def test_correlation_graphs(self):
df_coeffs = correlation_coefficients(self.df,
max_rt_diff=5.0,
coeff_thres=0.7,
pvalue_thres=1.0,
method="pearson",
block=5000,
ncpus=None)
graph = correlation_graphs(df_coeffs, self.df)
n0 = list(graph.nodes(data=True))[0]
n1 = list(graph.nodes(data=True))[-1]
e0 = list(graph.edges(data=True))[0]
e1 = list(graph.edges(data=True))[-1]
# order is different between python 2 and 3
np.testing.assert_almost_equal(
[n0[1]["mz"], n0[1]["intensity"], n0[1]["rt"]],
[168.989654, 520.0, 120.0])
np.testing.assert_almost_equal(
[n1[1]["mz"], n1[1]["intensity"], n1[1]["rt"]],
[493.063765, 163.33, 192.5])
np.testing.assert_almost_equal([
e0[2]["rvalue"], e0[2]["pvalue"], e0[2]["mzdiff"], e0[2]["rtdiff"]
], [1.0, 0.0, 167.982378, 1.0])
np.testing.assert_almost_equal([
e1[2]["rvalue"], e1[2]["pvalue"], e1[2]["mzdiff"], e1[2]["rtdiff"]
], [1.0, 0.0, 1.003355, 2.5])
def group_features(df,
db_out,
max_rt_diff=5.0,
coeff_thres=0.7,
pvalue_thres=1.0,
method="pearson",
block=5000,
ncpus=None):
conn = sqlite3.connect(db_out)
cursor = conn.cursor()
cursor.execute("DROP TABLE IF EXISTS groups")
cursor.execute("""CREATE TABLE groups (
group_id INTEGER DEFAULT NULL,
peak_id_a TEXT DEFAULT NULL,
peak_id_b TEXT DEFAULT NULL,
degree_a INTEGER DEFAULT NULL,
degree_b INTEGER DEFAULT NULL,
r_value REAL DEFAULT NULL,
p_value REAL DEFAULT NULL,
rt_diff REAL DEFAULT NULL,
mz_diff REAL DEFAULT NULL,
PRIMARY KEY (peak_id_a, peak_id_b));""")
df_coeffs = statistics.correlation_coefficients(df, max_rt_diff,
coeff_thres, pvalue_thres,
method, block, ncpus)
graph = statistics.correlation_graphs(df_coeffs, df)
sub_graphs = list(
graph.subgraph(c) for c in nx.weakly_connected_components(graph))
for i in range(len(sub_graphs)):
sub_graphs[i].graph[
"groupid"] = i + 1 # not stored in output - place holder
sub_graph_edges = []
# sort edges
edges = sorted(sub_graphs[i].edges(data=True),
key=lambda e: (e[0], e[1]))
for edge in edges:
sub_graph_edges.append(
(i + 1, str(edge[0]), str(edge[1]),
sub_graphs[i].degree(edge[0]), sub_graphs[i].degree(edge[1]),
round(float(edge[2]["rvalue"]), 2), float(edge[2]["pvalue"]),
float(edge[2]["rtdiff"]), float(edge[2]["mzdiff"])))
cursor.executemany(
"""insert into groups (group_id, peak_id_a, peak_id_b, degree_a, degree_b,
r_value, p_value, rt_diff, mz_diff) values (?,?,?,?,?,?,?,?,?)""",
sub_graph_edges)
conn.commit()
conn.close()
return graph
def test_correlation_coefficients(self):
df_coeffs_comp = pd.DataFrame(
{
"name_a":
["M169T120", "M169T120", "M337T121", "M215T170", "M492T190"],
"name_b":
["M337T121", "M505T122", "M505T122", "M231T174", "M493T192"],
"r_value": [
np.float64(1.0),
np.float64(1.0),
np.float64(1.0),
np.float64(1.0),
np.float64(1.0)
],
"p_value": [
np.float64(0.0),
np.float64(0.0),
np.float64(0.0),
np.float64(0.0),
np.float64(5.85415087865495e-157)
]
},
columns=["name_a", "name_b", "r_value", "p_value"])
df_coeffs = correlation_coefficients(self.df,
max_rt_diff=5.0,
coeff_thres=0.7,
pvalue_thres=1.0,
method="pearson",
block=5000,
ncpus=None)
pd.testing.assert_frame_equal(df_coeffs, df_coeffs_comp)
df_coeffs_comp = pd.DataFrame(
{
"name_a":
["M169T120", "M169T120", "M337T121", "M215T170", "M492T190"],
"name_b":
["M337T121", "M505T122", "M505T122", "M231T174", "M493T192"],
"r_value": [
np.float64(1.0),
np.float64(1.0),
np.float64(1.0),
np.float64(1.0),
np.float64(1.0)
],
"p_value": [
np.float64(0.0),
np.float64(0.0),
np.float64(0.0),
np.float64(0.0),
np.float64(0.0)
]
},
columns=["name_a", "name_b", "r_value", "p_value"])
df_coeffs = correlation_coefficients(self.df,
max_rt_diff=5.0,
coeff_thres=0.7,
pvalue_thres=1.0,
method="spearman",
block=5000,
ncpus=None)
pd.testing.assert_frame_equal(df_coeffs, df_coeffs_comp)
df_coeffs = correlation_coefficients(self.df,
max_rt_diff=50000.0,
coeff_thres=0.0,
pvalue_thres=1.0,
method="pearson",
block=5000,
ncpus=None)
self.assertEqual(df_coeffs.shape, (136, 4))