def analyze(self,
M_c,
T,
X_L,
X_D,
kernel_list=(),
n_steps=1,
c=(),
r=(),
max_iterations=-1,
max_time=-1):
"""Evolve the latent state by running MCMC transition kernels
:param M_c: The column metadata
:type M_c: dict
:param T: The data table in mapped representation (all floats, generated
by data_utils.read_data_objects)
:param X_L: the latent variables associated with the latent state
:type X_L: dict
:param X_D: the particular cluster assignments of each row in each view
:type X_D: list of lists
:param kernel_list: names of the MCMC transition kernels to run
:type kernel_list: list of strings
:param n_steps: the number of times to run each MCMC transition kernel
:type n_steps: int
:param c: the (global) column indices to run MCMC transition kernels on
:type c: list of ints
:param r: the (global) row indices to run MCMC transition kernels on
:type r: list of ints
:param max_iterations: the maximum number of times ot run each MCMC
transition kernel. Applicable only if
max_time != -1.
:type max_iterations: int
:param max_time: the maximum amount of time (seconds) to run MCMC
transition kernels for before stopping to return
progress
:type max_time: float
:returns: X_L, X_D -- the evolved latent state
"""
if not xu.get_is_multistate(X_L, X_D):
SEED = self.get_next_seed()
X_L_prime, X_D_prime = _do_analyze(M_c, T, X_L, X_D, kernel_list,
n_steps, c, r, max_iterations,
max_time, SEED)
return X_L_prime, X_D_prime
else:
X_L_prime_list = []
X_D_prime_list = []
for X_L_i, X_D_i in zip(X_L, X_D):
SEED = self.get_next_seed()
X_L_i_prime, X_D_i_prime = _do_analyze(M_c, T, X_L_i, X_D_i,
kernel_list, n_steps, c,
r, max_iterations,
max_time, SEED)
X_L_prime_list.append(X_L_i_prime)
X_D_prime_list.append(X_D_i_prime)
return X_L_prime_list, X_D_prime_list
def analyze(self, M_c, T, X_L, X_D, kernel_list=(), n_steps=1, c=(), r=(),
max_iterations=-1, max_time=-1):
"""Evolve the latent state by running MCMC transition kernels
:param M_c: The column metadata
:type M_c: dict
:param T: The data table in mapped representation (all floats, generated
by data_utils.read_data_objects)
:param X_L: the latent variables associated with the latent state
:type X_L: dict
:param X_D: the particular cluster assignments of each row in each view
:type X_D: list of lists
:param kernel_list: names of the MCMC transition kernels to run
:type kernel_list: list of strings
:param n_steps: the number of times to run each MCMC transition kernel
:type n_steps: int
:param c: the (global) column indices to run MCMC transition kernels on
:type c: list of ints
:param r: the (global) row indices to run MCMC transition kernels on
:type r: list of ints
:param max_iterations: the maximum number of times ot run each MCMC
transition kernel. Applicable only if
max_time != -1.
:type max_iterations: int
:param max_time: the maximum amount of time (seconds) to run MCMC
transition kernels for before stopping to return
progress
:type max_time: float
:returns: X_L, X_D -- the evolved latent state
"""
if not xu.get_is_multistate(X_L, X_D):
SEED = self.get_next_seed()
X_L_prime, X_D_prime = _do_analyze(M_c, T, X_L, X_D,
kernel_list, n_steps, c, r,
max_iterations, max_time,
SEED)
return X_L_prime, X_D_prime
else:
seeds = [self.get_next_seed() for seed_idx in range(len(X_L))]
args = itertools.izip(
itertools.cycle([M_c]),
itertools.cycle([T]),
X_L, X_D,
itertools.cycle([kernel_list]),
itertools.cycle([n_steps]),
itertools.cycle([c]),
itertools.cycle([r]),
itertools.cycle([max_iterations]),
itertools.cycle([max_time]),
seeds,
)
result = self.pool.map_async(_do_analyze2, args)
X_L_prime_list, X_D_prime_list = zip(*result.get())
return X_L_prime_list, X_D_prime_list
def analyze(self, M_c, T, X_L, X_D, kernel_list=(), n_steps=1, c=(), r=(),
max_iterations=-1, max_time=-1):
"""Evolve the latent state by running MCMC transition kernels
:param M_c: The column metadata
:type M_c: dict
:param T: The data table in mapped representation (all floats, generated
by data_utils.read_data_objects)
:param X_L: the latent variables associated with the latent state
:type X_L: dict
:param X_D: the particular cluster assignments of each row in each view
:type X_D: list of lists
:param kernel_list: names of the MCMC transition kernels to run
:type kernel_list: list of strings
:param n_steps: the number of times to run each MCMC transition kernel
:type n_steps: int
:param c: the (global) column indices to run MCMC transition kernels on
:type c: list of ints
:param r: the (global) row indices to run MCMC transition kernels on
:type r: list of ints
:param max_iterations: the maximum number of times ot run each MCMC
transition kernel. Applicable only if
max_time != -1.
:type max_iterations: int
:param max_time: the maximum amount of time (seconds) to run MCMC
transition kernels for before stopping to return
progress
:type max_time: float
:returns: X_L, X_D -- the evolved latent state
"""
if not xu.get_is_multistate(X_L, X_D):
SEED = self.get_next_seed()
X_L_prime, X_D_prime = _do_analyze(M_c, T, X_L, X_D,
kernel_list, n_steps, c, r,
max_iterations, max_time,
SEED)
return X_L_prime, X_D_prime
else:
X_L_prime_list = []
X_D_prime_list = []
for X_L_i, X_D_i in zip(X_L, X_D):
SEED = self.get_next_seed()
X_L_i_prime, X_D_i_prime = _do_analyze(M_c, T, X_L_i, X_D_i,
kernel_list, n_steps, c, r,
max_iterations, max_time,
SEED)
X_L_prime_list.append(X_L_i_prime)
X_D_prime_list.append(X_D_i_prime)
return X_L_prime_list, X_D_prime_list
def analyze(self, M_c, T, X_L, X_D, kernel_list=(), n_steps=1, c=(), r=(),
max_iterations=-1, max_time=-1, **kwargs):
"""Evolve the latent state by running MCMC transition kernels
:param M_c: The column metadata
:type M_c: dict
:param T: The data table in mapped representation (all floats, generated
by data_utils.read_data_objects)
:type T: list of lists
:param X_L: the latent variables associated with the latent state
:type X_L: dict
:param X_D: the particular cluster assignments of each row in each view
:type X_D: list of lists
:param kernel_list: names of the MCMC transition kernels to run
:type kernel_list: list of strings
:param n_steps: the number of times to run each MCMC transition kernel
:type n_steps: int
:param c: the (global) column indices to run MCMC transition kernels on
:type c: list of ints
:param r: the (global) row indices to run MCMC transition kernels on
:type r: list of ints
:param max_iterations: the maximum number of times ot run each MCMC
transition kernel. Applicable only if
max_time != -1.
:type max_iterations: int
:param max_time: the maximum amount of time (seconds) to run MCMC
transition kernels for before stopping to return
progress
:type max_time: float
:param kwargs: optional arguments to pass to hadoop_line_processor.jar.
Currently, presence of a 'chunk_size' kwarg causes
different behavior.
:returns: X_L, X_D -- the evolved latent state
"""
output_path = self.output_path
input_filename = self.input_filename
table_data_filename = self.table_data_filename
analyze_args_dict_filename = self.command_dict_filename
xu.assert_vpn_is_connected()
#
table_data = dict(M_c=M_c, T=T)
analyze_args_dict = dict(command='analyze', kernel_list=kernel_list,
n_steps=n_steps, c=c, r=r, max_time=max_time)
# chunk_analyze is a special case of analyze
if 'chunk_size' in kwargs:
chunk_size = kwargs['chunk_size']
chunk_filename_prefix = kwargs['chunk_filename_prefix']
chunk_dest_dir = kwargs['chunk_dest_dir']
analyze_args_dict['command'] = 'chunk_analyze'
analyze_args_dict['chunk_size'] = chunk_size
analyze_args_dict['chunk_filename_prefix'] = chunk_filename_prefix
# WARNING: chunk_dest_dir MUST be writeable by hadoop user mapred
analyze_args_dict['chunk_dest_dir'] = chunk_dest_dir
if not xu.get_is_multistate(X_L, X_D):
X_L = [X_L]
X_D = [X_D]
#
SEEDS = kwargs.get('SEEDS', None)
xu.write_analyze_files(input_filename, X_L, X_D,
table_data, table_data_filename,
analyze_args_dict, analyze_args_dict_filename,
SEEDS)
os.system('cp %s analyze_input' % input_filename)
n_tasks = len(X_L)
self.send_hadoop_command(n_tasks)
was_successful = self.get_hadoop_results()
hadoop_output = None
if was_successful:
hu.copy_hadoop_output(output_path, 'analyze_output')
X_L_list, X_D_list = hu.read_hadoop_output(output_path)
hadoop_output = X_L_list, X_D_list
return hadoop_output
