def test_from_weight_array(self):
mh = tm.Minhash(8, 42, 64)
a = mh.from_weight_array(
tm.VectorFloat([0.2, 0.6, 0.22, 0.26, 0.62, 0.66]))
b = mh.from_weight_array(
tm.VectorFloat([0.26, 0.6, 0.22, 0.26, 0.62, 1.0]))
assert len(a) == 128
assert round(mh.get_weighted_distance(a, b), 3) == 0.094
def test_knn_graph(self):
random.seed(42)
data = []
for _ in range(100):
row = []
for _ in range(10):
row.append(random.randint(0, 20))
data.append(tm.VectorUint(row))
mh = tm.Minhash()
lf = tm.LSHForest()
lf.batch_add(mh.batch_from_sparse_binary_array(data))
lf.index()
f = tm.VectorUint()
t = tm.VectorUint()
w = tm.VectorFloat()
lf.get_knn_graph(f, t, w, 10)
assert len(f) == 1000
assert t[0] == 0
assert t[1] == 26
assert t[2] == 36
assert t[3] == 67
assert t[4] == 33
assert t[5] == 83
def main():
""" Main function """
# Use 128 permutations to create the MinHash
enc = tm.Minhash(1024)
lf = tm.LSHForest(128, file_backed=True)
# d = 1000
# n = 1000000
d = 10000
n = 1000
# Generating some random data
start = timer()
for _ in range(n):
# data.append(tm.VectorUint(np.random.randint(0, high=2, size=d)))
lf.add(
enc.from_sparse_binary_array(
tm.VectorUint(np.random.randint(0, high=2, size=d))))
print(f"Generating the data took {(timer() - start) * 1000}ms.")
# Index the added data
start = timer()
lf.index()
print(f"Indexing took {(timer() - start) * 1000}ms.")
# Find the 10 nearest neighbors of the first entry
start = timer()
knng_from = tm.VectorUint()
knng_to = tm.VectorUint()
knng_weight = tm.VectorFloat()
_ = lf.get_knn_graph(knng_from, knng_to, knng_weight, 10)
print(f"The kNN search took {(timer() - start) * 1000}ms.")
def main():
""" Main function """
# Initialize and configure tmap
dims = 256
enc = tm.Minhash(len(DATA.columns), 42, dims)
lf = tm.LSHForest(dims * 2, 32, weighted=True)
fps = []
for _, row in DATA.iterrows():
fps.append(tm.VectorFloat(list(row)))
lf.batch_add(enc.batch_from_weight_array(fps))
lf.index()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, CFG_TMAP)
lf.clear()
legend_labels = {(1, "PRAD"), (2, "LUAD"), (3, "BRCA"), (4, "KIRC"),
(5, "COAD")}
# Create the plot
faerun = Faerun(view="front", coords=False, legend_title="")
faerun.add_scatter(
"RNASEQ",
{
"x": x,
"y": y,
"c": LABELS,
"labels": LABELS
},
colormap="tab10",
point_scale=5.0,
max_point_size=10,
shader="smoothCircle",
has_legend=True,
categorical=True,
legend_labels=legend_labels,
legend_title="Tumor Types",
)
faerun.add_tree("RNASEQ_tree", {
"from": s,
"to": t
},
point_helper="RNASEQ",
color="#666666")
faerun.plot("rnaseq")
def main():
""" Main function """
# Use 128 permutations to create the MinHash
enc = tm.Minhash(128)
lf = tm.LSHForest(128)
d = 1000
n = 10000
data = []
# Generating some random data
start = timer()
for _ in range(n):
data.append(tm.VectorUchar(np.random.randint(0, high=2, size=d)))
print(f"Generating the data took {(timer() - start) * 1000}ms.")
# Use batch_add to parallelize the insertion of the arrays
start = timer()
lf.batch_add(enc.batch_from_binary_array(data))
print(f"Adding the data took {(timer() - start) * 1000}ms.")
# Index the added data
start = timer()
lf.index()
print(f"Indexing took {(timer() - start) * 1000}ms.")
# Construct the k-nearest neighbour graph
start = timer()
knng_from = tm.VectorUint()
knng_to = tm.VectorUint()
knng_weight = tm.VectorFloat()
_ = lf.get_knn_graph(knng_from, knng_to, knng_weight, 10)
print(f"The kNN search took {(timer() - start) * 1000}ms.")
def main():
""" Main function """
# Initialize and configure tmap
dims = 1024
enc = tm.Minhash(28 * 28, 42, dims)
lf = tm.LSHForest(dims * 2, 128)
print("Converting images ...")
for image in IMAGES:
img = Image.fromarray(np.uint8(np.split(np.array(image), 28)))
buffered = BytesIO()
img.save(buffered, format="JPEG")
img_str = base64.b64encode(buffered.getvalue())
IMAGE_LABELS.append("data:image/bmp;base64," +
str(img_str).replace("b'", "").replace("'", ""))
tmp = []
for _, image in enumerate(IMAGES):
tmp.append(tm.VectorFloat(image / 255))
print("Running tmap ...")
start = timer()
lf.batch_add(enc.batch_from_weight_array(tmp))
lf.index()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, CFG)
print("tmap: " + str(timer() - start))
legend_labels = [
(0, "T-shirt/top"),
(1, "Trouser"),
(2, "Pullover"),
(3, "Dress"),
(4, "Coat"),
(5, "Sandal"),
(6, "Shirt"),
(7, "Sneaker"),
(8, "Bag"),
(9, "Ankle boot"),
]
faerun = Faerun(clear_color="#111111", view="front", coords=False)
faerun.add_scatter(
"FMNIST",
{
"x": x,
"y": y,
"c": LABELS,
"labels": IMAGE_LABELS
},
colormap="tab10",
shader="smoothCircle",
point_scale=2.5,
max_point_size=10,
has_legend=True,
categorical=True,
legend_labels=legend_labels,
)
faerun.add_tree("FMNIST_tree", {
"from": s,
"to": t
},
point_helper="FMNIST",
color="#666666")
faerun.plot("fmnist", template="url_image")