Daniel dalamar66

## currency.png

      
              6 files
            
          
              0 forks
            
          
                0 comments
              
            
              0 stars
            
          
                dalamar66
                / currency.png
            
            
              Created
              January 25, 2017 16:12
                — forked from mrbcuda/currency.png
            
              
                A mashup of financial turbulence and regime switching examples having missing bits into a standalone example without missing bits. Uses sources from Quantivity and Systematic Investor blogs as well as the CRAN RHmm and TTR packages. Uses quantmod and FRED as a data source. The turbulence calculation clearly is not the same as referenced original…
              
          
## Cumulative Utility of Household Debt.R
library(quantmod)
getSymbols(c("GDP", "CMDEBT"), src="FRED")
plot(cumsum(na.omit(diff(GDP) - diff(CMDEBT))))

## svm_rsi_trend.R
# Some code to asses an SVM with a two-dimensional feature space:
# trend (price - simple moving average) and relative strength index.
# The code is an adaptation of the code found in the following linkedin post:
# "Trading the RSI using a Support Vector Machine"
# "https://www.linkedin.com/pulse/article/20141103165037-172934333-trading-the-rsi-using-a-support-vector-machine"

# Settings
sma.window = 50 # Number of observations in simple moving average.
rsi.window = 3  # Number of observation in relative strength index (RSI)

## keras.py
""" From:  http://danielhnyk.cz/predicting-sequences-vectors-keras-using-rnn-lstm/ """
from keras.models import Sequential
from keras.layers.core import TimeDistributedDense, Activation, Dropout
from keras.layers.recurrent import GRU
import numpy as np

def _load_data(data, steps = 40):
    docX, docY = [], []
    for i in range(0, data.shape[0]/steps-1):
        docX.append(data[i*steps:(i+1)*steps,:])

## keras_prediction.py
import pandas as pd
from random import random

flow = (list(range(1,10,1)) + list(range(10,1,-1)))*1000
pdata = pd.DataFrame({"a":flow, "b":flow})
pdata.b = pdata.b.shift(9)
data = pdata.iloc[10:] * random()  # some noise

import numpy as np

## twttr_sentiment_bench.R
# Short scripts for testing three different sentiment classifiers on tweets,
# acquiring the tweets used for testing,
# calculating systems' precision, recall and F-measures.


require(RCurl)   # For downloading file from a given URL.
require(twitteR) # Used for the 'twitter' class.
require(sentiment) # For bayes and voter classifiers.
source("sent140.R")  # Used for the Sentiment 140 API. Can be downloaded from here:
# https://github.com/okugami79/sentiment140/blob/master/R/sentiment.r

## sentiment_score_simple.R
# Code to fetch news streams from 5 live sources, process the streams and text
# and apply a simple sentiment scoring algorigthm.
#
# A writeup of the analysis can be found here:
# https://www.linkedin.com/pulse/article/20141109035942-34768479-r-sentiment-scoring-hsbc-w-harvard-general-inquirer

# Define the packages we want to load:
packs = c(
  "tm",                         # Text mining
  "tm.plugin.webmining",        # Web-source plugin for text mining

## svm_rsi_trend.R
# Some code to asses an SVM with a two-dimensional feature space:
# trend (price - simple moving average) and relative strength index.
# The code is an adaptation of the code found in the following linkedin post:
# "Trading the RSI using a Support Vector Machine"
# "https://www.linkedin.com/pulse/article/20141103165037-172934333-trading-the-rsi-using-a-support-vector-machine"

# Settings
sma.window = 50 # Number of observations in simple moving average.
rsi.window = 3  # Number of observation in relative strength index (RSI)

## findBestArma.R
findBestArma = function(
   xx,
   minOrder=c(0,0),
   maxOrder=c(5,5),
   trace=FALSE )
{
   bestAic = 1e9
   len = NROW( xx )
   for( p in minOrder[1]:maxOrder[1] ) for( q in minOrder[2]:maxOrder[2] )
   {

## armaSearch.R
armaSearch = function(
   xx,
   minOrder=c(0,0),
   maxOrder=c(5,5),
   trace=FALSE )
{
   bestAic = 1e9
   len = NROW( xx )
   for( p in minOrder[1]:maxOrder[1] ) for( q in minOrder[2]:maxOrder[2] )
   {
	library(quantmod)
	getSymbols(c("GDP", "CMDEBT"), src="FRED")
	plot(cumsum(na.omit(diff(GDP) - diff(CMDEBT))))
	# Some code to asses an SVM with a two-dimensional feature space:
	# trend (price - simple moving average) and relative strength index.
	# The code is an adaptation of the code found in the following linkedin post:
	# "Trading the RSI using a Support Vector Machine"
	# "https://www.linkedin.com/pulse/article/20141103165037-172934333-trading-the-rsi-using-a-support-vector-machine"

	# Settings
	sma.window = 50 # Number of observations in simple moving average.
	rsi.window = 3 # Number of observation in relative strength index (RSI)
	""" From: http://danielhnyk.cz/predicting-sequences-vectors-keras-using-rnn-lstm/ """
	from keras.models import Sequential
	from keras.layers.core import TimeDistributedDense, Activation, Dropout
	from keras.layers.recurrent import GRU
	import numpy as np

	def _load_data(data, steps = 40):
	docX, docY = [], []
	for i in range(0, data.shape[0]/steps-1):
	docX.append(data[isteps:(i+1)steps,:])
	import pandas as pd
	from random import random

	flow = (list(range(1,10,1)) + list(range(10,1,-1)))*1000
	pdata = pd.DataFrame({"a":flow, "b":flow})
	pdata.b = pdata.b.shift(9)
	data = pdata.iloc[10:] * random() # some noise

	import numpy as np
	# Short scripts for testing three different sentiment classifiers on tweets,
	# acquiring the tweets used for testing,
	# calculating systems' precision, recall and F-measures.


	require(RCurl) # For downloading file from a given URL.
	require(twitteR) # Used for the 'twitter' class.
	require(sentiment) # For bayes and voter classifiers.
	source("sent140.R") # Used for the Sentiment 140 API. Can be downloaded from here:
	# https://github.com/okugami79/sentiment140/blob/master/R/sentiment.r
	# Code to fetch news streams from 5 live sources, process the streams and text
	# and apply a simple sentiment scoring algorigthm.
	#
	# A writeup of the analysis can be found here:
	# https://www.linkedin.com/pulse/article/20141109035942-34768479-r-sentiment-scoring-hsbc-w-harvard-general-inquirer

	# Define the packages we want to load:
	packs = c(
	"tm", # Text mining
	"tm.plugin.webmining", # Web-source plugin for text mining
	findBestArma = function(
	xx,
	minOrder=c(0,0),
	maxOrder=c(5,5),
	trace=FALSE )
	{
	bestAic = 1e9
	len = NROW( xx )
	for( p in minOrder[1]:maxOrder[1] ) for( q in minOrder[2]:maxOrder[2] )
	{
	armaSearch = function(
	xx,
	minOrder=c(0,0),
	maxOrder=c(5,5),
	trace=FALSE )
	{
	bestAic = 1e9
	len = NROW( xx )
	for( p in minOrder[1]:maxOrder[1] ) for( q in minOrder[2]:maxOrder[2] )
	{