File size: 16,498 Bytes
b9157b9
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
8b6417b
b9157b9
8b6417b
 
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
 
b9157b9
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b6417b
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
8b6417b
 
 
 
 
 
 
 
 
b9157b9
 
 
 
 
 
 
 
8b6417b
 
 
 
 
 
 
 
 
 
91db1e9
8b6417b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91db1e9
8b6417b
 
 
 
 
 
 
91db1e9
8b6417b
 
 
 
 
 
 
91db1e9
8b6417b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9157b9
 
 
8b6417b
b9157b9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "fce70006-809b-4c98-b89c-00910b8bbea1",
   "metadata": {},
   "source": [
    "Implementation for blog post"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "1eaa3a9f-0b39-4d77-91d6-f935d226ac98",
   "metadata": {},
   "outputs": [],
   "source": [
    "import math\n",
    "import pickle\n",
    "import os\n",
    "import time\n",
    "import matplotlib.pyplot as plt\n",
    "from tabulate import tabulate\n",
    "\n",
    "from transformers import pipeline\n",
    "import json\n",
    "import pandas as pd\n",
    "\n",
    "# Get candidate labels\n",
    "with open(\"packing_label_structure.json\", \"r\") as file:\n",
    "    candidate_labels = json.load(file)\n",
    "keys_list = list(candidate_labels.keys())\n",
    "\n",
    "# Load test data (list of dictionaries)\n",
    "# with open(\"test_data.json\", \"r\") as file:\n",
    "#     packing_data = json.load(file)\n",
    "# Extract trip descriptions and classification (trip_types)\n",
    "# trip_descriptions = [trip['description'] for trip in packing_data]\n",
    "# trip_types = [trip['trip_types'] for trip in packing_data]\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "bb1bc7ed-227e-4c0b-b769-ead4daf01c57",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      " activity_type :\n",
      "\t hut trek (summer)\n",
      "\t hut trek (winter)\n",
      "\t camping trip (wild camping)\n",
      "\t camping trip (campground)\n",
      "\t ski tour / skitour\n",
      "\t snowboard / splitboard trip\n",
      "\t long-distance hike / thru-hike\n",
      "\t digital nomad trip\n",
      "\t city trip\n",
      "\t road trip (car/camper)\n",
      "\t festival trip\n",
      "\t yoga / wellness retreat\n",
      "\t micro-adventure / weekend trip\n",
      "\t beach vacation\n",
      "\t cultural exploration\n",
      "\t nature escape\n",
      "\n",
      " activities :\n",
      "\t swimming\n",
      "\t going to the beach\n",
      "\t relaxing\n",
      "\t sightseeing\n",
      "\t biking\n",
      "\t running\n",
      "\t skiing\n",
      "\t cross-country skiing\n",
      "\t ski touring\n",
      "\t hiking\n",
      "\t hut-to-hut hiking\n",
      "\t rock climbing\n",
      "\t ice climbing\n",
      "\t snowshoe hiking\n",
      "\t kayaking / canoeing\n",
      "\t stand-up paddleboarding (SUP)\n",
      "\t snorkeling\n",
      "\t scuba diving\n",
      "\t surfing\n",
      "\t paragliding\n",
      "\t horseback riding\n",
      "\t photography\n",
      "\t fishing\n",
      "\t rafting\n",
      "\t yoga\n",
      "\n",
      " climate_or_season :\n",
      "\t cold destination / winter\n",
      "\t warm destination / summer\n",
      "\t variable weather / spring / autumn\n",
      "\t tropical / humid\n",
      "\t dry / desert-like\n",
      "\t rainy climate\n",
      "\n",
      " style_or_comfort :\n",
      "\t ultralight\n",
      "\t lightweight (but comfortable)\n",
      "\t luxury (including evening wear)\n",
      "\t minimalist\n",
      "\n",
      " dress_code :\n",
      "\t casual\n",
      "\t formal (business trip)\n",
      "\t conservative\n",
      "\n",
      " accommodation :\n",
      "\t indoor\n",
      "\t huts with half board\n",
      "\t sleeping in a tent\n",
      "\t sleeping in a car\n",
      "\n",
      " transportation :\n",
      "\t own vehicle\n",
      "\t no own vehicle\n",
      "\n",
      " special_conditions :\n",
      "\t off-grid / no electricity\n",
      "\t self-supported (bring your own cooking gear)\n",
      "\t travel with children\n",
      "\t pet-friendly\n",
      "\t snow and ice\n",
      "\t high alpine terrain\n",
      "\t snow, ice and avalanche-prone terrain\n",
      "\t no special conditions to consider\n",
      "\n",
      " trip_length_days :\n",
      "\t 1 day\n",
      "\t 2 days\n",
      "\t 3 days\n",
      "\t 4 days\n",
      "\t 5 days\n",
      "\t 6 days\n",
      "\t 7 days\n",
      "\t 7+ days\n"
     ]
    }
   ],
   "source": [
    "for key in candidate_labels:\n",
    "    print(\"\\n\", key, \":\")\n",
    "    for item in candidate_labels[key]:\n",
    "        print(\"\\t\", item)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "4b3a1bcb-3450-4128-b941-952f145baf99",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Hardware accelerator e.g. GPU is available in the environment, but no `device` argument is passed to the `Pipeline` object. Model will be on CPU.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                             Label     Score\n",
      "0                   beach vacation  0.376311\n",
      "1   micro-adventure / weekend trip  0.350168\n",
      "2                    nature escape  0.133974\n",
      "3               digital nomad trip  0.031636\n",
      "4             cultural exploration  0.031271\n",
      "5          yoga / wellness retreat  0.012846\n",
      "6                    festival trip  0.012700\n",
      "7   long-distance hike / thru-hike  0.009527\n",
      "8                hut trek (summer)  0.008148\n",
      "9                        city trip  0.007793\n",
      "10          road trip (car/camper)  0.006512\n",
      "11              ski tour / skitour  0.005670\n",
      "12       camping trip (campground)  0.004448\n",
      "13     snowboard / splitboard trip  0.004113\n",
      "14     camping trip (wild camping)  0.002714\n",
      "15               hut trek (winter)  0.002170\n"
     ]
    }
   ],
   "source": [
    "key = keys_list[0]\n",
    "model_name = \"facebook/bart-large-mnli\"\n",
    "trip_descr = \"I am planning a trip to Greece with my boyfriend, where we will visit two islands. We have booked an apartment on each island for a few days and plan to spend most of our time relaxing. Our main goals are to enjoy the beach, try delicious local food, and possibly go on a hike—if it’s not too hot. We will be relying solely on public transport. We’re in our late 20s and traveling from the Netherlands.\"\n",
    "classifier = pipeline(\"zero-shot-classification\", model = model_name)\n",
    "result = classifier(trip_descr, candidate_labels[keys_list[0]])\n",
    "# Create DataFrame\n",
    "df = pd.DataFrame({\n",
    "    \"Label\": result[\"labels\"],\n",
    "    \"Score\": result[\"scores\"]\n",
    "})\n",
    "print(df)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "04208f9e-59bb-408b-92c6-941d064bf43d",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "beach vacation\n"
     ]
    }
   ],
   "source": [
    "# the labels are sorted by score. We choose the first one as our best guess for a class label\n",
    "class_label = result[\"labels\"][0]\n",
    "print(class_label)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9f5f1c45-b411-4de1-a0a6-a7ecde5d8eae",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                             Label     Score\n",
      "0                   beach vacation  0.376311\n",
      "1   micro-adventure / weekend trip  0.350168\n",
      "2                    nature escape  0.133974\n",
      "3               digital nomad trip  0.031636\n",
      "4             cultural exploration  0.031271\n",
      "5          yoga / wellness retreat  0.012846\n",
      "6                    festival trip  0.012700\n",
      "7   long-distance hike / thru-hike  0.009527\n",
      "8                hut trek (summer)  0.008148\n",
      "9                        city trip  0.007793\n",
      "10          road trip (car/camper)  0.006512\n",
      "11              ski tour / skitour  0.005670\n",
      "12       camping trip (campground)  0.004448\n",
      "13     snowboard / splitboard trip  0.004113\n",
      "14     camping trip (wild camping)  0.002714\n",
      "15               hut trek (winter)  0.002170\n"
     ]
    }
   ],
   "source": [
    "# we do this for each superclass and receive a list of class labels for our trip. We did do things differently for activities\n",
    "cut_off = 0.5\n",
    "result_activ = classifier(trip_descr, candidate_labels[\"activities\"], multi_label=True)\n",
    "indices = [i for i, score in enumerate(result_activ['scores']) if score > cut_off]\n",
    "classes = [result_activ['labels'][i] for i in indices]\n",
    "\n",
    "df = pd.DataFrame({\n",
    "    \"Label\": result[\"labels\"],\n",
    "    \"Score\": result[\"scores\"]\n",
    "})\n",
    "print(df)\n",
    "print(classes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "7c5c50c4-7d58-4f5a-8f22-e4c06298a2f7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['going to the beach', 'relaxing', 'hiking']\n"
     ]
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3a7287c2-78f0-4a53-af72-1bc0f62da36f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# doing this for all superclasses, depending on local machine this might take a while\n",
    "def pred_trip(model_name, trip_descr, cut_off = 0.5):\n",
    "    \"\"\"\n",
    "    Classifies trip\n",
    "    \n",
    "    Parameters:\n",
    "    model_name: name of hugging-face model\n",
    "    trip_descr: text describing the trip\n",
    "    cut_off: cut_off for choosing activities\n",
    "\n",
    "    Returns:\n",
    "    pd Dataframe: with class predictions and true values\n",
    "    \"\"\"\n",
    "    \n",
    "    classifier = pipeline(\"zero-shot-classification\", model=model_name)\n",
    "    df = pd.DataFrame(columns=['superclass', 'pred_class'])\n",
    "    for i, key in enumerate(keys_list):\n",
    "        print(f\"\\rProcessing {i + 1}/{len(keys_list)}\", end=\"\", flush=True)\n",
    "        if key == 'activities':\n",
    "            result = classifier(trip_descr, candidate_labels[key], multi_label=True)\n",
    "            indices = [i for i, score in enumerate(result['scores']) if score > cut_off]\n",
    "            classes = [result['labels'][i] for i in indices]\n",
    "        else:\n",
    "            result = classifier(trip_descr, candidate_labels[key])\n",
    "            classes = result[\"labels\"][0]\n",
    "        df.loc[i] = [key, classes]\n",
    "    return df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "43481d4c-039a-4a37-bd6d-dfe638bf9732",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Hardware accelerator e.g. GPU is available in the environment, but no `device` argument is passed to the `Pipeline` object. Model will be on CPU.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processing 9/9           superclass                              pred_class\n",
      "0       activity_type                          beach vacation\n",
      "1          activities  [going to the beach, relaxing, hiking]\n",
      "2   climate_or_season               warm destination / summer\n",
      "3    style_or_comfort                              minimalist\n",
      "4          dress_code                                  casual\n",
      "5       accommodation                    huts with half board\n",
      "6      transportation                          no own vehicle\n",
      "7  special_conditions               off-grid / no electricity\n",
      "8    trip_length_days                                 7+ days\n"
     ]
    }
   ],
   "source": [
    "result = pred_trip(model_name, trip_descr, cut_off = 0.5)\n",
    "print(result)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c4799d6b-6ab5-42da-a992-afe3666d0015",
   "metadata": {},
   "source": [
    "Now use gradio app"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "35e14ac8-4445-4586-a115-081cf1ef2686",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prerequisites\n",
    "from transformers import pipeline\n",
    "import json\n",
    "import pandas as pd\n",
    "import gradio as gr\n",
    "\n",
    "# get candidate labels\n",
    "with open(\"packing_label_structure.json\", \"r\") as file:\n",
    "    candidate_labels = json.load(file)\n",
    "keys_list = list(candidate_labels.keys())\n",
    "\n",
    "# Load packing item data\n",
    "with open(\"packing_templates_self_supported_offgrid_expanded.json\", \"r\") as file:\n",
    "    packing_items = json.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "8eefd4cc-c375-4cc0-956b-472b36bafdb7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7860\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7860/\" 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"
    }
   ],
   "source": [
    "demo = gr.Interface(\n",
    "    fn=pred_trip,\n",
    "    inputs=[\n",
    "        gr.Textbox(label=\"Model name\", value = \"MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli\"),\n",
    "        gr.Textbox(label=\"Trip description\"),\n",
    "        gr.Number(label=\"Activity cut-off\", value = 0.5),\n",
    "    ],\n",
    "    # outputs=\"dataframe\",\n",
    "    outputs=[gr.Dataframe(label=\"DataFrame\"), gr.Textbox(label=\"List of words\")],\n",
    "    title=\"Trip classification\",\n",
    "    description=\"Enter a text describing your trip\",\n",
    ")\n",
    "\n",
    "# Launch the Gradio app\n",
    "if __name__ == \"__main__\":\n",
    "    demo.launch()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "11006b67-bfd5-42a7-99c4-36c3db3affac",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Hardware accelerator e.g. GPU is available in the environment, but no `device` argument is passed to the `Pipeline` object. Model will be on CPU.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Processing 9/9"
     ]
    }
   ],
   "source": [
    "test = pred_trip(model_name, trip_descr, cut_off = 0.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0f6cd8d1-b742-4034-a3e2-e55c3ddd2904",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "5db16415-47c1-42c6-861c-5d26f4b3bb03",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "facebook/bart-large-mnli\n",
      "I am planning a trip to Greece with my boyfriend, where we will visit two islands. We have booked an apartment on each island for a few days and plan to spend most of our time relaxing. Our main goals are to enjoy the beach, try delicious local food, and possibly go on a hike—if it’s not too hot. We will be relying solely on public transport. We’re in our late 20s and traveling from the Netherlands.\n"
     ]
    }
   ],
   "source": [
    "print(model_name)\n",
    "print(trip_descr)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bbca6bc6-bd97-4d43-8a6e-fe338f2735f2",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python (huggingface_env)",
   "language": "python",
   "name": "huggingface_env"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.20"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}