daveklotz
daveklotz
/ results.txt
Created
July 31, 2021 20:26
Results of Back Testing from 2021, 2018 and 2017
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| 2021 through July 27th | |
| ====================== | |
| +-------------+-----------+----------+------------+------------+ | |
| | Certainty | NumBets | Stake | Winnings | ROI | | |
| |-------------+-----------+----------+------------+------------| | |
| | Pr > 0.0 | 1395 | 162761 | 1366 | 0.00839267 | | |
| | Pr > 0.05 | 439 | 48121 | 4786 | 0.0994576 | | |
| | Pr > 0.10 | 125 | 13991 | 1503 | 0.107426 | | |
| | Pr > 0.15 | 64 | 7294 | 226 | 0.0309844 | |
daveklotz
/ daily-sheet-generation.py
Created
July 31, 2021 19:48
Generate the data and run the ANN so I can get picks for today's games
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| ###### | |
| # NOTE: this includes calculaiton for my first Wins Above Replacement approach, as well as the current DRA- approach | |
| ###### | |
| games = mlbgame.day(2021,7,30) | |
| daily_game_id = 1 | |
| unique_row_id = 1. # just to make sure i have the same format as legacy spreadsheet | |
| location_index = 0 |
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| units = 10 | |
| ann = tf.keras.models.Sequential() | |
| ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid')) | |
| ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid')) | |
| ann.add(tf.keras.layers.Dense(units=units, activation='sigmoid')) | |
| ann.add(tf.keras.layers.Dense(units=1, activation='sigmoid')) | |
| ann.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy']) |