test fixes

mhcflurry/downloads.py

@@ -87,7 +87,8 @@ def get_default_class1_models_dir(test_exists=True):
         if test_exists and not exists(result):
             raise IOError("No such directory: %s" % result)
         return result
-    return get_path("models_class1", "models", test_exists=test_exists)
+    return get_path(
+        "models_class1_pan", "models.combined", test_exists=test_exists)
 
 
 def get_default_class1_presentation_models_dir(test_exists=True):

test/test_batch_generator.py

@@ -139,7 +139,7 @@ def test_large(sample_rate=1.0):
 
     pan_train_df = pandas.read_csv(
         get_path(
-            "models_class1_pan", "models.with_mass_spec/train_data.csv.bz2"))
+            "models_class1_pan", "models.combined/train_data.csv.bz2"))
     pan_sub_train_df = pan_train_df
     pan_sub_train_df["label"] = pan_sub_train_df["measurement_value"]
     del pan_sub_train_df["measurement_value"]
@@ -149,7 +149,7 @@ def test_large(sample_rate=1.0):
     multi_train_df = multi_train_df.sample(frac=sample_rate)
 
     pan_predictor = Class1AffinityPredictor.load(
-        get_path("models_class1_pan", "models.with_mass_spec"),
+        get_path("models_class1_pan", "models.combined"),
         optimization_level=0,
         max_models=1)
 

test/test_calibrate_percentile_ranks_command.py

@@ -20,7 +20,7 @@ setup = startup
 
 
 def run_and_check(n_jobs=0, delete=True, additional_args=[]):
-    source_models_dir = get_path("models_class1_pan", "models.with_mass_spec")
+    source_models_dir = get_path("models_class1_pan", "models.combined")
     dest_models_dir = tempfile.mkdtemp(prefix="mhcflurry-test-models")
 
     # Save a new predictor that has no percent rank calibration data.
@@ -40,7 +40,7 @@ def run_and_check(n_jobs=0, delete=True, additional_args=[]):
         "mhcflurry-calibrate-percentile-ranks",
         "--models-dir", dest_models_dir,
         "--match-amino-acid-distribution-data", get_path(
-            "data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
+            "data_curated", "curated_training_data.affinity.csv.bz2"),
         "--motif-summary",
         "--num-peptides-per-length", "1000",
         "--allele", "HLA-A*02:01", "HLA-B*07:02",

test/test_class1_neural_network.py

@@ -44,7 +44,7 @@ def test_class1_neural_network_a0205_training_accuracy():
 
     df = pandas.read_csv(
         get_path(
-            "data_curated", "curated_training_data.no_mass_spec.csv.bz2"))
+            "data_curated", "curated_training_data.affinity.csv.bz2"))
     df = df.loc[
         df.allele == allele
     ]

test/test_speed.py

@@ -2,6 +2,10 @@
 Profile prediction speed
 
 """
+import logging
+logging.getLogger('tensorflow').disabled = True
+logging.getLogger('matplotlib').disabled = True
+
 import numpy
 numpy.random.seed(0)
 import time
@@ -32,7 +36,7 @@ def setup():
         get_path("models_class1", "models"))
 
     PAN_ALLELE_PREDICTOR = Class1AffinityPredictor.load(
-        get_path("models_class1_pan", "models.with_mass_spec"))
+        get_path("models_class1_pan", "models.combined"))
 
 
 def teardown():

test/test_train_and_related_commands.py

@@ -65,7 +65,7 @@ def run_and_check(n_jobs=0):
 
     args = [
         "mhcflurry-class1-train-allele-specific-models",
-        "--data", get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
+        "--data", get_path("data_curated", "curated_training_data.affinity.csv.bz2"),
         "--hyperparameters", hyperparameters_filename,
         "--allele", "HLA-A*02:01", "HLA-A*03:01",
         "--out-models-dir", models_dir,
@@ -117,7 +117,7 @@ def run_and_check_with_model_selection(n_jobs=1):
 
     args = [
         "mhcflurry-class1-train-allele-specific-models",
-        "--data", get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
+        "--data", get_path("data_curated", "curated_training_data.affinity.csv.bz2"),
         "--hyperparameters", hyperparameters_filename,
         "--allele", "HLA-A*02:01", "HLA-A*03:01",
         "--out-models-dir", models_dir1,
@@ -135,7 +135,7 @@ def run_and_check_with_model_selection(n_jobs=1):
     args = [
         "mhcflurry-class1-select-allele-specific-models",
         "--data",
-        get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"),
+        get_path("data_curated", "curated_training_data.affinity.csv.bz2"),
         "--exclude-data", models_dir1 + "/train_data.csv.bz2",
         "--out-models-dir", models_dir2,
         "--models-dir", models_dir1,

test/test_train_pan_allele_models_command.py

@@ -116,7 +116,7 @@ def run_and_check(n_jobs=0, delete=True, additional_args=[]):
         json.dump(HYPERPARAMETERS_LIST, fd)
 
     data_df = pandas.read_csv(
-        get_path("data_curated", "curated_training_data.no_mass_spec.csv.bz2"))
+        get_path("data_curated", "curated_training_data.affinity.csv.bz2"))
     selected_data_df = data_df.loc[data_df.allele.str.startswith("HLA-A")]
     selected_data_df.to_csv(
         os.path.join(models_dir, "_train_data.csv"), index=False)