source: framspy/FramsticksLib.py @ 1116

Last change on this file since 1116 was 1116, checked in by Maciej Komosinski, 22 months ago

Improved performance significantly by moving the step-by-step simulation loop from python to FramScript?

File size: 11.1 KB
Line 
1from typing import List  # to be able to specify a type hint of list(something)
2import json
3import sys, os
4import argparse
5import numpy as np
6import frams
7
8
9class FramsticksLib:
10        """Communicates directly with Framsticks library (.dll or .so).
11        You can perform basic operations like mutation, crossover, and evaluation of genotypes.
12        This way you can perform evolution controlled by python as well as access and manipulate genotypes.
13        You can even design and use in evolution your own genetic representation implemented entirely in python,
14        or access and control the simulation and simulated creatures step by step.
15
16        Should you want to modify or extend this class, first see and test the examples in frams-test.py.
17
18        You need to provide one or two parameters when you run this class: the path to Framsticks where .dll/.so resides
19        and, optionally, the name of the Framsticks dll/so (if it is non-standard). See::
20                FramsticksLib.py -h"""
21
22        PRINT_FRAMSTICKS_OUTPUT: bool = False  # set to True for debugging
23        DETERMINISTIC: bool = False  # set to True to have the same results in each run
24
25        GENOTYPE_INVALID = "/*invalid*/"  # this is how genotype invalidity is represented in Framsticks
26        EVALUATION_SETTINGS_FILE = "eval-allcriteria.sim"  # MUST be compatible with the standard-eval expdef
27
28
29        # This function is not needed because in python, "For efficiency reasons, each module is only imported once per interpreter session."
30        # @staticmethod
31        # def getFramsModuleInstance():
32        #       """If some other party needs access to the frams module to directly access or modify Framsticks objects,
33        #       use this function to avoid importing the "frams" module multiple times and avoid potentially initializing
34        #       it many times."""
35        #       return frams
36
37        def __init__(self, frams_path, frams_lib_name, simsettings):
38                if frams_lib_name is None:
39                        frams.init(frams_path)  # could add support for setting alternative directories using -D and -d
40                else:
41                        frams.init(frams_path, "-L" + frams_lib_name)  # could add support for setting alternative directories using -D and -d
42
43                print('Available objects:', dir(frams))
44                print()
45
46                print('Performing a basic test 1/2... ', end='')
47                simplest = self.getSimplest("1")
48                assert simplest == "X" and type(simplest) is str
49                print('OK.')
50                print('Performing a basic test 2/2... ', end='')
51                assert self.isValid(["X[0:0],", "X[0:0]", "X[1:0]"]) == [False, True, False]
52                print('OK.')
53                if not self.DETERMINISTIC:
54                        frams.Math.randomize();
55                frams.Simulator.expdef = "standard-eval"  # this expdef (or fully compatible) must be used by EVALUATION_SETTINGS_FILE
56                if simsettings is not None:
57                        self.EVALUATION_SETTINGS_FILE = simsettings
58                frams.Simulator.ximport(self.EVALUATION_SETTINGS_FILE, 4 + 8 + 16)
59
60
61        def getSimplest(self, genetic_format) -> str:
62                return frams.GenMan.getSimplest(genetic_format).genotype._string()
63
64
65        def evaluate(self, genotype_list: List[str]):
66                """
67                Returns:
68                        List of dictionaries containing the performance of genotypes evaluated using self.EVALUATION_SETTINGS_FILE.
69                        Note that for whatever reason (e.g. incorrect genotype), the dictionaries you will get may be empty or
70                        partially empty and may not have the fields you expected, so handle such cases properly.
71                """
72                assert isinstance(genotype_list, list)  # because in python str has similar capabilities as list and here it would pretend to work too, so to avoid any ambiguity
73
74                if not self.PRINT_FRAMSTICKS_OUTPUT:
75                        ec = frams.MessageCatcher.new()  # mute potential errors, warnings, messages
76
77                frams.GenePools[0].clear()
78                for g in genotype_list:
79                        frams.GenePools[0].add(g)
80                frams.ExpProperties.evalsavefile = ""  # no need to store results in a file - we will get evaluations directly from Genotype's "data" field
81                frams.Simulator.init()
82                frams.Simulator.start()
83
84                # step = frams.Simulator.step  # cache reference to avoid repeated lookup in the loop (just for performance)
85                # while frams.Simulator.running._int():  # standard-eval.expdef sets running to 0 when the evaluation is complete
86                #       step()
87                frams.Simulator.eval("while(Simulator.running) Simulator.step();")  # fastest
88                # Timing for evaluating a single simple creature 100x:
89                # - python step without caching: 2.2s
90                # - python step with caching   : 1.6s
91                # - pure FramScript and eval() : 0.4s
92
93                if not self.PRINT_FRAMSTICKS_OUTPUT:
94                        if ec.error_count._value() > 0:  # errors are important and should not be ignored, at least display how many
95                                print("[ERROR]", ec.error_count, "error(s) and", ec.warning_count, "warning(s) while evaluating", len(genotype_list), "genotype(s)")
96                        ec.close()
97
98                results = []
99                for g in frams.GenePools[0]:
100                        serialized_dict = frams.String.serialize(g.data[frams.ExpProperties.evalsavedata._value()])
101                        evaluations = json.loads(serialized_dict._string())
102                        # now, for consistency with FramsticksCLI.py, add "num" and "name" keys that are missing because we got data directly from Genotype, not from the file produced by standard-eval.expdef's function printStats(). What we do below is what printStats() does.
103                        result = {"num": g.num._value(), "name": g.name._value(), "evaluations": evaluations}
104                        results.append(result)
105
106                return results
107
108
109        def mutate(self, genotype_list: List[str]) -> List[str]:
110                """
111                Returns:
112                        The genotype(s) of the mutated source genotype(s). self.GENOTYPE_INVALID for genotypes whose mutation failed (for example because the source genotype was invalid).
113                """
114                assert isinstance(genotype_list, list)  # because in python str has similar capabilities as list and here it would pretend to work too, so to avoid any ambiguity
115
116                mutated = []
117                for g in genotype_list:
118                        mutated.append(frams.GenMan.mutate(frams.Geno.newFromString(g)).genotype._string())
119                assert len(genotype_list) == len(mutated), "Submitted %d genotypes, received %d validity values" % (len(genotype_list), len(mutated))
120                return mutated
121
122
123        def crossOver(self, genotype_parent1: str, genotype_parent2: str) -> str:
124                """
125                Returns:
126                        The genotype of the offspring. self.GENOTYPE_INVALID if the crossing over failed.
127                """
128                return frams.GenMan.crossOver(frams.Geno.newFromString(genotype_parent1), frams.Geno.newFromString(genotype_parent2)).genotype._string()
129
130
131        def dissimilarity(self, genotype_list: List[str]) -> np.ndarray:
132                """
133                Returns:
134                        A square array with dissimilarities of each pair of genotypes.
135                """
136                assert isinstance(genotype_list, list)  # because in python str has similar capabilities as list and here it would pretend to work too, so to avoid any ambiguity
137
138                # if you want to override what EVALUATION_SETTINGS_FILE sets, you can do it below:
139                # frams.SimilMeasure.simil_type = 1
140                # frams.SimilMeasureHungarian.simil_partgeom = 1
141                # frams.SimilMeasureHungarian.simil_weightedMDS = 1
142
143                n = len(genotype_list)
144                square_matrix = np.zeros((n, n))
145                genos = []  # prepare an array of Geno objects so we don't need to convert raw strings to Geno objects all the time
146                for g in genotype_list:
147                        genos.append(frams.Geno.newFromString(g))
148                for i in range(n):
149                        for j in range(n):  # maybe calculate only one triangle if you really need a 2x speedup
150                                square_matrix[i][j] = frams.SimilMeasure.evaluateDistance(genos[i], genos[j])._double()
151
152                for i in range(n):
153                        assert square_matrix[i][i] == 0, "Not a correct dissimilarity matrix, diagonal expected to be 0"
154                non_symmetric_diff = square_matrix - square_matrix.T
155                non_symmetric_count = np.count_nonzero(non_symmetric_diff)
156                if non_symmetric_count > 0:
157                        non_symmetric_diff_abs = np.abs(non_symmetric_diff)
158                        max_pos1d = np.argmax(non_symmetric_diff_abs)  # location of largest discrepancy
159                        max_pos2d_XY = np.unravel_index(max_pos1d, non_symmetric_diff_abs.shape)  # 2D coordinates of largest discrepancy
160                        max_pos2d_YX = max_pos2d_XY[1], max_pos2d_XY[0]  # 2D coordinates of largest discrepancy mirror
161                        worst_guy_XY = square_matrix[max_pos2d_XY]  # this distance and the other below (its mirror) are most different
162                        worst_guy_YX = square_matrix[max_pos2d_YX]
163                        print("[WARN] Dissimilarity matrix: expecting symmetry, but %g out of %d pairs were asymmetrical, max difference was %g (%g %%)" %
164                              (non_symmetric_count / 2,
165                               n * (n - 1) / 2,
166                               non_symmetric_diff_abs[max_pos2d_XY],
167                               non_symmetric_diff_abs[max_pos2d_XY] * 100 / ((worst_guy_XY + worst_guy_YX) / 2)))  # max diff is not necessarily max %
168                return square_matrix
169
170
171        def isValid(self, genotype_list: List[str]) -> List[bool]:
172                assert isinstance(genotype_list, list)  # because in python str has similar capabilities as list and here it would pretend to work too, so to avoid any ambiguity
173                valid = []
174                for g in genotype_list:
175                        valid.append(frams.Geno.newFromString(g).is_valid._int() == 1)
176                assert len(genotype_list) == len(valid), "Tested %d genotypes, received %d validity values" % (len(genotype_list), len(valid))
177                return valid
178
179
180def parseArguments():
181        parser = argparse.ArgumentParser(description='Run this program with "python -u %s" if you want to disable buffering of its output.' % sys.argv[0])
182        parser.add_argument('-path', type=ensureDir, required=True, help='Path to the Framsticks library (.dll or .so) without trailing slash.')
183        parser.add_argument('-lib', required=False, help='Library name. If not given, "frams-objects.dll" or "frams-objects.so" is assumed depending on the platform.')
184        parser.add_argument('-simsettings', required=False, help='The name of the .sim file with settings for evaluation, mutation, crossover, and similarity estimation. If not given, "eval-allcriteria.sim" is assumed by default. Must be compatible with the "standard-eval" expdef.')
185        parser.add_argument('-genformat', required=False, help='Genetic format for the demo run, for example 4, 9, or S. If not given, f1 is assumed.')
186        return parser.parse_args()
187
188
189def ensureDir(string):
190        if os.path.isdir(string):
191                return string
192        else:
193                raise NotADirectoryError(string)
194
195
196if __name__ == "__main__":
197        # A demo run.
198
199        # TODO ideas:
200        # - check_validity with three levels (invalid, corrected, valid)
201        # - a pool of binaries running simultaneously, balance load - in particular evaluation
202
203        parsed_args = parseArguments()
204        framsLib = FramsticksLib(parsed_args.path, parsed_args.lib, parsed_args.simsettings)
205
206        print("Sending a direct command to Framsticks library that calculates \"4\"+2 yields", frams.Simulator.eval("return \"4\"+2;"))
207
208        simplest = framsLib.getSimplest('1' if parsed_args.genformat is None else parsed_args.genformat)
209        print("\tSimplest genotype:", simplest)
210        parent1 = framsLib.mutate([simplest])[0]
211        parent2 = parent1
212        MUTATE_COUNT = 10
213        for x in range(MUTATE_COUNT):  # example of a chain of 10 mutations
214                parent2 = framsLib.mutate([parent2])[0]
215        print("\tParent1 (mutated simplest):", parent1)
216        print("\tParent2 (Parent1 mutated %d times):" % MUTATE_COUNT, parent2)
217        offspring = framsLib.crossOver(parent1, parent2)
218        print("\tCrossover (Offspring):", offspring)
219        print('\tDissimilarity of Parent1 and Offspring:', framsLib.dissimilarity([parent1, offspring])[0, 1])
220        print('\tPerformance of Offspring:', framsLib.evaluate([offspring]))
221        print('\tValidity of Parent1, Parent 2, and Offspring:', framsLib.isValid([parent1, parent2, offspring]))
Note: See TracBrowser for help on using the repository browser.