Sandbox

In [1]:

    

import sys
import os
sys.path.append("../")  # include the root directory as the main
import pandas as pd
import numpy as np


    

In [3]:

    

from aind.isolation import Board
from aind.sample_players import RandomPlayer
from aind.sample_players import GreedyPlayer


    

In [4]:

    

# create an isolation board (by default 7x7)
player1 = RandomPlayer()
player2 = GreedyPlayer()
game = Board(player1, player2)


    

In [6]:

    

# place player 1 on the board at row 2, column 3, then place player 2 on
# the board at row 0, column 5; display the resulting board state.  Note
# that the .apply_move() method changes the calling object in-place.
game.apply_move((2, 3))
game.apply_move((0, 5))
print(game.to_string())


    

    




     0   1   2   3   4   5   6
0  |   |   |   |   |   | 2 |   | 
1  |   |   |   |   |   |   |   | 
2  |   |   |   | 1 |   |   |   | 
3  |   |   |   |   |   |   |   | 
4  |   |   |   |   |   |   |   | 
5  |   |   |   |   |   |   |   | 
6  |   |   |   |   |   |   |   | 

In [7]:

    

# players take turns moving on the board, so player1 should be next to move
assert(player1 == game.active_player)

# get a list of the legal moves available to the active player
print(game.get_legal_moves())


    

    




[(1, 5), (4, 2), (4, 4), (1, 1), (0, 2), (3, 5), (0, 4), (3, 1)]

In [8]:

    

# get a successor of the current state by making a copy of the board and
# applying a move. Notice that this does NOT change the calling object
# (unlike .apply_move()).
new_game = game.forecast_move((1, 1))
assert(new_game.to_string() != game.to_string())
print("\nOld state:\n{}".format(game.to_string()))
print("\nNew state:\n{}".format(new_game.to_string()))


    

    




Old state:
     0   1   2   3   4   5   6
0  |   |   |   |   |   | 2 |   | 
1  |   |   |   |   |   |   |   | 
2  |   |   |   | 1 |   |   |   | 
3  |   |   |   |   |   |   |   | 
4  |   |   |   |   |   |   |   | 
5  |   |   |   |   |   |   |   | 
6  |   |   |   |   |   |   |   | 


New state:
     0   1   2   3   4   5   6
0  |   |   |   |   |   | 2 |   | 
1  |   | 1 |   |   |   |   |   | 
2  |   |   |   | - |   |   |   | 
3  |   |   |   |   |   |   |   | 
4  |   |   |   |   |   |   |   | 
5  |   |   |   |   |   |   |   | 
6  |   |   |   |   |   |   |   | 

In [9]:

    

# play the remainder of the game automatically -- outcome can be "illegal
# move", "timeout", or "forfeit"
winner, history, outcome = game.play()
print("\nWinner: {}\nOutcome: {}".format(winner, outcome))
print(game.to_string())
print("Move history:\n{!s}".format(history))


    

    




Winner: <aind.sample_players.GreedyPlayer object at 0x000001E95C3023C8>
Outcome: illegal move
     0   1   2   3   4   5   6
0  | - |   |   | 2 | - | - |   | 
1  |   |   | - |   |   | - |   | 
2  |   | - | - | - | - |   |   | 
3  |   |   | - | - | - |   | - | 
4  | - |   | - | - | - |   | - | 
5  |   |   | - | - | - | - |   | 
6  |   | - |   | - |   | 1 |   | 

Move history:
[[0, 4], [2, 4], [1, 2], [4, 3], [0, 0], [2, 2], [2, 1], [3, 4], [3, 3], [5, 3], [5, 2], [3, 2], [4, 0], [4, 4], [6, 1], [6, 3], [4, 2], [5, 5], [5, 4], [3, 6], [4, 6], [1, 5], [6, 5], [0, 3]]

In [2]:

    

import pandas as pd


    

In [3]:

    

l_data = []
with open('../data/data_test.txt', 'r') as fr:
    for row in fr:
        if 'Win Rate:' in row:
            l_data.append([float(x.replace('%', '')) for x in row.strip().split()[2:]])


    

In [4]:

    

df_tests = pd.DataFrame(l_data, columns=['AB_Improved', 'AB_Custom', 'AB_Custom_2', 'AB_Custom_3'])


    

In [5]:

    

df_tests


    

    
Out[5]:






  

    

      

      
AB_Improved
      
AB_Custom
      
AB_Custom_2
      
AB_Custom_3
    
  
  

    

      
0
      
75.0
      
67.1
      
70.0
      
61.4
    
    

      
1
      
71.4
      
73.6
      
71.4
      
69.3
    
    

      
2
      
70.7
      
70.7
      
72.9
      
65.0
    
    

      
3
      
69.3
      
70.7
      
66.4
      
69.3
    
    

      
4
      
66.4
      
73.6
      
65.7
      
67.9
    
    

      
5
      
64.3
      
72.1
      
69.3
      
62.9
    
    

      
6
      
67.9
      
69.3
      
68.6
      
62.9
    
    

      
7
      
70.7
      
65.7
      
71.4
      
67.9
    
    

      
8
      
70.0
      
71.4
      
69.3
      
65.0
    
    

      
9
      
69.3
      
72.9
      
73.6
      
64.3
    
  

In [14]:

    

import pandas as pd
from scipy.stats import ttest_ind
#performs t-test
b = df_tests.AB_Improved
a = df_tests.AB_Custom
tval, p_value = ttest_ind(a, b, equal_var=False)
print("t-value = {:0.6f}, p-value = {:0.8f}".format(tval, p_value/2))


    

    




t-value = 0.969089, p-value = 0.17271971

In [19]:

    

(a>b).sum()


    

    
Out[19]:





5

In [18]:

    

b = df_tests.AB_Improved
a = df_tests.AB_Custom_2
tval, p_value = ttest_ind(a, b, equal_var=False)
print("t-value = {:0.6f}, p-value = {:0.8f}".format(tval, p_value/2))


    

    




t-value = 0.293111, p-value = 0.38642045

In [13]:

    

b = df_tests.AB_Improved
a = df_tests.AB_Custom_3
tval, p_value = ttest_ind(a, b, equal_var=False)
print("t-value = {:0.6f}, p-value = {:0.8f}".format(tval, p_value/2))


    

    




t-value = -3.040156, p-value = 0.00352281

In [ ]: