fixes

Dockerfile

@@ -42,14 +42,12 @@ WORKDIR /home/user
 # Setup virtual envs and install convenience packages.  Note: installing
 # cherrypy as part of the mhcflurry installation weirdly fails on a unicode
 # issue in python2, but installing it separately seems to work.
-# We also install bokeh so that dask distributed will have an admin web interface.
 RUN virtualenv venv-py3 --python=python3 && \
     venv-py3/bin/pip install --upgrade pip && \
     venv-py3/bin/pip install --upgrade \
         numpy \
-        bokeh \
         cherrypy \
-        git+https://github.com/dask/distributed.git \
+        git+https://github.com/hammerlab/kubeface.git \
         jupyter \
         lxml \
         scipy \

downloads-generation/models_class1_allele_specific_ensemble/GENERATE.sh

@@ -39,7 +39,7 @@ time mhcflurry-class1-allele-specific-ensemble-train \
     --ensemble-size 8 \
     --model-architectures models.json \
     --train-data "$(mhcflurry-downloads path data_combined_iedb_kim2014)/combined_human_class1_dataset.csv" \
-    --min-samples-per-allele 100 \
+    --min-samples-per-allele 200 \
     --out-manifest models.csv \
     --out-models models \
     --verbose \

downloads-generation/models_class1_allele_specific_ensemble/README.md

@@ -11,9 +11,10 @@ To generate this download we run:
 ```
 ./GENERATE.sh \
     --parallel-backend kubeface \
+    --target-tasks 200 \
     --backend kubernetes \
-    --storage-prefix gs://kubeface \
-    --worker-image hammerlab/mhcflurry:latest \
+    --storage-prefix gs://kubeface-tim \
+    --worker-image hammerlab/mhcflurry-misc:latest \
     --kubernetes-task-resources-memory-mb 10000 \
     --worker-path-prefix venv-py3/bin \
     --max-simultaneous-tasks 200 \

downloads-generation/models_class1_allele_specific_ensemble/models.py

 import sys
-from mhcflurry.class1_allele_specific.train import HYPERPARAMETER_DEFAULTS
+from mhcflurry.class1_allele_specific_ensemble import HYPERPARAMETER_DEFAULTS
 import json
 
 models = HYPERPARAMETER_DEFAULTS.models_grid(

mhcflurry/class1_allele_specific_ensemble/__init__.py

+from .class1_ensemble_multi_allele_predictor import (
+    Class1EnsembleMultiAllelePredictor,
+    HYPERPARAMETER_DEFAULTS)
+
+__all__ = [
+    "Class1EnsembleMultiAllelePredictor",
+    "HYPERPARAMETER_DEFAULTS",
+]

mhcflurry/class1_allele_specific_ensemble/class1_ensemble_multi_allele_predictor.py

@@ -278,8 +278,11 @@ class Class1EnsembleMultiAllelePredictor(object):
     def fit(
             self,
             measurement_collection,
-            parallel_backend=parallelism.ConcurrentFuturesParallelBackend(),
+            parallel_backend=None,
             target_tasks=1):
+        if parallel_backend is None:
+            parallel_backend = parallelism.get_default_backend()
+
         fit_name = time.asctime().replace(" ", "_")
         assert len(measurement_collection.df) > 0
 

setup.py

@@ -99,5 +99,9 @@ if __name__ == '__main__':
         },
         install_requires=required_packages,
         long_description=readme,
-        packages=['mhcflurry', 'mhcflurry.class1_allele_specific'],
+        packages=[
+            'mhcflurry',
+            'mhcflurry.class1_allele_specific',
+            'mhcflurry.class1_allele_specific_ensemble',
+        ],
     )