[REF, DOC] Use logging to generate reports

tedana/combine.py

@@ -7,6 +7,8 @@
 from tedana.due import due, Doi
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 @due.dcite(Doi('10.1002/(SICI)1522-2594(199907)42:1<87::AID-MRM13>3.0.CO;2-O'),
@@ -31,6 +33,14 @@ def _combine_t2s(data, tes, ft2s):
     combined : (M x T) :obj:`numpy.ndarray`
         Data combined across echoes according to T2* estimates.
     """
+    RepLGR.info("Multi-echo data were then optimally combined using the "
+                "T2* combination method (Posse et al., 1999).")
+    RefLGR.info("Posse, S., Wiese, S., Gembris, D., Mathiak, K., Kessler, "
+                "C., Grosse‐Ruyken, M. L., ... & Kiselev, V. G. (1999). "
+                "Enhancement of BOLD‐contrast sensitivity by single‐shot "
+                "multi‐echo functional MR imaging. Magnetic Resonance in "
+                "Medicine: An Official Journal of the International Society "
+                "for Magnetic Resonance in Medicine, 42(1), 87-97.")
     n_vols = data.shape[-1]
     alpha = tes * np.exp(-tes / ft2s)
     if alpha.ndim == 2:
@@ -70,6 +80,16 @@ def _combine_paid(data, tes):
     combined : (M x T) :obj:`numpy.ndarray`
         Data combined across echoes according to SNR/signal.
     """
+    RepLGR.info("Multi-echo data were then optimally combined using the "
+                "parallel-acquired inhomogeneity desensitized (PAID) "
+                "combination method.")
+    RefLGR.info("Poser, B. A., Versluis, M. J., Hoogduin, J. M., & Norris, "
+                "D. G. (2006). BOLD contrast sensitivity enhancement and "
+                "artifact reduction with multiecho EPI: parallel‐acquired "
+                "inhomogeneity‐desensitized fMRI. "
+                "Magnetic Resonance in Medicine: An Official Journal of the "
+                "International Society for Magnetic Resonance in Medicine, "
+                "55(6), 1227-1235.")
     n_vols = data.shape[-1]
     alpha = data.mean(axis=-1) * tes
     alpha = np.tile(alpha[:, :, np.newaxis], (1, 1, n_vols))

tedana/decay.py

@@ -7,6 +7,8 @@
 from tedana import utils
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def mono_exp(tes, s0, t2star):
@@ -84,6 +86,12 @@ def fit_decay(data, tes, mask, masksum, fittype):
         in :math:`S_0` map with 0.
     3.  Generate limited :math:`T_2^*` and :math:`S_0` maps by doing something.
     """
+    RepLGR.info("A monoexponential model was fit to the data at each voxel "
+                "using log-linear regression in order to estimate T2* and S0 "
+                "maps. For each voxel, the value from the adaptive mask was "
+                "used to determine which echoes would be used to estimate T2* "
+                "and S0.")
+
     if data.shape[1] != len(tes):
         raise ValueError('Second dimension of data ({0}) does not match number '
                          'of echoes provided (tes; {1})'.format(data.shape[1], len(tes)))

tedana/decomposition/_utils.py

@@ -7,6 +7,8 @@
 from scipy import stats
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def eimask(dd, ees=None):

tedana/decomposition/ica.py

@@ -9,6 +9,8 @@
 from sklearn.decomposition import FastICA
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def tedica(data, n_components, fixed_seed, maxit=500, maxrestart=10):
@@ -41,9 +43,10 @@ def tedica(data, n_components, fixed_seed, maxit=500, maxrestart=10):
     -----
     Uses `sklearn` implementation of FastICA for decomposition
     """
-
     warnings.filterwarnings(action='ignore', module='scipy',
                             message='^internal gelsd')
+    RepLGR.info("Independent component analysis was then used to "
+                "decompose the dimensionally reduced dataset.")
 
     if fixed_seed == -1:
         fixed_seed = np.random.randint(low=1, high=1000)

tedana/decomposition/pca.py

@@ -14,6 +14,8 @@
 from tedana.due import due, BibTeX
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 @due.dcite(BibTeX(
@@ -195,6 +197,40 @@ def tedpca(data_cat, data_oc, combmode, mask, t2s, t2sG,
                     'tree.')
         algorithm = 'kundu'
 
+    if algorithm == 'mle':
+        alg_str = "using MLE dimensionality estimation (Minka, 2001)"
+        RefLGR.info("Minka, T. P. (2001). Automatic choice of dimensionality "
+                    "for PCA. In Advances in neural information processing "
+                    "systems (pp. 598-604).")
+    elif algorithm == 'kundu':
+        alg_str = ("followed by the Kundu component selection decision "
+                   "tree (Kundu et al., 2013)")
+        RefLGR.info("Kundu, P., Brenowitz, N. D., Voon, V., Worbe, Y., "
+                    "Vértes, P. E., Inati, S. J., ... & Bullmore, E. T. "
+                    "(2013). Integrated strategy for improving functional "
+                    "connectivity mapping using multiecho fMRI. Proceedings "
+                    "of the National Academy of Sciences, 110(40), "
+                    "16187-16192.")
+    elif algorithm == 'kundu-stabilize':
+        alg_str = ("followed by the 'stabilized' Kundu component "
+                   "selection decision tree (Kundu et al., 2013)")
+        RefLGR.info("Kundu, P., Brenowitz, N. D., Voon, V., Worbe, Y., "
+                    "Vértes, P. E., Inati, S. J., ... & Bullmore, E. T. "
+                    "(2013). Integrated strategy for improving functional "
+                    "connectivity mapping using multiecho fMRI. Proceedings "
+                    "of the National Academy of Sciences, 110(40), "
+                    "16187-16192.")
+
+    if source_tes == -1:
+        dat_str = "the optimally combined data"
+    elif source_tes == 0:
+        dat_str = "the z-concatenated multi-echo data"
+    else:
+        dat_str = "a z-concatenated subset of echoes from the input data"
+
+    RepLGR.info("Principal component analysis {0} was applied to "
+                "{1} for dimensionality reduction.".format(alg_str, dat_str))
+
     n_samp, n_echos, n_vols = data_cat.shape
     source_tes = np.array([int(ee) for ee in str(source_tes).split(',')])
 

tedana/gscontrol.py

@@ -11,6 +11,8 @@
 from tedana import io, utils
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def gscontrol_raw(catd, optcom, n_echos, ref_img, dtrank=4):
@@ -45,6 +47,8 @@ def gscontrol_raw(catd, optcom, n_echos, ref_img, dtrank=4):
         Input `optcom` with global signal removed from time series
     """
     LGR.info('Applying amplitude-based T1 equilibration correction')
+    RepLGR.info("Global signal regression was applied to the multi-echo "
+                "and optimally combined datasets.")
     if catd.shape[0] != optcom.shape[0]:
         raise ValueError('First dimensions of catd ({0}) and optcom ({1}) do not '
                          'match'.format(catd.shape[0], optcom.shape[0]))
@@ -134,6 +138,11 @@ def gscontrol_mmix(optcom_ts, mmix, mask, comptable, ref_img):
     meica_mix_T1c.1D          T1 global signal-corrected mixing matrix
     ======================    =================================================
     """
+    LGR.info('Performing T1c global signal regression to remove spatially '
+             'diffuse noise')
+    RepLGR.info("T1c global signal regression was then applied to the "
+                "data in order to remove spatially diffuse noise.")
+
     all_comps = comptable.index.values
     acc = comptable[comptable.classification == 'accepted'].index.values
     ign = comptable[comptable.classification == 'ignored'].index.values

tedana/io.py

@@ -14,6 +14,8 @@
 from tedana.stats import computefeats2, get_coeffs
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def split_ts(data, mmix, mask, comptable):

tedana/metrics/kundu_fit.py

@@ -13,6 +13,8 @@
 
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 F_MAX = 500
 Z_MAX = 8
@@ -87,6 +89,10 @@ def dependence_metrics(catd, tsoc, mmix, t2s, tes, ref_img,
                              '({0}) does not match number of volumes in '
                              't2s ({1})'.format(catd.shape[2], t2s.shape[1]))
 
+    RepLGR.info("A series of TE-dependence metrics were calculated for "
+                "each ICA component, including Kappa, Rho, and variance "
+                "explained.")
+
     # mask everything we can
     tsoc = tsoc[mask, :]
     catd = catd[mask, ...]

tedana/selection/_utils.py

@@ -6,6 +6,8 @@
 import numpy as np
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def clean_dataframe(comptable):

tedana/selection/tedica.py

@@ -9,6 +9,8 @@
 from tedana.selection._utils import getelbow, clean_dataframe
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def manual_selection(comptable, acc=None, rej=None):
@@ -30,6 +32,9 @@ def manual_selection(comptable, acc=None, rej=None):
         Component metric table with classification.
     """
     LGR.info('Performing manual ICA component selection')
+    RepLGR.info("Next, components were manually classified as "
+                "BOLD (TE-dependent), non-BOLD (TE-independent), or "
+                "uncertain (low-variance).")
     if ('classification' in comptable.columns and
             'original_classification' not in comptable.columns):
         comptable['original_classification'] = comptable['classification']
@@ -110,6 +115,16 @@ def kundu_selection_v2(comptable, n_echos, n_vols):
     https://gist.github.com/emdupre/ca92d52d345d08ee85e104093b81482e
     """
     LGR.info('Performing ICA component selection with Kundu decision tree v2.5')
+    RepLGR.info("Next, component selection was performed to identify "
+                "BOLD (TE-dependent), non-BOLD (TE-independent), and "
+                "uncertain (low-variance) components using the Kundu "
+                "decision tree (v2.5; Kundu et al., 2013).")
+    RefLGR.info("Kundu, P., Brenowitz, N. D., Voon, V., Worbe, Y., "
+                "Vértes, P. E., Inati, S. J., ... & Bullmore, E. T. "
+                "(2013). Integrated strategy for improving functional "
+                "connectivity mapping using multiecho fMRI. Proceedings "
+                "of the National Academy of Sciences, 110(40), "
+                "16187-16192.")
     comptable['classification'] = 'accepted'
     comptable['rationale'] = ''
 

tedana/selection/tedpca.py

@@ -9,6 +9,8 @@
 from tedana.selection._utils import (getelbow_cons, getelbow, clean_dataframe)
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 F_MAX = 500
 

tedana/stats.py

@@ -9,6 +9,8 @@
 from tedana import utils
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def getfbounds(n_echos):

tedana/utils.py

@@ -12,6 +12,8 @@
 from tedana.due import due, BibTeX
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def load_image(data):
@@ -63,6 +65,9 @@ def make_adaptive_mask(data, mask=None, getsum=False):
         Valued array indicating the number of echos with sufficient signal in a
         given voxel. Only returned if `getsum = True`
     """
+    RepLGR.info("An adaptive mask was then generated, in which each voxel's "
+                "value reflects the number of echoes with 'good' data.")
+
     # take temporal mean of echos and extract non-zero values in first echo
     echo_means = data.mean(axis=-1)  # temporal mean of echos
     first_echo = echo_means[echo_means[:, 0] != 0, 0]

tedana/viz.py

@@ -15,6 +15,8 @@
 LGR = logging.getLogger(__name__)
 MPL_LGR = logging.getLogger('matplotlib')
 MPL_LGR.setLevel(logging.WARNING)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def trim_edge_zeros(arr):

tedana/workflows/parser_utils.py

@@ -2,6 +2,7 @@
 Functions for parsers.
 """
 import os.path as op
+import logging
 
 
 def is_valid_file(parser, arg):
@@ -12,3 +13,16 @@ def is_valid_file(parser, arg):
         parser.error('The file {0} does not exist!'.format(arg))
 
     return arg
+
+
+class ContextFilter(logging.Filter):
+    """
+    A filter to allow specific logging handlers to ignore specific loggers.
+    We use this to prevent our report-generation and reference-compiling
+    loggers from printing to the general log file or to stdout.
+    """
+    NAMES = ['REPORT', 'REFERENCES']
+
+    def filter(self, record):
+        if not any([n in record.name for n in self.NAMES]):
+            return True

tedana/workflows/t2smap.py

@@ -13,6 +13,8 @@
 from tedana.workflows.parser_utils import is_valid_file
 
 LGR = logging.getLogger(__name__)
+RepLGR = logging.getLogger('REPORT')
+RefLGR = logging.getLogger('REFERENCES')
 
 
 def _get_parser():