utils.py

import numpy as np
import numpy.random as npr
from sklearn.manifold import TSNE
import pandas as pd 
import matplotlib.pyplot as plt

def alias_setup(probs):
    K       = len(probs)
    q       = np.zeros(K)
    J       = np.zeros(K, dtype=np.int)

    # Sort the data into the outcomes with probabilities
    # that are larger and smaller than 1/K.
    smaller = []
    larger  = []
    for kk, prob in enumerate(probs):
        q[kk] = K*prob
        if q[kk] < 1.0:
            smaller.append(kk)
        else:
            larger.append(kk)

    # Loop though and create little binary mixtures that
    # appropriately allocate the larger outcomes over the
    # overall uniform mixture.
    while len(smaller) > 0 and len(larger) > 0:
        small = smaller.pop()
        large = larger.pop()

        J[small] = large
        q[large] = q[large] - (1.0 - q[small])

        if q[large] < 1.0:
            smaller.append(large)
        else:
            larger.append(large)

    return J, q

def alias_draw(J, q):
    K  = len(J)

    # Draw from the overall uniform mixture.
    kk = int(np.floor(npr.rand()*K))

    # Draw from the binary mixture, either keeping the
    # small one, or choosing the associated larger one.
    if npr.rand() < q[kk]:
        return kk
    else:
        return J[kk]

def visualize(vocab,embeddings):
    """
    plot a 2d t-sne of the generated embeddings
    
    Arguments:
        embeddings {array} -- vector with n-dimension features for each point
    """
    #tsne = TSNE(n_components = 2,random_state = 0)
    #X_tsne = tsne.fit_transform(embeddings)
    df = pd.DataFrame(embeddings,index=vocab,columns = ['x','y'])
    fig = plt.figure()
    ax = fig.add_subplot(1, 1, 1)

    ax.scatter(df['x'], df['y'])
    for word, pos in df.iterrows():
        ax.annotate(word, pos)
    plt.show()