From 03f44c8f4ad20d162eabb2f7e81ff47ca9e0c86c Mon Sep 17 00:00:00 2001
From: Tim O'Donnell <timodonnell@gmail.com>
Date: Fri, 23 Sep 2016 12:28:56 -0400
Subject: [PATCH] Update docs
---
mhcflurry/class1_allele_specific/cross_validation.py | 6 +++---
mhcflurry/class1_allele_specific/train.py | 4 +++-
mhcflurry/parallelism.py | 11 +++++++++++
mhcflurry/predict.py | 7 ++++++-
4 files changed, 23 insertions(+), 5 deletions(-)
diff --git a/mhcflurry/class1_allele_specific/cross_validation.py b/mhcflurry/class1_allele_specific/cross_validation.py
index 6bcd092c..5ceeb4b7 100644
--- a/mhcflurry/class1_allele_specific/cross_validation.py
+++ b/mhcflurry/class1_allele_specific/cross_validation.py
@@ -126,9 +126,9 @@ def cross_validation_folds(
impute_kwargs : dict, optional
Additional kwargs to pass to mhcflurry.Dataset.impute_missing_values.
- n_jobs : integer, optional
- The number of jobs to run in parallel. If -1, then the number of jobs
- is set to the number of cores.
+ parallel_backend : mhcflurry.parallelism.ParallelBackend, optional
+ Futures implementation to use for running on multiple threads,
+ processes, or nodes
Returns
-----------
diff --git a/mhcflurry/class1_allele_specific/train.py b/mhcflurry/class1_allele_specific/train.py
index c4f29e49..7e5824b8 100644
--- a/mhcflurry/class1_allele_specific/train.py
+++ b/mhcflurry/class1_allele_specific/train.py
@@ -259,7 +259,9 @@ def train_across_models_and_folds(
return_predictors : boolean, optional
Include the trained predictors in the result.
- parallel_backend : parallel backend, optional
+ parallel_backend : mhcflurry.parallelism.ParallelBackend, optional
+ Futures implementation to use for running on multiple threads,
+ processes, or nodes
Returns
-----------
diff --git a/mhcflurry/parallelism.py b/mhcflurry/parallelism.py
index 9bce9c01..18008b4e 100644
--- a/mhcflurry/parallelism.py
+++ b/mhcflurry/parallelism.py
@@ -5,6 +5,10 @@ DEFAULT_BACKEND = None
class ParallelBackend(object):
+ """
+ Thin wrapper of futures implementations. Designed to support
+ concurrent.futures as well as dask.distributed's workalike implementation.
+ """
def __init__(self, executor, module, verbose=1):
self.executor = executor
self.module = module
@@ -33,6 +37,9 @@ class ParallelBackend(object):
class DaskDistributedParallelBackend(ParallelBackend):
+ """
+ ParallelBackend that uses dask.distributed
+ """
def __init__(self, scheduler_ip_and_port, verbose=1):
from dask import distributed # pylint: disable=import-error
executor = distributed.Executor(scheduler_ip_and_port)
@@ -46,6 +53,10 @@ class DaskDistributedParallelBackend(ParallelBackend):
class ConcurrentFuturesParallelBackend(ParallelBackend):
+ """
+ ParallelBackend that uses Python's concurrent.futures module.
+ Can use either threads or processes.
+ """
def __init__(self, num_workers=1, processes=False, verbose=1):
if processes:
executor = futures.ProcessPoolExecutor(num_workers)
diff --git a/mhcflurry/predict.py b/mhcflurry/predict.py
index 8b886b4e..6534971e 100644
--- a/mhcflurry/predict.py
+++ b/mhcflurry/predict.py
@@ -22,6 +22,9 @@ from .common import normalize_allele_name, UnsupportedAllele
def predict(alleles, peptides, loaders=None):
"""
+ Make predictions across all combinations of the specified alleles and
+ peptides.
+
Parameters
----------
alleles : list of str
@@ -30,6 +33,9 @@ def predict(alleles, peptides, loaders=None):
peptides : list of str
Peptide amino acid sequences.
+ loaders : list of Class1AlleleSpecificPredictorLoader, optional
+ Loaders to try. Will be tried in the order given.
+
Returns DataFrame with columns "Allele", "Peptide", and "Prediction"
"""
if loaders is None:
@@ -64,4 +70,3 @@ def predict(alleles, peptides, loaders=None):
result_dict["Peptide"].append(peptides[i])
result_dict["Prediction"].append(ic50)
return pd.DataFrame(result_dict)
-
--
GitLab