trying to prompt engineer fixes for other_stats table

test_pretrained.ipynb

@@ -16,7 +16,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 34,
    "metadata": {},
    "outputs": [
     {
@@ -26,9 +26,9 @@
       "Total dataset examples: 1044\n",
       "\n",
       "\n",
-      "What is the average number of tov in home games by the Miami Heat?\n",
-      "SELECT AVG(tov_home) FROM game WHERE team_name_home = 'Miami Heat';\n",
-      "14.627184466019418\n"
+      "What was the largest deficit overcome by the Miami Heat in any home victory?\n",
+      "SELECT o.largest_lead_away AS max_deficit_overcome FROM game g JOIN other_stats o ON g.game_id = o.game_id WHERE g.team_name_home = 'Miami Heat' AND g.wl_home = 'W' ORDER BY o.largest_lead_away DESC LIMIT 1;\n",
+      "46\n"
      ]
     }
    ],
@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 35,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -83,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 36,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -163,9 +163,9 @@
     ");\n",
     "\n",
     "other_stats Table\n",
-    "Stores additional game statistics, linked to the game table via game_id.\n",
+    "Stores additional 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",
+    "  \"game_id\" TEXT,             -- Unique game identifier, matches id column from 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",
@@ -174,19 +174,20 @@
     "  \"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",
+    "  \"lead_changes\" INTEGER,     -- Number of lead changes \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",
+    "  \"total_turnovers_home\" INTEGER, -- Total turnovers by the home team\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",
+    "  \"team_abbreviation_away\" TEXT,  -- Away team abbreviation\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",
+    "  \"total_turnovers_away\" INTEGER, -- Total turnovers by the away team\n",
     "  \"team_rebounds_away\" INTEGER, -- Away team rebounds\n",
     "  \"pts_off_to_away\" INTEGER   -- Points off turnovers by the away team\n",
     ");\n",
@@ -228,19 +229,28 @@
     "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",
+    "Use team_name_home and team_name_away to match teams to the game table. Use team_abbreviation_home and team_abbreviation away to match teams to the other_stats table.\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",
+    "Example: To get statistics from 2005, use a statement like: season_id = '22005'. To get statistics from 1972, use a statement like: season_id = \"21972\". To get statistics from 2015, use a statement like: season_id = \"22015\".\n",
     "\n",
-    "The game_id column links the game and other_stats tables.\n",
+    "The game_id column can be used to join the game and other_stats tables.\n",
     "\n",
     "Ensure queries return relevant columns and avoid unnecessary joins.\n",
     "\n",
+    "When obtaining certain statistics by team from the game table, use the team_name_home and team_name_away columns. \n",
+    "For example, to obtain home game data for the Washington Wizards from the game table use a statement like: team_name_home = 'Washington Wizards'\n",
+    "To obtain away game data from the Los Angeles Lakers from the game table use a statement like: team_name_away = 'Los Angeles Lakers'\n",
+    "To obtain general game data where home or away is not specified for the Chicago Bulls from the game table, use a statement like: (team_name_home = 'Chicago Bulls' OR team_name_away = 'Chicago Bulls')\n",
+    "\n",
+    "When obtaining certain statistics by team from the other_stats table, use the team_abbreviation_home and team_abbreviation away columns.\n",
+    "For example, to obtain home statistics from the Charlotte Hornets from the other_stats table use a statement like: team_abbreviation_home = 'CHA'\n",
+    "To obtain away statistics from the Dallas Mavericks from the other_stats table, use a statement like: team_abbreviation_away = 'DAL'\n",
+    "To obtain general statistics from the other_stats table where home or away is not specified for the Detroit Pistons use a statement like: (team_abbreviation_home = 'DET' OR team_abbreviation_away = 'DET)\n",
+    "\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",
@@ -250,6 +260,19 @@
     "WHERE team_name_home = 'Los Angeles Lakers';\n",
     "\n",
     "Request:\n",
+    "\"Which teams are located in the state of California?\"\n",
+    "SQLite:\n",
+    "SELECT full_name FROM team WHERE state = 'California';\n",
+    "\n",
+    "Request:\n",
+    "\"How many total team rebounds did the Los Angeles Clippers have in away games where they scored over 15 fast break points?\"\n",
+    "SQLite:\n",
+    "SELECT SUM(os.team_rebounds_away) \n",
+    "FROM other_stats os  \n",
+    "JOIN game g ON os.game_id = g.game_id  \n",
+    "WHERE g.team_abbreviation_away = 'LAC' AND os.pts_fb_away > 15;\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",
@@ -258,6 +281,11 @@
     "AND (team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat');\n",
     "\n",
     "Request:\n",
+    "\"Which team had the highest number of team turnovers in an away game?\"\n",
+    "SQLite:\n",
+    "SELECT team_abbreviation_away FROM other_stats ORDER BY team_turnovers_away DESC LIMIT 1;\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",
@@ -267,7 +295,34 @@
     "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: \"\"\""
+    "Request:\n",
+    "\"Which teams were founded before 1979?\"\n",
+    "SQLite:\n",
+    "SELECT full_name FROM team WHERE year_founded < 1979;\n",
+    "\n",
+    "Request:\n",
+    "\"Which game had the most lead changes in the 2020 season?\"\n",
+    "SQLite:\n",
+    "SELECT game_id, lead_changes  \n",
+    "FROM other_stats \n",
+    "WHERE game_id IN \n",
+    "(SELECT game_id FROM game WHERE season_id = '22020')\n",
+    "ORDER BY lead_changes DESC LIMIT 1;\n",
+    "\n",
+    "Request:\n",
+    "\"Find the Boston Celtics largest home victory margin in the 2008 season.\"\n",
+    "SQLite:\n",
+    "SELECT MAX(pts_home - pts_away) AS biggest_win\n",
+    "FROM game\n",
+    "WHERE team_name_home = 'Boston Celtics' AND season_id = '22008';\n",
+    "\n",
+    "Request:\n",
+    "\"How many fast break points did the Atlanta Hawks score at home?\"\n",
+    "SQLite:\n",
+    "SELECT SUM(pts_fb_home) as total_fb_points  FROM other_stats  WHERE team_abbreviation_home = 'ATL';\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 user request. Request:\n",
+    "\"\"\""
    ]
   },
   {
@@ -279,7 +334,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 37,
    "metadata": {},
    "outputs": [
     {
@@ -287,9 +342,9 @@
      "output_type": "stream",
      "text": [
       "SQLite:\n",
-      "SELECT AVG(tov_home) \n",
-      "FROM game \n",
-      "WHERE team_name_home = 'Miami Heat';\n",
+      "SELECT MAX(pts_home - pts_away) AS largest_deficit\n",
+      "FROM game\n",
+      "WHERE wl_home = 'W' AND team_name_home = 'Miami Heat';\n",
       "\n"
      ]
     }
@@ -314,7 +369,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 38,
    "metadata": {},
    "outputs": [
     {
@@ -322,7 +377,7 @@
      "output_type": "stream",
      "text": [
       "cleaned\n",
-      "(14.627184466019418,)\n"
+      "(43.0,)\n"
      ]
     }
    ],
@@ -360,22 +415,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 39,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "How many times have the Houston Rockets won an away game while scoring at least 110 points?\n",
-      "SELECT COUNT(*)  FROM game  WHERE team_abbreviation_away = 'HOU'  AND pts_away >= 110  AND wl_away = 'W';\n",
-      "425\n",
+      "How many home games did the Chicago Bulls play in the 2020 season?\n",
+      "SELECT COUNT(*) FROM game WHERE team_name_home = 'Chicago Bulls' AND season_id = '22020';\n",
+      "36.0\n",
       "SQLite:\n",
-      "SELECT COUNT(*) \n",
+      "SELECT COUNT(*) as total_home_games \n",
       "FROM game \n",
-      "WHERE team_name_away = 'Houston Rockets' \n",
-      "AND wl_away = 'W' \n",
-      "AND pts_away >= 110;\n",
+      "WHERE team_name_home = 'Chicago Bulls' AND season_id = '22020';\n",
       "\n",
       "Statement valid? True\n",
       "SQLite matched? False\n",
@@ -508,7 +561,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 40,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -556,7 +609,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 41,
    "metadata": {},
    "outputs": [
     {
@@ -564,21 +617,18 @@
      "output_type": "stream",
      "text": [
       "Completed 50\n",
-      "Completed 100\n",
-      "Completed 150\n",
-      "Completed 200\n",
       "\n",
       "Less than 90 results:\n",
-      "Percent valid: 0.8612244897959184\n",
-      "Percent SQLite matched: 0.4163265306122449\n",
-      "Percent result matched: 0.6530612244897959\n",
+      "Percent valid: 0.62\n",
+      "Percent SQLite matched: 0.12\n",
+      "Percent result matched: 0.4\n",
       "Dataset length: 245\n"
      ]
     }
    ],
    "source": [
     "less_than_90_df = pd.read_csv(\"./train-data/less_than_90.tsv\", sep='\\t')\n",
-    "run_evaluation(less_than_90_df, \"Less than 90\")\n",
+    "run_evaluation(less_than_90_df.sample(n=50), \"Less than 90\")\n",
     "print(\"Dataset length: \" + str(len(less_than_90_df)))"
    ]
   },
@@ -591,7 +641,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [
     {
@@ -616,9 +666,9 @@
       "Completed 800\n",
       "\n",
       "Queries from game results:\n",
-      "Percent valid: 0.7708830548926014\n",
-      "Percent SQLite matched: 0.1431980906921241\n",
-      "Percent result matched: 0.40692124105011934\n",
+      "Percent valid: 0.6181384248210023\n",
+      "Percent SQLite matched: 0.015513126491646777\n",
+      "Percent result matched: 0.24343675417661098\n",
       "Dataset length: 838\n"
      ]
     }
@@ -638,7 +688,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [
     {
@@ -650,9 +700,9 @@
       "Completed 150\n",
       "\n",
       "Queries from other stats results:\n",
-      "Percent valid: 0.07792207792207792\n",
-      "Percent SQLite matched: 0.0\n",
-      "Percent result matched: 0.0\n",
+      "Percent valid: 0.6168831168831169\n",
+      "Percent SQLite matched: 0.06493506493506493\n",
+      "Percent result matched: 0.34415584415584416\n",
       "Dataset length: 154\n"
      ]
     }
@@ -672,7 +722,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
@@ -682,9 +732,9 @@
       "Completed 50\n",
       "\n",
       "Queries from team results:\n",
-      "Percent valid: 0.75\n",
-      "Percent SQLite matched: 0.2692307692307692\n",
-      "Percent result matched: 0.6153846153846154\n",
+      "Percent valid: 0.8846153846153846\n",
+      "Percent SQLite matched: 0.6346153846153846\n",
+      "Percent result matched: 0.8269230769230769\n",
       "Dataset length: 52\n"
      ]
     }