def analyze_data(config): # pylint: disable=redefined-outer-name
"""
:param Config config:
"""
dss = config.value('analyze_dataset', 'train')
ds = {"train": train_data, "dev": dev_data, "eval": eval_data}[dss]
epoch = config.int('epoch', 1)
print("Analyze dataset", dss, "epoch", epoch, file=log.v1)
ds.init_seq_order(epoch=epoch)
stat_prefix = config.value('statistics_save_prefix', 'statistics')
dtype = config.value('statistics_dtype', 'float64')
target = config.value('target', 'classes')
data_key = config.value('data_key', 'data')
assert ds.is_data_sparse(target), "need for prior calculation"
assert not ds.is_data_sparse(data_key), "needed for mean/var estimation"
from Util import inplace_increment, progress_bar_with_time, NumbersDict
priors = numpy.zeros((ds.get_data_dim(target), ), dtype=dtype)
mean = numpy.zeros((ds.get_data_dim(data_key), ), dtype=dtype)
mean_sq = numpy.zeros((ds.get_data_dim(data_key), ), dtype=dtype)
total_targets_len = 0
total_data_len = 0
# Note: This is not stable! See :class:`Util.Stats` for a better alternative.
seq_idx = 0
while ds.is_less_than_num_seqs(seq_idx):
progress_bar_with_time(ds.get_complete_frac(seq_idx))
ds.load_seqs(seq_idx, seq_idx + 1)
targets = ds.get_data(seq_idx, target)
inplace_increment(priors, targets, 1)
total_targets_len += targets.shape[0]
data = ds.get_data(seq_idx, data_key)
new_total_data_len = total_data_len + data.shape[0]
f = float(total_data_len) / new_total_data_len
mean = mean * f + numpy.sum(data, axis=0) * (1.0 - f)
mean_sq = mean_sq * f + numpy.sum(data * data, axis=0) * (1.0 - f)
total_data_len = new_total_data_len
seq_idx += 1
log_priors = numpy.log(priors)
log_priors -= numpy.log(NumbersDict(ds.get_num_timesteps())[target])
std_dev = numpy.sqrt(mean_sq - mean * mean)
print("Finished. %i total target frames, %i total data frames" %
(total_targets_len, total_data_len),
file=log.v1)
priors_fn = stat_prefix + ".log_priors.txt"
mean_fn = stat_prefix + ".mean.txt"
std_dev_fn = stat_prefix + ".std_dev.txt"
print("Dump priors to", priors_fn, file=log.v1)
numpy.savetxt(priors_fn, log_priors)
print("Dump mean to", mean_fn, file=log.v1)
numpy.savetxt(mean_fn, mean)
print("Dump std dev to", std_dev_fn, file=log.v1)
numpy.savetxt(std_dev_fn, std_dev)
print("Done.", file=log.v1)
def analyze_data(config): # pylint: disable=redefined-outer-name
"""
:param Config config:
"""
dss = config.value('analyze_dataset', 'train')
ds = {"train": train_data, "dev": dev_data, "eval": eval_data}[dss]
epoch = config.int('epoch', 1)
print("Analyze dataset", dss, "epoch", epoch, file=log.v1)
ds.init_seq_order(epoch=epoch)
stat_prefix = config.value('statistics_save_prefix', 'statistics')
dtype = config.value('statistics_dtype', 'float64')
target = config.value('target', 'classes')
data_key = config.value('data_key', 'data')
assert ds.is_data_sparse(target), "need for prior calculation"
assert not ds.is_data_sparse(data_key), "needed for mean/var estimation"
from Util import inplace_increment, progress_bar_with_time, NumbersDict
priors = numpy.zeros((ds.get_data_dim(target),), dtype=dtype)
mean = numpy.zeros((ds.get_data_dim(data_key),), dtype=dtype)
mean_sq = numpy.zeros((ds.get_data_dim(data_key),), dtype=dtype)
total_targets_len = 0
total_data_len = 0
# Note: This is not stable! See :class:`Util.Stats` for a better alternative.
seq_idx = 0
while ds.is_less_than_num_seqs(seq_idx):
progress_bar_with_time(ds.get_complete_frac(seq_idx))
ds.load_seqs(seq_idx, seq_idx + 1)
targets = ds.get_data(seq_idx, target)
inplace_increment(priors, targets, 1)
total_targets_len += targets.shape[0]
data = ds.get_data(seq_idx, data_key)
new_total_data_len = total_data_len + data.shape[0]
f = float(total_data_len) / new_total_data_len
mean = mean * f + numpy.sum(data, axis=0) * (1.0 - f)
mean_sq = mean_sq * f + numpy.sum(data * data, axis=0) * (1.0 - f)
total_data_len = new_total_data_len
seq_idx += 1
log_priors = numpy.log(priors)
log_priors -= numpy.log(NumbersDict(ds.get_num_timesteps())[target])
std_dev = numpy.sqrt(mean_sq - mean * mean)
print("Finished. %i total target frames, %i total data frames" % (total_targets_len, total_data_len), file=log.v1)
priors_fn = stat_prefix + ".log_priors.txt"
mean_fn = stat_prefix + ".mean.txt"
std_dev_fn = stat_prefix + ".std_dev.txt"
print("Dump priors to", priors_fn, file=log.v1)
numpy.savetxt(priors_fn, log_priors)
print("Dump mean to", mean_fn, file=log.v1)
numpy.savetxt(mean_fn, mean)
print("Dump std dev to", std_dev_fn, file=log.v1)
numpy.savetxt(std_dev_fn, std_dev)
print("Done.", file=log.v1)
def analyze_data(config):
dss = config.value('analyze_dataset', 'train')
ds = {"train": train_data, "dev": dev_data, "eval": eval_data}[dss]
epoch = config.int('epoch', 1)
print >> log.v1, "Analyze dataset", dss, "epoch", epoch
ds.init_seq_order(epoch=epoch)
stat_prefix = config.value('statistics_save_prefix', 'statistics')
dtype = config.value('statistics_dtype', 'float64')
target = config.value('target', 'classes')
data_key = config.value('data_key', 'data')
assert ds.is_data_sparse(target), "need for prior calculation"
assert not ds.is_data_sparse(data_key), "needed for mean/var estimation"
from Util import inplace_increment, progress_bar_with_time, NumbersDict
priors = numpy.zeros((ds.get_data_dim(target), ), dtype=dtype)
mean = numpy.zeros((ds.get_data_dim(data_key), ), dtype=dtype)
mean_sq = numpy.zeros((ds.get_data_dim(data_key), ), dtype=dtype)
total_targets_len = 0
total_data_len = 0
seq_idx = 0
while ds.is_less_than_num_seqs(seq_idx):
progress_bar_with_time(ds.get_complete_frac(seq_idx))
ds.load_seqs(seq_idx, seq_idx + 1)
targets = ds.get_data(seq_idx, target)
inplace_increment(priors, targets, 1)
total_targets_len += targets.shape[0]
data = ds.get_data(seq_idx, data_key)
new_total_data_len = total_data_len + data.shape[0]
f = float(total_data_len) / new_total_data_len
mean = mean * f + numpy.sum(data, axis=0) * (1.0 - f)
mean_sq = mean_sq * f + numpy.sum(data * data, axis=0) * (1.0 - f)
total_data_len = new_total_data_len
seq_idx += 1
log_priors = numpy.log(priors)
log_priors -= numpy.log(NumbersDict(ds.get_num_timesteps())[target])
var = numpy.sqrt(mean_sq - mean * mean)
print >> log.v1, "Finished. %i total target frames, %i total data frames" % (
total_targets_len, total_data_len)
priors_fn = stat_prefix + ".log_priors.txt"
mean_fn = stat_prefix + ".mean.txt"
var_fn = stat_prefix + ".var.txt"
print >> log.v1, "Dump priors to", priors_fn
numpy.savetxt(priors_fn, log_priors)
print >> log.v1, "Dump mean to", mean_fn
numpy.savetxt(mean_fn, mean)
print >> log.v1, "Dump var to", var_fn
numpy.savetxt(var_fn, var)
print >> log.v1, "Done."
def analyze_data(config):
dss = config.value('analyze_dataset', 'train')
ds = {"train": train_data, "dev": dev_data, "eval": eval_data}[dss]
epoch = config.int('epoch', 1)
print >> log.v1, "Analyze dataset", dss, "epoch", epoch
ds.init_seq_order(epoch=epoch)
stat_prefix = config.value('statistics_save_prefix', 'statistics')
dtype = config.value('statistics_dtype', 'float64')
target = config.value('target', 'classes')
data_key = config.value('data_key', 'data')
assert ds.is_data_sparse(target), "need for prior calculation"
assert not ds.is_data_sparse(data_key), "needed for mean/var estimation"
from Util import inplace_increment, progress_bar_with_time, NumbersDict
priors = numpy.zeros((ds.get_data_dim(target),), dtype=dtype)
mean = numpy.zeros((ds.get_data_dim(data_key),), dtype=dtype)
mean_sq = numpy.zeros((ds.get_data_dim(data_key),), dtype=dtype)
total_targets_len = 0
total_data_len = 0
seq_idx = 0
while ds.is_less_than_num_seqs(seq_idx):
progress_bar_with_time(ds.get_complete_frac(seq_idx))
ds.load_seqs(seq_idx, seq_idx + 1)
targets = ds.get_data(seq_idx, target)
inplace_increment(priors, targets, 1)
total_targets_len += targets.shape[0]
data = ds.get_data(seq_idx, data_key)
new_total_data_len = total_data_len + data.shape[0]
f = float(total_data_len) / new_total_data_len
mean = mean * f + numpy.sum(data, axis=0) * (1.0 - f)
mean_sq = mean_sq * f + numpy.sum(data * data, axis=0) * (1.0 - f)
total_data_len = new_total_data_len
seq_idx += 1
log_priors = numpy.log(priors)
log_priors -= numpy.log(NumbersDict(ds.get_num_timesteps())[target])
var = numpy.sqrt(mean_sq - mean * mean)
print >> log.v1, "Finished. %i total target frames, %i total data frames" % (total_targets_len, total_data_len)
priors_fn = stat_prefix + ".log_priors.txt"
mean_fn = stat_prefix + ".mean.txt"
var_fn = stat_prefix + ".var.txt"
print >> log.v1, "Dump priors to", priors_fn
numpy.savetxt(priors_fn, log_priors)
print >> log.v1, "Dump mean to", mean_fn
numpy.savetxt(mean_fn, mean)
print >> log.v1, "Dump var to", var_fn
numpy.savetxt(var_fn, var)
print >> log.v1, "Done."