fix

mhcflurry/class1_affinity_predictor.py

@@ -419,7 +419,9 @@ class Class1AffinityPredictor(object):
                 series = transform.to_series()
                 if percent_ranks_df is None:
                     percent_ranks_df = pandas.DataFrame(index=series.index)
-                assert_equal(series.index.values, percent_ranks_df.index.values)
+                numpy.testing.assert_array_almost_equal(
+                    series.index.values,
+                    percent_ranks_df.index.values)
                 percent_ranks_df[allele] = series
             percent_ranks_path = join(models_dir, "percent_ranks.csv")
             percent_ranks_df.to_csv(

test/test_batch_generator.py

@@ -11,7 +11,6 @@ import pstats
 import pandas
 import numpy
 
-from mhcflurry.allele_encoding import MultipleAlleleEncoding
 from mhcflurry.downloads import get_path
 from mhcflurry.batch_generator import (
     MultiallelicMassSpecBatchGenerator)
@@ -119,102 +118,3 @@ def test_basic():
         experiment_allele_colocations[('exp2', 'HLA-A*03:01')],
         experiment_allele_colocations[('exp2', 'HLA-A*02:01')])
 
-
-def test_large(sample_rate=1.0):
-    multi_train_df = pandas.read_csv(
-        data_path("multiallelic_ms.benchmark1.csv.bz2"))
-    multi_train_df["label"] = multi_train_df.hit
-    multi_train_df["is_affinity"] = False
-
-    sample_table = multi_train_df.loc[
-        multi_train_df.label == True
-    ].drop_duplicates("sample_id").set_index("sample_id").loc[
-        multi_train_df.sample_id.unique()
-    ]
-    grouped = multi_train_df.groupby("sample_id").nunique()
-    for col in sample_table.columns:
-        if (grouped[col] > 1).any():
-            del sample_table[col]
-    sample_table["alleles"] = sample_table.hla.str.split()
-
-    pan_train_df = pandas.read_csv(
-        get_path(
-            "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"]
-    pan_sub_train_df["is_affinity"] = True
-
-    pan_sub_train_df = pan_sub_train_df.sample(frac=sample_rate)
-    multi_train_df = multi_train_df.sample(frac=sample_rate)
-
-    pan_predictor = Class1AffinityPredictor.load(
-        get_path("models_class1_pan", "models.combined"),
-        optimization_level=0,
-        max_models=1)
-
-    allele_encoding = MultipleAlleleEncoding(
-        experiment_names=multi_train_df.sample_id.values,
-        experiment_to_allele_list=sample_table.alleles.to_dict(),
-        max_alleles_per_experiment=sample_table.alleles.str.len().max(),
-        allele_to_sequence=pan_predictor.allele_to_sequence,
-    )
-    allele_encoding.append_alleles(pan_sub_train_df.allele.values)
-    allele_encoding = allele_encoding.compact()
-
-    combined_train_df = pandas.concat(
-        [multi_train_df, pan_sub_train_df], ignore_index=True, sort=True)
-
-    print("Total size", combined_train_df)
-
-    planner = MultiallelicMassSpecBatchGenerator(
-        hyperparameters=dict(
-            batch_generator_validation_split=0.2,
-            batch_generator_batch_size=128,
-            batch_generator_affinity_fraction=0.5))
-
-    s = time.time()
-    profiler = cProfile.Profile()
-    profiler.enable()
-    planner.plan(
-        affinities_mask=combined_train_df.is_affinity.values,
-        experiment_names=combined_train_df.sample_id.values,
-        alleles_matrix=allele_encoding.alleles,
-        is_binder=numpy.where(
-            combined_train_df.is_affinity.values,
-            combined_train_df.label.values,
-            to_ic50(combined_train_df.label.values)) < 1000.0)
-    profiler.disable()
-    stats = pstats.Stats(profiler)
-    stats.sort_stats("cumtime").reverse_order().print_stats()
-    print(planner.summary())
-    print("Planning took [sec]: ", time.time() - s)
-
-    (train_iter, test_iter) = planner.get_train_and_test_generators(
-        x_dict={
-            "idx": numpy.arange(len(combined_train_df)),
-        },
-        y_list=[])
-
-    train_batch_sizes = []
-    indices_total = numpy.zeros(len(combined_train_df))
-    for (kind, it) in [("train", train_iter), ("test", test_iter)]:
-        for (i, (x_item, y_item)) in enumerate(it):
-            idx = x_item["idx"]
-            indices_total[idx] += 1
-            batch_df = combined_train_df.iloc[idx]
-            if not batch_df.is_affinity.all():
-                # Test each batch has at most one multiallelic ms experiment.
-                assert_equal(
-                    batch_df.loc[~batch_df.is_affinity].sample_id.nunique(), 1)
-            if kind == "train":
-                train_batch_sizes.append(len(batch_df))
-
-    # At most one short batch.
-    assert_less(sum(b != 128 for b in train_batch_sizes), 2)
-    assert_greater(
-        sum(b == 128 for b in train_batch_sizes), len(train_batch_sizes) - 2)
-
-    # Each point used exactly once.
-    assert_equal(
-        indices_total, numpy.ones(len(combined_train_df)))

test/test_class1_processing_neural_network.py

@@ -131,10 +131,6 @@ def test_neural_network_input():
         results['peptide_length'], df.peptide.str.len().values)
 
 
-def test_big():
-    train_basic_network(num=100000)
-
-
 def test_small():
     train_basic_network(num=10000)