venuktan

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

import java.io.InputStream;
import java.net.URI;

/**
 * Created with IntelliJ IDEA.

venuktan

/*
Thierry Bertin-Mahieux (2010) Columbia University
tb2332@columbia.edu


This code contains a set of getters functions to access the fields
from an HDF5 song file (regular file with one song or summary file
with many songs) in Java.
The goal is to reproduce the Python getters behaviour.

venuktan

import scipy as S

def coo_submatrix_pull(matr, rows, cols):
    """
    Pulls out an arbitrary i.e. non-contiguous submatrix out of
    a sparse.coo_matrix. 
    """
    if type(matr) != S.sparse.coo_matrix:
        raise TypeError('Matrix must be sparse COOrdinate format')
    

venuktan

from __future__ import print_function

from sklearn.datasets import fetch_20newsgroups
from sklearn.decomposition import TruncatedSVD
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import HashingVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import Normalizer
from sklearn import metrics

venuktan

def splitData(df, trainPerc=0.6, cvPerc=0.2, testPerc=0.2):
    """
    return: training, cv, test
            (as pandas dataframes)
    params:
              df: pandas dataframe
       trainPerc: float | percentage of data for trainin set (default=0.6
          cvPerc: float | percentage of data for cross validation set (default=0.2)
        testPerc: float | percentage of data for test set (default=0.2)
                  (trainPerc + cvPerc + testPerc must equal 1.0)

venuktan

import numpy as np

def Markov(p, s, steps):
    for i in range(steps):
        s = s * p
        print s
    return s

p = np.matrix('.5, .5, 0, 0, 0, 0; .4, .1, .5, 0, 0, 0; 0, .3, .2, .5, 0, 0; 0, 0, .2, .3, .5, 0; 0, 0, 0, .1, .4, .5; 0, 0, 0, 0, 0, 1')
s = np.matrix('1, 0, 0, 0, 0, 0')

venuktan

d1={"foo": 3, "baz": -1, "bar": 5}
d2={"foo": 3, "ven": 10, "bar": 5}
d_1_2= dict(list(d1.items()) + list(d2.items()))

dict([[k, d2.get(k, 0)] for k in d_1_2] )#right outer join
dict([[k, d1.get(k, 0)] for k in d_1_2] )#left outer join

venuktan

import numpy as np

def sigmoid(x):
    return 1.0/(1.0 + np.exp(-x))

def sigmoid_prime(x):
    return sigmoid(x)*(1.0-sigmoid(x))

def tanh(x):
    return np.tanh(x)

venuktan

def PrintException():
    exc_type, exc_obj, tb = sys.exc_info()
    f = tb.tb_frame
    lineno = tb.tb_lineno
    filename = f.f_code.co_filename
    linecache.checkcache(filename)
    line = linecache.getline(filename, lineno, f.f_globals)
    print 'EXCEPTION IN ({}, LINE {} "{}"): {}'.format(filename, lineno, line.strip(), exc_obj)

venuktan

import numpy
from nearpy import Engine
from nearpy.hashes import RandomBinaryProjections, HashPermutationMapper, HashPermutations
from nearpy.distances import CosineDistance
from nearpy.filters.nearestfilter import NearestFilter
from nearpy.storage import RedisStorage
import glob
import time 
from redis import Redis