def get_ui_copy_and_paste(pqo,
fn,
args_dict,
with_abundance=False,
num_bins=NUM_BINS):
df = pd.read_csv(fn, sep='\t')
fg = "\n".join(df.loc[df["foreground"].notnull(), "foreground"].tolist())
if not with_abundance:
bg = "\n".join(df.loc[df["background"].notnull(),
"background"].tolist())
return userinput.Userinput(pqo=pqo,
foreground_string=fg,
background_string=bg,
num_bins=num_bins,
args_dict=args_dict)
else:
bg = df.loc[df["background"].notnull(), "background"].tolist()
in_ = [
str(ele)
for ele in df.loc[df["intensity"].notnull(), "intensity"].tolist()
]
background_string = ""
for ele in zip(bg, in_):
an, in_ = ele
background_string += an + "\t" + in_ + "\n"
return userinput.Userinput(pqo=pqo,
foreground_string=fg,
background_string=background_string,
num_bins=num_bins,
args_dict=args_dict)
def test_cleanupforanalysis_genome_Userinput_File(pqo_STRING, STRING_examples,
args_dict):
"""
python/test_userinput.py::test_cleanupforanalysis_characterize_foreground_REST_API[edge case, empty DFs with NaNs] XPASS
"""
ENSPs, taxid = STRING_examples
enrichment_method = "genome"
args_dict_temp = args_dict.copy()
args_dict_temp.update({
"enrichment_method": enrichment_method,
"taxid": taxid
})
werkzeug_fn = werkzeug.datastructures.FileStorage(
stream=StringIO("foreground\n" + "\n".join(ENSPs)))
werkzeug_fn.seek(0)
ui = userinput.Userinput(pqo_STRING,
fn=werkzeug_fn,
args_dict=args_dict_temp)
# no NaNs where ANs are expected
foreground = ui.foreground[ui.col_foreground]
assert sum(foreground.isnull()) == 0
assert sum(foreground.notnull()) > 0
# foreground
assert isinstance(foreground.iloc[0], str)
# no duplicates
assert foreground.duplicated().any() == False
foreground_n = ui.get_foreground_n()
background_n = ui.get_background_n()
assert background_n >= foreground_n
def test_cleanupforanalysis_genome_Userinput_copyNpaste(
pqo_STRING, STRING_examples, args_dict):
"""
python/test_userinput.py::test_cleanupforanalysis_characterize_foreground_REST_API[edge case, empty DFs with NaNs] XPASS
"""
ENSPs, taxid = STRING_examples
fg = format_for_REST_API(ENSPs)
enrichment_method = "genome"
args_dict_temp = args_dict.copy()
args_dict_temp.update({
"enrichment_method": enrichment_method,
"taxid": taxid
})
ui = userinput.Userinput(pqo_STRING,
foreground_string=fg,
args_dict=args_dict_temp)
# no NaNs where ANs are expected
foreground = ui.foreground[ui.col_foreground]
assert sum(foreground.isnull()) == 0
assert sum(foreground.notnull()) > 0
# foreground
assert isinstance(foreground.iloc[0], str)
# no duplicates
assert foreground.duplicated().any() == False
foreground_n = ui.get_foreground_n()
background_n = ui.get_background_n()
assert background_n >= foreground_n
def test_cleanupforanalysis_compare_groups_Userinput(
pqo_STRING, fixture_fg_bg_meth_expected_cases, args_dict):
enrichment_method = "compare_groups"
foreground, background, _ = fixture_fg_bg_meth_expected_cases
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = "\n".join(background.loc[background.background.notnull(),
"background"].tolist())
args_dict_temp = args_dict.copy()
args_dict_temp["enrichment_method"] = enrichment_method
ui = userinput.Userinput(pqo_STRING,
foreground_string=fg,
background_string=bg,
args_dict=args_dict_temp)
# no NaNs where ANs are expected
foreground = ui.foreground[ui.col_foreground]
assert sum(foreground.isnull()) == 0
assert sum(foreground.notnull()) > 0
background = ui.background[ui.col_background]
assert sum(background.isnull()) == 0
assert sum(background.notnull()) > 0
# foreground and background are strings
assert isinstance(foreground.iloc[0], str)
assert isinstance(background.iloc[0], str)
# if there were duplicates in the original input they should still be preserved in the cleaned up DF
# not equal because of splice variants
# remove NaNs from df_orig
foreground_df_orig = ui.df_orig[ui.col_foreground]
background_df_orig = ui.df_orig[ui.col_background]
assert foreground.duplicated().sum() >= foreground_df_orig[
foreground_df_orig.notnull()].duplicated().sum()
assert background.duplicated().sum() >= background_df_orig[
background_df_orig.notnull()].duplicated().sum()
def test_cleanupforanalysis_compare_samples_Userinput(
pqo_STRING, fixture_fg_bg_meth_expected_cases, args_dict):
enrichment_method = "compare_samples"
foreground, background, _ = fixture_fg_bg_meth_expected_cases
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = "\n".join(background.loc[background.background.notnull(),
"background"].tolist())
args_dict_temp = args_dict.copy()
args_dict_temp["enrichment_method"] = enrichment_method
ui = userinput.Userinput(pqo_STRING,
foreground_string=fg,
background_string=bg,
args_dict=args_dict_temp)
# no NaNs where ANs are expected
foreground = ui.foreground[ui.col_foreground]
assert sum(foreground.isnull()) == 0
assert sum(foreground.notnull()) > 0
background = ui.background[ui.col_background]
assert sum(background.isnull()) == 0
assert sum(background.notnull()) > 0
# foreground and background are strings
assert isinstance(foreground.iloc[0], str)
assert isinstance(background.iloc[0], str)
# no duplicates
assert foreground.duplicated().any() == False
assert background.duplicated().any() == False
def test_check_parse_and_fail_cleanup_0(foreground, background, enrichment_method, pqo):
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = "\n".join(background.loc[background.background.notnull(), "background"].tolist())
ui = userinput.Userinput(pqo=pqo, foreground_string=fg, background_string=bg, num_bins=NUM_BINS, enrichment_method=enrichment_method)
assert ui.check_parse == False
assert ui.check_cleanup == False
assert ui.check == False
def test_cleanupforanalysis_abundance_correction_Userinput(
pqo_STRING, fixture_fg_bg_meth_expected_cases, args_dict):
foreground, background, enrichment_method = fixture_fg_bg_meth_expected_cases
if enrichment_method != "abundance_correction":
# assert 1 == 1
return None
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = background.loc[background.background.notnull(), "background"].tolist()
in_ = [
str(ele) for ele in background.loc[background.intensity.notnull(),
"intensity"].tolist()
]
background_string = ""
for ele in zip(bg, in_):
an, in_ = ele
background_string += an + "\t" + in_ + "\n"
args_dict_temp = args_dict.copy()
args_dict_temp["enrichment_method"] = enrichment_method
ui = userinput.Userinput(pqo_STRING,
foreground_string=fg,
background_string=background_string,
args_dict=args_dict_temp)
# no NaNs where ANs are expected
foreground = ui.foreground[ui.col_foreground]
assert sum(foreground.isnull()) == 0
assert sum(foreground.notnull()) > 0
background = ui.background[ui.col_background]
assert sum(background.isnull()) == 0
assert sum(background.notnull()) > 0
# every AN has an abundance val
foreground_intensity = ui.foreground[ui.col_intensity]
assert sum(foreground_intensity.isnull()) == 0
assert sum(foreground_intensity.notnull()) > 0
background_intensity = ui.background[ui.col_intensity]
assert sum(background_intensity.isnull()) == 0
assert sum(background_intensity.notnull()) > 0
# foreground and background are strings and abundance values are floats
assert isinstance(foreground.iloc[0], str)
assert isinstance(background.iloc[0], str)
assert isinstance(foreground_intensity.iloc[0], float)
assert isinstance(background_intensity.iloc[0], float)
# no duplicates
assert foreground.duplicated().any() == False
assert background.duplicated().any() == False
# sorted abundance values
assert non_decreasing(foreground_intensity.tolist()) == True
assert non_decreasing(background_intensity.tolist()) == True
def test_check_parse_and_cleanup_copy_and_paste_2(foreground, background,
enrichment_method,
pqo_STRING, args_dict):
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = "\n".join(background.loc[background.background.notnull(),
"background"].tolist())
args_dict["enrichment_method"] = enrichment_method
ui = userinput.Userinput(pqo=pqo_STRING,
foreground_string=fg,
background_string=bg,
num_bins=NUM_BINS,
args_dict=args_dict)
assert ui.check_parse == True
def test_check_parse_with_copy_and_paste_1(foreground, background,
enrichment_method, pqo_STRING,
args_dict):
fg = "\n".join(foreground[foreground.notnull()].tolist())
bg = background.loc[background.background.notnull(), "background"].tolist()
in_ = [
str(ele) for ele in background.loc[background.intensity.notnull(),
"intensity"].tolist()
]
background_string = ""
for ele in zip_longest(bg, in_, fillvalue=np.nan):
an, in_ = ele
background_string += an + "\t" + str(in_) + "\n"
args_dict["enrichment_method"] = enrichment_method
ui = userinput.Userinput(pqo=pqo_STRING,
foreground_string=fg,
background_string=background_string,
num_bins=NUM_BINS,
args_dict=args_dict)
assert ui.check_parse == True
assert ui.foreground.shape == (8, 2)
def get_ui_fn(pqo, fn, args_dict, num_bins=NUM_BINS):
return userinput.Userinput(pqo=pqo,
fn=fn,
args_dict=args_dict,
num_bins=num_bins)
def get_ui_fn(pqo, fn, enrichment_method, num_bins=NUM_BINS):
return userinput.Userinput(pqo=pqo, fn=fn, enrichment_method=enrichment_method, num_bins=num_bins)
def test_check_parse_and_cleanup_FN_missing(pqo):
fn_example_data = os.path.join(variables.EXAMPLE_FOLDER, "This_does_not_exist_and_therefore_can_not_be_parsed.txt")
ui = userinput.Userinput(pqo=pqo, fn=fn_example_data, num_bins=NUM_BINS)
assert ui.check_parse == False
assert ui.check_cleanup == False
assert ui.check == False
def test_check_parse_and_cleanup_FN_comma(pqo):
fn_example_data = os.path.join(variables.EXAMPLE_FOLDER, "HeLa_Ubi_exampledata.txt")
ui = userinput.Userinput(pqo=pqo, fn=fn_example_data, num_bins=NUM_BINS)
assert ui.check_parse == True
assert ui.check_cleanup == True
assert ui.check == True