first cut at adding data augmentation python notebook

augment_data.ipynb

@@ -0,0 +1,376 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Augment data from TSV files to change team names and years"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create dictionary for mapping team names and abbreviations"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "30\n",
+      "30\n",
+      "30\n",
+      "30\n",
+      "0,Atlanta Hawks,0,ATL,0\n",
+      "1,Boston Celtics,1,BOS,1\n",
+      "2,Cleveland Cavaliers,2,CLE,2\n",
+      "3,New Orleans Pelicans,3,NOP,3\n",
+      "4,Chicago Bulls,4,CHI,4\n",
+      "5,Dallas Mavericks,5,DAL,5\n",
+      "6,Denver Nuggets,6,DEN,6\n",
+      "7,Golden State Warriors,7,GSW,7\n",
+      "8,Houston Rockets,8,HOU,8\n",
+      "9,Los Angeles Clippers,9,LAC,9\n",
+      "10,Los Angeles Lakers,10,LAL,10\n",
+      "11,Miami Heat,11,MIA,11\n",
+      "12,Milwaukee Bucks,12,MIL,12\n",
+      "13,Minnesota Timberwolves,13,MIN,13\n",
+      "14,Brooklyn Nets,14,BKN,14\n",
+      "15,New York Knicks,15,NYK,15\n",
+      "16,Orlando Magic,16,ORL,16\n",
+      "17,Indiana Pacers,17,IND,17\n",
+      "18,Philadelphia 76ers,18,PHI,18\n",
+      "19,Phoenix Suns,19,PHX,19\n",
+      "20,Portland Trail Blazers,20,POR,20\n",
+      "21,Sacramento Kings,21,SAC,21\n",
+      "22,San Antonio Spurs,22,SAS,22\n",
+      "23,Oklahoma City Thunder,23,OKC,23\n",
+      "24,Toronto Raptors,24,TOR,24\n",
+      "25,Utah Jazz,25,UTA,25\n",
+      "26,Memphis Grizzlies,26,MEM,26\n",
+      "27,Washington Wizards,27,WAS,27\n",
+      "28,Detroit Pistons,28,DET,28\n",
+      "29,Charlotte Hornets,29,CHA,29\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create team map and team array\n",
+    "team_map = {\n",
+    "    \"Atlanta Hawks\": 0,\n",
+    "    \"Boston Celtics\": 1,\n",
+    "    \"Cleveland Cavaliers\": 2,\n",
+    "    \"New Orleans Pelicans\": 3,\n",
+    "    \"Chicago Bulls\": 4,\n",
+    "    \"Dallas Mavericks\": 5,\n",
+    "    \"Denver Nuggets\": 6,\n",
+    "    \"Golden State Warriors\": 7,\n",
+    "    \"Houston Rockets\": 8,\n",
+    "    \"Los Angeles Clippers\": 9,\n",
+    "    \"Los Angeles Lakers\": 10,\n",
+    "    \"Miami Heat\": 11,\n",
+    "    \"Milwaukee Bucks\": 12,\n",
+    "    \"Minnesota Timberwolves\": 13,\n",
+    "    \"Brooklyn Nets\": 14,\n",
+    "    \"New York Knicks\": 15,\n",
+    "    \"Orlando Magic\": 16,\n",
+    "    \"Indiana Pacers\": 17,\n",
+    "    \"Philadelphia 76ers\": 18,\n",
+    "    \"Phoenix Suns\": 19,\n",
+    "    \"Portland Trail Blazers\": 20,\n",
+    "    \"Sacramento Kings\": 21,\n",
+    "    \"San Antonio Spurs\": 22,\n",
+    "    \"Oklahoma City Thunder\": 23,\n",
+    "    \"Toronto Raptors\": 24,\n",
+    "    \"Utah Jazz\": 25,\n",
+    "    \"Memphis Grizzlies\": 26,\n",
+    "    \"Washington Wizards\": 27,\n",
+    "    \"Detroit Pistons\": 28,\n",
+    "    \"Charlotte Hornets\": 29\n",
+    "}\n",
+    "\n",
+    "team_array = [\n",
+    "\"Atlanta Hawks\",\n",
+    "\"Boston Celtics\",\n",
+    "\"Cleveland Cavaliers\",\n",
+    "\"New Orleans Pelicans\",\n",
+    "\"Chicago Bulls\",\n",
+    "\"Dallas Mavericks\",\n",
+    "\"Denver Nuggets\",\n",
+    "\"Golden State Warriors\",\n",
+    "\"Houston Rockets\",\n",
+    "\"Los Angeles Clippers\",\n",
+    "\"Los Angeles Lakers\",\n",
+    "\"Miami Heat\",\n",
+    "\"Milwaukee Bucks\",\n",
+    "\"Minnesota Timberwolves\",\n",
+    "\"Brooklyn Nets\",\n",
+    "\"New York Knicks\",\n",
+    "\"Orlando Magic\",\n",
+    "\"Indiana Pacers\",\n",
+    "\"Philadelphia 76ers\",\n",
+    "\"Phoenix Suns\",\n",
+    "\"Portland Trail Blazers\",\n",
+    "\"Sacramento Kings\",\n",
+    "\"San Antonio Spurs\",\n",
+    "\"Oklahoma City Thunder\",\n",
+    "\"Toronto Raptors\",\n",
+    "\"Utah Jazz\",\n",
+    "\"Memphis Grizzlies\",\n",
+    "\"Washington Wizards\",\n",
+    "\"Detroit Pistons\",\n",
+    "\"Charlotte Hornets\"]\n",
+    "\n",
+    "# Check that array and dictionary are aligned properly\n",
+    "for i in range(len(team_array)):\n",
+    "    if i != team_map[team_array[i]]:\n",
+    "        print(\"Invalid!\")\n",
+    "\n",
+    "# Create abbreviation map and array\n",
+    "abbreviation_array = [\n",
+    "\"ATL\",\n",
+    "\"BOS\",\n",
+    "\"CLE\",\n",
+    "\"NOP\",\n",
+    "\"CHI\",\n",
+    "\"DAL\",\n",
+    "\"DEN\",\n",
+    "\"GSW\",\n",
+    "\"HOU\",\n",
+    "\"LAC\",\n",
+    "\"LAL\",\n",
+    "\"MIA\",\n",
+    "\"MIL\",\n",
+    "\"MIN\",\n",
+    "\"BKN\",\n",
+    "\"NYK\",\n",
+    "\"ORL\",\n",
+    "\"IND\",\n",
+    "\"PHI\",\n",
+    "\"PHX\",\n",
+    "\"POR\",\n",
+    "\"SAC\",\n",
+    "\"SAS\",\n",
+    "\"OKC\",\n",
+    "\"TOR\",\n",
+    "\"UTA\",\n",
+    "\"MEM\",\n",
+    "\"WAS\",\n",
+    "\"DET\",\n",
+    "\"CHA\"]\n",
+    "\n",
+    "abbreviation_map = {}\n",
+    "for i in range(len(abbreviation_array)):\n",
+    "    abbreviation_map[abbreviation_array[i]] = i\n",
+    "\n",
+    "print(len(team_array))\n",
+    "print(len(team_map))\n",
+    "print(len(abbreviation_array))\n",
+    "print(len(abbreviation_map))\n",
+    "\n",
+    "# Check that team names, abbreviation and index maps all line up\n",
+    "for i in range(len(team_array)):\n",
+    "    print(str(i) + \",\" + team_array[i] + \",\" + str(team_map[team_array[i]]) + \",\" + abbreviation_array[i] + \",\" + str(abbreviation_map[abbreviation_array[i]]))\n",
+    " "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create function to augment data by updating team names in SQL queries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import random\n",
+    "import pandas as pd\n",
+    "import sqlite3 as sql\n",
+    "\n",
+    "# Find team names in the sample\n",
+    "def find_teams_in_sample(sample, team_list):\n",
+    "    result = []\n",
+    "    for i in range(len(team_list)):\n",
+    "        if team_list[i] in sample:\n",
+    "            result.append(i)\n",
+    "    return result\n",
+    "\n",
+    "# Get random number excluding the one already used\n",
+    "def get_random_excluding(floor, ceiling, excluded_number):\n",
+    "    number = random.randint(floor, ceiling)\n",
+    "    while number == excluded_number:\n",
+    "        number = random.randint(floor, ceiling)\n",
+    "    return number\n",
+    "\n",
+    "def augment_dataframe(df, team_list, abbreviation_list, database):\n",
+    "    augmented_df = df.copy()\n",
+    "    for _, row in df.iterrows():\n",
+    "        team_idx = find_teams_in_sample(row[\"natural_query\"], team_list)\n",
+    "        # Only do simple update if only one team detected \n",
+    "        if len(team_idx) == 1:\n",
+    "            team_idx = team_idx[0]\n",
+    "\n",
+    "            # Check if team name is used in SQL query\n",
+    "            if team_list[team_idx] in row[\"sql_query\"]:\n",
+    "                # Create updated query with new team \n",
+    "                new_team_name = team_list[get_random_excluding(0, 29, team_idx)]\n",
+    "                new_natural_query = row[\"natural_query\"].replace(team_list[team_idx], new_team_name)\n",
+    "                new_sql_query = row[\"sql_query\"].replace(team_list[team_idx], new_team_name)\n",
+    "\n",
+    "                # Obtain result of running on sqlite database\n",
+    "                try:\n",
+    "                    database.execute(new_sql_query)\n",
+    "                    rows = database.fetchall()\n",
+    "                    if len(rows) == 1:\n",
+    "                        if len(rows[0]) == 2 and rows[0][1] == None:\n",
+    "                            result = str(rows[0][0])\n",
+    "                        else:\n",
+    "                            result = \" | \".join(str(x) for x in rows[0]) \n",
+    "                    else:\n",
+    "                        result = \" | \".join(str(x) for x in rows)\n",
+    "                    # Append new row to augmented dataframe if result successful\n",
+    "                    new_row = pd.DataFrame([{'natural_query': new_natural_query, 'sql_query': new_sql_query, 'result': result}])\n",
+    "                    augmented_df = pd.concat([augmented_df, new_row], ignore_index=True)\n",
+    "                except:\n",
+    "                    pass\n",
+    "\n",
+    "            # Check if abbreviation is in SQL query used instead\n",
+    "            elif abbreviation_list[team_idx] in row[\"sql_query\"]:\n",
+    "                # Create updated query with new team \n",
+    "                new_index = get_random_excluding(0, 29, team_idx)\n",
+    "                new_team_name = team_list[new_index]\n",
+    "                new_team_abbreviation = abbreviation_list[new_index]\n",
+    "                new_natural_query = row[\"natural_query\"].replace(team_list[team_idx], new_team_name)\n",
+    "                new_sql_query = row[\"sql_query\"].replace(abbreviation_list[team_idx], new_team_abbreviation)\n",
+    "\n",
+    "                # Obtain result of running on sqlite database\n",
+    "                try:\n",
+    "                    database.execute(new_sql_query)\n",
+    "                    rows = database.fetchall()\n",
+    "                    if len(rows) == 1:\n",
+    "                        \n",
+    "                        if len(rows[0]) == 2 and rows[0][1] == None:\n",
+    "                            result = str(rows[0][0])\n",
+    "                        else:\n",
+    "                            result = \" | \".join(str(x) for x in rows[0]) \n",
+    "                    else:\n",
+    "                        result = \" | \".join(str(x) for x in rows)\n",
+    "                    # Append new row to augmented dataframe if result successful\n",
+    "                    new_row = pd.DataFrame([{'natural_query': new_natural_query, 'sql_query': new_sql_query, 'result': result}])\n",
+    "                    augmented_df = pd.concat([augmented_df, new_row], ignore_index=True)\n",
+    "                except:\n",
+    "                    pass\n",
+    "    return augmented_df\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Test functions on small dataframe sample"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Total dataset examples: 1044\n",
+      "New Dataset Length:\n",
+      "6\n",
+      "\n",
+      "What is the total free throws made by the Indiana Pacers at home?\n",
+      "SELECT SUM(ftm_home) as total_ftm  FROM game  WHERE team_name_home = 'Indiana Pacers';\n",
+      "39545.0\n",
+      "\n",
+      "How many total rebounds did the Los Angeles Lakers grab in the 1985 season?\n",
+      "SELECT SUM(reb) AS total_rebounds FROM (     SELECT reb_home AS reb FROM game WHERE team_abbreviation_home = 'LAL' AND season_id = '21985'     UNION ALL     SELECT reb_away AS reb FROM game WHERE team_abbreviation_away = 'LAL' AND season_id = '21985' );\n",
+      "3655.0\n",
+      "\n",
+      "How many home games did the Orlando Magic play in the 2013 season?\n",
+      "SELECT COUNT(*) FROM game WHERE team_name_home = 'Orlando Magic' AND season_id = '22013';\n",
+      "41.0\n",
+      "\n",
+      "What is the total free throws made by the Denver Nuggets at home?\n",
+      "SELECT SUM(ftm_home) as total_ftm  FROM game  WHERE team_name_home = 'Denver Nuggets';\n",
+      "43821.0\n",
+      "\n",
+      "How many total rebounds did the Miami Heat grab in the 1985 season?\n",
+      "SELECT SUM(reb) AS total_rebounds FROM (     SELECT reb_home AS reb FROM game WHERE team_abbreviation_home = 'MIA' AND season_id = '21985'     UNION ALL     SELECT reb_away AS reb FROM game WHERE team_abbreviation_away = 'MIA' AND season_id = '21985' );\n",
+      "None\n",
+      "\n",
+      "How many home games did the Atlanta Hawks play in the 2013 season?\n",
+      "SELECT COUNT(*) FROM game WHERE team_name_home = 'Atlanta Hawks' AND season_id = '22013';\n",
+      "41\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Load dataset\n",
+    "train_df = pd.read_csv(\"./train-data/sql_train.tsv\", sep='\\t')\n",
+    "\n",
+    "# Display dataset info\n",
+    "print(f\"Total dataset examples: {len(train_df)}\")\n",
+    "#print(train_df.head())\n",
+    "\n",
+    "# Setup sqlite database connection\n",
+    "connection = sql.connect('./nba-data/nba.sqlite')\n",
+    "cursor = connection.cursor()\n",
+    "\n",
+    "# Test augmentation on sample of 3 rows\n",
+    "test_df = train_df.sample(n=3)\n",
+    "#for _, row in test_df.iterrows():\n",
+    "    #print(row)\n",
+    "#print()\n",
+    "#print()\n",
+    "\n",
+    "# Run augmentation function and print output\n",
+    "augmented_df = augment_dataframe(test_df, team_array, abbreviation_array, cursor)\n",
+    "print(\"New Dataset Length:\")\n",
+    "print(len(augmented_df))\n",
+    "print()\n",
+    "for _, row in augmented_df.iterrows():\n",
+    "    print(row[\"natural_query\"])\n",
+    "    print(row[\"sql_query\"])\n",
+    "    print(row[\"result\"])\n",
+    "    print()"
+   ]
+  }
+ ],
+ "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": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

train-data/sql_train.tsv

@@ -561,14 +561,14 @@ What is the highest combined pts in any game involving the Milwaukee Bucks?	SELE
 How many home games did the Los Angeles Lakers play in the 2022 season?	SELECT COUNT(*) FROM game WHERE team_name_home = 'Los Angeles Lakers' AND season_id = '22022';	41.0
 What is the highest combined pts in any game involving the Milwaukee Bucks?	SELECT MAX(pts_home + pts_away) FROM game WHERE team_name_home = 'Milwaukee Bucks' OR team_name_away = 'Milwaukee Bucks';	337.0
 How many away games did the Chicago Bulls play in the 2020 season?	SELECT COUNT(*) FROM game WHERE team_name_away = 'Chicago Bulls' AND season_id = '22020';	36.0
-In which season did the Golden State Warriors have the highest average fg_pct at home?	SELECT season_id, AVG(fg_pct_home) as avg_stat FROM game WHERE team_name_home = 'Golden State Warriors' GROUP BY season_id ORDER BY avg_stat DESC LIMIT 1;	1981.0
+In which season did the Golden State Warriors have the highest average fg_pct at home?	SELECT season_id, AVG(fg_pct_home) as avg_stat FROM game WHERE team_name_home = 'Golden State Warriors' GROUP BY season_id ORDER BY avg_stat DESC LIMIT 1;  21981|0.5885
 How many away games did the Chicago Bulls play in the 2001 season?	SELECT COUNT(*) FROM game WHERE team_name_away = 'Chicago Bulls' AND season_id = '22001';	41.0
 What is the average number of fg_pct in away games by the Miami Heat?	SELECT AVG(fg_pct_away) FROM game WHERE team_name_away = 'Miami Heat';	0.4499279161205765
 How many away games did the Chicago Bulls play in the 2002 season?	SELECT COUNT(*) FROM game WHERE team_name_away = 'Chicago Bulls' AND season_id = '22002';	41.0
 What is the highest combined reb in any game involving the Los Angeles Clippers?	SELECT MAX(reb_home + reb_away) FROM game WHERE team_name_home = 'Los Angeles Clippers' OR team_name_away = 'Los Angeles Clippers';	134.0
 How many home games did the Los Angeles Lakers play in the 2005 season?	SELECT COUNT(*) FROM game WHERE team_name_home = 'Los Angeles Lakers' AND season_id = '22005';	41.0
 How many home games did the Los Angeles Lakers play in the 2003 season?	SELECT COUNT(*) FROM game WHERE team_name_home = 'Los Angeles Lakers' AND season_id = '22003';	41.0
-In which season did the Golden State Warriors have the highest average ast at home?	SELECT season_id, AVG(ast_home) as avg_stat FROM game WHERE team_name_home = 'Golden State Warriors' GROUP BY season_id ORDER BY avg_stat DESC LIMIT 1;	2016.0
+In which season did the Golden State Warriors have the highest average ast at home?	SELECT season_id, AVG(ast_home) as avg_stat FROM game WHERE team_name_home = 'Golden State Warriors' GROUP BY season_id ORDER BY avg_stat DESC LIMIT 1; 2016.0
 What is the average number of reb in away games by the Boston Celtics?	SELECT AVG(reb_away) FROM game WHERE team_name_away = 'Boston Celtics';	42.40882509303562
 In which season did the Los Angeles Clippers have the highest average ast at home?	SELECT season_id, AVG(ast_home) as avg_stat FROM game WHERE team_name_home = 'Los Angeles Clippers' GROUP BY season_id ORDER BY avg_stat DESC LIMIT 1;	21988.0
 What is the highest combined ast in any game involving the Houston Rockets?	SELECT MAX(ast_home + ast_away) FROM game WHERE team_name_home = 'Houston Rockets' OR team_name_away = 'Houston Rockets';	81.0
@@ -716,7 +716,7 @@ What is the total points in the paint by the Minnesota Timberwolves away when th
 What is the average points scored by the Toronto Raptors at home when they had more than 10 second chance points in 1996?	SELECT AVG(g.pts_home) as avg_points  FROM game g  JOIN other_stats os ON g.game_id = os.game_id  WHERE g.team_name_home = 'Toronto Raptors' AND os.pts_2nd_chance_home > 10 AND g.season_id = '21996';	96.458
 What is the total number of points scored by the Atlanta Hawks at home?	SELECT SUM(pts_home) as total_points  FROM game  WHERE team_name_home = 'Atlanta Hawks';	233546.0
 How many games did the Boston Celtics lose at home in the 1996 season?	SELECT COUNT(*) as losses  FROM game  WHERE team_name_home = 'Boston Celtics' AND wl_home = 'L' AND season_id = '21996';	30.0
-What is the highest field goals made by the Chicago Bulls at home?	SELECT MAX(fgm_home) as max_fgm  FROM game  WHERE team_name_home = 'Chicago Bulls';	0.67
+What is the highest field goals made by the Chicago Bulls at home?	SELECT MAX(fgm_home) as max_fgm  FROM game  WHERE team_name_home = 'Chicago Bulls';	67.0
 How many games did the Cleveland Cavaliers lose away in 1996?	SELECT COUNT(*) as away_losses  FROM game  WHERE team_name_away = 'Cleveland Cavaliers' AND wl_away = 'L' AND season_id = '21996';	24.0
 What is the total points scored by the Dallas Mavericks away?	SELECT SUM(pts_away) as total_points  FROM game  WHERE team_name_away = 'Dallas Mavericks';	187891.0
 How many games did the Denver Nuggets win at home in 1996?	SELECT COUNT(*) as home_wins  FROM game  WHERE team_name_home = 'Denver Nuggets' AND wl_home = 'W' AND season_id = '21996';	12.0