def get_training_data(vectors_filename, vocab_filename, vocab_thresh):
bigrams_vocab = load_bigrams(vocab_filename, vocab_thresh)
word_vectors = word_vecs.load(vectors_filename)
n = 300
N = len(bigrams_vocab)
# Construct matrix B row-wise
print 'Constructing matrix B row-wise'
B = np.zeros(shape=(N, 2 * n))
for idx, label in enumerate(bigrams_vocab):
b_1 = word_vectors[label.split('_')[0]]
b_2 = word_vectors[label.split('_')[1]]
row = np.concatenate((b_1, b_2))
B[idx] = row
# if idx > 5000:
# break
# B = np.matrix(B)
# Construct Y Matrix (an individual column from this will make for a y-vector)
print 'Constructing matrix Y row-wise'
Y = np.zeros(shape=(N, n))
for idx, label in enumerate(bigrams_vocab):
row = word_vectors[label]
Y[idx] = row
# if idx > 5000:
# break
Y = np.matrix(Y) # turn this bad boy into a matrix
# Cut off some rows...
# B = B[0:10]
# Y = Y[0:10]
return B, Y
def train(vectors_filename, vocab_filename, vocab_thresh):
bigrams_vocab = load_bigrams(vocab_filename, vocab_thresh)
word_vectors = word_vecs.load(vectors_filename)
n = 50
N = len(bigrams_vocab)
# Construct matrix B row-wise
print 'Constructing matrix B row-wise'
B = np.zeros(shape=(N, 2 * n))
for idx, label in enumerate(bigrams_vocab):
b_1 = word_vectors[label.split('_')[0]]
b_2 = word_vectors[label.split('_')[1]]
row = np.concatenate((b_1, b_2))
B[idx] = row
B = np.matrix(B)
print 'Computing pseudoinverse'
B_inv = np.linalg.pinv(B)
# Construct Y Matrix (an individual column from this will make for a y-vector)
print 'Constructing matrix Y row-wise'
Y = np.zeros(shape=(N, n))
for idx, label in enumerate(bigrams_vocab):
row = word_vectors[label]
Y[idx] = row
Y = np.matrix(Y)
# Recover linear approximation matrix A row-wise
print 'Recovering linear approximation matrix A row-wise'
global A # mark A as global -- we are gonna change it (John: how am I supposed to do this with nice class variables?!)
A = np.zeros(shape=(n, 2 * n))
for i in range(n): # 0..n-1
y = Y[:, i]
a_i = B_inv * y
A[i] = np.transpose(a_i)
def train(vectors_filename, vocab_filename, vocab_thresh):
bigrams_vocab = load_bigrams(vocab_filename, vocab_thresh);
word_vectors = word_vecs.load(vectors_filename);
n = 50
N = len(bigrams_vocab)
# Construct matrix B row-wise
print 'Constructing matrix B row-wise'
B = np.zeros(shape=(N,2*n))
for idx, label in enumerate(bigrams_vocab):
b_1 = word_vectors[label.split('_')[0]]
b_2 = word_vectors[label.split('_')[1]]
row = np.concatenate((b_1,b_2))
B[idx] = row
B = np.matrix(B)
print 'Computing pseudoinverse'
B_inv = np.linalg.pinv(B)
# Construct Y Matrix (an individual column from this will make for a y-vector)
print 'Constructing matrix Y row-wise'
Y = np.zeros(shape=(N,n))
for idx, label in enumerate(bigrams_vocab):
row = word_vectors[label]
Y[idx] = row
Y = np.matrix(Y)
# Recover linear approximation matrix A row-wise
print 'Recovering linear approximation matrix A row-wise'
global A # mark A as global -- we are gonna change it (John: how am I supposed to do this with nice class variables?!)
A = np.zeros(shape=(n,2*n))
for i in range(n): # 0..n-1
y = Y[:,i]
a_i = B_inv*y
A[i] = np.transpose(a_i)
def get_training_data(vectors_filename, vocab_filename, vocab_thresh):
bigrams_vocab = load_bigrams(vocab_filename, vocab_thresh);
word_vectors = word_vecs.load(vectors_filename);
n = 300
N = len(bigrams_vocab)
# Construct matrix B row-wise
print 'Constructing matrix B row-wise'
B = np.zeros(shape=(N,2*n))
for idx, label in enumerate(bigrams_vocab):
b_1 = word_vectors[label.split('_')[0]]
b_2 = word_vectors[label.split('_')[1]]
row = np.concatenate((b_1,b_2))
B[idx] = row
# if idx > 5000:
# break
# B = np.matrix(B)
# Construct Y Matrix (an individual column from this will make for a y-vector)
print 'Constructing matrix Y row-wise'
Y = np.zeros(shape=(N,n))
for idx, label in enumerate(bigrams_vocab):
row = word_vectors[label]
Y[idx] = row
# if idx > 5000:
# break
Y = np.matrix(Y) # turn this bad boy into a matrix
# Cut off some rows...
# B = B[0:10]
# Y = Y[0:10]
return B, Y
#!/usr/bin/env python
import numpy as np
import load_word_vecs as word_vecs
from sklearn.decomposition import PCA
# import matplotlib.pyplot as plt
# from mpl_toolkits.mplot3d import Axes3D
import test_bigrams as tb
import matplotlib
import pylab as pl
import train_neural_network as tnn
if __name__ == '__main__':
vecs = word_vecs.load("../data/vectors.txt")
labels, wordVecsMatrix = word_vecs.get_matrix(vecs)
pca = PCA(n_components=2)
# pca.fit(wordVecsMatrix);
# reduced_X = pca.transform(wordVecsMatrix)
# print "Running PCA"
# pca = PCA(n_components=2)
# pca.fit(wordVecsMatrix);
# reduced_X = pca.transform(wordVecsMatrix)
# fig = pl.figure()
# ax = fig.add_subplot(111, projection='3d')
#plot full data
#!/usr/bin/env python
import numpy as np
import load_word_vecs as word_vecs
import bh_tsne.bhtsne as tsne
if __name__ == '__main__':
labels, wordVecsMatrix = word_vecs.get_matrix(word_vecs.load("../data/vectors.txt"))
# #runs tsne on wordVecsMatrix (change if we want to just look at some subset of the bigrams)
points = tsne.bh_tsne(wordVecsMatrix);
# np.save("../data/tsne_coordinates", points);
#!/usr/bin/env python
import numpy as np
import load_word_vecs as word_vecs
if __name__ == '__main__':
vecs = word_vecs.load("../../glove/vectors.txt")
#!/usr/bin/env python
import numpy as np
import load_word_vecs as word_vecs
from sklearn.decomposition import PCA
# import matplotlib.pyplot as plt
# from mpl_toolkits.mplot3d import Axes3D
import test_bigrams as tb
import matplotlib
import pylab as pl
import train_neural_network as tnn
if __name__ == '__main__':
vecs = word_vecs.load("../data/vectors.txt")
labels, wordVecsMatrix = word_vecs.get_matrix(vecs)
pca = PCA(n_components=2)
# pca.fit(wordVecsMatrix);
# reduced_X = pca.transform(wordVecsMatrix)
# print "Running PCA"
# pca = PCA(n_components=2)
# pca.fit(wordVecsMatrix);
# reduced_X = pca.transform(wordVecsMatrix)
# fig = pl.figure()
# ax = fig.add_subplot(111, projection='3d')
#plot full data
# ax.scatter(reduced_X[:, 0], reduced_X[:, 1], reduced_X[:, 2])
# plt.show()
#!/usr/bin/env python
import numpy as np
import load_word_vecs as word_vecs
if __name__ == '__main__':
vecs = word_vecs.load("../../glove/vectors.txt")
