gostyle.py

   1 #!/usr/bin/python
   2 """
   3 This file contains several objects we use to process a pattern files for Go game.
   4 We use it to generate input sets for a neural network (libfann), or if we want to perform a PCA analysis to data.
   5 It generates input vectors from pattern files. See `Const.pat_file_regexp' for file format in regexp.
   6
   7 ===== EXAMPLE PAT FILE =====
   8 4632 (border:3 s:5000003 s:6000049 s:700004a)
   9 3497 (atariescape:0 border:0 ldist:4 lldist:2 s:30011a1)
  10 ...
  11 ===== END =====
  12 """
  13 import re
  14 import sys
  15 import cPickle
  16 import random
  17 from itertools import izip,count
  18
  19 class Const:
  20         """Class used to hold global const variables, such as the pat file format."""
  21         pat_file_regexp = '^\s*(\d+)\s*(.+)$'
  22
  23 def print_vector(vector, where=sys.stdout):
  24         """Helper method for printing vector (list of floats)."""
  25         for x in vector:
  26                 print >> where, x,
  27         print >> where
  28
  29 def print_set_to_file( data, filename):
  30         """
  31         Helper method for printing datasets for neural network.
  32         FORMAT of the file
  33         number_of_pairs len_of_input_vector len_of_output_vector
  34         first_input_vector
  35         first_output_vector
  36         second_input_vector
  37         ...
  38         """
  39         def print_set( data, where):
  40                 print >> where,  len(data), len(data[0][0]), len(data[0][1])
  41                 for i,o in data:
  42                         print_vector(i, where)
  43                         print_vector(o, where)
  44         fout = open(filename, 'w')
  45         print_set(data, fout)
  46         fout.close()
  47
  48 def dump_object_to_file(object, filename):
  49         """Helper function to save an object to file using cPickle module."""
  50         f=open(filename,'w')
  51         cPickle.dump(object, f,-1)
  52         f.close()
  53
  54 def load_object_from_file(filename):
  55         """Helper function to recover an object from file using cPickle module."""
  56         f=open(filename,'r')
  57         object = cPickle.load(f)
  58         f.close()
  59         return object
  60
  61 class VectorGenerator(object):
  62         """Abstract class. When called, returns a vector (list of floats). Has output_dim param."""
  63         def __call__(self):
  64                 raise NotImplementedError
  65
  66 class VectorToVector(VectorGenerator):
  67         """Abstract class. When called with a vector (list of floats), returns a vector. Has input_dim and output_dim params."""
  68         def __call__(self, vector):
  69                 raise NotImplementedError
  70
  71 ###
  72 ###             PCA Analysis
  73 ###  Note that you must have `numpy' and `mdp' python modules, otherwise the PCA will
  74 ###  fallback to doing nothing at all (but doing it completely compatibly with the rest of the code :-).
  75 try:
  76         from numpy import array
  77         import mdp
  78         class PCA(VectorToVector):
  79                 """
  80                 Object performing a PCA analysis on either a given vector (see `__call__' function),
  81                 or on a list of vectors (see `process_list_of_vectors' function).
  82                 """
  83                 def __init__(self, list_of_train_vectors, *args, **kwargs):
  84                         self.pca = mdp.nodes.PCANode(*args, **kwargs)
  85                         self.pca.train(array(list_of_train_vectors))
  86                         self.pca.stop_training()
  87                         self.input_dim = self.pca.input_dim
  88                 def __call__(self, vector):
  89                         return list(self.pca(array([vector]))[0])
  90                 def process_list_of_vectors(self, list_of_vectors):
  91                         return [ list(vec) for vec in self.pca(array(list_of_vectors)) ]
  92                 def get_projection_info(self):
  93                         return self.pca.get_recmatrix()
  94                 def get_eigenvalues(self):
  95                         return self.pca.d
  96                 def get_eigenvectors(self):
  97                         return list(self.pca.v)
  98
  99 except ImportError, e:
 100         print >>sys.stderr, "Warning: %s. PCA will not work."%(str(e))
 101
 102         class PCA(VectorToVector):
 103                 """Default dummy class for PCA, not very useless."""
 104                 def __init__(self, *args, **kwargs):
 105                         pass
 106                 def __call__(self, list_of_vectors):
 107                         return list_of_vectors
 108                 def process_list_of_vectors(self, list_of_vectors):
 109                         return list_of_vectors
 110
 111
 112 class Compose(VectorGenerator):
 113         """
 114         A class used as a composer of different objects, such as InputVectorGenerator and PCA.
 115         Use this if you want to e.g. generate PCA processed vectors.
 116         """
 117         def __init__(self, vector_generator, vector_to_vector):
 118                 if not isinstance(vector_generator, VectorGenerator):
 119                         raise TypeError
 120                 if not isinstance(vector_to_vector, VectorToVector):
 121                         raise TypeError
 122                 self.vector_generator = vector_generator
 123                 self.vector_to_vector = vector_to_vector
 124         #       if vector_generator.output_dim != vector_to_vector.input_dim:
 125         #               raise RuntimeError("Dimensions of Composed object mismatch.")
 126         def __call__(self, *args, **kwargs):
 127                 return self.vector_to_vector(self.vector_generator(*args, **kwargs))
 128
 129 class OccurenceVectorGenerator(VectorGenerator):
 130         """
 131         A class used to generate input vectors based on a relative number of occurences of some input patterns.
 132         The object is initialized with a file of patterns. It takes the topmost `num_features' patterns.
 133         """
 134         def generate_top_pattern_dict(self):
 135                 rexp=re.compile(Const.pat_file_regexp)
 136                 self.top_pattern_dict = {}
 137                 self.top_pattern_str = {}
 138                 i = 0
 139                 input_file = open(self.filename)
 140                 for line in input_file:
 141                         if i >= self.output_dim:
 142                                 break
 143                         s = rexp.match(line).group(2)
 144                         self.top_pattern_dict[s] = i
 145                         self.top_pattern_str[i] = s
 146                         i += 1
 147                 input_file.close()
 148
 149         def __init__(self, main_pat_file, num_features):
 150                 self.output_dim = num_features
 151                 self.filename = main_pat_file
 152                 self.generate_top_pattern_dict()
 153
 154         def __call__(self, pat_file):
 155                 vector = [0]*len(self.top_pattern_dict)
 156                 rexp=re.compile(Const.pat_file_regexp)
 157                 i = 0
 158                 input_file = open(pat_file)
 159                 for line in input_file:
 160                         match = rexp.match(line)
 161                         if not match:
 162                                 raise IOError("Wrong file format: " + pat_file)
 163                         if match.group(2) in self.top_pattern_dict:
 164                                 index=self.top_pattern_dict[match.group(2)]
 165                                 vector[index] += int(match.group(1))
 166                                 i += 1
 167                         if i >= len(self.top_pattern_dict):
 168                                 break
 169                 input_file.close()
 170                 if len(vector) != self.output_dim:
 171                         raise RuntimeError
 172                 return vector
 173
 174         def stringof(self, i):
 175                 return self.top_pattern_str[i]
 176
 177 class Rescale(VectorToVector):
 178         """Class that rescales vectors to a given interval!"""
 179         def __init__(self, a=-1.0, b=1.0):
 180                 if a >= b:
 181                         raise RuntimeError("a must be < b")
 182                 self.a = a
 183                 self.avg = (a + b) * 0.5
 184                 self.tot = b - a
 185         def __call__(self, vector):
 186                 if len(vector) == 0:
 187                         raise RuntimeError
 188                 to_zero = 0 - min(vector)
 189                 maximum = max(vector) + to_zero
 190                 if maximum == 0:
 191                         return [ self.avg  for _ in vector ]
 192                 return [ self.tot * (x + to_zero) / maximum + self.a for x in vector ]
 193
 194 class InputVectorGenerator(VectorGenerator):
 195         """
 196         First we generate an occurence vector by OccurenceVectorGenerator.
 197         Then, an input vector is generated as a relative number of occurences of the topmost patterns.
 198         The occurences are mapped so that the most frequently used
 199         one is mapped to 1.0 and the rest is mapped relatively on the scale (1.0,-1.0). See `__call__' function.
 200         """
 201         def __init__(self, *args, **kwargs):
 202                 self.ovg = OccurenceVectorGenerator(*args, **kwargs)
 203                 self.gen = Compose(self.ovg, Rescale(-1.0, 1.0))
 204         def __call__(self, *args, **kwargs):
 205                 return self.gen(*args, **kwargs)
 206         def ovg(self):
 207                 return self.ovg
 208
 209 def linear_combination(list_of_vectors, coefs):
 210         if len(list_of_vectors) != len(coefs):
 211                 raise Exception("len(list_of_vectors) != len(coefs)")
 212         if len(list_of_vectors) == 0:
 213                 return
 214         len_vec=len(list_of_vectors[0])
 215         res_vec=[0]*len_vec
 216         for p in xrange(len(list_of_vectors)):
 217                 for i in xrange(len_vec):
 218                         res_vec[i] += coefs[p] * list_of_vectors[p][i]
 219         return res_vec
 220
 221 def get_random_norm_coefs( num ):
 222         coefs=[]
 223         rnd_nums= [ random.random() for i in xrange(num-1) ] + [1]
 224         rnd_nums.sort()
 225         first=0
 226         for next in rnd_nums:
 227                 coefs.append(next-first)
 228                 first=next
 229         return coefs
 230
 231 class Combinator(object):
 232         def __init__(self, num_lincombs = 1, skip_subset_len = [0], max_len = 2):
 233                 self.num_lincombs = num_lincombs
 234                 self.skip_subset_len = skip_subset_len
 235                 self.max_len = max_len
 236         def get_subsets(self, set):
 237                 if len(set) == 0:
 238                         return [[]]
 239                 sub=self.get_subsets(set[1:])
 240                 return sub + filter( lambda x : ( self.max_len==0 or len(x)<=self.max_len ), [ set[:1]+subset  for subset in sub] )
 241         def combine(self, data):
 242                 combinations = []
 243                 for subset in self.get_subsets(range(len(data))):
 244                         if len(subset) in self.skip_subset_len:
 245                                 continue
 246                         input_vectors = [ data[index][0] for index in subset ]
 247                         output_vectors = [ data[index][1] for index in subset ]
 248                         for i in xrange(self.num_lincombs):
 249                                 coefs = get_random_norm_coefs(len(subset))
 250                                 combinations += [(linear_combination(input_vectors, coefs), linear_combination(output_vectors, coefs))]
 251                 return combinations
 252
 253 class PlayerStrategyIdentificator(object):
 254         """Object holding information about default strategies for players."""
 255         def __init__(self, strategy_players):
 256                 self.strategy_players = strategy_players
 257
 258                 self.player_strategy={}
 259                 self.all_players = []
 260                 self.all_strategies = []
 261                 for strategy, players in self.strategy_players.items():
 262                         self.all_strategies += [strategy]
 263                         for player in players:
 264                                 self.all_players += [player]
 265                                 self.player_strategy[player] = strategy
 266
 267         def __call__(self, player_name):
 268                 return self.player_strategy[player_name]
 269
 270 class StrategyOutputVectorGenerator(VectorGenerator):
 271         """
 272         This object generates output vectors for players with strategies specified in `PlayerStrategyIdentificator' object.
 273         It is initialized with a list of strategies `valid_strategies' it shall take into acount.
 274         When called (see `__call__') with a name of a player with a strategy from `valid_strategies' it returns a vector
 275         that corresponds to the strategy like this.
 276         """
 277         def __init__(self, strategy_players, valid_strategies=None):
 278                 self.identificator = PlayerStrategyIdentificator(strategy_players)
 279                 if valid_strategies == None:
 280                         valid_strategies = self.identificator.all_strategies
 281                 index=0
 282                 self.valid_strategy_index={}
 283                 for s in valid_strategies:
 284                         self.valid_strategy_index[s]= index
 285                         index += 1
 286         def __call__(self, player_name):
 287                 try:
 288                         player_strat = self.identificator(player_name)
 289                         player_strat_index = self.valid_strategy_index[player_strat]
 290                         return [ 1.0 if i == player_strat_index else -1.0 for i in xrange(len(self.valid_strategy_index)) ]
 291                 except KeyError:
 292                         return None
 293
 294 class PlanarOutputVectorGenerator(VectorGenerator):
 295         """Class that explicitly returns predefined output vectors for given players."""
 296         def __init__(self, player_vector):
 297                 self.player_vector = player_vector
 298                 self.players = player_vector.keys()
 299         def __call__(self, player_name):
 300                 try:
 301                         return self.player_vector[player_name]
 302                 except KeyError:
 303                         return None
 304
 305 if __name__ == '__main__':
 306         print >>sys.stderr, "This is just a library file..."