def avgPrefs(prefsfiles):
"""Gets average of site-specific preferences.
Args:
`prefsfiles` (list)
List of CSV files containing preferences, must all be
for same sites and characters.
Returns:
A `pandas.DataFrame` containing the average of the
preferences in `prefsfiles`. In this returned
data frame, `site` is the index
>>> tf1 = tempfile.NamedTemporaryFile
>>> tf2 = tempfile.NamedTemporaryFile
>>> with tf1(mode='w') as file1, tf2(mode='w') as file2:
... x = file1.write('site,A,C,G,T\\n'
... '10,0.2,0.2,0.5,0.1\\n'
... '2a,0.3,0.3,0.3,0.1')
... file1.flush()
... x = file2.write('site,A,C,G,T\\n'
... '10,0.4,0.1,0.1,0.4\\n'
... '2a,0.3,0.4,0.1,0.2')
... file2.flush()
... avg = avgPrefs([file1.name, file2.name])
>>> (avg['site'] == ['2a', '10']).all()
True
>>> numpy.allclose(avg['A'], [0.3, 0.3])
True
>>> numpy.allclose(avg['C'], [0.35, 0.15])
True
>>> numpy.allclose(avg['G'], [0.2, 0.3])
True
>>> numpy.allclose(avg['T'], [0.15, 0.25])
True
"""
assert len(prefsfiles) >= 1
prefs = [
pandas.read_csv(f, index_col='site').sort_index() for f in prefsfiles
]
# make sure all have the same columns in the same order
cols = prefs[0].columns
for i in range(len(prefs)):
assert set(cols) == set(prefs[i].columns)
prefs[i] = prefs[i][cols]
avgprefs = pandas.concat(prefs).groupby('site').mean().reset_index()
# natural sort by site: https://stackoverflow.com/a/29582718
avgprefs = avgprefs.reindex(index=natsort.order_by_index(
avgprefs.index, natsort.index_realsorted(avgprefs.site)))
return avgprefs
def test_index_realsorted_returns_results_identical_to_index_natsorted_with_REAL():
a = ['a50', 'a51.', 'a50.31', 'a-50', 'a50.4', 'a5.034e1', 'a50.300']
assert index_realsorted(a) == index_natsorted(a, alg=ns.REAL)
def tidyToWide(tidy_df, valuecol):
"""Converts tidy `diffsel` data frame to wide form.
The `diffsel` data frames returned by ``dms2_diffsel`` (and
also other dataframes, such as the `fracsurvive` ones
from ``dms_fracsurvive`` are in tidy form. This function
converts them to wide form.
Args:
`tidy_df` (pandas DataFrame)
Data frame in tidy form. Should have columns named
`site`, `wildtype`, `mutation`, and something
with the name matching `valuecol`.
`valuecol` (string)
Name of value column in `df`, such `diffsel` or
`fracsurvive`.
Returns:
Wide form dataframe. Will have columns `site` (as string),
`wildtype`, and all characters (e.g., amino acids)
for which values are given. Natural sorted by `site`.
>>> tidy_df = pandas.read_csv(io.StringIO(
... '''site wildtype mutation diffsel
... 3 A D -1.5
... 3 A C 10.1
... 2 A C 10.1
... 1 C D 9.5
... 1 C A 0.2
... 2 A D -1.5'''),
... delim_whitespace=True, index_col=False)
>>> wide_df = tidyToWide(tidy_df, valuecol='diffsel')
>>> print(wide_df.to_string(float_format=lambda x: '{0:.1f}'.format(x)))
site A C D wildtype
0 1 0.2 0.0 9.5 C
1 2 0.0 10.1 -1.5 A
2 3 0.0 10.1 -1.5 A
"""
assert isinstance(tidy_df, pandas.DataFrame)
cols = ['site', 'wildtype', 'mutation', valuecol]
assert set(cols) == set(
tidy_df.columns), ('expected columns '
'{0}\nactual columns {1}'.format(
cols, tidy_df.columns))
# make site a string
tidy_df['site'] = tidy_df['site'].astype(str)
# sort on site as here: https://stackoverflow.com/a/29582718
tidy_df = tidy_df.reindex(index=natsort.order_by_index(
tidy_df.index, natsort.index_realsorted(tidy_df.site)))
# convert to wide form, keeping wildtype identities
tidy_df = tidy_df.set_index('site', drop=True)
wt = tidy_df['wildtype']
wide_df = (tidy_df.pivot(
columns='mutation',
values=valuecol).fillna(0.0).join(wt).reset_index())
wide_df = wide_df.drop_duplicates().reset_index(drop=True)
return wide_df
def test_index_realsorted_returns_results_identical_to_index_natsorted():
a = ['a50', 'a51.', 'a50.31', 'a50.4', 'a5.034e1', 'a50.300']
assert index_realsorted(a) == index_natsorted(a)
def test_index_realsorted_returns_results_identical_to_index_natsorted_with_REAL():
a = ["a50", "a51.", "a50.31", "a-50", "a50.4", "a5.034e1", "a50.300"]
assert index_realsorted(a) == index_natsorted(a, alg=ns.REAL)
def test_index_realsorted_is_identical_to_index_natsorted_with_real_alg(float_list):
assert index_realsorted(float_list) == index_natsorted(float_list, alg=ns.REAL)
def test_index_realsorted_is_identical_to_index_natsorted_with_real_alg(
float_list):
assert index_realsorted(float_list) == index_natsorted(float_list,
alg=ns.REAL)