fixed issue with inconsistent formatting in training data

test_pretrained.ipynb

@@ -26,9 +26,9 @@
       "Total dataset examples: 1044\n",
       "\n",
       "\n",
-      "What is the highest combined pts in any game involving the Miami Heat?\n",
-      "SELECT MAX(pts_home + pts_away) FROM game WHERE team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat';\n",
-      "290.0\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"
      ]
     }
    ],
@@ -241,7 +241,7 @@
     "\n",
     "To filter by season, use season_id = '2YYYY'.\n",
     "\n",
-    "Example: To get games from 2005, use season_id = '22005'.\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",
@@ -306,9 +306,9 @@
      "output_type": "stream",
      "text": [
       "SQLite:\n",
-      "SELECT MAX(pts_home + pts_away) \n",
-      "FROM game \n",
-      "WHERE (team_name_home = 'Miami Heat' OR team_name_away = 'Miami Heat');\n",
+      "SELECT MAX(largest_lead_home) \n",
+      "FROM other_stats \n",
+      "WHERE team_name_home = 'Golden State Warriors' AND season_id = '22018';\n",
       "\n"
      ]
     }
@@ -340,8 +340,18 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "cleaned\n",
-      "(290.0,)\n"
+      "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"
      ]
     }
    ],
@@ -375,7 +385,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [
     {
@@ -390,15 +400,15 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "What is the average number of reb in away games by the Detroit Pistons?\n",
-      "SELECT AVG(reb_away) FROM game WHERE team_name_away = 'Detroit Pistons';\n",
-      "42.10948081264108\n",
+      "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 AVG(reb_away) \n",
+      "SELECT COUNT(*) \n",
       "FROM game \n",
-      "WHERE team_name_away = 'Detroit Pistons';\n",
+      "WHERE ast_home >= 30 OR ast_away >= 30;\n",
       "\n",
-      "[(42.10948081264108,)]\n",
+      "[(11305,)]\n",
       "SQL matched? True\n",
       "Result matched? True\n"
      ]
@@ -426,8 +436,13 @@
     "        query_match = (query == sample_query)\n",
     "\n",
     "        # Check if this is a multi-line query\n",
-    "        if \"|\" in sample_result:\n",
-    "            result_list = sample_result.split(\"|\") \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",
@@ -435,7 +450,10 @@
     "                for r in row:\n",
     "                    if str(r) in result_list:\n",
     "                        return query_match, True\n",
-    "            print(rows)\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",