ashunigion

Project Title

One Paragraph of project description goes here

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

ashunigion

label_0 = train_data[train_labels==0]
label_1 = train_data[train_labels==1]
#it can be repeated for all the intermediate labels
#...
label_9 = train_data[train_labels==9]

ashunigion

from sklearn.cluster import KMeans

kmeans_0 = KMeans(n_clusters=10, init='k-means++',random_state=0).fit(label_0)
sample_0 = kmeans_0.cluster_centers_

kmeans_1 = KMeans(n_clusters=10, init='k-means++',random_state=0).fit(label_1)
sample_1 = kmeans_1.cluster_centers_
#the code can be repeated for all the intermediate labels
#...
kmeans_9 = KMeans(n_clusters=10, init='k-means++',random_state=0).fit(label_9)

ashunigion

proto_sample = np.concatenate((sample_0,sample_1,
                               sample_2,sample_3,
                               sample_4,sample_5,
                               sample_6,sample_7,
                               sample_8,sample_9
                              ), axis = 0
                             )

ashunigion

# generating the labels for prototyped training data
sample_0_labels = np.full((10,), 0)
sample_1_labels = np.full((10,), 1)
# similarly intermediate labels can be generated
# ...
sample_9_labels = np.full((10,), 9)

# stacking the labels into a single array
proto_labels = np.concatenate((sample_0_labels,sample_1_labels,
                               sample_2_labels,sample_3_labels,

ashunigion

# the following snippet was provided as starter code by UCSD for the course 
# Machine Learning Fundamentals on edX
def rand_prototypes(M):
    """
    Returns M randomly samples data points and corresponding labels.

    Parameters: 
    M (int): number of data points to be sampled 

    Returns: 

ashunigion

# the following code snippet was provided by UCSD for Machine Learning Fundamentals on edX
@interact_manual( M=(100,2000,100), rounds=(1,10))
def comparison(M,rounds):
  """
  Shows the mean error of both the prototyping methods.  As we randomly prototyping the data, 
  it makes sense to do it multiple times and take the mean error. 
  
  Parameters:
  M(int): number of data points to be sampled
  r(int): number of times random dataset chosen to calculate the mean error

ashunigion

import nltk
nltk.download('reuters')
from nltk.corpus import reuters

def read_corpus(category="crude"):
    """ Read files from the specified Reuter's category. And adds
        START and END to beginning and end of each document.
        
        Params:
            category (string): category name

ashunigion

# dont forget to import "pprint"
reuters_corpus = read_corpus()
pprint.pprint(reuters_corpus[:3], compact=True, width=100)

# first three document from the corpus
# [['<START>', 'japan', 'to', 'revise', 'long', '-', 'term', 'energy', 'demand', 'downwards', 'the',
#  'ministry', 'of', 'international', 'trade', 'and', 'industry', '(', 'miti', ')', 'will', 'revise',
#  'its', 'long', '-', 'term', 'energy', 'supply', '/', 'demand', 'outlook', 'by', 'august', 'to',
#  'meet', 'a', 'forecast', 'downtrend', 'in', 'japanese', 'energy', 'demand', ',', 'ministry',
#  'officials', 'said', '.', 'miti', 'is', 'expected', 'to', 'lower', 'the', 'projection', 'for',

ashunigion

def distinct_words(corpus):
    """ Determine a list of distinct words for the corpus.
        Params:
            corpus (list of list of strings): corpus of documents
        Return:
            corpus_words (list of strings): list of distinct words across the corpus, sorted (using python 'sorted' function)
            num_corpus_words (integer): number of distinct words across the corpus
    """
    corpus_words = []
    num_corpus_words = -1