def test_constructor():
# This should work fine
G = GenotypePhenotypeGraph()
assert type(G) is GenotypePhenotypeGraph
assert G.gpm is None
with pytest.raises(ValueError):
G.model(1., 1.)
def test_pos(test_data):
# requires G
with pytest.raises(TypeError):
gpgraph.pyplot.pos.flattened()
# pass dumb argument
with pytest.raises(ValueError):
gpgraph.pyplot.pos.flattened("stupid")
for d in test_data:
gpm = GenotypePhenotypeMap(genotypes=d["genotypes"],
wildtype=d["wildtype"],
phenotypes=d["phenotypes"])
G = GenotypePhenotypeGraph()
# test check for loaded dataset.
with pytest.raises(ValueError):
gpgraph.pyplot.pos.flattened(G)
# Load in data
G.add_gpm(gpm)
# Should work
ret = gpgraph.pyplot.pos.flattened(G)
# Check basic sanity of returns
assert type(ret) is dict
for k in ret:
G.nodes[k]
assert type(ret[k]) is list
assert len(ret[k]) == 2
# Check for bad scale values
with pytest.raises(ValueError):
gpgraph.pyplot.pos.flattened(G, scale=0)
with pytest.raises(ValueError):
gpgraph.pyplot.pos.flattened(G, scale=-1)
# these should work
ret = gpgraph.pyplot.pos.flattened(G, scale=10.0)
assert type(ret) is dict
ret = gpgraph.pyplot.pos.flattened(G, scale=22.3)
assert type(ret) is dict
# make sure it takes vertical parameter. not really testing if it has
# effect (test for graphs are annoying... )
ret = gpgraph.pyplot.pos.flattened(G, scale=1, vertical=True)
assert type(ret) is dict
def test_read_json(gpgraph_test):
"""Test reading from json"""
read_gpm = GenotypePhenotypeGraph.read_json("data/test_data.json")
# Test instance was created
assert isinstance(read_gpm, GenotypePhenotypeGraph)
# Test elements align
np.testing.assert_array_equal(gpgraph_test.nodes, read_gpm.nodes)
def test_add_model(test_data):
for d in test_data:
gpm = GenotypePhenotypeMap(genotypes=d["genotypes"],
wildtype=d["wildtype"],
phenotypes=d["phenotypes"],
bad_pheno=d["phenotypes"])
# Give negative phenotypes (which models except ratio will not like)
gpm.data.loc[:, "bad_pheno"] = gpm.data.loc[:, "bad_pheno"] * -1
G = GenotypePhenotypeGraph()
# Make sure model checks properly for adding gpm first
with pytest.raises(ValueError):
G.add_model()
# Use basic hamming connectivity model
G.add_gpm(gpm, "hamming", 1)
# Try calculating ratio and sswm models
for m in ["ratio", "sswm"]:
G.add_model(column="phenotypes", model=m)
# Try calculating moran and mcclandish with multiple population sizes
for m in ["moran", "mcclandish"]:
for N in [1, 3, 10, 30, 100, 300, 1000, 3000, 10000]:
G.add_model(column="phenotypes", model=m, population_size=N)
# Pass in some crappy data
with pytest.raises(ValueError):
G.add_model(column="bad_pheno", model="sswm")
# should work for ratio
G.add_model(column="bad_pheno", model="ratio")
# Pass in string data
with pytest.raises(ValueError):
G.add_model(column="genotypes", model="sswm")
# don't pass in required arg
with pytest.raises(ValueError):
G.add_model(column="phenotypes", model="mcclandish")
# pass in nonsensical version of required arg
with pytest.raises(ValueError):
G.add_model(column="phenotypes",
model="mcclandish",
population_size=-5)
# pass in undefined model
with pytest.raises(ValueError):
G.add_model(column="phenotypes", model="not_a_real_model")
# pass in unrecognized arg to a model
with pytest.raises(ValueError):
G.add_model(column="phenotypes", model="sswm", population_size=10)
# pass in incompatible model
def bad_model(v1):
return 5
with pytest.raises(ValueError):
G.add_model(column="phenotypes", model=bad_model)
# okay model, only float args
def okay_model(v1, v2):
return 5
G.add_model(column="phenotypes", model=okay_model)
# okay model, float and custom kwarg
def okay_model(v1, v2, needed_kwarg):
return 5
G.add_model(column="phenotypes", model=okay_model, needed_kwarg=5)
# check node property setting for this model where we know the answer
for e in G.edges:
assert G.edges[e]["prob"] == 5
# pass in no model (should set all prob to 1)
G.add_model(column="phenotypes")
for e in G.edges:
assert G.edges[e]["prob"] == 1
# pass in nothing (all prob should be 1)
G.add_model()
for e in G.edges:
assert G.edges[e]["prob"] == 1
# pass in no data with model. prob should all be 0 for sswm because
# fitness is same all genotypes.
G.add_model(model="sswm")
for e in G.edges:
assert G.edges[e]["prob"] == 0
def test_add_gpm(test_data):
# Check hamming = 1
G = GenotypePhenotypeGraph()
gpm = GenotypePhenotypeMap(genotypes=["SG", "PF", "SF", "PG"])
G.add_gpm(gpm, "hamming", cutoff=1)
new_edges = list(G.edges)
new_edges.sort()
hamming_edges = [(0, 2), (2, 0), (0, 3), (3, 0), (1, 2), (2, 1), (1, 3),
(3, 1)]
hamming_edges.sort()
for i in range(len(new_edges)):
assert np.array_equal(hamming_edges[i], new_edges[i])
# Check hamming = 2
G = GenotypePhenotypeGraph()
gpm = GenotypePhenotypeMap(genotypes=["SG", "PF", "SF", "PG"])
G.add_gpm(gpm, "hamming", cutoff=2)
new_edges = list(G.edges)
new_edges.sort()
hamming_edges = [(0, 1), (1, 0), (0, 2), (2, 0), (0, 3), (3, 0), (1, 2),
(2, 1), (1, 3), (3, 1), (2, 3), (3, 2)]
hamming_edges.sort()
for i in range(len(new_edges)):
assert np.array_equal(hamming_edges[i], new_edges[i])
# Check amino acid codon = 1
G = GenotypePhenotypeGraph()
gpm = GenotypePhenotypeMap(genotypes=["SG", "PF", "SF", "PG"])
G.add_gpm(gpm, "codon", cutoff=1)
new_edges = list(G.edges)
new_edges.sort()
codon_edges = [(0, 3), (3, 0), (1, 2), (2, 1)]
codon_edges.sort()
for i in range(len(new_edges)):
assert np.array_equal(codon_edges[i], new_edges[i])
for d in test_data:
gpm = GenotypePhenotypeMap(genotypes=d["genotypes"],
wildtype=d["wildtype"],
phenotypes=d["phenotypes"])
G = GenotypePhenotypeGraph()
G.add_gpm(gpm)
assert type(G.gpm) is GenotypePhenotypeMap
assert len(G.nodes) == len(gpm.genotypes)
for i in range(len(G.nodes)):
G.nodes[i]["genotypes"] == gpm.genotypes[i]
G.nodes[i]["phenotypes"] == gpm.phenotypes[i]
def test_read_csv(gpgraph_test):
"""Test reading from csv"""
read_gpm = GenotypePhenotypeGraph.read_csv("data/test_data_external.csv",
wildtype='RDDWKAQ')
# Test instance was created
assert isinstance(read_gpm, GenotypePhenotypeGraph)
def gpgraph_test(gpmap_base):
gpgraph_test = GenotypePhenotypeGraph(gpmap_base)
return gpgraph_test