def create_filters():
"""Create and store the pickled filters dataframes."""
df1 = apy.find_filters("hsapiens_gene_ensembl")
df1.to_pickle(os.path.join(DATADIR, "filters_hsapiens_gene_ensembl.pkl"))
df4 = apy.find_filters("closure_ECO")
df4.to_pickle(os.path.join(DATADIR, "filters_closure_ECO.pkl"))
df5 = apy.find_filters("hsapiens_encode")
df5.to_pickle(os.path.join(DATADIR, "filters_hsapiens_encode.pkl"))
df6 = apy.find_filters("chircus_snp")
df6.to_pickle(os.path.join(DATADIR, "filters_chircus_snp.pkl"))
df7 = apy.find_filters("hsapiens_peak")
df7.to_pickle(os.path.join(DATADIR, "filters_hsapiens_peak.pkl"))
def test_find_filters_snp(df_filters_snp_chircus_snp):
"""Test the available filters returned by find_filters() for the
chircus_snp dataset."""
expect = (df_filters_snp_chircus_snp.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
result = (find_filters("chircus_snp").sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
assert_frame_equal(result, expect)
def test_find_filters_genomic(df_filters_genomic_hsapiens_encode):
"""Test the available filters returned by find_filters() for the
hsapiens_encode dataset."""
expect = (df_filters_genomic_hsapiens_encode.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
result = (find_filters("hsapiens_encode").sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
assert_frame_equal(result, expect)
def test_find_filters_ontology(df_filters_ontology_closure_eco):
"""Test the available filters returned by find_filters() for the
closure_ECO dataset."""
expect = (df_filters_ontology_closure_eco.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
result = (find_filters("closure_ECO").sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
assert_frame_equal(result, expect)
def test_find_filters_default(df_filters_ensembl_hsapiens_gene):
"""Test the available filters returned by find_filters() for the
default dataset (hsapiens_gene_ensembl)."""
expect = (df_filters_ensembl_hsapiens_gene.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
result = (find_filters().sort_values(by="Filter_ID",
axis=0).reset_index(drop=True))
assert_frame_equal(result, expect)
def test_find_filters_funcgen(df_filters_funcgen_hsapiens_peak):
"""Test the available filters returned by find_filters() for the
hsapiens_peak dataset."""
expect = (df_filters_funcgen_hsapiens_peak.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
result = (find_filters("hsapiens_peak").sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
assert_frame_equal(result, expect)
def test_find_filters_output(df_filters_ensembl_hsapiens_gene):
"""Test the available filters returned by find_filters with a given
filename for the default dataset (hsapiens_gene_ensembl)."""
expect = (df_filters_ensembl_hsapiens_gene.sort_values(
by="Filter_ID", axis=0).reset_index(drop=True))
_ = find_filters(save=True, output="tested.csv")
saved = pd.read_csv("tested.csv")
result = (saved.replace(np.nan,
"").sort_values(by="Filter_ID",
axis=0).reset_index(drop=True))
try:
assert_frame_equal(result, expect)
finally:
os.remove("tested.csv")
