def test_two_dimensional_tensor(pts):
"""Verify that the oneDimensionalCover fails for an input
with more than one dimension, and that the CubicalCover
does not."""
one_d = OneDimensionalCover()
with pytest.raises(ValueError):
one_d.fit(pts)
cubical = CubicalCover()
_ = cubical.fit(pts)
def test_cubical_fit_transform_consistent_with_OneD(filter, kind, n_intervals,
overlap_fraction):
"""Check that CubicalCover gives the same results as OneDimensionalCover,
on one-d data """
one_d = OneDimensionalCover(kind, n_intervals, overlap_fraction)
cubical = CubicalCover(kind, n_intervals, overlap_fraction)
x_one_d = one_d.fit_transform(filter)
x_cubical = cubical.fit_transform(filter)
assert_almost_equal(x_one_d, x_cubical)
def test_pipeline_cloned(X, clone_pipeline, layout_dim,
color_by_columns_dropdown):
"""Verify that the pipeline is changed on interaction if and only if
`clone_pipeline` is False (with `layout_dim` set to 2 or 3)."""
# TODO: Monitor development of the ipytest project to convert these into
# true notebook tests integrated with pytest
params = {
"cover": {
"initial": {"n_intervals": 10, "kind": "uniform",
"overlap_frac": 0.1},
"new": {"n_intervals": 15, "kind": "balanced", "overlap_frac": 0.2}
},
"clusterer": {
"initial": {"affinity": "euclidean"},
"new": {"affinity": "manhattan"}
},
"contract_nodes": {"initial": True, "new": False},
"min_intersection": {"initial": 4, "new": 1},
}
pipe = make_mapper_pipeline(
cover=CubicalCover(**params["cover"]["initial"]),
clusterer=FirstSimpleGap(**params["clusterer"]["initial"]),
contract_nodes=params["contract_nodes"]["initial"],
min_intersection=params["min_intersection"]["initial"]
)
fig = plot_interactive_mapper_graph(
pipe, X, clone_pipeline=clone_pipeline, layout_dim=layout_dim,
color_by_columns_dropdown=color_by_columns_dropdown
)
# Get relevant widgets and change their states, then check final values
for step, values in params.items():
if step in ["cover", "clusterer"]:
for param_name, initial_param_value in values["initial"].items():
new_param_value = values["new"][param_name]
widgets = _get_widgets_by_trait(fig, "description", param_name)
for w in widgets:
w.set_state({'value': new_param_value})
final_param_value_actual = \
pipe.get_mapper_params()[f"{step}__{param_name}"]
final_param_value_expected = \
initial_param_value if clone_pipeline else new_param_value
assert final_param_value_actual == final_param_value_expected
else:
initial_param_value = values["initial"]
new_param_value = values["new"]
widgets = _get_widgets_by_trait(fig, "description", step)
for w in widgets:
w.set_state({'value': new_param_value})
final_param_value_actual = \
pipe.get_mapper_params()[f"{step}"]
final_param_value_expected = \
initial_param_value if clone_pipeline else new_param_value
assert final_param_value_actual == final_param_value_expected
def Mappe(data, intervals):
filter_func = Eccentricity()
cover = CubicalCover(n_intervals=intervals, overlap_frac=0.3)
clusterer = DBSCAN()
n_jobs = 2
pipe = make_mapper_pipeline(
filter_func=filter_func,
cover=cover,
clusterer=clusterer,
verbose=False,
n_jobs=n_jobs,
)
g = pipe.fit_transform(data)
A = g.get_edgelist()
G = nx.Graph(A)
return G
def main():
directory = DOTENV_KEY2VAL["DATA_DIR"]
image_dir = directory + "/patch_92/"
diagnosis_json = "collected_diagnoses_complete.json"
(
cn_patients,
mci_patients,
ad_patients,
) = utils.get_earliest_available_diagnosis(directory + diagnosis_json)
images_all = utils.get_arrays_from_dir(
image_dir, cn_patients + mci_patients + ad_patients)
cn_patient_list = [
1 for patient in range(len(cn_patients) - 1)
] # substracting one due to unfound MRI for one CN patient
mci_patient_list = [2 for patient in range(len(mci_patients))]
ad_patient_list = [3 for patient in range(len(ad_patients))]
diags = np.array(cn_patient_list + mci_patient_list +
ad_patient_list).reshape(-1, 1)
ohe = OneHotEncoder()
labels = ohe.fit_transform(diags).toarray()
images = []
for image in images_all:
images.append(image.flatten())
images_all = np.asarray(images)
pca = PCA(n_components=440)
pca.fit(images_all)
fig, ax0 = plt.subplots(nrows=1, sharex=True, figsize=(6, 6))
ax0.plot(
np.arange(1, pca.n_components_ + 1),
pca.explained_variance_ratio_,
"+",
linewidth=2,
)
ax0.set_ylabel("PCA explained variance ratio")
ax0.legend(prop=dict(size=12))
plt.savefig(DOTENV_KEY2VAL["GEN_FIGURES_DIR"] + "elbow_plot.png")
n_components = 3
pca = PCA(n_components=n_components)
images_all_projected = pca.fit_transform(images_all)
images_all_projected = np.append(images_all_projected, labels, axis=1)
mapper_pipeline = make_mapper_pipeline(
filter_func=Projection(columns=[index for index in range(2)]),
cover=CubicalCover(n_intervals=10, overlap_frac=0.25),
clusterer=DBSCAN(eps=0.5, min_samples=5),
verbose=True,
n_jobs=4,
)
plotly_params = {"node_trace": {"marker_colorscale": "Blues"}}
fig = plot_static_mapper_graph(
mapper_pipeline,
images_all_projected,
layout_dim=3,
color_by_columns_dropdown=True,
plotly_params=plotly_params,
)
fig.write_html(DOTENV_KEY2VAL["GEN_FIGURES_DIR"] +
"mapper_2_dimensional_reduction.html")
images_all_projected = pd.DataFrame(images_all_projected)
fig = px.scatter_3d(
images_all_projected,
x=0,
y=1,
z=2,
color=3,
title="3D scatterplot of the PCA of the image data",
)
fig.write_html(DOTENV_KEY2VAL["GEN_FIGURES_DIR"] +
"scatterplot_pca_3d.html")