File size: 5,248 Bytes
dac5ca8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
175
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "2534f67e",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Installing Gradio\n",
    "!pip install gradio transformers -q\n",
    "\n",
    "# Import the required Libraries\n",
    "import gradio as gr\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import pickle\n",
    "import transformers\n",
    "from transformers import AutoTokenizer \n",
    "from transformers import AutoConfig\n",
    "from transformers import AutoModelForSequenceClassification\n",
    "from transformers import TFAutoModelForSequenceClassification\n",
    "from transformers import pipeline\n",
    "from scipy.special import softmax"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "1dc8e034",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Requirements\n",
    "model_path =\"HOLYBOY/Sentiment_Analysis\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(model_path)\n",
    "config = AutoConfig.from_pretrained(model_path)\n",
    "model = AutoModelForSequenceClassification.from_pretrained(model_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "02f78081",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Preprocess text (username and link placeholders)\n",
    "def preprocess(text):\n",
    "    new_text = []\n",
    "    for t in text.split(\" \"):\n",
    "        t = \"@user\" if t.startswith(\"@\") and len(t) > 1 else t\n",
    "        t = \"http\" if t.startswith(\"http\") else t\n",
    "        new_text.append(t)\n",
    "    return \" \".join(new_text)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "70126857",
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---- Function to process the input and return prediction\n",
    "def sentiment_analysis(text):\n",
    "    text = preprocess(text)\n",
    "\n",
    "    encoded_input = tokenizer(text, return_tensors = \"pt\") # for PyTorch-based models\n",
    "    output = model(**encoded_input)\n",
    "    scores_ = output[0][0].detach().numpy()\n",
    "    scores_ = softmax(scores_)\n",
    "    \n",
    "    # Format output dict of scores\n",
    "    labels = [\"Negative\", \"Neutral\", \"Positive\"]\n",
    "    scores = {l:float(s) for (l,s) in zip(labels, scores_) }\n",
    "    \n",
    "    return scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4901894b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7865\n",
      "\n",
      "Could not create share link. Please check your internet connection or our status page: https://status.gradio.app. \n",
      "\n",
      "Also please ensure that your antivirus or firewall is not blocking the binary file located at: C:\\Users\\user\\anaconda3\\lib\\site-packages\\gradio\\frpc_windows_amd64_v0.2\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7865/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# ---- Gradio app interface\n",
    "app = gr.Interface(fn = sentiment_analysis,\n",
    "                   inputs = gr.Textbox(\"Input your tweet to classify or use the example provided below...\"),\n",
    "                   outputs = \"label\",\n",
    "                   title = \"Public Perception of COVID-19 Vaccines\",\n",
    "                   description  = \"This app analyzes Perception of text based on tweets about COVID-19 Vaccines using a fine-tuned distilBERT model\",\n",
    "                   interpretation = \"default\",\n",
    "                   examples = [[\"The idea of introducing the vaccine is good\"],\n",
    "                               [\"I am definately not taking the jab\"], \n",
    "                               [\"The vaccine is bad and can cause serious health implications\"], \n",
    "                               [\"I dont have any opinion \"]]\n",
    "                   )\n",
    "\n",
    "app.launch(share =True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "21753359",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6c96cb45",
   "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": "3.8.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}