File size: 22,425 Bytes
fab07ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f56cc5ad",
   "metadata": {},
   "source": [
    "# NDIS Project - Azure OpenAI - PBSP Scoring - Page 4 - When to implement strategies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a8d844ea",
   "metadata": {
    "hide_input": false
   },
   "outputs": [],
   "source": [
    "import openai\n",
    "import re\n",
    "from ipywidgets import interact\n",
    "import ipywidgets as widgets\n",
    "from IPython.display import display, clear_output, Javascript, HTML, Markdown\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.ticker as mtick\n",
    "import json\n",
    "import spacy\n",
    "from spacy import displacy\n",
    "from dotenv import load_dotenv\n",
    "import pandas as pd\n",
    "import argilla as rg\n",
    "from argilla.metrics.text_classification import f1\n",
    "import warnings\n",
    "warnings.filterwarnings('ignore')\n",
    "%matplotlib inline\n",
    "pd.set_option('display.max_rows', 500)\n",
    "pd.set_option('display.max_colwidth', 10000)\n",
    "pd.set_option('display.width', 10000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96b83a1d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#initializations\n",
    "openai.api_key = os.environ['API_KEY']\n",
    "openai.api_base = os.environ['API_BASE']\n",
    "openai.api_type = os.environ['API_TYPE']\n",
    "openai.api_version = os.environ['API_VERSION']\n",
    "deployment_name = os.environ['DEPLOYMENT_ID']\n",
    "\n",
    "#argilla\n",
    "rg.init(\n",
    "    api_url=os.environ[\"ARGILLA_API_URL\"],\n",
    "    api_key=os.environ[\"ARGILLA_API_KEY\"]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8934eadb",
   "metadata": {},
   "outputs": [],
   "source": [
    "#sentence extraction\n",
    "def extract_sentences(paragraph):\n",
    "    symbols = ['\\\\.', '!', '\\\\?', ';', ':', ',', '\\\\_', '\\n', '\\\\-']\n",
    "    pattern = '|'.join([f'{symbol}' for symbol in symbols])\n",
    "    sentences = re.split(pattern, paragraph)\n",
    "    sentences = [sentence.strip() for sentence in sentences if sentence.strip()]\n",
    "    return sentences"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "02fda761",
   "metadata": {},
   "outputs": [],
   "source": [
    "def process_response(response, query):\n",
    "    sentences = []\n",
    "    topics = []\n",
    "    scores = []\n",
    "    lines = response.strip().split(\"\\n\")\n",
    "    for line in lines:\n",
    "        if \"When to implement:\" in line:\n",
    "            topic = \"WHEN TO IMPLEMENT\"\n",
    "        elif \"None:\" in line:\n",
    "            topic = \"NONE\"\n",
    "        else:\n",
    "            try:\n",
    "                phrase = line.split(\"(Confidence Score:\")[0].strip()\n",
    "                score = float(line.split(\"(Confidence Score:\")[1].strip().replace(\")\", \"\"))\n",
    "                sentences.append(phrase)\n",
    "                topics.append(topic)\n",
    "                scores.append(score)\n",
    "            except:\n",
    "                pass\n",
    "    result_df = pd.DataFrame({'Phrase': sentences, 'Topic': topics, 'Score': scores})\n",
    "    try:\n",
    "        result_df['Phrase'] = result_df['Phrase'].str.replace('\\d+\\.', '', regex=True)\n",
    "        result_df['Phrase'] = result_df['Phrase'].str.replace('^\\s', '', regex=True)\n",
    "    except:\n",
    "        sentences = extract_sentences(query)\n",
    "        topics = ['NONE'] * len(sentences)\n",
    "        scores = [0.9] * len(sentences)\n",
    "        result_df = pd.DataFrame({'Phrase': sentences, 'Topic': topics, 'Score': scores})\n",
    "    return result_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "714fafb4",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_prompt(query):\n",
    "    prompt = f\"\"\"\n",
    "    The paragraph below, which is written by a disability practitioner in a behaviour support plan, covers one or more strategies that will be implemented when dealing with the person with a disability:\n",
    "\n",
    "    Practitioner Paragraph:\n",
    "    {query}\n",
    "\n",
    "    Requirement:\n",
    "    - From the practitioner paragraph above, identify the phrases that represent when each of the mentioned strategies needs to be implemented. \n",
    "\n",
    "    Specifications of a correct answer:\n",
    "    - Please provide a response that closely matches the information in the practitioner paragraph and does not deviate significantly from it.\n",
    "    - Provide your answer in a numbered list. \n",
    "    - All the phrases in your answer must be exact substrings in the practitioner paragraph. without changing any characters.\n",
    "    - All the upper case and lower case characters in the phrases in your answer must match the upper case and lower case characters in the practitioner paragraph.\n",
    "    - Do not add an \"ing\" to any verbs in your answer if the original verbs in the practitioner paragraph do not include \"ing\".\n",
    "    - Start numbering the phrases from number 1.\n",
    "    - Start your answer for the phrases with the title \"When to implement:\"\n",
    "    - For each phrase in your answer, provide a confidence score that ranges between 0.50 and 1.00, where a score of 0.50 indicates you are very weakly confident that the phrase represents when the strategy needs to be implemented, whereas a score of 1.00 indicates you are very strongly confident that the phrase represents when the strategy needs to be implemented.\n",
    "    - Never include any phrase in your answer that does not exist in the practitioner paragraph.\n",
    "    - If none of the phrases in the practitioner paragraph mentions when the strategies need to be implemented, do not include a list titled \"When to implement:\" in your answer.\n",
    "    - Include another numbered list titled \"None:\", which includes all the remaining phrases in the practitioner paragraph that do not represent when the strategies need to be implemented. Provide a confidence score for each of these phrases as well.\n",
    "\n",
    "    Example correct answer:\n",
    "\n",
    "    When to implement:\n",
    "    1. volunteer at an animal shelter or attend a petting zoo on a monthly basis. (Confidence Score: 0.97)\n",
    "    2. facilitating outdoor activities such as walks or hikes on a weekly basis. (Confidence Score: 0.95)\n",
    "    3. providing job coaching to help Eddie succeed in his role initially on a daily basis and gradually decreasing to bi-weekly. (Confidence Score: 0.93)\n",
    "    4. identifying educational resources such as online courses or local music schools on an ongoing basis. (Confidence Score: 0.90)\n",
    "\n",
    "    None:\n",
    "    1. I support Eddie, who is a 25-year old man with a disability. (Confidence Score: 0.96)\n",
    "    2. Taylor has a plenty of likes, interests and hobbies. In the following lines, I will expain the strategies I am using these to enhance his quality of life.  (Confidence Score: 0.94)\n",
    "    \"\"\"\n",
    "    return prompt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99da147a",
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_response_chatgpt(prompt):\n",
    "    response=openai.ChatCompletion.create(   \n",
    "        engine=deployment_name,   \n",
    "        messages=[         \n",
    "        {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},                  \n",
    "        {\"role\": \"user\", \"content\": prompt}     \n",
    "        ],\n",
    "        temperature=0\n",
    "    )\n",
    "    reply = response[\"choices\"][0][\"message\"][\"content\"]\n",
    "    return reply"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f4592a82",
   "metadata": {},
   "outputs": [],
   "source": [
    "#query = \"\"\"\n",
    "#As a disability practitioner who supports Taylor, a 15-year-old boy with a disability, there are several strategies that can be implemented to enhance his quality of life. One important strategy is to identify and support his interests. Taylor enjoys playing video games, so incorporating video game time into his daily schedule would be beneficial for him. Additionally, Taylor is a fan of superhero movies, so setting up movie nights with his family or friends once a month would be a fun way for him to enjoy his interest. Another strategy is to support Taylor's relationships. Taylor has expressed an interest in making new friends, so facilitating social events or encouraging him to join a club related to his interests could help him expand his social circle. Additionally, Taylor has a close relationship with his older sister, so setting up a weekly video chat or arranging for them to participate in an activity together every other week would be important. In addition, supporting Taylor's health is important for his overall well-being. Taylor enjoys swimming, so facilitating regular swimming sessions at the local pool twice a week would be beneficial for his physical and mental health. These strategies aim to enhance Taylor's quality of life and promote his overall well-being. Another important strategy is to support Taylor's education. Taylor has expressed a desire to improve his math skills, so I will work with him to identify educational resources and set up weekly tutoring sessions. Additionally, Taylor has shown an interest in learning to cook, so setting up bi-weekly cooking classes would provide him with an opportunity to learn a new skill and gain confidence in the kitchen. These strategies will help Taylor pursue his educational interests and achieve his personal goals.\n",
    "#\"\"\"\n",
    "#prompt = get_prompt(query)\n",
    "#response = get_response_chatgpt(prompt)\n",
    "#result_df = process_response(response, query)\n",
    "#print(response)\n",
    "#result_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "56d2bac8",
   "metadata": {},
   "outputs": [],
   "source": [
    "def convert_df(result_df):\n",
    "    new_df = pd.DataFrame(columns=['text', 'prediction'])\n",
    "    new_df['text'] = result_df['Phrase']\n",
    "    new_df['prediction'] = result_df.apply(lambda row: [[row['Topic'], row['Score']]], axis=1)\n",
    "    return new_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "905eaf2a",
   "metadata": {},
   "outputs": [],
   "source": [
    "topic_color_dict = {\n",
    "        'WHEN TO IMPLEMENT': '#90EE90',\n",
    "        'NONE': '#F08080'\n",
    "    }\n",
    "\n",
    "def color(df, color):\n",
    "    return df.style.format({'Score': '{:,.2%}'.format}).bar(subset=['Score'], color=color)\n",
    "\n",
    "def annotate_query(highlights, query, topics):\n",
    "    ents = []\n",
    "    for h, t in zip(highlights, topics):\n",
    "        ent_dict = {}\n",
    "        for match in re.finditer(h, query, re.IGNORECASE):\n",
    "            ent_dict = {\"start\": match.start(), \"end\": match.end(), \"label\": t}\n",
    "            break\n",
    "        if len(ent_dict.keys()) > 0:\n",
    "            ents.append(ent_dict)\n",
    "        else:\n",
    "            h_re = \" \".join(h.split(\" \")[1:])\n",
    "            print(h_re)\n",
    "            for match in re.finditer(h_re, query, re.IGNORECASE):\n",
    "                ent_dict = {\"start\": match.start(), \"end\": match.end(), \"label\": t}\n",
    "                break\n",
    "            if len(ent_dict.keys()) > 0:\n",
    "                ents.append(ent_dict)\n",
    "    return ents\n",
    "\n",
    "def path_to_image_html(path):\n",
    "    return path\n",
    "\n",
    "passing_score = 0.75\n",
    "final_passing = 0.0\n",
    "def display_final_df(agg_df):\n",
    "    crits = [\n",
    "            'WHEN TO IMPLEMENT'\n",
    "        ]\n",
    "    if not isinstance(agg_df, str):\n",
    "        tags = []\n",
    "        orig_crits = crits\n",
    "        crits = [x for x in crits if x in agg_df.index.tolist()]\n",
    "        bools = [agg_df.loc[crit, 'Final_Score'] > final_passing for crit in crits]\n",
    "        paths = ['YES' if x else 'NO' for x in bools]\n",
    "        df = pd.DataFrame({'When to Implement': crits, 'USED': paths})\n",
    "        rem_crits = [x for x in orig_crits if x not in crits]\n",
    "        if len(rem_crits) > 0:\n",
    "            df2 = pd.DataFrame({'When to Implement': rem_crits, 'USED': ['NO'] * len(rem_crits)})\n",
    "            df = pd.concat([df, df2])\n",
    "    else:\n",
    "        df = pd.DataFrame({'When to Implement': [crits[0]], 'USED': ['NO']})\n",
    "    df = df.set_index('When to Implement')\n",
    "    pd.set_option('display.max_colwidth', None)\n",
    "    display(HTML('<div style=\"text-align: center;\">' + df.to_html(classes=[\"align-center\"], index=True, escape=False ,formatters=dict(USED=path_to_image_html)) + '</div>'))\n",
    "    "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2c6e9fe7",
   "metadata": {},
   "source": [
    "### <font color='red'>Quality Marker Q7a:</font> \n",
    "#### All strategies are described in enough detail for someone to understand what needs to be done <font color='red'>and when it needs to be implemented.</font>"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "76dd8cab",
   "metadata": {
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "#demo with Voila\n",
    "\n",
    "bhvr_label = widgets.Label(value='Please type your answer:')\n",
    "bhvr_text_input = widgets.Textarea(\n",
    "    value='',\n",
    "    placeholder='Type your answer',\n",
    "    description='',\n",
    "    disabled=False,\n",
    "    layout={'height': '300px', 'width': '90%'}\n",
    ")\n",
    "\n",
    "bhvr_nlp_btn = widgets.Button(\n",
    "    description='Score Answer',\n",
    "    disabled=False,\n",
    "    button_style='success', # 'success', 'info', 'warning', 'danger' or ''\n",
    "    tooltip='Score Answer',\n",
    "    icon='check',\n",
    "    layout={'height': '70px', 'width': '250px'}\n",
    ")\n",
    "bhvr_agr_btn = widgets.Button(\n",
    "    description='Validate Data',\n",
    "    disabled=False,\n",
    "    button_style='success', # 'success', 'info', 'warning', 'danger' or ''\n",
    "    tooltip='Validate Data',\n",
    "    icon='check',\n",
    "    layout={'height': '70px', 'width': '250px'}\n",
    ")\n",
    "bhvr_eval_btn = widgets.Button(\n",
    "    description='Evaluate Model',\n",
    "    disabled=False,\n",
    "    button_style='success', # 'success', 'info', 'warning', 'danger' or ''\n",
    "    tooltip='Evaluate Model',\n",
    "    icon='check',\n",
    "    layout={'height': '70px', 'width': '250px'}\n",
    ")\n",
    "btn_box = widgets.HBox([bhvr_nlp_btn, bhvr_agr_btn, bhvr_eval_btn], \n",
    "                       layout={'width': '100%', 'height': '160%'})\n",
    "bhvr_outt = widgets.Output()\n",
    "bhvr_outt.layout.height = '100%'\n",
    "bhvr_outt.layout.width = '100%'\n",
    "bhvr_box = widgets.VBox([bhvr_text_input, btn_box, bhvr_outt], \n",
    "                   layout={'width': '100%', 'height': '160%'})\n",
    "dataset_rg_name = 'pbsp-page4-when-to-implement-argilla-ds'\n",
    "dataset_rg_url = f'http://localhost:6900/datasets/argilla/{dataset_rg_name}'\n",
    "agrilla_df = None\n",
    "annotated = False\n",
    "def on_bhvr_button_next(b):\n",
    "    global agrilla_df\n",
    "    with bhvr_outt:\n",
    "        clear_output()\n",
    "        query = bhvr_text_input.value\n",
    "        prompt = get_prompt(query)\n",
    "        response = get_response_chatgpt(prompt)\n",
    "        result_df = process_response(response, query)\n",
    "        sub_result_df = result_df[(result_df['Score'] >= passing_score) & (result_df['Topic'] != 'NONE')]\n",
    "        sub_2_result_df = result_df[result_df['Topic'] == 'NONE']\n",
    "        highlights = []\n",
    "        if len(sub_result_df) > 0:\n",
    "            highlights = sub_result_df['Phrase'].tolist()\n",
    "            highlight_topics = sub_result_df['Topic'].tolist()    \n",
    "            ents = annotate_query(highlights, query, highlight_topics)\n",
    "            colors = {}\n",
    "            for ent, ht in zip(ents, highlight_topics):\n",
    "                colors[ent['label']] = topic_color_dict[ht]\n",
    "\n",
    "            ex = [{\"text\": query,\n",
    "                   \"ents\": ents,\n",
    "                   \"title\": None}]\n",
    "            title = \"When to Implement Highlights\"\n",
    "            display(HTML(f'<center><h1>{title}</h1></center>'))\n",
    "            html = displacy.render(ex, style=\"ent\", manual=True, jupyter=True, options={'colors': colors})\n",
    "            display(HTML(html))\n",
    "            title = \"When to Implement Classifications\"\n",
    "            display(HTML(f'<center><h1>{title}</h1></center>'))\n",
    "            for top in topic_color_dict.keys():\n",
    "                top_result_df = sub_result_df[sub_result_df['Topic'] == top]\n",
    "                if len(top_result_df) > 0:\n",
    "                    top_result_df = top_result_df.sort_values(by='Score', ascending=False).reset_index(drop=True)\n",
    "                    top_result_df = top_result_df.set_index('Phrase')\n",
    "                    top_result_df = top_result_df[['Score']]\n",
    "                    display(HTML(\n",
    "                        f'<left><h2 style=\"text-decoration: underline; text-decoration-color:{topic_color_dict[top]};\">{top}</h2></left>'))\n",
    "                    display(color(top_result_df, topic_color_dict[top]))\n",
    "            \n",
    "            agg_df = sub_result_df.groupby('Topic')['Score'].sum()\n",
    "            agg_df = agg_df.to_frame()\n",
    "            agg_df.index.name = 'Topic'\n",
    "            agg_df.columns = ['Total Score']\n",
    "            agg_df = agg_df.assign(\n",
    "                Final_Score=lambda x: x['Total Score'] / x['Total Score'].sum() * 100.00\n",
    "            )\n",
    "            agg_df = agg_df.sort_values(by='Final_Score', ascending=False)\n",
    "            agg_df['Topic'] = agg_df.index\n",
    "            rem_topics= [x for x in list(topic_color_dict.keys()) if not x in agg_df.Topic.tolist()]\n",
    "            if len(rem_topics) > 0:\n",
    "                rem_agg_df = pd.DataFrame({'Topic': rem_topics, 'Final_Score': 0.0, 'Total Score': 0.0})\n",
    "                agg_df = pd.concat([agg_df, rem_agg_df])\n",
    "            title = \"Final Scores\"\n",
    "            display(HTML(f'<left><h1>{title}</h1></left>'))\n",
    "            display_final_df(agg_df)\n",
    "            if len(sub_2_result_df) > 0:\n",
    "                sub_result_df = pd.concat([sub_result_df, sub_2_result_df]).reset_index(drop=True)\n",
    "            agrilla_df = sub_result_df.copy()\n",
    "        else:\n",
    "            print(query)\n",
    "            display_final_df('None')\n",
    "            if len(sub_2_result_df) > 0:\n",
    "                agrilla_df = sub_2_result_df.copy()\n",
    "\n",
    "def on_agr_button_next(b):\n",
    "    global agrilla_df, annotated\n",
    "    with bhvr_outt:\n",
    "        clear_output()\n",
    "        if agrilla_df is not None:\n",
    "            # convert the dataframe to the structure accepted by argilla\n",
    "            converted_df = convert_df(agrilla_df)\n",
    "            # convert pandas dataframe to DatasetForTextClassification\n",
    "            dataset_rg = rg.DatasetForTextClassification.from_pandas(converted_df)\n",
    "            # delete the old DatasetForTextClassification from the Argilla web app if exists\n",
    "            rg.delete(dataset_rg_name, workspace=\"admin\")\n",
    "            # load the new DatasetForTextClassification into the Argilla web app\n",
    "            rg.log(dataset_rg, name=dataset_rg_name, workspace=\"admin\")\n",
    "            # Make sure all classes are present for annotation\n",
    "            rg_settings = rg.TextClassificationSettings(label_schema=list(topic_color_dict.keys()))\n",
    "            rg.configure_dataset(name=dataset_rg_name, workspace=\"admin\", settings=rg_settings)\n",
    "            annotated = True\n",
    "        else:\n",
    "            display(Markdown(\"<h2 style='color:red; text-align:center;'>Please score the answer first!</h2>\"))\n",
    "            \n",
    "def on_eval_button_next(b):\n",
    "    global annotated\n",
    "    with bhvr_outt:\n",
    "        clear_output()\n",
    "        if annotated:\n",
    "            display(f1(dataset_rg_name).visualize())\n",
    "        else:\n",
    "            display(Markdown(\"<h2 style='color:red; text-align:center;'>Please score the answer and validate the data first!</h2>\"))\n",
    "\n",
    "bhvr_nlp_btn.on_click(on_bhvr_button_next)\n",
    "bhvr_agr_btn.on_click(on_agr_button_next)\n",
    "bhvr_eval_btn.on_click(on_eval_button_next)\n",
    "\n",
    "display(bhvr_label, bhvr_box)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a2e51901",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "kernelspec": {
   "display_name": "Python 3.9 (Argilla)",
   "language": "python",
   "name": "argilla"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.16"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": false,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "258.097px"
   },
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}