viveksck

import random

class Markov(object):
	
	def __init__(self, open_file):
		self.cache = {}
		self.open_file = open_file
		self.words = self.file_to_words()
		self.word_size = len(self.words)
		self.database()

viveksck

"""
Three ways of computing the Hellinger distance between two discrete
probability distributions using NumPy and SciPy.
"""

import numpy as np
from scipy.linalg import norm
from scipy.spatial.distance import euclidean

viveksck

viveksck

from __future__ import division
import numpy as np
import pandas as pd
import random

def sample(data):
    sample = [random.choice(data) for _ in xrange(len(data))]
    return sample

def bootstrap_t_test(treatment, control, nboot = 1000, direction = "less"):

viveksck

from pyspark import SparkContext

import numpy as np

from sklearn.cross_validation import train_test_split, Bootstrap
from sklearn.datasets import make_classification
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier

def run(sc):

viveksck

"""
(C) Mathieu Blondel - 2010
License: BSD 3 clause

Implementation of the collapsed Gibbs sampler for
Latent Dirichlet Allocation, as described in

Finding scientifc topics (Griffiths and Steyvers)
"""

viveksck

viveksck

viveksck

def better_table(table, caption, name):
    
    start = r"""
\begin{{table}}[!htb]
\sisetup{{round-mode=places, round-precision=2}}
\caption{{{}}}\label{{table:{}}}
\centering
""".format(caption, name)
    
    end = r"\end{table}"

viveksck