class EmbeddingNetworkBuilder:
""" Basically a wrapper around sklearns LSH forest """
def __init__(self, lsh_init=None):
if lsh_init == None:
self._lsh_forest = LSHForest(n_estimators=25, n_candidates=1000)
else:
self._lsh_forest = lsh_init
self.iw = None
self.m = None
def fit_lsh_forest(self, embedding):
self._lsh_forest.fit(embedding.m)
self._embedding = embedding
def extract_nn_network(self, nn=20):
dir_graph_mat = self._lsh_forest.kneighbors_graph(X=self._embedding.m,
n_neighbors=nn + 1)
return dir_graph_mat
def make_undirected(self, dir_graph_mat):
nodes = set(range(dir_graph_mat.shape[0]))
edges = set([])
for node_i in dir_graph_mat.shape[0]:
for node_j in dir_graph_mat[node_i].nonzero()[1]:
edges.add((node_i, node_j))
return nodes, edges
def get_forest(self):
return self._lsh_forest
def get_node_to_word(self):
return self.iw
class EmbeddingNetworkBuilder:
""" Basically a wrapper around sklearns LSH forest """
def __init__(self, lsh_init=None):
if lsh_init == None:
self._lsh_forest = LSHForest(n_estimators=25, n_candidates=1000)
else:
self._lsh_forest = lsh_init
self.iw = None
self.m = None
def fit_lsh_forest(self, embedding):
self._lsh_forest.fit(embedding.m)
self._embedding = embedding
def extract_nn_network(self, nn=20):
dir_graph_mat = self._lsh_forest.kneighbors_graph(X=self._embedding.m, n_neighbors=nn+1)
return dir_graph_mat
def make_undirected(self, dir_graph_mat):
nodes = set(range(dir_graph_mat.shape[0]))
edges = set([])
for node_i in dir_graph_mat.shape[0]:
for node_j in dir_graph_mat[node_i].nonzero()[1]:
edges.add((node_i, node_j))
return nodes, edges
def get_forest(self):
return self._lsh_forest
def get_node_to_word(self):
return self.iw
def test_graphs():
"""Smoke tests for graph methods."""
n_samples_sizes = [5, 10, 20]
n_features = 3
rng = np.random.RandomState(42)
for n_samples in n_samples_sizes:
X = rng.rand(n_samples, n_features)
lshf = LSHForest(min_hash_match=0)
lshf.fit(X)
kneighbors_graph = lshf.kneighbors_graph(X)
radius_neighbors_graph = lshf.radius_neighbors_graph(X)
assert_equal(kneighbors_graph.shape[0], n_samples)
assert_equal(kneighbors_graph.shape[1], n_samples)
assert_equal(radius_neighbors_graph.shape[0], n_samples)
assert_equal(radius_neighbors_graph.shape[1], n_samples)
def test_graphs():
# Smoke tests for graph methods.
n_samples_sizes = [5, 10, 20]
n_features = 3
rng = np.random.RandomState(42)
for n_samples in n_samples_sizes:
X = rng.rand(n_samples, n_features)
lshf = LSHForest(min_hash_match=0)
ignore_warnings(lshf.fit)(X)
kneighbors_graph = lshf.kneighbors_graph(X)
radius_neighbors_graph = lshf.radius_neighbors_graph(X)
assert_equal(kneighbors_graph.shape[0], n_samples)
assert_equal(kneighbors_graph.shape[1], n_samples)
assert_equal(radius_neighbors_graph.shape[0], n_samples)
assert_equal(radius_neighbors_graph.shape[1], n_samples)
import numpy as np
from sklearn.neighbors import NearestNeighbors, LSHForest
from igraph import Graph, EdgeSeq
from timeit import timeit
import random
random.seed(100)
#robjects.r['load']('../processed_sub_Data.RData')
print "Reading sparce matrix..."
matrix = mmread("sub_matrix")
print "Converting matrix to dense format..."
a = np.array(matrix.todense())
print a.shape
print "Initialize LSH..."
lshf = LSHForest(n_neighbors=10, random_state=1, n_estimators=10)
print "fit LSH..."
lshf.fit(a)
K = lshf.kneighbors_graph(a)
print "convert into adjacency matrix..."
K = K.toarray()
g = Graph.Adjacency(K.tolist())
es = EdgeSeq(g)
print "writing graph edgelist..."
g.write_edgelist("src_dst_lsh.csv")
