "    candidate_labels=list(faker_functions.keys())\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d8cd7a50-aa79-48e4-aba9-7e78a4e64074",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_highest_score_functions(result, faker_functions, threshold=0.18):\n",
    "    sequence_to_function = {}\n",
    "    \n",
    "    for item in result:\n",
    "        sequence = item['sequence']\n",
    "        label = item['labels'][0]\n",
    "        score = item['scores'][0]\n",
    "        \n",
    "        if (score >= threshold):\n",
    "            sequence_to_function[sequence] = faker_functions.get(label)\n",
    "        else:\n",
    "            sequence_to_function[sequence] = None\n",
    "    \n",
    "    return sequence_to_function"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5c1989e2-99b8-4de3-b7f9-45c625405eb9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'The first name of a user': <bound method Provider.first_name of <faker.providers.person.en_US.Provider object at 0x34cecc050>>,\n",
       " 'login id': <bound method Provider.user_name of <faker.providers.internet.en_US.Provider object at 0x34ceb2cd0>>,\n",
       " 'full name of member': <bound method Provider.name of <faker.providers.person.en_US.Provider object at 0x34cecc050>>}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "get_highest_score_functions(result, faker_functions, threshold=0.18)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "799de95c-3d08-4da9-8a84-c3bc81ab5928",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}