def test_csv(test_data, tmp_path):
"""
Write to a csv and make sure it reads back in properly.
"""
for d in test_data:
gpm = GenotypePhenotypeMap(genotype=d["genotype"],
wildtype=d["wildtype"],
phenotype=d["phenotype"],
uncertainty=d["uncertainty"])
# Write out a csv file
out_file = os.path.join(tmp_path, "tmp.csv")
gpm.to_csv(out_file, index=False)
assert os.path.exists(out_file)
gpm_read = gpmap.read_csv(out_file, wildtype=d["wildtype"])
# Make sure the written and read gpmaps ar ethe same
conftest.compare_gpmap(gpm, gpm_read)
# Do not give wildtype. Should still work because the wildtype was
# inferred.
gpm_read = gpmap.read_csv(out_file)
conftest.compare_gpmap(gpm, gpm_read)
# Check ability to read labels back in
site_labels = [f"{x}" for x in range(10, 10 + len(d["wildtype"]), 1)]
gpm = GenotypePhenotypeMap(genotype=d["genotype"],
wildtype=d["wildtype"],
site_labels=site_labels)
out_file = os.path.join(tmp_path, "tmp.csv")
gpm.to_csv(out_file)
gpm_read = gpmap.read_csv(out_file)
for i in range(len(gpm_read.site_labels)):
# Skip virtual site_labels added for invariant sites
if len(d["mutations"][i]) == 1:
continue
assert gpm_read.site_labels[i] == gpm.site_labels[i]
# Read in with bad wildtype. Should throw warning and then have
# sequential site labels.
with pytest.warns(UserWarning):
gpm_read = gpmap.read_csv(out_file, wildtype=d["mutant"])
assert np.array_equal(gpm_read.site_labels, range(len(d["wildtype"])))
def test_excel(test_data, tmp_path):
"""
Test reading/writing/fidelity of excel.
"""
for d in test_data:
gpm = GenotypePhenotypeMap(genotype=d["genotype"],
wildtype=d["wildtype"],
phenotype=d["phenotype"],
uncertainty=d["uncertainty"])
# Write excel file
excel_file = os.path.join(tmp_path, "tmp.xlsx")
gpm.to_excel(filename=excel_file)
assert os.path.isfile(excel_file)
# Read in and make sure it worked.
new_gpm = gpmap.read_excel(filename=excel_file, wildtype=d["wildtype"])
conftest.compare_gpmap(gpm, new_gpm)
# Do not give wildtype. Should still work because the wildtype was
# inferred.
gpm_read = gpmap.read_excel(filename=excel_file)
conftest.compare_gpmap(gpm, gpm_read)
# Check ability to read labels back in
site_labels = [f"{x}" for x in range(10, 10 + len(d["wildtype"]), 1)]
gpm = GenotypePhenotypeMap(genotype=d["genotype"],
wildtype=d["wildtype"],
site_labels=site_labels)
out_file = os.path.join(tmp_path, "tmp.xlsx")
gpm.to_excel(out_file)
gpm_read = gpmap.read_excel(out_file)
for i in range(len(gpm_read.site_labels)):
# Skip virtual site_labels added for invariant sites
if len(d["mutations"][i]) == 1:
continue
assert gpm_read.site_labels[i] == gpm.site_labels[i]
# Read in with bad wildtype. Should throw warning and then have
# sequential site labels.
with pytest.warns(UserWarning):
gpm_read = gpmap.read_excel(out_file, wildtype=d["mutant"])
assert np.array_equal(gpm_read.site_labels, range(len(d["wildtype"])))
def test_json(test_data, tmp_path):
"""
Test reading/writing/fidelity of json.
"""
for d in test_data:
gpm = GenotypePhenotypeMap(wildtype=d["wildtype"],
genotype=d["genotype"],
phenotype=d["phenotype"],
uncertainty=d["uncertainty"])
# Write json file
json_file = os.path.join(tmp_path, "tmp.json")
gpm.to_json(filename=json_file)
assert os.path.isfile(json_file)
# Read json file
new_gpm = gpmap.read_json(filename=json_file)
conftest.compare_gpmap(gpm, new_gpm)
def test_dict(test_data):
"""
Test converstion of gpmap to dict.
"""
# Stupidly trivial map
gpmap.read_dict({"wildtype": "0", "data": {"genotype": ["0"]}})
# Make sure wildtype check is working
with pytest.raises(ValueError):
gpmap.read_dict({"data": {"genotype": ["0"]}})
# Make sure wildtype length/genotype length check working
with pytest.raises(ValueError):
gpmap.read_dict({"wildtype": "01", "data": {"genotype": ["0"]}})
for d in test_data:
gpm = GenotypePhenotypeMap(wildtype=d["wildtype"],
genotype=d["genotype"],
phenotype=d["phenotype"],
uncertainty=d["uncertainty"])
# Write out as a dcitionary
gpm_as_dict = gpm.to_dict()
# Check wildtype meta data, mutations meta data
assert gpm_as_dict["wildtype"] == d["wildtype"]
for i in range(len(gpm_as_dict["mutations"])):
assert np.array_equal(gpm_as_dict["mutations"][i],
d["mutations"][i])
# This is a pandas data conversion. Don't check in detail, just make sure
# the conversion dumped out a a dict.
assert type(gpm_as_dict["data"]) is dict
# Read dictionary back in and make sure it's the same
new_gpm = gpmap.read_dict(gpm_as_dict)
conftest.compare_gpmap(gpm, new_gpm)
def test_dataframe(test_data, tmp_path):
"""
Test reading of dataframe.
"""
for d in test_data:
# Pretty standard map
gpm = GenotypePhenotypeMap(genotype=d["genotype"],
wildtype=d["wildtype"],
phenotype=d["phenotype"],
uncertainty=d["uncertainty"])
df = pd.DataFrame({
"genotype": d["genotype"],
"phenotype": d["phenotype"],
"uncertainty": d["uncertainty"]
})
gpm_from_df = gpmap.read_dataframe(df, wildtype=d["wildtype"])
conftest.compare_gpmap(gpm, gpm_from_df)
# Minimal map
gpm = GenotypePhenotypeMap(wildtype=d["wildtype"],
genotype=d["genotype"])
df = pd.DataFrame({"genotype": d["genotype"]})
gpm_from_df = gpmap.read_dataframe(df, wildtype=d["wildtype"])
conftest.compare_gpmap(gpm, gpm_from_df)
# Read without wildtype --> should still work
gpm_from_df = gpmap.read_dataframe(df)
conftest.compare_gpmap(gpm, gpm_from_df)
# Map without genotype (fail)
df = pd.DataFrame({"phenotype": d["phenotype"]})
with pytest.raises(ValueError):
gpm_from_df = gpmap.read_dataframe(df, wildtype=d["wildtype"])