File size: 22,961 Bytes
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2c9e91
4be750a
 
 
 
 
 
 
 
 
7dc8863
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2c9e91
4be750a
f2c9e91
 
 
 
 
 
 
 
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2c9e91
4be750a
 
 
ce9fc6c
 
4be750a
ce9fc6c
 
 
 
 
 
 
 
 
 
 
4be750a
ce9fc6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4be750a
ce9fc6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4be750a
ce9fc6c
f2c9e91
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce9fc6c
 
 
 
 
7dc8863
ce9fc6c
 
 
 
 
 
 
 
4be750a
 
 
 
 
ce9fc6c
 
 
 
 
 
 
 
 
 
4be750a
ce9fc6c
4be750a
ce9fc6c
 
 
 
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
f2c9e91
4be750a
 
 
 
 
 
 
 
 
f2c9e91
 
 
 
4be750a
 
 
 
 
 
 
7dc8863
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f2c9e91
4be750a
 
 
 
 
 
7dc8863
 
 
 
 
 
 
 
 
 
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7dc8863
4be750a
 
ce9fc6c
 
 
 
 
 
 
 
4be750a
 
 
 
7dc8863
 
 
ce9fc6c
7dc8863
4be750a
7dc8863
4be750a
7dc8863
f2c9e91
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce9fc6c
 
 
 
 
4be750a
7dc8863
 
 
 
 
 
 
ce9fc6c
 
 
 
 
 
 
7dc8863
 
 
 
ce9fc6c
4be750a
ce9fc6c
 
 
 
506f5a9
ce9fc6c
4be750a
 
ce9fc6c
4be750a
 
 
ce9fc6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4be750a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Run pre-trained DeepSeek Coder 1.3B Model on Chat-GPT 4o generated dataset"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## First load dataset into pandas dataframe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total dataset examples: 1044\n",
      "\n",
      "\n",
      "What was the largest lead the Golden State Warriors had in a game during the 2018 season?\n",
      "SELECT MAX(other_stats.largest_lead_home)  FROM other_stats  JOIN game ON other_stats.game_id = game.game_id  WHERE game.team_name_home = 'Golden State Warriors'  AND game.season_id = '22018';\n",
      "44\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd \n",
    "\n",
    "# Load dataset and check length\n",
    "df = pd.read_csv(\"./train-data/sql_train.tsv\", sep='\\t')\n",
    "print(\"Total dataset examples: \" + str(len(df)))\n",
    "print(\"\\n\")\n",
    "\n",
    "# Test sampling\n",
    "sample = df.sample(n=1)\n",
    "print(sample[\"natural_query\"].values[0])\n",
    "print(sample[\"sql_query\"].values[0])\n",
    "print(sample[\"result\"].values[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load pre-trained DeepSeek model using transformers and pytorch packages"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer, AutoModelForCausalLM\n",
    "import torch\n",
    "\n",
    "# Set device to cuda if available, otherwise CPU\n",
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "\n",
    "# Load model and tokenizer\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"./deepseek-coder-1.3b-instruct\")\n",
    "model = AutoModelForCausalLM.from_pretrained(\"./deepseek-coder-1.3b-instruct\", torch_dtype=torch.bfloat16, device_map=device) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create prompt to setup the model for better performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_text = \"\"\"You are an AI assistant that converts natural language queries into valid SQLite queries.\n",
    "Database Schema and Explanations\n",
    "\n",
    "team Table\n",
    "Stores information about NBA teams.\n",
    "CREATE TABLE IF NOT EXISTS \"team\" (\n",
    "  \"id\" TEXT PRIMARY KEY,      -- Unique identifier for the team\n",
    "  \"full_name\" TEXT,           -- Full official name of the team (e.g., \"Los Angeles Lakers\")\n",
    "  \"abbreviation\" TEXT,        -- Shortened team name (e.g., \"LAL\")\n",
    "  \"nickname\" TEXT,            -- Commonly used nickname for the team (e.g., \"Lakers\")\n",
    "  \"city\" TEXT,                -- City where the team is based\n",
    "  \"state\" TEXT,               -- State where the team is located\n",
    "  \"year_founded\" REAL         -- Year the team was established\n",
    ");\n",
    "\n",
    "game Table\n",
    "Contains detailed statistics for each NBA game, including home and away team performance.\n",
    "CREATE TABLE IF NOT EXISTS \"game\" (\n",
    "  \"season_id\" TEXT,            -- Season identifier, formatted as \"2YYYY\" (e.g., \"21970\" for the 1970 season)\n",
    "  \"team_id_home\" TEXT,         -- ID of the home team (matches \"id\" in team table)\n",
    "  \"team_abbreviation_home\" TEXT, -- Abbreviation of the home team\n",
    "  \"team_name_home\" TEXT,       -- Full name of the home team\n",
    "  \"game_id\" TEXT PRIMARY KEY,  -- Unique identifier for the game\n",
    "  \"game_date\" TIMESTAMP,       -- Date the game was played (YYYY-MM-DD format)\n",
    "  \"matchup_home\" TEXT,         -- Matchup details including opponent (e.g., \"LAL vs. BOS\")\n",
    "  \"wl_home\" TEXT,              -- \"W\" if the home team won, \"L\" if they lost\n",
    "  \"min\" INTEGER,               -- Total minutes played in the game\n",
    "  \"fgm_home\" REAL,             -- Field goals made by the home team\n",
    "  \"fga_home\" REAL,             -- Field goals attempted by the home team\n",
    "  \"fg_pct_home\" REAL,          -- Field goal percentage of the home team\n",
    "  \"fg3m_home\" REAL,            -- Three-point field goals made by the home team\n",
    "  \"fg3a_home\" REAL,            -- Three-point attempts by the home team\n",
    "  \"fg3_pct_home\" REAL,         -- Three-point field goal percentage of the home team\n",
    "  \"ftm_home\" REAL,             -- Free throws made by the home team\n",
    "  \"fta_home\" REAL,             -- Free throws attempted by the home team\n",
    "  \"ft_pct_home\" REAL,          -- Free throw percentage of the home team\n",
    "  \"oreb_home\" REAL,            -- Offensive rebounds by the home team\n",
    "  \"dreb_home\" REAL,            -- Defensive rebounds by the home team\n",
    "  \"reb_home\" REAL,             -- Total rebounds by the home team\n",
    "  \"ast_home\" REAL,             -- Assists by the home team\n",
    "  \"stl_home\" REAL,             -- Steals by the home team\n",
    "  \"blk_home\" REAL,             -- Blocks by the home team\n",
    "  \"tov_home\" REAL,             -- Turnovers by the home team\n",
    "  \"pf_home\" REAL,              -- Personal fouls by the home team\n",
    "  \"pts_home\" REAL,             -- Total points scored by the home team\n",
    "  \"plus_minus_home\" INTEGER,   -- Plus/minus rating for the home team\n",
    "  \"video_available_home\" INTEGER, -- Indicates whether video is available (1 = Yes, 0 = No)\n",
    "  \"team_id_away\" TEXT,         -- ID of the away team\n",
    "  \"team_abbreviation_away\" TEXT, -- Abbreviation of the away team\n",
    "  \"team_name_away\" TEXT,       -- Full name of the away team\n",
    "  \"matchup_away\" TEXT,         -- Matchup details from the away team’s perspective\n",
    "  \"wl_away\" TEXT,              -- \"W\" if the away team won, \"L\" if they lost\n",
    "  \"fgm_away\" REAL,             -- Field goals made by the away team\n",
    "  \"fga_away\" REAL,             -- Field goals attempted by the away team\n",
    "  \"fg_pct_away\" REAL,          -- Field goal percentage of the away team\n",
    "  \"fg3m_away\" REAL,            -- Three-point field goals made by the away team\n",
    "  \"fg3a_away\" REAL,            -- Three-point attempts by the away team\n",
    "  \"fg3_pct_away\" REAL,         -- Three-point field goal percentage of the away team\n",
    "  \"ftm_away\" REAL,             -- Free throws made by the away team\n",
    "  \"fta_away\" REAL,             -- Free throws attempted by the away team\n",
    "  \"ft_pct_away\" REAL,          -- Free throw percentage of the away team\n",
    "  \"oreb_away\" REAL,            -- Offensive rebounds by the away team\n",
    "  \"dreb_away\" REAL,            -- Defensive rebounds by the away team\n",
    "  \"reb_away\" REAL,             -- Total rebounds by the away team\n",
    "  \"ast_away\" REAL,             -- Assists by the away team\n",
    "  \"stl_away\" REAL,             -- Steals by the away team\n",
    "  \"blk_away\" REAL,             -- Blocks by the away team\n",
    "  \"tov_away\" REAL,             -- Turnovers by the away team\n",
    "  \"pf_away\" REAL,              -- Personal fouls by the away team\n",
    "  \"pts_away\" REAL,             -- Total points scored by the away team\n",
    "  \"plus_minus_away\" INTEGER,   -- Plus/minus rating for the away team\n",
    "  \"video_available_away\" INTEGER, -- Indicates whether video is available (1 = Yes, 0 = No)\n",
    "  \"season_type\" TEXT           -- Regular season or playoffs\n",
    ");\n",
    "\n",
    "other_stats Table\n",
    "Stores additional game statistics, linked to the game table via game_id.\n",
    "CREATE TABLE IF NOT EXISTS \"other_stats\" (\n",
    "  \"game_id\" TEXT,             -- Unique game identifier (links to \"game\" table)\n",
    "  \"league_id\" TEXT,           -- League identifier\n",
    "  \"team_id_home\" TEXT,        -- Home team identifier\n",
    "  \"team_abbreviation_home\" TEXT, -- Home team abbreviation\n",
    "  \"team_city_home\" TEXT,      -- Home team city\n",
    "  \"pts_paint_home\" INTEGER,   -- Points in the paint by the home team\n",
    "  \"pts_2nd_chance_home\" INTEGER, -- Second chance points by the home team\n",
    "  \"pts_fb_home\" INTEGER,      -- Fast break points by the home team\n",
    "  \"largest_lead_home\" INTEGER,-- Largest lead by the home team\n",
    "  \"lead_changes\" INTEGER,     -- Number of lead changes in the game\n",
    "  \"times_tied\" INTEGER,       -- Number of times the score was tied\n",
    "  \"team_turnovers_home\" INTEGER, -- Home team turnovers\n",
    "  \"total_turnovers_home\" INTEGER, -- Total turnovers in the game\n",
    "  \"team_rebounds_home\" INTEGER, -- Home team rebounds\n",
    "  \"pts_off_to_home\" INTEGER,  -- Points off turnovers by the home team\n",
    "  \"team_id_away\" TEXT,        -- Away team identifier\n",
    "  \"pts_paint_away\" INTEGER,   -- Points in the paint by the away team\n",
    "  \"pts_2nd_chance_away\" INTEGER, -- Second chance points by the away team\n",
    "  \"pts_fb_away\" INTEGER,      -- Fast break points by the away team\n",
    "  \"largest_lead_away\" INTEGER,-- Largest lead by the away team\n",
    "  \"team_turnovers_away\" INTEGER, -- Away team turnovers\n",
    "  \"total_turnovers_away\" INTEGER, -- Total turnovers in the game\n",
    "  \"team_rebounds_away\" INTEGER, -- Away team rebounds\n",
    "  \"pts_off_to_away\" INTEGER   -- Points off turnovers by the away team\n",
    ");\n",
    "\n",
    "\n",
    "Team Name Information\n",
    "In the plaintext user questions, only the full team names will be used, but in the queries you may use the full team names or the abbreviations. \n",
    "The full team names can be used with the game table, while the abbreviations should be used with the other_stats table.\n",
    "Notice they are separated by the | character in the following list:\n",
    "\n",
    "Atlanta Hawks|ATL\n",
    "Boston Celtics|BOS\n",
    "Cleveland Cavaliers|CLE\n",
    "New Orleans Pelicans|NOP\n",
    "Chicago Bulls|CHI\n",
    "Dallas Mavericks|DAL\n",
    "Denver Nuggets|DEN\n",
    "Golden State Warriors|GSW\n",
    "Houston Rockets|HOU\n",
    "Los Angeles Clippers|LAC\n",
    "Los Angeles Lakers|LAL\n",
    "Miami Heat|MIA\n",
    "Milwaukee Bucks|MIL\n",
    "Minnesota Timberwolves|MIN\n",
    "Brooklyn Nets|BKN\n",
    "New York Knicks|NYK\n",
    "Orlando Magic|ORL\n",
    "Indiana Pacers|IND\n",
    "Philadelphia 76ers|PHI\n",
    "Phoenix Suns|PHX\n",
    "Portland Trail Blazers|POR\n",
    "Sacramento Kings|SAC\n",
    "San Antonio Spurs|SAS\n",
    "Oklahoma City Thunder|OKC\n",
    "Toronto Raptors|TOR\n",
    "Utah Jazz|UTA\n",
    "Memphis Grizzlies|MEM\n",
    "Washington Wizards|WAS\n",
    "Detroit Pistons|DET\n",
    "Charlotte Hornets|CHA\n",
    "\n",
    "\n",
    "\n",
    "Query Guidelines\n",
    "Use team_name_home and team_name_away to match teams.\n",
    "\n",
    "To filter by season, use season_id = '2YYYY'.\n",
    "\n",
    "Example: To get games from 2005, use season_id = '22005'. To get games from 1972, use season_id = \"21972\". To get games from 2015, use season_id = \"22015\".\n",
    "\n",
    "The game_id column links the game and other_stats tables.\n",
    "\n",
    "Ensure queries return relevant columns and avoid unnecessary joins.\n",
    "\n",
    "Example User Requests and SQLite Queries\n",
    "Request:\n",
    "\"What is the most points the Los Angeles Lakers have ever scored at home?\"\n",
    "SQLite:\n",
    "SELECT MAX(pts_home) \n",
    "FROM game \n",
    "WHERE team_name_home = 'Los Angeles Lakers';\n",
    "\n",
    "Request:\n",
    "\"How many points did the Miami Heat score on January 10, 2010?\"\n",
    "SQLite:\n",
    "SELECT team_name_home, pts_home, team_name_away, pts_away \n",
    "FROM game \n",
    "WHERE DATE(game_date) = '2010-01-10' \n",
    "AND (team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat');\n",
    "\n",
    "Request:\n",
    "\"Which team won the most home games in the 2000 season?\"\n",
    "SQLite:\n",
    "SELECT team_name_home, COUNT(*) AS wins\n",
    "FROM game\n",
    "WHERE wl_home = 'W' AND season_id = '22000'\n",
    "GROUP BY team_name_home\n",
    "ORDER BY wins DESC\n",
    "LIMIT 1;\n",
    "\n",
    "Generate only the SQLite query prefaced by SQLite: and no other text, do not output an explanation of the query. Now generate an SQLite query for the following question: \"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Test model performance on a single example"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\generation\\configuration_utils.py:634: UserWarning: `do_sample` is set to `False`. However, `top_p` is set to `0.95` -- this flag is only used in sample-based generation modes. You should set `do_sample=True` or unset `top_p`.\n",
      "  warnings.warn(\n",
      "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
      "Setting `pad_token_id` to `eos_token_id`:32021 for open-end generation.\n",
      "The attention mask is not set and cannot be inferred from input because pad token is same as eos token. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
      "c:\\Users\\Dean\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\transformers\\integrations\\sdpa_attention.py:53: UserWarning: 1Torch was not compiled with flash attention. (Triggered internally at C:\\actions-runner\\_work\\pytorch\\pytorch\\builder\\windows\\pytorch\\aten\\src\\ATen\\native\\transformers\\cuda\\sdp_utils.cpp:555.)\n",
      "  attn_output = torch.nn.functional.scaled_dot_product_attention(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SQLite:\n",
      "SELECT MAX(largest_lead_home) \n",
      "FROM other_stats \n",
      "WHERE team_name_home = 'Golden State Warriors' AND season_id = '22018';\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Create message with sample query and run model\n",
    "message=[{ 'role': 'user', 'content': input_text + sample[\"natural_query\"].values[0]}]\n",
    "inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors=\"pt\").to(model.device)\n",
    "outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)\n",
    "\n",
    "# Print output\n",
    "query_output = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)\n",
    "print(query_output)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test sample output on sqlite3 database"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "cleaned\n"
     ]
    },
    {
     "ename": "OperationalError",
     "evalue": "no such column: team_name_home",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mOperationalError\u001b[0m                          Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[5], line 15\u001b[0m\n\u001b[0;32m     13\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m     14\u001b[0m     query \u001b[38;5;241m=\u001b[39m query_output\n\u001b[1;32m---> 15\u001b[0m \u001b[43mcursor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mquery\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m     16\u001b[0m rows \u001b[38;5;241m=\u001b[39m cursor\u001b[38;5;241m.\u001b[39mfetchall()\n\u001b[0;32m     17\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m row \u001b[38;5;129;01min\u001b[39;00m rows:\n",
      "\u001b[1;31mOperationalError\u001b[0m: no such column: team_name_home"
     ]
    }
   ],
   "source": [
    "import sqlite3 as sql\n",
    "\n",
    "# Create connection to sqlite3 database\n",
    "connection = sql.connect('./nba-data/nba.sqlite')\n",
    "cursor = connection.cursor()\n",
    "\n",
    "# Execute query from model output and print result\n",
    "if query_output[0:7] == \"SQLite:\":\n",
    "    print(\"cleaned\")\n",
    "    query = query_output[7:]\n",
    "elif query_output[0:4] == \"SQL:\":\n",
    "    query = query_output[4:]\n",
    "else:\n",
    "    query = query_output\n",
    "cursor.execute(query)\n",
    "rows = cursor.fetchall()\n",
    "for row in rows:\n",
    "    print(row)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create function to compare output to ground truth result from examples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n",
      "Setting `pad_token_id` to `eos_token_id`:32021 for open-end generation.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "How many games had at least one team with 30+ assists?\n",
      "SELECT COUNT(*)  FROM game  WHERE ast_home >= 30 OR ast_away >= 30;\n",
      "11305\n",
      "SQLite:\n",
      "SELECT COUNT(*) \n",
      "FROM game \n",
      "WHERE ast_home >= 30 OR ast_away >= 30;\n",
      "\n",
      "[(11305,)]\n",
      "SQL matched? True\n",
      "Result matched? True\n"
     ]
    }
   ],
   "source": [
    "def compare_result(sample_query, sample_result, query_output):\n",
    "    # Clean model output to only have the query output\n",
    "    if query_output[0:7] == \"SQLite:\":\n",
    "        query = query_output[7:]\n",
    "    elif query_output[0:4] == \"SQL:\":\n",
    "        query = query_output[4:]\n",
    "    else:\n",
    "        query = query_output\n",
    "    \n",
    "    # Try to execute query, if it fails, then this is a failure of the model\n",
    "    try:\n",
    "        # Execute query and obtain result\n",
    "        cursor.execute(query)\n",
    "        rows = cursor.fetchall()\n",
    "\n",
    "        # Strip all whitespace before comparing queries since there may be differences in spacing, newlines, tabs, etc.\n",
    "        query = query.replace(\" \", \"\").replace(\"\\n\", \"\").replace(\"\\t\", \"\")\n",
    "        sample_query = sample_query.replace(\" \", \"\").replace(\"\\n\", \"\").replace(\"\\t\", \"\")\n",
    "        query_match = (query == sample_query)\n",
    "\n",
    "        # Check if this is a multi-line query\n",
    "        if \"|\" in sample_result or \"(\" in sample_result:\n",
    "            if \"(\" in sample_result:\n",
    "                sample_result = sample_result.replace(\"(\", \"\").replace(\")\", \"\")\n",
    "                result_list = sample_result.split(\",\") \n",
    "            else:\n",
    "                result_list = sample_result.split(\"|\") \n",
    "\n",
    "            for i in range(len(result_list)):\n",
    "                result_list[i] = str(result_list[i]).strip()\n",
    "            result = False\n",
    "            for row in rows:\n",
    "                for r in row:\n",
    "                    if str(r) in result_list:\n",
    "                        return query_match, True\n",
    "            if len(rows) == 1:\n",
    "                for r in rows[0]:\n",
    "                    if r == str(len(result_list)):\n",
    "                        return query_match, True\n",
    "            return query_match, result\n",
    "        else:\n",
    "            print(rows)\n",
    "            result = False\n",
    "            for row in rows:\n",
    "                for r in row:\n",
    "                    if str(r) in str(sample_result):\n",
    "                        return query_match, True\n",
    "\n",
    "            # Compare results and return\n",
    "            return query_match, result\n",
    "    except:\n",
    "        return False, False\n",
    "\n",
    "# Obtain sample\n",
    "sample = df.sample(n=1)\n",
    "print(sample[\"natural_query\"].values[0])\n",
    "print(sample[\"sql_query\"].values[0])\n",
    "print(sample[\"result\"].values[0])\n",
    "\n",
    "# Create message with sample query and run model\n",
    "message=[{ 'role': 'user', 'content': input_text + sample[\"natural_query\"].values[0]}]\n",
    "inputs = tokenizer.apply_chat_template(message, add_generation_prompt=True, return_tensors=\"pt\").to(model.device)\n",
    "outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)\n",
    "\n",
    "# Print output\n",
    "query_output = tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)\n",
    "print(query_output)\n",
    "\n",
    "result = compare_result(sample[\"sql_query\"].values[0], sample[\"result\"].values[0], query_output)\n",
    "print(\"SQL matched? \" + str(result[0]))\n",
    "print(\"Result matched? \" + str(result[1]))"
   ]
  }
 ],
 "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": "3.12.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}