cnh

#1. Loop through all the text files in the directory and store contents in a giant list

import os, glob
path_files_texts = []
path_to_dir_of_path_reports = "/path/to/txt/files"

# Loop through all the text files in the directory and store contents in a giant list
for file in glob.glob(os.path.join(path_to_dir_of_path_reports, "*.txt")):
    # Open each file and read its contents into a string
    with open(file, "r" , encoding='cp1252') as f:

cnh

cnh

cnh

# If you come from bash you might have to change your $PATH.
# export PATH=$HOME/bin:/usr/local/bin:$PATH

# Path to your oh-my-zsh installation.
export ZSH="/Users/xeadmin/.oh-my-zsh"

# Set name of the theme to load --- if set to "random", it will
# load a random theme each time oh-my-zsh is loaded, in which case,
# to know which specific one was loaded, run: echo $RANDOM_THEME
# See https://github.com/ohmyzsh/ohmyzsh/wiki/Themes

cnh

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 28 12:56:51 2017

@author: tp53
'''

'''
http://biopython.org/DIST/docs/api/Bio.SeqUtils-module.html

cnh

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 21 08:29:57 2017

@author: tp53
"""

import pandas as pd
import numpy as np

cnh

#import data manipulation modules
import numpy as np
import pandas as pd

from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import train_test_split

from keras.models import Sequential, load_model #to save , load and persist models
from keras.layers import Activation
from keras.optimizers import SGD

cnh

#import data manipulation modules
import numpy as np
import pandas as pd

from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import train_test_split

from keras.models import Sequential, load_model #to save , load and persist models
from keras.layers import Activation
from keras.optimizers import SGD

cnh

1. General Background and Overview

• Probabilistic Data Structures for Web Analytics and Data Mining : A great overview of the space of probabilistic data structures and how they are used in approximation algorithm implementation.
• Models and Issues in Data Stream Systems
• Philippe Flajolet’s contribution to streaming algorithms : A presentation by Jérémie Lumbroso that visits some of the hostorical perspectives and how it all began with Flajolet
• Approximate Frequency Counts over Data Streams by Gurmeet Singh Manku & Rajeev Motwani : One of the early papers on the subject.
• [Methods for Finding Frequent Items in Data Streams](http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.187.9800&rep

cnh

#!/usr/bin/env python
# encoding: utf-8

import tweepy #https://github.com/tweepy/tweepy
import csv

#Twitter API credentials
consumer_key = ""
consumer_secret = ""
access_key = ""