def main():
""" Main function """
enc = tm.Minhash()
mh_a = enc.from_binary_array(tm.VectorUchar([1, 1, 1, 1, 0, 1, 0, 1, 1,
0]))
mh_b = enc.from_binary_array(tm.VectorUchar([1, 0, 1, 1, 0, 1, 1, 0, 1,
0]))
mh_c = enc.from_binary_array(tm.VectorUchar([1, 0, 1, 1, 1, 1, 1, 0, 1,
0]))
dist_a_b = enc.get_distance(mh_a, mh_b)
dist_b_c = enc.get_distance(mh_b, mh_c)
print(dist_a_b)
print(dist_b_c)
def main():
""" Main function """
# Use 128 permutations to create the MinHash
enc = tm.Minhash(128)
lf = tm.LSHForest(128)
d = 10000
n = 1000
data = []
# Generating some random data
start = timer()
for i 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.")
# The configuration for the MST plot
# Distribute the tree more evenly
cfg = tm.LayoutConfiguration()
cfg.sl_scaling_min = 1
cfg.sl_scaling_max = 1
cfg.node_size = 1 / 50
# Construct the k-nearest neighbour graph
start = timer()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, config=cfg)
print(f"layout_from_lsh_forest took {(timer() - start) * 1000}ms.")
# Plot spanning tree layout
start = timer()
for i in range(len(s)):
plt.plot(
[x[s[i]], x[t[i]]],
[y[s[i]], y[t[i]]],
"r-",
linewidth=1.0,
alpha=0.5,
zorder=1,
)
plt.scatter(x, y, s=0.1, zorder=2)
plt.tight_layout()
plt.savefig("lsh_forest_knng_mpl.png")
print(f"Plotting using matplotlib took {(timer() - start) * 1000}ms.")
def main():
""" Main function """
# Initialize and configure tmap
dims = 1024
enc = tm.Minhash(dims)
lf = tm.LSHForest(dims, 128)
print("Converting images ...")
for image in tqdm(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):
avg = sum(image) / sum([1 if x > 0 else 0 for x in image])
tmp.append(tm.VectorUchar([1 if x >= avg else 0 for x in image]))
# tmp.append(tm.VectorUint(image))
print("Running tmap ...")
lf.batch_add(enc.batch_from_binary_array(tmp))
# LF.batch_add(ENC.batch_from_int_weight_array(tmp))
lf.index()
x, y, s, t, _ = tm.layout_from_lsh_forest(lf, CFG)
faerun = Faerun(clear_color="#111111", view="front", coords=False)
faerun.add_scatter(
"MNIST",
{
"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,
)
faerun.add_tree("MNIST_tree", {
"from": s,
"to": t
},
point_helper="MNIST",
color="#666666")
faerun.plot("i3d-tmap-mnist", path="outputs", template="url_image")
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_from_binary_array to encode the data
start = timer()
data = enc.batch_from_binary_array(data)
print(f"Encoding the data took {(timer() - start) * 1000}ms.")
# Use batch_add to parallelize the insertion of the arrays
start = timer()
lf.batch_add(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.")
# Find the 10 nearest neighbors of the first entry
start = timer()
_ = lf.query_linear_scan_by_id(0, 10)
print(f"The kNN search took {(timer() - start) * 1000}ms.")
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 test_from_binary_array(self):
mh = tm.Minhash(8)
a = mh.from_binary_array(tm.VectorUchar([1, 1, 1, 1, 0, 1]))
b = mh.from_binary_array(tm.VectorUchar([1, 1, 1, 1, 1, 0]))
assert len(a) == 8
assert mh.get_distance(a, b) == 0.125