def make_int_to_action(file):
ita_data = CsvDataset(file)
ita = [0 for i in range(0, len(ita_data.feature_vectors))]
for fv in ita_data.feature_vectors:
idx = int(fv[0])
ita[idx] = fv[1]
return ita
def summarize(dir):
Nagents = 2
summary = Summary()
for w in os.listdir(dir):
wpath = os.path.join(dir, w)
if os.path.isdir(wpath):
print(wpath)
try:
wfile = open(os.path.join(wpath, "result.csv"))
except:
print("! No 'results.csv' in '" + wpath + "'")
continue
results = CsvDataset(wfile)
wfile.close()
try:
wfile = open(os.path.join(wpath, "game-log.csv"))
except:
print("! No 'game-log.csv' in '" + wpath + "'")
continue
log = CsvDataset(wfile)
wfile.close()
# Commit
log_ai = [log.attribute_index("a0"), log.attribute_index("a1")]
for fv in results.feature_vectors:
if fv[0] == "winner":
summary.win_counts[int(fv[1])] += 1
elif fv[0] == "score":
summary.score.add(float(fv[1]))
policies = [None, None]
switches = [0, 0]
for fv in log.feature_vectors:
for i in range(0, Nagents):
if policies[i] is None:
policies[i] = fv[log_ai[i]]
elif policies[i] != fv[log_ai[i]]:
switches[i] += 1
policies[i] = fv[log_ai[i]]
for i in range(0, Nagents):
summary.switches[i].add(switches[i])
return summary
def process_data( data ): global acc, headers, master, Ngames_idx, options if master is None: master = CsvDataset( attributes=data.attributes[:], feature_vectors=[] ) Ngames_idx = master.attribute_index( "Ngames" ) mean_attributes = [master.attribute_index( a ) for a in [ "mean", "state_branching_mean", "action_branching_mean", "tree_depth_mean", "steps_mean"]] var_attributes = [master.attribute_index( a ) for a in [ "var", "state_branching_var", "action_branching_var", "tree_depth_var", "steps_var"]] min_attributes = [master.attribute_index( a ) for a in ["steps_min"]] max_attributes = [master.attribute_index( a ) for a in ["steps_max"]] else: if len(master.attributes) != len(data.attributes): on_error( "Unequal column count" ) for i in range(0, len(master.attributes)): if master.attributes[i].name != data.attributes[i].name: on_error( "Different headers" ) hidx = None if options.combine is not None: hidx = [data.attribute_index( name ) for name in eval( options.combine )] # print( eval( options.combine ) ) for fv in data.feature_vectors: key = len(acc) if hidx is not None: key = tuple(fv[i] for i in hidx) try: exemplar = acc[key] acc[key] = combine( exemplar, fv ) except KeyError: acc[key] = fv[:]
# ----------------------------------------------------------------------------
# Main
# ----------------------------------------------------------------------------
cl_parser = OptionParser(usage="%prog [options] file")
cl_parser.add_option("-o",
dest="output_file",
type="string",
default=None,
help="The file to write the output to (default: stdout)")
(options, args) = cl_parser.parse_args()
if len(args) == 0:
cl_parser.error("No input file")
elif len(args) > 1:
print("WARNING: Multiple input files; ignoring all but the first")
arff_file = open(args[0], "r")
if options.output_file is None:
# Saying 'open( "sys.stdout" )' doesn't seem to accomplish this
output_file = sys.stdout
else:
output_file = open(options.output_file, "w")
arff_dataset = ArffDataset(arff_file)
csv_dataset = CsvDataset.from_arff_dataset(arff_dataset)
output_file.write(repr(csv_dataset))
output_file.close()
else:
output_file = open(options.output_file, "w")
out_attributes = [
"Domain", "Algorithm", "domain_params", "criterion", "ss.abstraction",
"par.priority", "par.classifier", "random_abstraction.k", "ss.budget_type",
"ss.budget", "V_mean", "V_var", "V_conf", "ss.width", "ss.depth",
"seed.world", "seed.sim"
]
# out_attributes = [
# "domain", "criterion", "ss.abstraction", "par.subtree_refinement_order", "par.classifier", "random_partition.k", "ss.budget_type", "ss.budget",
# "V_mean", "V_var", "V_conf", "ss.width", "ss.depth", "seed"
# ]
out_data = CsvDataset(attributes=[CsvAttribute(a) for a in out_attributes],
feature_vectors=[])
with open(args[0], "r") as input_file:
in_data = CsvDataset(input_file)
# [jhostetler:20160804] The Saving domain had an extra header in its output,
# causing everything to be shifted by 1.
Nepisodes_idx = len(in_data.attributes)
try:
Nepisodes_idx = in_data.attribute_index("Nepisodes")
except KeyError:
# Exception indicates that problematic field was not present
pass
if Nepisodes_idx != len(in_data.attributes):
print("WARNING: Found 'Nepisodes' header; correcting dataset")
sailing_p = in_data.attribute_index("sailing.p")
cl_parser.add_option("--attribute",
dest="attribute",
type="string",
default=None,
help="The attribute to match")
cl_parser.add_option("--value",
dest="value",
type="string",
default=None,
help="The value to match")
(options, args) = cl_parser.parse_args()
def open_output(options):
if options.output_file == "-":
# Saying 'open( "sys.stdout" )' doesn't seem to accomplish this
return sys.stdout
else:
return open(options.output_file, "w")
with open(args[0], "r") as input_file:
in_data = CsvDataset(input_file)
out_data = CsvDataset(attributes=in_data.attributes, feature_vectors=[])
idx = in_data.attribute_index(options.attribute)
for fv in in_data.feature_vectors:
if fv[idx] == options.value:
out_data.feature_vectors.append(fv[:])
with open_output(options) as output_file:
output_file.write(repr(out_data))
cl_parser.add_option( "--loose", dest="loose", action="store_true", default=False, help="If specified, files are not checked for header or column count equality." ) cl_parser.add_option( "--no-headers", dest="no_headers", action="store_true", default=False, help="If specified, indicates that the files have no header rows." ) cl_parser.add_option( "--combine", dest="combine", type="string", default=None, help="""A python list of header names. If specified, results will be combined for all rows that have the same value in all specified columns.""" ) (options, args) = cl_parser.parse_args(); if options.output_file == "-": # Saying 'open( "sys.stdout" )' doesn't seem to accomplish this output_file = sys.stdout else: output_file = open( options.output_file, "w" ) for file in args: print( file ) input_file = open( file, "r" ) in_data = CsvDataset( input_file ) process_data( in_data ) input_file.close() conf_idx = master.attribute_index( "conf" ) var_idx = master.attribute_index( "var" ) Ngames_idx = master.attribute_index( "Ngames" ) for fv in acc.values(): fv[conf_idx] = 1.96 * math.sqrt( float(fv[var_idx]) ) / math.sqrt( float(fv[Ngames_idx]) ) master.feature_vectors = [map(str, v) for v in acc.values()] output_file.write( repr(master) ) output_file.close()
dest="complete",
action="store_true",
default=False,
help=
"If specified, only parameterizations for which results are available for all budgets are considered."
)
(options, args) = cl_parser.parse_args()
if options.output_file == "-":
# Saying 'open( "sys.stdout" )' doesn't seem to accomplish this
output_file = sys.stdout
else:
output_file = open(options.output_file, "w")
with open(args[0], "r") as input_file:
in_data = CsvDataset(input_file)
domain_kb = KeyBuilder(in_data, ["domain_params"])
# par_kb = KeyBuilder( in_data, ["ss.abstraction", "par.priority", "par.classifier"] )
par_kb = KeyBuilder(in_data, ["Algorithm"])
values = dict()
# The "blocks" are Domain x Budget
block_kb = KeyBuilder(in_data, ["domain_params", "ss.budget"])
column_kb = KeyBuilder(in_data, ["Algorithm"])
friedman = dict()
alg_set = set()
for fv in in_data.feature_vectors:
if not fv[in_data.attribute_index("Algorithm")].startswith(
"PAR"): # != "par":
continue
print("par: " + fv[in_data.attribute_index("Algorithm")])
# Set output
if options.output_file is None:
output_file = sys.stdout
else:
output_file = open(options.output_file, "w")
out_fields = [
"experiment", "algorithm", "faults", "N", "Nblackout", "V", "V_stdev",
"V_median", "V_min", "V_max", "R_end", "R_end_stdev", "R_end_median",
"R_end_min", "R_end_max", "t_blackout", "t_blackout_stdev",
"t_blackout_median", "t_blackout_min", "t_blackout_max", "NLoadShed",
"NLoadShed_stdev", "NLoadShed_median", "NLoadShed_min", "NLoadShed_max",
"NIsland", "NIsland_stdev", "NIsland_median", "NIsland_min", "NIsland_max"
]
out_data = CsvDataset(attributes=list(map(CsvAttribute, out_fields)),
feature_vectors=[])
missing = []
for filename in args:
# for filename in glob.iglob( args[0] ):
# experiment = os.path.dirname( filename )
experiment = filename
print("'" + experiment + "'")
with open(experiment + ".csv") as fparams:
params = CsvDataset(fparams)
try:
f = open(os.path.join(filename, "rewards.csv"))
except IOError as ex:
print("WARNING: Skipping " + filename)
print(str(ex))
missing.append(
# header_file.close()
for rewards_filename in args:
missing = None
with open(rewards_filename, "r+") as rewards_file:
lines = sum(1 for line in rewards_file)
if lines == 2:
# Assumed good
print(rewards_filename)
if False:
# if lines == 1:
print("Missing header: " + rewards_filename)
rewards_file.seek(0, 0)
bad_dataset = CsvDataset(rewards_file, headers=False)
bad_dataset.attributes = header_dataset.attributes[:]
params_filename = os.path.dirname(rewards_filename) + ".csv"
print(params_filename)
with open(params_filename) as params_file:
params_dataset = CsvDataset(params_file)
params = params_dataset.feature_vectors[0]
# Fix the feature vectors
fv = bad_dataset.feature_vectors[0]
fv[0] = str(0) # Filled with NUL for some reason
for i in range(0, 3):
# Copy missing parameters
attr_name = header_dataset.attributes[i].name
attr_idx = params_dataset.attribute_index(attr_name)
print("\tInsert " + attr_name + " = " + params[attr_idx])
fv.insert(i, params[attr_idx])
dest="fix_fault_time",
default=False,
help=
"Enable correction for early experiments that activated the fault one step later"
)
(options, args) = cl_parser.parse_args()
if options.output_file == "-":
output_file = sys.stdout
else:
output_file = open(options.output_file, "w")
out_fields = [
"Tstable", "Tepisode", "Vu", "Ru_end", "Nfaults", "fault0", "fault1"
]
out_data = CsvDataset(attributes=map(CsvAttribute, out_fields),
feature_vectors=[])
for filename in args:
with open(filename) as f:
data = CsvDataset(f)
[iTstable, iTepisode, iNfaults, ifault0,
ifault1] = map(data.attribute_index,
["Tstable", "Tepisode", "Nfaults", "fault0", "fault1"])
for fv in data.feature_vectors:
Tstable = int(fv[iTstable])
Tepisode = int(fv[iTepisode])
T = Tstable + Tepisode
r = 0.0
Rend = 0
for t in range(0, T):
i = data.attribute_index("t" + str(t))
cl_parser.add_option( "--delim", dest="delim", type="string", default=",", help="""The delimiter string (default: ","). """ ) cl_parser.add_option( "--loose", dest="loose", action="store_true", default=False, help="If specified, files are not checked for header or column count equality." ) (options, args) = cl_parser.parse_args(); if options.output_file == "-": output_file = sys.stdout else: output_file = open( options.output_file, "w" ) # Find the largest set of headers headers = HeaderAccumulator() for file in args: input_file = open( file, "r" ) in_data = CsvDataset( input_file ) print( file + ": " + str(len(in_data.attributes)) ) headers.add( in_data.attributes ) input_file.close() print( headers.attributes ) # Treat the largest header set as canonical master = CsvDataset( attributes=headers.attributes[:], feature_vectors=[] ) for file in args: input_file = open( file, "r" ) in_data = CsvDataset( input_file ) process_data( master, in_data ) input_file.close() output_file.write( repr(master) ) output_file.close()
default="-",
help="The file to write the output to (default: stdout)")
# cl_parser.add_option( "--complete", dest="complete", action="store_true", default=False,
# help="If specified, only parameterizations for which results are available for all budgets are considered." )
(options, args) = cl_parser.parse_args()
if options.output_file == "-":
# Saying 'open( "sys.stdout" )' doesn't seem to accomplish this
output_file = sys.stdout
rank_file = sys.stdout
else:
output_file = open(options.output_file, "w")
rank_file = open("rank-" + options.output_file, "w")
with open(args[0], "r") as input_file:
in_data = CsvDataset(input_file)
# The "blocks" are Domain x Budget
block_kb = KeyBuilder(in_data, ["domain_params", "ss.budget"])
# The "treatments" are the different PARSS variants
column_kb = KeyBuilder(in_data, ["Algorithm"])
# This will be a two-level map Block -> Column -> V_mean
friedman = dict()
alg_set = set([
"PAR(bf; DT)", "PAR(bf; random)", "PAR(uniform; DT)",
"PAR(uniform; random)", "PAR(variance; DT)", "PAR(variance; random)"
])
# Gather results into 'friedman' table
for fv in in_data.feature_vectors:
alg = fv[in_data.attribute_index("Algorithm")]
if alg not in alg_set:
cl_parser.add_argument("-N", type=int, default=0, help="Size of each subset")
cl_parser.add_argument("-k",
type=int,
default=1,
help="Number of subsets for cross-validation")
cl_parser.add_argument("--seed",
type=int,
default=0,
help="RNG seed (default: no particular seed)")
args = cl_parser.parse_args()
if args.N == 0 and args.k != 1:
raise RuntimeError("If args.N == 0, then args.k must be 1")
with open(args.input_file[0]) as input_file:
data = CsvDataset(input_file)
t_blackout = data.attribute_index("t_blackout")
faults = data.attribute_index("faults")
recoverable_faults = []
for fv in data.feature_vectors:
t = int(fv[t_blackout])
if t > 10 and t < 311:
recoverable_faults.append(fv[faults])
if args.N * args.k > len(recoverable_faults):
raise AssertionError("Not enough faults for requested dataset size")
rng = random.Random()
if args.seed != 0:
rng.seed(args.seed)
rng.shuffle(recoverable_faults)
next = 0
for i in range(0, args.k):
def make_action_to_int(file):
ati_data = CsvDataset(file)
ati = dict()
for fv in ati_data.feature_vectors:
ati[fv[1]] = int(fv[0])
return ati
cl_parser = OptionParser(usage="%prog [options] file")
cl_parser.add_option("--subdivide",
dest="subdivide",
type="string",
default=None,
help="Attribute to subdivide.")
cl_parser.add_option("--subdivisions",
dest="subdivisions",
type="int",
default=1,
help="Number of subdivisions.")
(options, args) = cl_parser.parse_args()
csv_file = open(args[0], "r")
csv_dataset = CsvDataset(csv_file)
count = 0
for fv in csv_dataset.feature_vectors:
print(fv)
exploded = CsvDataset(attributes=csv_dataset.attributes[:],
feature_vectors=[fv[:]])
print(exploded.feature_vectors[0])
if options.subdivide is not None:
idx = exploded.attribute_index(options.subdivide)
n = int(exploded.feature_vectors[0][idx])
q = n / options.subdivisions
r = n % options.subdivisions
sub = [q] * options.subdivisions
for i in range(0, r):
sub[i] += 1
import statistics
cl_parser = argparse.ArgumentParser(
description="Creates random subsets of faults")
cl_parser.add_argument("input_file",
type=str,
nargs=1,
help="A 'rewards.csv' input file")
cl_parser.add_argument("-d",
type=int,
default=60,
help="Size of intervals for analysis")
args = cl_parser.parse_args()
with open(args.input_file[0]) as fin:
data = CsvDataset(fin)
intervals = []
for fv in data.feature_vectors:
i = data.attribute_index("r1")
j = i + args.d
while j < len(data.attributes):
ri = float(fv[i])
rj = float(fv[j])
intervals.append(abs(rj - ri))
i += 2
j += 2
print("n: " + str(len(intervals)))
print("mean: " + str(statistics.mean(intervals)))
print("stddev: " + str(statistics.stdev(intervals)))
print("min: " + str(min(intervals)))
help="If specified, only parameterizations for which results are available for all budgets are considered." )
(options, args) = cl_parser.parse_args();
if options.output_file == "-":
# Saying 'open( "sys.stdout" )' doesn't seem to accomplish this
output_file = sys.stdout
else:
output_file = open( options.output_file, "w" )
fault_str = "faults"
out_attributes = [
"Domain", "domain_parameters", fault_str, "Algorithm", "algorithm_parameters", "budget_type", "budget",
"Vc", "Vu", "dV", "Rc_end", "Ru_end", "dR", "NLoadShed", "NIsland"
]
out_data = CsvDataset( attributes=[CsvAttribute( a ) for a in out_attributes], feature_vectors=[] )
with open( args[0], "r" ) as input_file:
c_data = CsvDataset( input_file )
with open( args[1], "r" ) as input_file:
u_data = CsvDataset( input_file )
# Index map for fault sets in baseline data
u_idx = dict()
for i in range(0, len(u_data.feature_vectors)):
u_fv = u_data.feature_vectors[i]
u_idx[u_fv[u_data.attribute_index(fault_str)]] = i
for c_fv in c_data.feature_vectors:
faults = c_fv[c_data.attribute_index(fault_str)]
Vc = float( c_fv[c_data.attribute_index("V")] )