9 from data_about_players
import Data
11 from knn
import KNNOutputVectorGenerator
14 def __init__( self
, filename
):
15 s
= "./gnet/gnet_train -l 3 -n 30 -p 30 -e 0.0003 -o gonet.net ./"+filename
17 ret
= subprocess
.call(args
)
19 s
= "./gnet/gnet_run gonet.net"
21 self
.p
= subprocess
.Popen(args
, stdin
=subprocess
.PIPE
, stdout
=subprocess
.PIPE
)
22 def __call__(self
, vector
):
23 self
.p
.stdin
.write(' '.join([str(a
) for a
in vector
]) + '\n')
24 a
= self
.p
.stdout
.readline()
25 return [ float(num
) for num
in a
.split()]
27 if __name__
== '__main__':
28 main_pat_filename
= Data
.main_pat_filename
31 player_vector
= Data
.questionare_total
32 # players_ignore = [ "Yi Ch'ang-ho 2004-" ]#, "Fujisawa Hideyuki","Yuki Satoshi", "Otake Hideo", "Yi Ch'ang-ho 2005+","Takao Shinji","Hane Naoki","Kobayashi Koichi" ]
33 players_ignore
= [ "Yi Ch'ang-ho 2004-", "Yi Ch'ang-ho 2005+" ]#,"Takao Shinji","Hane Naoki","Kobayashi Koichi" ]
34 players_all
= [ p
for p
in player_vector
.keys() if p
not in players_ignore
]
36 ### Object creating input vector when called
37 print "Creating input vector generator from main pat file:", main_pat_filename
39 i
= InputVectorGenerator(main_pat_filename
, num_features
)
41 # Create list of input vectors
43 for name
in players_all
:
44 input_vectors
+= [i(Data
.pat_files_folder
+ name
)]
46 #print '"%s"'%(players_all[2],)
47 #print input_vectors[2]
49 if len(input_vectors
) == 0:
50 print >>sys
.stderr
, "No reference vectors."
54 # Change this to False, if you do not want to use PCA
57 # Create PCA object, trained on input_vectors
58 print >>sys
.stderr
, "Running PCA."
59 pca
= PCA(input_vectors
, reduce=True)
60 # Perform a PCA on input vectors
61 input_vectors
= pca
.process_list_of_vectors(input_vectors
)
62 # Creates a Composed object that first generates an input vector
63 # and then performs a PCA analysis on it.
66 ### n/4-fold cross validation
67 #bounds = random.sample(range(1,len(players_all)), len(players_all) / 10 )
69 for x
in range(1,len(players_all
)/4):
70 bounds
+= [4*x
for _
in [1] if 4*x
< len(players_all
)]
72 print >>sys
.stderr
, "Pop too small."
77 return [ x
/ 5.0 - 1.0 for x
in vec
]
80 return list(2.0*numpy
.random
.random(k
)-1.0)
82 errs
=[ [] for _
in xrange(len(players_all
)) ]
85 sentinel
=len(players_all
)
87 for _
in xrange(number_runs
):
89 for b
in bounds
+[sentinel
]:
90 validation_set
= range(prev
, b
)
91 reference_set
= range(0,prev
) + range(b
,sentinel
)
93 print "Reference set :",
94 for pr
in range(0, prev
):
96 for pr
in validation_set
:
98 for pr
in range(b
, sentinel
):
105 for index
in reference_set
:
106 data
.append( (input_vectors
[index
], norm(player_vector
[players_all
[index
]])) )
109 ### We can enlarge the data set by adding linear combinations of input and output vectors
110 use_lin_combinations
= False
111 if use_lin_combinations
:
112 data
+= Combinator().combine(data
)
114 print_set_to_file(data
,'nn_cross.data')
116 nn
= NeuralNet('nn_cross.data')
117 # Create list of output vectors using weighted kNN algorithm approximating output_vector
118 output_vectors
= [ nn(input_vectors
[index
]) for index
in validation_set
]
120 ### Object creating output vector when called;
122 for index
in reference_set
:
123 ref_dict
[tuple(input_vectors
[index
])] = norm(player_vector
[players_all
[index
]])
125 #oknn = KNNOutputVectorGenerator(ref_dict, k=5, weight_param=0.799)
126 oknn
= KNNOutputVectorGenerator(ref_dict
, k
=4, weight_param
=0.8)
128 # Create list of output vectors using weighted kNN algorithm approximating output_vector
129 output_vectors
= [ oknn(input_vectors
[index
]) for index
in validation_set
]
131 output_vectors
= [ rand_vect(4) for index
in validation_set
]
133 desired_vectors
= [ norm(player_vector
[players_all
[index
]]) for index
in validation_set
]
136 for vec_set
,text
in [(output_vectors
, "Output: "), (desired_vectors
, "Desired:")]:
144 for num1
, (o
,d
) in zip(validation_set
, zip(output_vectors
, desired_vectors
)):
146 for num
,(x
,y
) in enumerate(zip(o
,d
)):
153 #print "Total square err: %2.3f"%( sum(errs) / number_runs,)
154 mar
= numpy
.array(errs
)
156 print "Mean square err per player: " + "%2.3f ( = sd %2.3f) "%(mean
, sqrt(mean
))
157 mean
= numpy
.array(es
).mean()
158 print "Mean square err per style: " + "%2.3f ( = sd %2.3f) "%(mean
, sqrt(mean
))
159 for num
, style
in enumerate(esps
):
160 mean
= numpy
.array(style
).mean()
161 print "%2.3f "%(mean
,)
163 print "Players sorted by mean square error:"
164 p
= zip([numpy
.array(errs
[p
]).mean() for p
in xrange(len(players_all
)) ], players_all
)
167 print "%2.3f %s"%(err
,name
)