statsample-timeseries 0.0.3 → 0.3.0

data/VERSION

@@ -1 +0,0 @@
-0.0.3

data/bin/bio-statsample-timeseries

@@ -1,74 +0,0 @@
-#!/usr/bin/env ruby
-#
-# BioRuby bio-statsample-timeseries Plugin BioStatsampleTimeseries
-# Author:: Ankur Goel
-# Copyright:: 2013
-
- USAGE = "Describe bio-statsample-timeseries"
-
-if ARGV.size == 0
-  print USAGE
-end
-
-require 'bio-statsample-timeseries'
-require 'optparse'
-
-# Uncomment when using the bio-logger 
-# require 'bio-logger'
-# Bio::Log::CLI.logger('stderr')
-# Bio::Log::CLI.trace('info')
-
-options = {:example_switch=>false,:show_help=>false}
-opts = OptionParser.new do |o|
-  o.banner = "Usage: #{File.basename($0)} [options] reponame\ne.g. #{File.basename($0)} the-perfect-gem"
-
-  o.on('--example_parameter [EXAMPLE_PARAMETER]', 'TODO: put a description for the PARAMETER') do |example_parameter|
-    # TODO: your logic here, below an example
-    options[:example_parameter] = 'this is a parameter'
-  end
-  
-  o.separator ""
-  o.on("--switch-example", 'TODO: put a description for the SWITCH') do
-    # TODO: your logic here, below an example
-    self[:example_switch] = true
-  end
-
-  # Uncomment the following when using the bio-logger 
-  # o.separator ""
-  # o.on("--logger filename",String,"Log to file (default stderr)") do | name |
-  #   Bio::Log::CLI.logger(name)
-  # end
-  #
-  # o.on("--trace options",String,"Set log level (default INFO, see bio-logger)") do | s |
-  #   Bio::Log::CLI.trace(s)
-  # end
-  # 
-  # o.on("-q", "--quiet", "Run quietly") do |q|
-  #   Bio::Log::CLI.trace('error')
-  # end
-  # 
-  # o.on("-v", "--verbose", "Run verbosely") do |v|
-  #   Bio::Log::CLI.trace('info')
-  # end
-  # 
-  # o.on("--debug", "Show debug messages") do |v|
-  #   Bio::Log::CLI.trace('debug')
-  # end
-
-  o.separator ""
-  o.on_tail('-h', '--help', 'display this help and exit') do
-    options[:show_help] = true
-  end
-end
-
-begin
-  opts.parse!(ARGV)
-
-  # Uncomment the following when using the bio-logger 
-  # Bio::Log::CLI.configure('bio-statsample-timeseries')
-
-  # TODO: your code here
-  # use options for your logic
-rescue OptionParser::InvalidOption => e
-  options[:invalid_argument] = e.message
-end

data/features/acf.feature

@@ -1,31 +0,0 @@
-Feature: ACF
-
-  As a statistician
-  So that I can evaluate autocorrelation of a series
-  I want to evaluate acf
-
-Background: a timeseries
-
-  Given the following values in a timeseries:
-    | timeseries |
-    | 10  20  30  40  50  60  70  80  90  100 |
-    | 110 120 130 140 150 160 170 180 190 200 |
-
-Scenario: cross-check acf for 10 lags
-  When I provide 10 lags for acf
-  And I calculate acf
-  Then I should get 11 values in resultant acf
-  And I should see "1.0, 0.85, 0.7015037593984963, 0.556015037593985, 0.4150375939849624, 0.2800751879699248, 0.15263157894736842, 0.034210526315789476, -0.07368421052631578, -0.16954887218045114, -0.2518796992481203" as complete series 
-
-Scenario: cross-check acf for 5 lags
-  When I provide 5 lags for acf
-  And I calculate acf
-  Then I should get 6 values in resultant acf
-  And I should see "1.0, 0.85, 0.7015037593984963, 0.556015037593985, 0.4150375939849624, 0.2800751879699248" as complete series
-
-Scenario: first value should be 1.0
-  When I provide 2 lags for acf
-  And I calculate acf
-  Then I should get 3 values in resultant acf
-  And I should see 1.0 as first value
-

data/features/pacf.feature

@@ -1,42 +0,0 @@
-Feature: PACF
-
-  As a statistician
-  So that I can quickly evaluate partial autocorrelation of a series
-  I want to evaluate pacf
-
-Background: a timeseries
-
-  Given the following values in a timeseries:
-    | timeseries |
-    | 10  20  30  40  50  60  70  80  90  100 |
-    | 110 120 130 140 150 160 170 180 190 200 |
-
-Scenario: check pacf for 10 lags with unbiased
-  When I provide 10 lags for pacf
-  When I provide yw yule walker as method
-  Then I should get Array as resultant output
-  Then I should get 11 values in resultant pacf
-
-Scenario: check pacf for 5 lags with mle
-  When I provide 5 lags for pacf
-  When I provide mle yule walker as method
-  Then I should get Array as resultant output
-  Then I should get 6 values in resultant pacf
-
-Scenario: check first value of pacf
-  When I provide 5 lags for pacf
-  When I provide yw yule walker as method
-  Then I should get Array as resultant output
-  And I should see 1.0 as first value
-
-Scenario: check all values in pacf for 5 lags with mle
-  When I provide 5 lags for pacf
-  When I provide mle yule walker as method
-  Then I should get Array as resultant output
-  And I should see "1.0, 0.85, -0.07566212829370711, -0.07635069706072706, -0.07698628638512295, -0.07747034005560738" as complete series 
-
-Scenario: check all values in pacf for 5 lags with unbiased
-  When I provide 5 lags for pacf
-  When I provide yw yule walker as method
-  Then I should get Array as resultant output
-  And I should see "1.0, 0.8947368421052632, -0.10582010582010604, -0.11350188273265083, -0.12357534824820737, -0.13686534216335522" as complete series 

data/features/step_definitions/step_definitions.rb

@@ -1,37 +0,0 @@
-require 'statsample-timeseries'
-include Statsample::TimeSeries
-
-Given /^the following values in a timeseries:$/ do |series|
-  arr = []
-  series.hashes.each do |sequence|
-    arr += sequence['timeseries'].split(' ').map(&:to_i).to_ts
-  end
-  @timeseries = arr.to_ts
-end
-
-When /^I provide (\d+) lags for p?acf$/ do |lags|
-  @lags = lags.to_i
-end
-
-When /^I provide (\w+) yule walker as method$/ do |method|
-  @method = method
-end
-
-Then /^I should get (\w+) as resultant output$/ do |klass|
-  @result = @timeseries.pacf(@lags, @method)
-  assert_equal @result.class.to_s, klass
-end
-
-Then /^I should get (\w+) values in resultant p?acf$/ do |values_count|
-  assert_equal @result.size, values_count.to_i
-end
-
-And /^I should see (\d+\.\d) as first value$/ do |first_value|
-  assert_equal @result.first, first_value.to_f
-end
-
-And /^I should see \"(.+)\" as complete series$/ do |series|
-  series = series.split(',').map(&:to_f)
-  assert_equal @result, series
-end
-

data/features/step_definitions/step_definitions_acf.rb

@@ -1,8 +0,0 @@
-require 'statsample-timeseries'
-include Statsample::TimeSeries
-
-#all instance variable and cucumber DSL s DRYed up in step_definitions.rb
-And /^I calculate acf$/ do
-  @result = @timeseries.acf(@lags)
-end
-

data/features/support/env.rb

@@ -1,15 +0,0 @@
-require 'bundler'
-begin
-  Bundler.setup(:default, :development)
-rescue Bundler::BundlerError => e
-  $stderr.puts e.message
-  $stderr.puts "Run `bundle install` to install missing gems"
-  exit e.status_code
-end
-
-$LOAD_PATH.unshift(File.dirname(__FILE__) + '/../../lib')
-require 'statsample-timeseries'
-
-require 'test/unit/assertions'
-
-World(Test::Unit::Assertions)

data/lib/statsample-timeseries/timeseries.rb

@@ -1,291 +0,0 @@
-require 'statsample-timeseries/timeseries/pacf'
-module Statsample::TimeSeriesShorthands
-  # Creates a new Statsample::TimeSeries object
-  # Argument should be equal to TimeSeries.new
-  def to_time_series(*args)
-    Statsample::TimeSeries::Series.new(self, :scale, *args)
-  end
-
-  alias :to_ts :to_time_series
-end
-
-class Array
-  include Statsample::TimeSeriesShorthands
-end
-
-module Statsample
-  module TimeSeries
-    # Collection of data indexed by time.
-    # The order goes from earliest to latest.
-    class Series < Statsample::Vector
-      include Statsample::TimeSeries::Pacf
-      # Calculates the autocorrelation coefficients of the series.
-      #
-      # The first element is always 1, since that is the correlation
-      # of the series with itself.
-      #
-      # Usage:
-      #
-      #  ts = (1..100).map { rand }.to_time_series
-      #
-      #  ts.acf   # => array with first 21 autocorrelations
-      #  ts.acf 3 # => array with first 3 autocorrelations
-      #
-      def acf(max_lags = nil)
-        max_lags ||= (10 * Math.log10(size)).to_i
-
-        (0..max_lags).map do |i|
-          if i == 0
-            1.0
-          else
-            m = self.mean
-
-            # can't use Pearson coefficient since the mean for the lagged series should
-            # be the same as the regular series
-            ((self - m) * (self.lag(i) - m)).sum / self.variance_sample / (self.size - 1)
-          end
-        end
-      end
-
-      #=Partial Autocorrelation
-      #Generates partial autocorrelation series for a timeseries
-      #==Parameters
-      #* *max_lags*: integer, optional - provide number of lags
-      #* *method*: string. Default: 'yw'.
-      #    * *yw*: For yule-walker algorithm unbiased approach
-      #    * *mle*: For Maximum likelihood algorithm approach
-      #    * *ld*: Forr Levinson-Durbin recursive approach
-      #==Returns
-      # array of pacf
-      def pacf(max_lags = nil, method = :yw)
-
-        method = method.downcase.to_sym
-        max_lags ||= (10 * Math.log10(size)).to_i
-        if method.eql? :yw or method.eql? :mle
-          Pacf::Pacf.pacf_yw(self, max_lags, method.to_s)
-        elsif method == :ld
-          series = self.acvf
-          Pacf::Pacf.levinson_durbin(series, max_lags, true)[2]
-        else
-          raise "Method presents for pacf are 'yw', 'mle' or 'ld'"
-        end
-      end
-	
-      #=Autoregressive estimation
-      #Generates AR(k) series for the calling timeseries by yule walker.
-      #==Parameters
-      #* *n*: integer, (default = 1500) number of observations for AR.
-      #* *k*: integer, (default = 1) order of AR process.
-      #==Returns
-      #Array constituting estimated AR series.
-      def ar(n = 1500, k = 1)
-        series = Statsample::TimeSeries.arima
-        #series = Statsample::TimeSeries::ARIMA.new
-        series.yule_walker(self, n, k)
-      end
-
-      #=AutoCovariance
-      #Provides autocovariance of timeseries.
-      #==Parameters
-      #* *demean* = true; optional. Supply false if series is not to be demeaned
-      #* *unbiased* = true; optional. true/false for unbiased/biased form of autocovariance
-      #==Returns
-      # Autocovariance value
-      def acvf(demean = true, unbiased = true)
-        #TODO: change parameters list in opts.merge as suggested by John
-        #functionality: computes autocovariance of timeseries data
-        #returns: array of autocovariances
-
-        if demean
-          demeaned_series = self - self.mean
-        else
-          demeaned_series = self
-        end
-        n = (10 * Math.log10(size)).to_i + 1
-        m = self.mean
-        if unbiased
-          d = Array.new(self.size, self.size)
-        else
-          d = ((1..self.size).to_a.reverse)[0..n]
-        end
-
-
-        0.upto(n - 1).map do |i|
-          (demeaned_series * (self.lag(i) - m)).sum / d[i]
-        end
-      end
-
-      #=Correlation
-      #Gives correlation of timeseries.
-      def correlate(a, v, mode = 'full')
-        #peforms cross-correlation of two series
-        #multiarray.correlate2(a, v, 'full')
-        if a.size < v.size
-          raise("Should have same size!")
-        end
-        ps = a.size + v.size - 1
-        a_padded = Array.new(ps, 0)
-        a_padded[0...a.size] = a
-
-        out = (mode.downcase.eql? 'full') ? Array.new(ps) : Array.new(a.size)
-        #ongoing
-      end
-
-      # Lags the series by k periods.
-      #
-      # The convention is to set the oldest observations (the first ones
-      # in the series) to nil so that the size of the lagged series is the
-      # same as the original.
-      #
-      # Usage:
-      #
-      #  ts = (1..10).map { rand }.to_time_series
-      #           # => [0.69, 0.23, 0.44, 0.71, ...]
-      #
-      #  ts.lag   # => [nil, 0.69, 0.23, 0.44, ...]
-      #  ts.lag 2 # => [nil, nil, 0.69, 0.23, ...]
-      #
-      def lag(k = 1)
-        return self if k == 0
-
-        dup.tap do |lagged|
-          (lagged.size - 1).downto k do |i|
-            lagged[i] = lagged[i - k]
-          end
-
-          (0...k).each do |i|
-            lagged[i] = nil
-          end
-          lagged.set_valid_data
-        end
-      end
-
-      #=Diff
-      # Performs the difference of the series.
-      # Note: The first difference of series is X(t) - X(t-1)
-      # But, second difference of series is NOT X(t) - X(t-2)
-      # It is the first difference of the first difference
-      # => (X(t) - X(t-1)) - (X(t-1) - X(t-2))
-      #==Params
-      #* *max_lags*: integer, (default: 1), number of differences reqd.
-      #==Usage
-      #
-      #  ts = (1..10).map { rand }.to_ts
-      #            # => [0.69, 0.23, 0.44, 0.71, ...]
-      #
-      #  ts.diff   # => [nil, -0.46, 0.21, 0.27, ...]
-      #==Returns
-      # Timeseries object
-      def diff(max_lags = 1)
-        ts = self
-        difference = []
-        max_lags.times do
-          difference = ts - ts.lag
-          ts = difference
-        end
-        difference
-      end
-
-      #=Moving Average
-      # Calculates the moving average of the series using the provided
-      # lookback argument. The lookback defaults to 10 periods.
-      #==Parameters
-      #* *n*: integer, (default = 10) - loopback argument
-      #
-      #==Usage
-      #
-      #   ts = (1..100).map { rand }.to_ts
-      #            # => [0.69, 0.23, 0.44, 0.71, ...]
-      #
-      #   # first 9 observations are nil
-      #   ts.ma    # => [ ... nil, 0.484... , 0.445... , 0.513 ... , ... ]
-      #
-      #==Returns
-      #Resulting moving average timeseries object
-      def ma(n = 10)
-        return mean if n >= size
-
-        ([nil] * (n - 1) + (0..(size - n)).map do |i|
-          self[i...(i + n)].inject(&:+) / n
-        end).to_time_series
-      end
-
-      #=Exponential Moving Average
-      # Calculates an exponential moving average of the series using a
-      # specified parameter. If wilder is false (the default) then the EMA
-      # uses a smoothing value of 2 / (n + 1), if it is true then it uses the
-      # Welles Wilder smoother of 1 / n.
-      #
-      # Warning for EMA usage: EMAs are unstable for small series, as they
-      # use a lot more than n observations to calculate. The series is stable
-      # if the size of the series is >= 3.45 * (n + 1)
-      #
-      #==Parameters
-      #* *n*: integer, (default = 10)
-      #* *wilder*: boolean, (default = false), if true, 1/n value is used for smoothing; if false, uses 2/(n+1) value
-      #
-      #==Usage
-      #   ts = (1..100).map { rand }.to_ts
-      #            # => [0.69, 0.23, 0.44, 0.71, ...]
-      #
-      #   # first 9 observations are nil
-      #   ts.ema   # => [ ... nil, 0.509... , 0.433..., ... ]
-      #
-      #==Returns
-      #EMA timeseries
-      def ema(n = 10, wilder = false)
-        smoother = wilder ? 1.0 / n : 2.0 / (n + 1)
-
-        # need to start everything from the first non-nil observation
-        start = self.data.index { |i| i != nil }
-
-        # first n - 1 observations are nil
-        base = [nil] * (start + n - 1)
-
-        # nth observation is just a moving average
-        base << self[start...(start + n)].inject(0.0) { |s, a| a.nil? ? s : s + a } / n
-
-        (start + n).upto size - 1 do |i|
-          base << self[i] * smoother + (1 - smoother) * base.last
-        end
-
-        base.to_time_series
-      end
-
-      #=Moving Average Convergence-Divergence
-      # Calculates the MACD (moving average convergence-divergence) of the time
-      # series - this is a comparison of a fast EMA with a slow EMA.
-      #
-      #==Parameters*:
-      #* *fast*: integer, (default = 12) - fast component of MACD
-      #* *slow*: integer, (default = 26) - slow component of MACD
-      #* *signal*: integer, (default = 9) - signal component of MACD
-      #
-      #==Usage
-      # ts = (1..100).map { rand }.to_ts
-      #            # => [0.69, 0.23, 0.44, 0.71, ...]
-      # ts.macd(13)
-      #
-      #==Returns
-      # Array of two timeseries - comparison of fast EMA with slow and EMA with signal value
-      def macd(fast = 12, slow = 26, signal = 9)
-        series = ema(fast) - ema(slow)
-        [series, series.ema(signal)]
-      end
-
-      # Borrow the operations from Vector, but convert to time series
-      def + series
-        super.to_a.to_ts
-      end
-
-      def - series
-        super.to_a.to_ts
-      end
-
-      def to_s
-        sprintf("Time Series(type:%s, n:%d)[%s]", @type.to_s, @data.size,
-                @data.collect{|d| d.nil? ? "nil":d}.join(","))
-      end
-    end
-  end
-end