def test_Norm_PQN_Values_Ref_Sample():
"""Probabilistic Quotient Normalization - testing with reference sample as a sample of the dataset."""
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
normPQN = sca.Norm_PQN(Imputated, ref_sample = Imputated.columns[0])
assert_frame_equal(MetAna_PQN, normPQN)
else:
df = pd.read_csv(filename, header=0, sep=',',
index_col=0).rename_axis('sample', axis='columns')
df = df.rename_axis('mz/rt', axis='index')
# these may exist, repeating information
df = df.drop(columns=["mz", "rt"], errors='ignore')
if not has_labels:
# force labels
df = mtl.add_labels(df, labels=['KO', 'WT'])
return df
aligned_all_neg = reading_MetAna_file('aligned_1ppm_min2_1ppm_negative.csv',
has_labels=True)
preprocessed = sca.NaN_Imputation(aligned_all_neg, 0).pipe(sca.ParetoScal)
dist_euclidian = dist.pdist(preprocessed.T, metric='euclidean')
Z_euc = hier.linkage(dist_euclidian, method='average')
# global_dist, discrims = ma.dist_discrim(aligned_all_neg, Z_euc, method='average')
# print(global_dist, discrims)
def test_dist_dicrim_average():
global_dist, discrims = ma.dist_discrim(aligned_all_neg,
Z_euc,
method='average')
# assert str(discrim_ave[0]) == str(np.array(list(discrim_ave[1].values())).mean())
assert global_dist == approx(np.array(list(discrims.values())).mean())
def test_Norm_RF_Values():
"""Normalization by a reference feature only - 301/2791.68 (random choice)."""
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
normRF = sca.Norm_Feat(Imputated, "301/2791.68")
# assert str(MetAna_N) == str(norm*1000)
assert_frame_equal(MetAna_N, normRF*1000)
def test_Norm_TI_Values():
"""Normalization by the total peak area"""
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
normTI = sca.Norm_TotalInt(Imputated)
assert_frame_equal(MetAna_NTI, normTI*1000)
def test_NaN_MinValue():
imputated = sca.NaN_Imputation(MetAna_O2, minsample=0)
minimum = (MetAna_O2.min().min())/2
where_null = MetAna_O2.isnull()
mean_imputed = imputated[where_null].mean().mean()
assert mean_imputed == approx(minimum)
def test_NaN_FeatRemove():
assert len(sca.NaN_Imputation(MetAna_O2, 1/2 + 0.00001)) == len(MetAna_I2T.columns)-1
def test_ParetoScal_values():
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
pareto = sca.ParetoScal(Imputated)
assert_frame_equal(MetAna_P, pareto)
def test_Norm_QN_Values():
"""Quantile Normalization with reference sample type = mean"""
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
normQN = sca.Norm_Quantile(Imputated, ref_type = 'mean')
assert_frame_equal(MetAna_QN, normQN)
def test_glog_values():
glog = sca.glog(MetAna_O2_I)
# assert str(MetAna_G.data) == str(glog.data)
assert_frame_equal(MetAna_G, glog)
def test_glog_lamb():
lamb = 100000
y = MetAna_O2_I.copy()
y = np.log2((y + (y**2 + lamb**2)**0.5)/2)
assert (y == (sca.glog(MetAna_O2_I, lamb = 100000))).all().all()
# Tests for ParetoScal
MetAna_O2_I = sca.NaN_Imputation(MetAna_O2, 0)
def test_ParetoScal_values():
Imputated = sca.NaN_Imputation(MetAna_O2, 0)
pareto = sca.ParetoScal(Imputated)
assert_frame_equal(MetAna_P, pareto)
# Tests for MeanCentering
# If Pareto and AutoScale work, MeanCentering should work
# Tests for AutoScal
MetAna_AS = reading_MetAna_file('MetAnalyst/MetAna_AutoScal.csv') # Auto Scaling only
def test_AutoScal_values():
