def test_precomputed_with_pca():
with assert_warns_message(
RuntimeWarning,
"n_pca cannot be given on a precomputed graph. Setting n_pca=None",
):
build_graph(squareform(pdist(data)), precomputed="distance", n_pca=20)
def test_build_landmark_with_too_many_landmarks():
build_graph(data, n_landmark=len(data))
def test_verbose():
print()
print("Verbose test: Landmark")
build_graph(data, decay=None, n_landmark=500, verbose=True).landmark_op
def test_balltree_cosine():
with assert_warns_message(
UserWarning,
"Metric cosine not valid for `sklearn.neighbors.BallTree`. Graph instantiation may be slower than normal.",
):
build_graph(data, n_pca=20, decay=10, distance="cosine", thresh=1e-4)
def test_bandwidth_no_decay():
with assert_warns_message(
UserWarning, "`bandwidth` is not used when `decay=None`."
):
build_graph(data, n_pca=20, decay=None, bandwidth=3, thresh=1e-4)
def test_duplicate_data():
with assert_warns_regex(
RuntimeWarning,
r"Detected zero distance between samples ([0-9and,\s]*). Consider removing duplicates to avoid errors in downstream processing.",
):
build_graph(np.vstack([data, data[:10]]), n_pca=20, decay=10, thresh=1e-4)
def test_verbose():
print()
print("Verbose test: kNN")
build_graph(data, decay=None, verbose=True)
def test_badstring_rank_threshold():
with assert_raises_message(
ValueError, "rank_threshold must be positive float or 'auto'."
):
build_graph(data, n_pca=True, rank_threshold="foobar")
def test_negative_rank_threshold():
with assert_raises_message(
ValueError, "rank_threshold must be positive float or 'auto'."
):
build_graph(data, n_pca=True, rank_threshold=-1)
def test_uncastable_n_pca():
with assert_raises_message(
ValueError,
"n_pca was not an instance of numbers.Number, could not be cast to False, and not None. Please supply an integer 0 <= n_pca < min(n_samples,n_features) or None",
):
build_graph(data, n_pca=[])
def test_negative_n_pca():
with assert_raises_message(
ValueError,
"n_pca cannot be negative. Please supply an integer 0 <= n_pca < min(n_samples,n_features) or None",
):
build_graph(data, n_pca=-1)
def test_badstring_n_pca():
with assert_raises_message(
ValueError,
"n_pca must be an integer 0 <= n_pca < min(n_samples,n_features), or in [None, False, True, 'auto'].",
):
build_graph(data, n_pca="foobar")
def test_0_n_pca():
assert build_graph(data, n_pca=0).n_pca is None
assert build_graph(data, n_pca=False).n_pca is None
def test_pandas_dataframe():
G = build_graph(pd.DataFrame(data))
assert isinstance(G, graphtools.base.BaseGraph)
assert isinstance(G.data, np.ndarray)
def test_build_knn_with_precomputed():
with assert_raises_message(
ValueError,
"kNNGraph does not support precomputed values. Use `graphtype='exact'` or `precomputed=None`",
):
build_graph(data, n_pca=None, graphtype="knn", precomputed="distance")
def test_sample_idx_and_precomputed():
build_graph(data,
n_pca=None,
sample_idx=np.arange(10),
precomputed='distance')
def test_build_knn_with_sample_idx():
with assert_raises_message(
ValueError,
"kNNGraph does not support batch correction. Use `graphtype='mnn'` or `sample_idx=None`",
):
build_graph(data, graphtype="knn", sample_idx=np.arange(len(data)))
def test_sample_idx_wrong_length():
build_graph(data, graphtype='mnn', sample_idx=np.arange(10))
def test_duplicate_data_many():
with assert_warns_regex(
RuntimeWarning,
"Detected zero distance between ([0-9]*) pairs of samples. Consider removing duplicates to avoid errors in downstream processing.",
):
build_graph(np.vstack([data, data[:21]]), n_pca=20, decay=10, thresh=1e-4)
def test_sample_idx_unique():
build_graph(data,
graph_class=graphtools.graphs.MNNGraph,
sample_idx=np.ones(len(data)))
def test_set_params():
G = build_graph(data, decay=None)
assert G.get_params() == {
"n_pca": 20,
"random_state": 42,
"kernel_symm": "+",
"theta": None,
"anisotropy": 0,
"knn": 3,
"knn_max": None,
"decay": None,
"bandwidth": None,
"bandwidth_scale": 1,
"distance": "euclidean",
"thresh": 0,
"n_jobs": -1,
"verbose": 0,
}, G.get_params()
G.set_params(n_jobs=4)
assert G.n_jobs == 4
assert G.knn_tree.n_jobs == 4
G.set_params(random_state=13)
assert G.random_state == 13
G.set_params(verbose=2)
assert G.verbose == 2
G.set_params(verbose=0)
with assert_raises_message(
ValueError, "Cannot update knn. Please create a new graph"
):
G.set_params(knn=15)
with assert_raises_message(
ValueError, "Cannot update knn_max. Please create a new graph"
):
G.set_params(knn_max=15)
with assert_raises_message(
ValueError, "Cannot update decay. Please create a new graph"
):
G.set_params(decay=10)
with assert_raises_message(
ValueError, "Cannot update distance. Please create a new graph"
):
G.set_params(distance="manhattan")
with assert_raises_message(
ValueError, "Cannot update thresh. Please create a new graph"
):
G.set_params(thresh=1e-3)
with assert_raises_message(
ValueError, "Cannot update theta. Please create a new graph"
):
G.set_params(theta=0.99)
with assert_raises_message(
ValueError, "Cannot update kernel_symm. Please create a new graph"
):
G.set_params(kernel_symm="*")
with assert_raises_message(
ValueError, "Cannot update anisotropy. Please create a new graph"
):
G.set_params(anisotropy=0.7)
with assert_raises_message(
ValueError, "Cannot update bandwidth. Please create a new graph"
):
G.set_params(bandwidth=5)
with assert_raises_message(
ValueError, "Cannot update bandwidth_scale. Please create a new graph"
):
G.set_params(bandwidth_scale=5)
G.set_params(
knn=G.knn,
decay=G.decay,
thresh=G.thresh,
distance=G.distance,
theta=G.theta,
anisotropy=G.anisotropy,
kernel_symm=G.kernel_symm,
)
def test_sample_idx_none():
build_graph(data, graphtype='mnn', sample_idx=None)
def test_knnmax_too_large():
with assert_warns_message(
UserWarning,
"Cannot set knn_max (9) to be less than knn (10). Setting knn_max=10",
):
build_graph(data, n_pca=20, decay=10, knn=10, knn_max=9, thresh=1e-4)
def test_build_mnn_with_precomputed():
build_graph(data, n_pca=None, graphtype='mnn', precomputed='distance')
def test_knn_no_knn_no_bandwidth():
with assert_raises_message(
ValueError, "Either `knn` or `bandwidth` must be provided."
):
build_graph(data, graphtype="knn", knn=None, bandwidth=None, thresh=1e-4)
def test_knn_graph_invalid_symm():
with assert_raises_message(
ValueError,
"kernel_symm 'invalid' not recognized. Choose from '+', '*', 'mnn', or 'none'.",
):
build_graph(data, graphtype="knn", knn=5, thresh=1e-4, kernel_symm="invalid")
def test_build_landmark_with_too_few_points():
build_graph(data[:50], n_landmark=25, n_svd=100)
def test_build_knn_with_exact_alpha():
with assert_raises_message(
ValueError,
"Cannot instantiate a kNNGraph with `decay=None`, `thresh=0` and `knn_max=None`. Use a TraditionalGraph instead.",
):
build_graph(data, graphtype="knn", decay=10, thresh=0)
def test_build_landmark_with_too_few_points():
with assert_warns_message(
RuntimeWarning,
"n_svd (100) >= n_samples (50) Consider using kNNGraph or lower n_svd",
):
build_graph(data[:50], n_landmark=25, n_svd=100)
def test_fractional_n_pca():
with assert_warns_message(
RuntimeWarning, "Cannot perform PCA to fractional 1.5 dimensions. Rounding to 2"
):
build_graph(data, n_pca=1.5)
