def test_calculate_cumulative_relative_abundance():
data1 = np.array([['', 'Step I'], ['219', 0.239709], ['218', 0.190986]])
data2 = np.array([['', 'Step II'], ['219', 0.434289], ['218', 0.193835]])
# create a dataframe, each sub list is one row
df1 = pandas.DataFrame(data=data1[1:, 1:],
index=data1[1:, 0],
columns=data1[0, 1:]).astype(np.dtype(np.float64))
df2 = pandas.DataFrame(data=data2[1:, 1:],
index=data2[1:, 0],
columns=data2[0, 1:]).astype(np.dtype(np.float64))
samples = [df1, df2]
result = calculate_cumulative_relative_abundance(samples)
df1_res = result[0]
df2_res = result[1]
# assert df1_res.columns.contains('Cum Rel Abund')
# assert df2_res.columns.contains('Cum Rel Abund')
assert 'Cum Rel Abund' in df1_res.columns
assert 'Cum Rel Abund' in df2_res.columns
assert df1_res.loc['219', 'Cum Rel Abund'] == 0.239709
assert df1_res.loc['218', 'Cum Rel Abund'] == 0.430695
assert df2_res.loc['219', 'Cum Rel Abund'] == 0.434289
assert df2_res.loc['218', 'Cum Rel Abund'] == 0.628124
def test_calculate_cumulative_prop_trf():
data1 = np.array([['', 'Step I'], ['219', 0.239709], ['218', 0.190986]])
data2 = np.array([['', 'Step II'], ['219', 0.434289], ['218', 0.193835]])
# create a dataframe, each sub list is one row
df1 = pandas.DataFrame(data=data1[1:, 1:],
index=data1[1:, 0],
columns=data1[0, 1:]).astype(np.dtype(np.float64))
df2 = pandas.DataFrame(data=data2[1:, 1:],
index=data2[1:, 0],
columns=data2[0, 1:]).astype(np.dtype(np.float64))
samples = [df1, df2]
samples = calculate_cumulative_relative_abundance(samples)
samples = remove_cumulative_abundance_over_one(samples)
result = calculate_cumulative_prop_trf(samples)
df1_res = result[0]
df2_res = result[1]
assert 'Cum Prop TRFs' in df1_res.columns
assert 'Cum Prop TRFs' in df2_res.columns
assert df1_res.loc['219', 'Cum Prop TRFs'] == 0.5
assert df1_res.loc['218', 'Cum Prop TRFs'] == 1.0
assert df2_res.loc['219', 'Cum Prop TRFs'] == 0.5
assert df2_res.loc['218', 'Cum Prop TRFs'] == 1.0
def setup_data():
''' setup some test data and
remove all rows cumulative relative abundance has gone over 1
'''
# this should get the last item truncated
data1 = np.array([['', 'Step I'],
['219', 0.7],
['218', 0.3],
['217', 0.1]])
# this should get no items truncacted as it adds to exactly 1
data2 = np.array([['', 'Step II'],
['219', 0.4],
['218', 0.2],
['217', 0.2]])
# this should get no items truncated as it never reaches 1
data3 = np.array([['', 'Step III'],
['219', 0.1],
['218', 0.2],
['217', 0.2]])
# create a dataframe, each sub list is one row
df1 = pandas.DataFrame(data=data1[1:, 1:], index=data1[1:, 0],
columns=data1[0, 1:]).astype(np.dtype(np.float64))
df2 = pandas.DataFrame(data=data2[1:, 1:], index=data2[1:, 0],
columns=data2[0, 1:]).astype(np.dtype(np.float64))
df3 = pandas.DataFrame(data=data3[1:, 1:], index=data3[1:, 0],
columns=data3[0, 1:]).astype(np.dtype(np.float64))
samples = [df1, df2, df3]
samples = calculate_cumulative_relative_abundance(samples)
result = remove_cumulative_abundance_over_one(samples)
return result