Spaces:
Runtime error
Runtime error
Upload reviewsentiment-analysis.ipynb
Browse files- reviewsentiment-analysis.ipynb +305 -0
reviewsentiment-analysis.ipynb
ADDED
@@ -0,0 +1,305 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cells": [
|
3 |
+
{
|
4 |
+
"cell_type": "code",
|
5 |
+
"execution_count": 25,
|
6 |
+
"metadata": {},
|
7 |
+
"outputs": [],
|
8 |
+
"source": [
|
9 |
+
"\n",
|
10 |
+
"import tensorflow as tf\n",
|
11 |
+
"import opendatasets as od\n",
|
12 |
+
"import numpy as np\n",
|
13 |
+
"from tensorflow.keras import layers\n",
|
14 |
+
"from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline\n",
|
15 |
+
"\n",
|
16 |
+
"tf.get_logger().setLevel('ERROR')\n",
|
17 |
+
"tokenizer = AutoTokenizer.from_pretrained(\"blanchefort/rubert-base-cased-sentiment-rurewiews\")"
|
18 |
+
]
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"cell_type": "code",
|
22 |
+
"execution_count": 26,
|
23 |
+
"metadata": {},
|
24 |
+
"outputs": [],
|
25 |
+
"source": [
|
26 |
+
"model = AutoModelForSequenceClassification.from_pretrained(\"blanchefort/rubert-base-cased-sentiment-rurewiews\")"
|
27 |
+
]
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"cell_type": "code",
|
31 |
+
"execution_count": 27,
|
32 |
+
"metadata": {},
|
33 |
+
"outputs": [],
|
34 |
+
"source": [
|
35 |
+
"pipe = pipeline(\"text-classification\", model=\"blanchefort/rubert-base-cased-sentiment-rurewiews\")"
|
36 |
+
]
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"cell_type": "code",
|
40 |
+
"execution_count": 28,
|
41 |
+
"metadata": {},
|
42 |
+
"outputs": [
|
43 |
+
{
|
44 |
+
"data": {
|
45 |
+
"text/plain": [
|
46 |
+
"[{'label': 'NEUTRAL', 'score': 0.5040543079376221}]"
|
47 |
+
]
|
48 |
+
},
|
49 |
+
"execution_count": 28,
|
50 |
+
"metadata": {},
|
51 |
+
"output_type": "execute_result"
|
52 |
+
}
|
53 |
+
],
|
54 |
+
"source": [
|
55 |
+
"pipe(\"Product is ok ok sounds also good but I am not feeling like 525 watts and weight also very less 525 watts means atleast 8kg or 10kg will be there and in paper they mentioned 5 modes are different on speaker what they given modes are different totally confused with this product\")"
|
56 |
+
]
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"cell_type": "code",
|
60 |
+
"execution_count": 29,
|
61 |
+
"metadata": {},
|
62 |
+
"outputs": [
|
63 |
+
{
|
64 |
+
"name": "stdout",
|
65 |
+
"output_type": "stream",
|
66 |
+
"text": [
|
67 |
+
"Skipping, found downloaded files in \"restaurent_review\\reviews\" (use force=True to force download)\n"
|
68 |
+
]
|
69 |
+
}
|
70 |
+
],
|
71 |
+
"source": [
|
72 |
+
"import gradio as gr\n",
|
73 |
+
"import pandas as pd\n",
|
74 |
+
"import opendatasets as od\n",
|
75 |
+
"\n",
|
76 |
+
"od.download_kaggle_dataset('vigneshwarsofficial/reviews', data_dir='restaurent_review')\n",
|
77 |
+
"prediction_data = pd.read_csv('restaurent_review/reviews/Restaurant_Reviews.tsv', delimiter='\\t')\n",
|
78 |
+
"\n",
|
79 |
+
"prediction_data.pop(\"Liked\")\n",
|
80 |
+
"\n",
|
81 |
+
"data = list(prediction_data[\"Review\"])\n",
|
82 |
+
"results = pipe(data)\n"
|
83 |
+
]
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"cell_type": "code",
|
87 |
+
"execution_count": 30,
|
88 |
+
"metadata": {},
|
89 |
+
"outputs": [
|
90 |
+
{
|
91 |
+
"data": {
|
92 |
+
"text/plain": [
|
93 |
+
"['Wow... Loved this place.',\n",
|
94 |
+
" 'Crust is not good.',\n",
|
95 |
+
" 'Not tasty and the texture was just nasty.',\n",
|
96 |
+
" 'Stopped by during the late May bank holiday off Rick Steve recommendation and loved it.',\n",
|
97 |
+
" 'The selection on the menu was great and so were the prices.']"
|
98 |
+
]
|
99 |
+
},
|
100 |
+
"execution_count": 30,
|
101 |
+
"metadata": {},
|
102 |
+
"output_type": "execute_result"
|
103 |
+
}
|
104 |
+
],
|
105 |
+
"source": [
|
106 |
+
"data[:5]"
|
107 |
+
]
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"cell_type": "code",
|
111 |
+
"execution_count": 31,
|
112 |
+
"metadata": {},
|
113 |
+
"outputs": [
|
114 |
+
{
|
115 |
+
"data": {
|
116 |
+
"text/html": [
|
117 |
+
"<div>\n",
|
118 |
+
"<style scoped>\n",
|
119 |
+
" .dataframe tbody tr th:only-of-type {\n",
|
120 |
+
" vertical-align: middle;\n",
|
121 |
+
" }\n",
|
122 |
+
"\n",
|
123 |
+
" .dataframe tbody tr th {\n",
|
124 |
+
" vertical-align: top;\n",
|
125 |
+
" }\n",
|
126 |
+
"\n",
|
127 |
+
" .dataframe thead th {\n",
|
128 |
+
" text-align: right;\n",
|
129 |
+
" }\n",
|
130 |
+
"</style>\n",
|
131 |
+
"<table border=\"1\" class=\"dataframe\">\n",
|
132 |
+
" <thead>\n",
|
133 |
+
" <tr style=\"text-align: right;\">\n",
|
134 |
+
" <th></th>\n",
|
135 |
+
" <th>count</th>\n",
|
136 |
+
" <th>sentiment</th>\n",
|
137 |
+
" </tr>\n",
|
138 |
+
" </thead>\n",
|
139 |
+
" <tbody>\n",
|
140 |
+
" <tr>\n",
|
141 |
+
" <th>0</th>\n",
|
142 |
+
" <td>283</td>\n",
|
143 |
+
" <td>Positive</td>\n",
|
144 |
+
" </tr>\n",
|
145 |
+
" <tr>\n",
|
146 |
+
" <th>1</th>\n",
|
147 |
+
" <td>419</td>\n",
|
148 |
+
" <td>Negative</td>\n",
|
149 |
+
" </tr>\n",
|
150 |
+
" <tr>\n",
|
151 |
+
" <th>2</th>\n",
|
152 |
+
" <td>298</td>\n",
|
153 |
+
" <td>Neutral</td>\n",
|
154 |
+
" </tr>\n",
|
155 |
+
" </tbody>\n",
|
156 |
+
"</table>\n",
|
157 |
+
"</div>"
|
158 |
+
],
|
159 |
+
"text/plain": [
|
160 |
+
" count sentiment\n",
|
161 |
+
"0 283 Positive\n",
|
162 |
+
"1 419 Negative\n",
|
163 |
+
"2 298 Neutral"
|
164 |
+
]
|
165 |
+
},
|
166 |
+
"execution_count": 31,
|
167 |
+
"metadata": {},
|
168 |
+
"output_type": "execute_result"
|
169 |
+
}
|
170 |
+
],
|
171 |
+
"source": [
|
172 |
+
"positive_counter = 0 \n",
|
173 |
+
"negative_counter = 0\n",
|
174 |
+
"neutral_counter = 0\n",
|
175 |
+
"for x in results:\n",
|
176 |
+
" if x['label'] == 'POSITIVE':\n",
|
177 |
+
" positive_counter = positive_counter + 1\n",
|
178 |
+
" elif x['label'] == 'NEGATIVE':\n",
|
179 |
+
" negative_counter = negative_counter + 1\n",
|
180 |
+
" else:\n",
|
181 |
+
" neutral_counter = neutral_counter + 1\n",
|
182 |
+
"\n",
|
183 |
+
"result_data = pd.DataFrame({\n",
|
184 |
+
" 'count': [positive_counter, negative_counter, neutral_counter],\n",
|
185 |
+
" 'sentiment': ['Positive', 'Negative', 'Neutral']\n",
|
186 |
+
"})\n",
|
187 |
+
"\n",
|
188 |
+
"result_data"
|
189 |
+
]
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"cell_type": "code",
|
193 |
+
"execution_count": 32,
|
194 |
+
"metadata": {},
|
195 |
+
"outputs": [
|
196 |
+
{
|
197 |
+
"name": "stdout",
|
198 |
+
"output_type": "stream",
|
199 |
+
"text": [
|
200 |
+
"Running on local URL: http://127.0.0.1:7866\n",
|
201 |
+
"Running on public URL: https://af39480688d32c192a.gradio.live\n",
|
202 |
+
"\n",
|
203 |
+
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
|
204 |
+
]
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"data": {
|
208 |
+
"text/html": [
|
209 |
+
"<div><iframe src=\"https://af39480688d32c192a.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
|
210 |
+
],
|
211 |
+
"text/plain": [
|
212 |
+
"<IPython.core.display.HTML object>"
|
213 |
+
]
|
214 |
+
},
|
215 |
+
"metadata": {},
|
216 |
+
"output_type": "display_data"
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"data": {
|
220 |
+
"text/plain": []
|
221 |
+
},
|
222 |
+
"execution_count": 32,
|
223 |
+
"metadata": {},
|
224 |
+
"output_type": "execute_result"
|
225 |
+
}
|
226 |
+
],
|
227 |
+
"source": [
|
228 |
+
"single_input_demo = gr.Interface.from_pipeline(pipe, title=\"Sentiment Analysis\")\n",
|
229 |
+
"single_input_demo.launch(share=True)"
|
230 |
+
]
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"cell_type": "code",
|
234 |
+
"execution_count": 33,
|
235 |
+
"metadata": {},
|
236 |
+
"outputs": [
|
237 |
+
{
|
238 |
+
"name": "stdout",
|
239 |
+
"output_type": "stream",
|
240 |
+
"text": [
|
241 |
+
"Running on local URL: http://127.0.0.1:7867\n",
|
242 |
+
"Running on public URL: https://4ce90a546387218f07.gradio.live\n",
|
243 |
+
"\n",
|
244 |
+
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from Terminal to deploy to Spaces (https://huggingface.co/spaces)\n"
|
245 |
+
]
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"data": {
|
249 |
+
"text/html": [
|
250 |
+
"<div><iframe src=\"https://4ce90a546387218f07.gradio.live\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
|
251 |
+
],
|
252 |
+
"text/plain": [
|
253 |
+
"<IPython.core.display.HTML object>"
|
254 |
+
]
|
255 |
+
},
|
256 |
+
"metadata": {},
|
257 |
+
"output_type": "display_data"
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"data": {
|
261 |
+
"text/plain": []
|
262 |
+
},
|
263 |
+
"execution_count": 33,
|
264 |
+
"metadata": {},
|
265 |
+
"output_type": "execute_result"
|
266 |
+
}
|
267 |
+
],
|
268 |
+
"source": [
|
269 |
+
"import plotly.express as plt\n",
|
270 |
+
"\n",
|
271 |
+
"def plotly_plot(): \n",
|
272 |
+
" p = plt.bar(result_data, x='sentiment', y='count', title='Restaurent Review Analysis', color=\"count\")\n",
|
273 |
+
" return p\n",
|
274 |
+
"\n",
|
275 |
+
"# show the results\n",
|
276 |
+
"outputs = gr.Plot()\n",
|
277 |
+
"\n",
|
278 |
+
"demo = gr.Interface(fn=plotly_plot, inputs=None, outputs=outputs, title=\"Restaurant Customer Review Sentiment Analysis\")\n",
|
279 |
+
"\n",
|
280 |
+
"demo.launch(share=True)"
|
281 |
+
]
|
282 |
+
}
|
283 |
+
],
|
284 |
+
"metadata": {
|
285 |
+
"kernelspec": {
|
286 |
+
"display_name": "Python 3",
|
287 |
+
"language": "python",
|
288 |
+
"name": "python3"
|
289 |
+
},
|
290 |
+
"language_info": {
|
291 |
+
"codemirror_mode": {
|
292 |
+
"name": "ipython",
|
293 |
+
"version": 3
|
294 |
+
},
|
295 |
+
"file_extension": ".py",
|
296 |
+
"mimetype": "text/x-python",
|
297 |
+
"name": "python",
|
298 |
+
"nbconvert_exporter": "python",
|
299 |
+
"pygments_lexer": "ipython3",
|
300 |
+
"version": "3.10.6"
|
301 |
+
}
|
302 |
+
},
|
303 |
+
"nbformat": 4,
|
304 |
+
"nbformat_minor": 2
|
305 |
+
}
|