def __init__(self, pid, mem, cpu, length=100):
self.__dict__.update(locals())
self.cpus = []
self.mems = []
self.br = False
super(StatProcessor, self).__init__()
self.logger = logger.setup_custom_logger("stats", logging.DEBUG)
def __init__(self, pid, mem, cpu, length=100):
self.__dict__.update(locals())
self.cpus = []
self.mems = []
self.br = False
super(StatProcessor, self).__init__()
self.logger = logger.setup_custom_logger("stats", logging.DEBUG)
def __init__(self,
experiment,
out_path,
processing_flag,
mem,
cpu,
last_processed,
dbdescr=None,
job_id=None):
self.__dict__.update(locals())
self.on = False
self.channels = []
self.collect_channels = False
self.channel_groups = {}
self.d = {
"name": experiment.name,
"yaml": None,
"results_of_interest": experiment.results_of_interest +\
["cpu", "mem"],
"stats": {
"status": "STARTING",
"pid": None,
"user": None,
"host": socket.gethostname(),
"create_time": None,
"last_heard": None,
"port": None
},
"processing": False,
"last_processed": "Never",
"hyperparams": None,
"logs": {
"cpu": {"cpu": []},
"mem": {"mem": []}
},
"log_stream": ""
}
self.logger = logger.setup_custom_logger("pl2mind", logging.DEBUG)
log_file = path.join(out_path, "model.log")
formatter = logging.Formatter(fmt="%(asctime)s:%(levelname)s:"
"%(module)s:%(message)s")
fh = logging.FileHandler(log_file, mode="w")
fh.setLevel(logging.DEBUG)
fh.setFormatter(formatter)
self.logger.addHandler(fh)
h = logging.StreamHandler(MetaLogHandler(self.d))
h.setLevel(logging.DEBUG)
h.setFormatter(formatter)
self.logger.addHandler(h)
self.write_json()
def __init__(self, experiment, checkpoint, ep, flag, last_processed):
self.__dict__.update(locals())
self.socket = None
self.out_path = "/".join(checkpoint.split("/")[:-1])
self.best_checkpoint = path.join(
self.out_path,
checkpoint.split("/")[-1].split(".")[0] + "_best.pkl")
self.persistent = False
super(ModelProcessor, self).__init__()
self.logger = logger.setup_custom_logger("processor", logging.DEBUG)
def __init__(self, experiment, checkpoint, ep,
flag, last_processed):
self.__dict__.update(locals())
self.socket = None
self.out_path = "/".join(checkpoint.split("/")[:-1])
self.best_checkpoint = path.join(self.out_path,
checkpoint.split(
"/")[-1].split(
".")[0] + "_best.pkl")
self.persistent = False
super(ModelProcessor, self).__init__()
self.logger = logger.setup_custom_logger("processor", logging.DEBUG)
def __init__(self, experiment, out_path, processing_flag, mem, cpu,
last_processed, dbdescr=None, job_id=None):
self.__dict__.update(locals())
self.on = False
self.channels = []
self.collect_channels = False
self.channel_groups = {}
self.d = {
"name": experiment.name,
"yaml": None,
"results_of_interest": experiment.results_of_interest +\
["cpu", "mem"],
"stats": {
"status": "STARTING",
"pid": None,
"user": None,
"host": socket.gethostname(),
"create_time": None,
"last_heard": None,
"port": None
},
"processing": False,
"last_processed": "Never",
"hyperparams": None,
"logs": {
"cpu": {"cpu": []},
"mem": {"mem": []}
},
"log_stream": ""
}
self.logger = logger.setup_custom_logger("pl2mind", logging.DEBUG)
log_file = path.join(out_path, "model.log")
formatter = logging.Formatter(fmt="%(asctime)s:%(levelname)s:"
"%(module)s:%(message)s")
fh = logging.FileHandler(log_file, mode="w")
fh.setLevel(logging.DEBUG)
fh.setFormatter(formatter)
self.logger.addHandler(fh)
h = logging.StreamHandler(MetaLogHandler(self.d))
h.setLevel(logging.DEBUG)
h.setFormatter(formatter)
self.logger.addHandler(h)
self.write_json()
import multiprocessing as mp
import networkx as nx
import numpy as np
import os
from os import path
import pickle
from pl2mind.analysis import feature_extraction as fe
from pl2mind.datasets import MRI
from pl2mind import logger
from pl2mind.tools import simtb_viewer
from pylearn2.datasets.transformer_dataset import TransformerDataset
from pylearn2.utils import serial
logger = logger.setup_custom_logger("pl2mind", logging.ERROR)
def save_simtb_montage(dataset, features, out_file, feature_dict,
target_stat=None, target_value=None):
"""
Saves a simtb montage.
"""
logger.info("Saving simtb montage")
weights_view = dataset.get_weights_view(features)
simtb_viewer.montage(weights_view, out_file=out_file,
feature_dict=feature_dict,
target_stat=target_stat,
target_value=target_value)
def save_helper(args):
__licence__ = "3-clause BSD"
__email__ = "*****@*****.**"
__maintainer__ = "Alvaro Ulloa"
import argparse
import logging
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
from pl2mind import logger
import scipy.signal as ss
logger = logger.setup_custom_logger("pl2mind", logging.WARNING)
def qea(im):
"""
Quasi-eigen approximation function.
Parameters
----------
im: array_like
1d vector that contains a time series
Returns
-------
ia: array_like
instantaneous amplitude
__maintainer__ = "Alvaro Ulloa"
import argparse
import logging
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import numpy as np
from pl2mind import logger
import scipy.signal as ss
logger = logger.setup_custom_logger("pl2mind", logging.WARNING)
def qea(im):
"""
Quasi-eigen approximation function.
Parameters
----------
im: array_like
1d vector that contains a time series
Returns
-------
ia: array_like
instantaneous amplitude
ip: array_like
from os import path
import pickle
from pl2mind import logger
from pylearn2.utils import serial
from random import shuffle
import re
from scipy import io
from scipy.stats import kurtosis
from scipy.stats import skew
import sys
from sys import stdout
logger = logger.setup_custom_logger("pl2mind", logging.ERROR)
def natural_sort(l):
convert = lambda text: int(text) if text.isdigit() else text.lower()
alphanum_key = lambda key: [ convert(c) for c in re.split('([0-9]+)', key) ]
return sorted(l, key = alphanum_key)
def save_variance_map(dataset, save_path):
logger.info("Saving variance file")
variance_map = dataset.X.std(axis=0)
np.save(save_path, variance_map)
def pull_niftis(source_directory, *args):
"""
Pull healthy and schizophrenia nitfi files from a source_directory.
Uses glob to get multiple files.
import logging
import multiprocessing as mp
from nipy import load_image
from nipy import save_image
import numpy as np
import pickle
from pl2mind import logger
import pprint
import re
from scipy import (reshape, zeros, where, std, argmax, sqrt, ceil, floor, sign,
negative, linspace, double, float16)
import subprocess
from sys import stdout
logger = logger.setup_custom_logger("pl2mind", logging.DEBUG)
# These are general names of regions for use elsewhere.
singles = ["Postcentral Gyrus",
"Cingulate Gyrus",
"Thalamus",
"Superior Frontal Gyrus",
"Pyramis",
"Caudate",
"Declive",
"Cuneus",
"Ulvula",
"Medial Frontal Gyrus",
"Precuneus",
"Lingual Gyrus",
"Paracentral Lobule",
import itertools
import logging
import multiprocessing as mp
from nipy import load_image
from nipy import save_image
import numpy as np
import pickle
from pl2mind import logger
import pprint
import re
from scipy import (reshape, zeros, where, std, argmax, sqrt, ceil, floor, sign,
negative, linspace, double, float16)
import subprocess
from sys import stdout
logger = logger.setup_custom_logger("pl2mind", logging.DEBUG)
# These are general names of regions for use elsewhere.
singles = [
"Postcentral Gyrus", "Cingulate Gyrus", "Thalamus",
"Superior Frontal Gyrus", "Pyramis", "Caudate", "Declive", "Cuneus",
"Ulvula", "Medial Frontal Gyrus", "Precuneus", "Lingual Gyrus",
"Paracentral Lobule", "Semi-Lunar Lobule", "Posterior Cingulate", "Culmen",
"Cerebellar Tonsil", "Cingulate Gyrus", "Middle Frontal Gyrus",
"Anterior Cingulate"
]
# Larger functional regions. Not used here, but can be referenced.
SC = [
"Caudate", "Putamen", "Thalamus", "Caudate Tail", "Caudate Body",
"Caudate Head"