Vivek Kulkarni viveksck

## pagerank.py
import numpy as np
from scipy.sparse import csc_matrix

def pageRank(G, s = .85, maxerr = .001):
    """
    Computes the pagerank for each of the n states.

    Used in webpage ranking and text summarization using unweighted
    or weighted transitions respectively.

## learning_curves.png

      
              4 files
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                viveksck
                / learning_curves.png
            
            
              Created
              November 22, 2013 04:19
                — forked from ogrisel/learning_curves.png
            
          
## mr_compute_gist.py
from mincepie import mapreducer, launcher
import gflags
import glob
import leargist
import numpy as np
import os
from PIL import Image
import uuid

# constant value

## gist:9473713
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()

## hellinger.py
"""
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

## Practical-Guide-to-Scientific-Computing.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                viveksck
                / Practical-Guide-to-Scientific-Computing.ipynb
            
            
              Created
              September 1, 2014 16:18
                — forked from groakat/Practical-Guide-to-Scientific-Computing.ipynb
            
          
      Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## bootstrap.py
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"):

## spark_parallel_boost.py
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):

## lda_gibbs.py
"""
(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)
"""

## fractal-dimension.py
# -----------------------------------------------------------------------------
# From https://en.wikipedia.org/wiki/Minkowski–Bouligand_dimension:
#
# In fractal geometry, the Minkowski–Bouligand dimension, also known as
# Minkowski dimension or box-counting dimension, is a way of determining the
# fractal dimension of a set S in a Euclidean space Rn, or more generally in a
# metric space (X, d).
# -----------------------------------------------------------------------------
import scipy.misc
import numpy as np
	import numpy as np
	from scipy.sparse import csc_matrix

	def pageRank(G, s = .85, maxerr = .001):
	"""
	Computes the pagerank for each of the n states.

	Used in webpage ranking and text summarization using unweighted
	or weighted transitions respectively.
	from mincepie import mapreducer, launcher
	import gflags
	import glob
	import leargist
	import numpy as np
	import os
	from PIL import Image
	import uuid

	# constant value
	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()
	"""
	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
	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"):
	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):
	"""
	(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)
	"""
	# -----------------------------------------------------------------------------
	# From https://en.wikipedia.org/wiki/Minkowski–Bouligand_dimension:
	#
	# In fractal geometry, the Minkowski–Bouligand dimension, also known as
	# Minkowski dimension or box-counting dimension, is a way of determining the
	# fractal dimension of a set S in a Euclidean space Rn, or more generally in a
	# metric space (X, d).
	# -----------------------------------------------------------------------------
	import scipy.misc
	import numpy as np