Initial setup for training

data/get_data.py

@@ -1,5 +1,8 @@
 from data.db_connect import Database
 
+import hashlib
+import numpy as np
+
 # Game date in YYYYmmDD
 def pull_training_data(database: Database, game_date: str, game_number: int, park_id: str):
     # Training data
@@ -278,7 +281,7 @@ def pull_training_data(database: Database, game_date: str, game_number: int, par
         print(f"Got the wrong number of games {len(curr_team_game)}")
         return None
 
-    training_result = (curr_team_game[0][0] == 1 and curr_team_game[0][2] == 1)
+    training_result = int((curr_team_game[0][0] == 1 and curr_team_game[0][2] == 1))
 
     select_previous_games = """
         SELECT
@@ -349,10 +352,10 @@ def pull_training_data(database: Database, game_date: str, game_number: int, par
     select_previous_games_data_1 = [first_of_the_year, game_date, curr_team_game[1][1]]
 
     training_data = [*curr_game[1:]]
-
     training_data = [*training_data, *curr_team_game[0][1:]]
+
     prev_games = database.selectall(select_previous_games, select_previous_games_data_0)
-    prev_game_data = [0] * 61
+    prev_game_data = [0] * 85
     if prev_games is not None:
         prev_win_streak = 0
         index = len(prev_games) - 1
@@ -372,11 +375,12 @@ def pull_training_data(database: Database, game_date: str, game_number: int, par
             prev_loss_streak,
             *prev_games[index][1:]
         ]
+
     training_data = [*training_data, *prev_game_data]
-
     training_data = [*training_data, *curr_team_game[1][1:]]
+
     prev_games = database.selectall(select_previous_games, select_previous_games_data_1)
-    prev_game_data = [0] * 61
+    prev_game_data = [0] * 85
     if prev_games is not None:
         prev_win_streak = 0
         index = len(prev_games) - 1
@@ -396,6 +400,30 @@ def pull_training_data(database: Database, game_date: str, game_number: int, par
             prev_loss_streak,
             *prev_games[index][1:]
         ]
+
     training_data = [*training_data, *prev_game_data]
 
     return (training_result, training_data)
+
+def convert_to_integer(value):
+    if isinstance(value, int):
+        return value
+    elif isinstance(value, str):
+        return int(
+            hashlib.blake2b(
+                data=value.encode(),
+                digest_size=3,
+            ).hexdigest(),
+            16
+        )
+    elif isinstance(value, float):
+        # Times 100 should be unique enough
+        return int(value * 100)
+    elif isinstance(value, bool):
+        return int(value)
+    else:
+        return -1000
+
+def normalize_training_data(data: list):
+    new_data = np.array([convert_to_integer(val) for val in data], dtype=np.int64)
+    return new_data