mjbommar

'''
@author Michael J Bommarito II
@date Feb 26, 2011
@license Simplified BSD, (C) 2011.

This script demonstrates how to use Python to archive historical tweets.
'''

import codecs
import csv

mjbommar

# @author: Michael J Bommarito II
# @date: Feb 21, 2011
# @email: [email protected]
# @packages: ggplot2

library(ggplot2)

setwd('/data/workspace/blog/wiunion/')

# Load and pre-process #tweets_wiunion

mjbommar

'''
@author Michael J Bommarito II
@contact [email protected]
@date Feb 21, 2011
@license Simplified BSD, (C) 2011.

Plot the network of the first 1000 #cn220 tweets with igraph and cairo.
'''

import cairo

mjbommar

#@author Michael J Bommarito
#@contact [email protected]
#@date Feb 20, 2011
#@ip Simplified BSD, (C) 2011.
# This is a simple example of an R script that will retrieve
# public tweets from a given hashtag.

library(RJSONIO)

# This function loads stored tag data to determine the current max_id.

mjbommar

# @author: Michael J Bommarito II
# @date: Feb 20, 2011
# @email: [email protected]
# @packages: gridExtra, ggplot2

library(gridExtra)
library(ggplot2)

setwd('/data/workspace/blog/cn220/')

mjbommar

#@author Michael J Bommarito II
#@date Feb 16, 2011

library(tm)

# Load the tweets
tweets <- unique(read.table('data/tweets_25bahman.csv', sep="\t", quote="", comment.char="", header=FALSE, nrows=100000, stringsAsFactors=FALSE))
names(tweets) <- c("id", "date", "user", "text")

# Build the corpus and then apply the tm pre-processing methods

mjbommar

'''
@author Michael J Bommarito II
@date Feb 16, 2011
'''

import codecs
import dateutil.parser
import multiprocessing
import nltk

mjbommar

import csv
import datetime
import dateutil.parser
import lxml, lxml.etree
import urllib2

# Setup date-related variables
today = datetime.date.today()
todayString = today.strftime('%m/%d/%Y')
rangeString = '20050825_{0}'.format(today.strftime('%Y%m%d'))

mjbommar

%% Initialize
clear all;
startDate = datenum('2005-08-25');
endDate = datenum('2010-10-20');
dateRange = busdays(startDate, endDate);

%% Load SPY data
csvFile = fopen('data/SPY.csv', 'r');
csvFields = textscan(csvFile, '%s %f %f %f %f %f %f',-1,'delimiter',',','HeaderLines',1);
fclose(csvFile);

mjbommar

import csv
import dateutil.parser
import lxml, lxml.etree

rangeString = '20050825_20101025'
xmlRoot = lxml.etree.parse("data/pomo_{0}.xml".format(rangeString)).getroot()
xmlData = xmlRoot.getchildren()[1]

pomoData = []