michaelguia

def mapper1(_, line):
    for word in line:
        yield ((len(word), word[0]), 1)

def reducer1(key, values):
    yield key, sum(values)

def mapper2(key, value):
    length, letter = key
    yield (length, (value, letter))

michaelguia

mport threading
import time
from queue import Queue
import sys
from os import listdir
from collections import Counter

q = Queue()
directory = sys.argv[1]
files = listdir(directory)

michaelguia

from multiprocessing import Pool
from time import sleep
import numpy as np

def sum_list(numbers):
    return sum(numbers)

master_list = np.arange(100000000).reshape(2,50000000)

l1 = [3, 5, 7]

michaelguia

SUMMARY: Hierarchical cluster analysis

1. Hierarchical cluster analysis of n objects is defined by a stepwise algorithm which merges two objects at each step, the two which have the least dissimilarity.

2. Dissimilarities between clusters of objects can be defined in several ways; for example, the maximum dissimilarity (complete linkage), minimum dissimilarity (single linkage) or average dissimilarity (average linkage).

3. Either rows or columns of a matrix can be clustered – in each case we choose the

michaelguia

import pandas as pd
import unicodedata
import string
import numpy as np
from nltk.util import ngrams
from nltk.tokenize import sent_tokenize, word_tokenize
from nltk.corpus import stopwords
from nltk.stem.snowball import SnowballStemmer
docs = []
docs.append('code PYTHON code.')

michaelguia

def to_categorical(y, num_classes=None):
    """Converts a class vector (integers) to binary class matrix.
    E.g. for use with categorical_crossentropy.
    # Arguments
        y: class vector to be converted into a matrix
            (integers from 0 to num_classes).
        num_classes: total number of classes.
    # Returns
        A binary matrix representation of the input.
    """

michaelguia

def PolynomialFeatures_labeled(input_df,power):
    '''Basically this is a cover for the sklearn preprocessing function. 
    The problem with that function is if you give it a labeled dataframe, it ouputs an unlabeled dataframe with potentially
    a whole bunch of unlabeled columns. 

    Inputs:
    input_df = Your labeled pandas dataframe (list of x's not raised to any power) 
    power = what order polynomial you want variables up to. (use the same power as you want entered into pp.PolynomialFeatures(power) directly)

    Ouput: