baseCode - 0.2.5

Clover coverage report - baseCode - 0.2.5

Coverage timestamp: Tue Apr 12 2005 11:31:58 EDT

FRAMES NO FRAMES

file stats:	LOC:	234		Methods:	11
	NCLOC:	113		Classes:	1

30 day Evaluation Version distributed via the Maven Jar Repository. Clover is not free. You have 30 days to evaluate it. Please visit http://www.thecortex.net/clover to obtain a licensed version of Clover

Source file

Conditionals

Statements

Methods

TOTAL

Stats.java

86.1%

94.1%

90.9%

91.3%

 package baseCode.math;
 
 import cern.colt.list.DoubleArrayList;
 import cern.jet.stat.Descriptive;
 
 /**
  * Miscellaneous functions used for statistical analysis. Some are optimized or specialized versions of methods that can
  * be found elsewhere.
  * 
  * @see <a href="http://hoschek.home.cern.ch/hoschek/colt/V1.0.3/doc/cern/jet/math/package-summary.html">cern.jet.math
  *      </a>
  * @see <a href="http://hoschek.home.cern.ch/hoschek/colt/V1.0.3/doc/cern/jet/stat/package-summary.html">cern.jet.stat
  *      </a>
  *      <p>
  *      Copyright (c) 2004
  *      </p>
  *      <p>
  *      Columbia University
  *      </p>
  * @author Paul Pavlidis
  * @version $Id: Stats.java,v 1.10 2004/07/27 03:18:58 pavlidis Exp $
  */
 public class Stats {
 
    private Stats() { /* block instantiation */
    };
 
    /**
     * Test whether a value is a valid fractional or probability value.
     * 
     * @param value
     * @return true if the value is in the interval 0 to 1.
     */
    public static boolean isValidFraction( double value ) {
       if ( value > 1.0 || value < 0.0 ) {
          return false;
       }
       return true;
    }
 
    /**
     * Compute the coefficient of variation of an array (standard deviation / mean)
     * 
     * @param data DoubleArrayList
     * @return the cv
     * @todo offer a regularized version of this function.
     */
    public static double cv( DoubleArrayList data ) {
       double mean = DescriptiveWithMissing.mean( data );
       return mean
             / Math.sqrt( DescriptiveWithMissing.sampleVariance( data, mean ) );
    }
 
    /**
     * Convert an array into a cumulative array. Summing is from the left hand side. Use this to make CDFs where the
     * concern is the left tail.
     * 
     * @param x DoubleArrayList
     * @return cern.colt.list.DoubleArrayList
     */
    public static DoubleArrayList cumulate( DoubleArrayList x ) {
       if ( x.size() == 0 ) {
          return new DoubleArrayList( 0 );
       }
 
       DoubleArrayList r = new DoubleArrayList();
 
       double sum = 0.0;
       for ( int i = 0; i < x.size(); i++ ) {
          sum += x.get( i );
          r.add( sum );
       }
       return r;
    }
 
    /**
     * Convert an array into a cumulative array. Summing is from the right hand side. This is useful for creating
     * upper-tail cumulative density histograms from count histograms, where the upper tail is expected to have very
     * small numbers that could be lost to rounding.
     * 
     * @param x the array of data to be cumulated.
     * @return cern.colt.list.DoubleArrayList
     */
    public static DoubleArrayList cumulateRight( DoubleArrayList x ) {
       if ( x.size() == 0 ) {
          return new DoubleArrayList( 0 );
       }
 
       DoubleArrayList r = new DoubleArrayList( new double[x.size()] );
 
       double sum = 0.0;
       for ( int i = x.size() - 1; i >= 0; i-- ) {
          sum += x.get( i );
          r.set( i, sum );
       }
       return r;
    }
 
    /**
     * Convert an array into a cumulative density function (CDF). This assumes that the input contains counts
     * representing the distribution in question.
     * 
     * @param x The input of counts (i.e. a histogram).
     * @return DoubleArrayList the CDF.
     */
    public static DoubleArrayList cdf( DoubleArrayList x ) {
       return cumulateRight( normalize( x ) );
    }
 
    /**
     * Divide the elements of an array by a given factor.
     * 
     * @param x Input array.
     * @param normfactor double
     * @return Normalized array.
     */
    public static DoubleArrayList normalize( DoubleArrayList x, double normfactor ) {
       if ( x.size() == 0 ) {
          return new DoubleArrayList( 0 );
       }
 
       DoubleArrayList r = new DoubleArrayList();
 
       for ( int i = 0; i < x.size(); i++ ) {
          r.add( x.get( i ) / normfactor );
       }
       return r;
 
    }
 
    /**
     * Adjust the elements of an array so they total to 1.0.
     * 
     * @param x Input array.
     * @return Normalized array.
     */
    public static DoubleArrayList normalize( DoubleArrayList x ) {
       return normalize( x, Descriptive.sum( x ) );
    }
 
    /**
     * calculate the mean of the values above (NOT greater or equal to) a particular index rank of an array. Quantile
     * must be a value from 0 to 100.
     * 
     * @see DescriptiveWithMissing#meanAboveQuantile
     * @param index the rank of the value we wish to average above.
     * @param array Array for which we want to get the quantile.
     * @param effectiveSize The size of the array, not including NaNs.
     * @return double
     */
    public static double meanAboveQuantile( int index, double[] array,
          int effectiveSize ) {
 
       double[] temp = new double[effectiveSize];
       double median;
       double returnvalue = 0.0;
       int k = 0;
 
       temp = array;
       median = quantile( index, array, effectiveSize );
 
       for ( int i = 0; i < effectiveSize; i++ ) {
          if ( temp[i] > median ) {
             returnvalue += temp[i];
             k++;
          }
       }
       return ( returnvalue / k );
    }
 
    /**
     * Compute the range of an array.
     * 
     * @param data DoubleArrayList
     * @return double
     */
    public static double range( DoubleArrayList data ) {
       return Descriptive.max( data ) - Descriptive.min( data );
    }
 
    /**
     * Given a double array, calculate the quantile requested. Note that no interpolation is done.
     * 
     * @see DescriptiveWithMissing#quantile
     * @param index - the rank of the value we wish to get. Thus if we have 200 items in the array, and want the median,
     *        we should enter 100.
     * @param values double[] - array of data we want quantile of
     * @param effectiveSize int the effective size of the array
     * @return double the value at the requested quantile
     */
    public static double quantile( int index, double[] values, int effectiveSize ) {
       double pivot = -1.0;
       if ( index == 0 ) {
          double ans = values[0];
          for ( int i = 1; i < effectiveSize; i++ ) {
             if ( ans > values[i] ) {
                ans = values[i];
             }
          }
          return ans;
       }
 
       double[] temp = new double[effectiveSize];
 
       for ( int i = 0; i < effectiveSize; i++ ) {
          temp[i] = values[i];
       }
 
       pivot = temp[0];
 
       double[] smaller = new double[effectiveSize];
       double[] bigger = new double[effectiveSize];
       int itrSm = 0;
       int itrBg = 0;
       for ( int i = 1; i < effectiveSize; i++ ) {
          if ( temp[i] <= pivot ) {
             smaller[itrSm] = temp[i];
             itrSm++;
          } else if ( temp[i] > pivot ) {
             bigger[itrBg] = temp[i];
             itrBg++;
          }
       }
       if ( itrSm > index ) { // quantile must be in the 'smaller' array
          return quantile( index, smaller, itrSm );
       } else if ( itrSm < index ) { // quantile is in the 'bigger' array
          return quantile( index - itrSm - 1, bigger, itrBg );
       } else {
          return pivot;
       }
 
    }
 
 }

1		package baseCode.math;
2
3		import cern.colt.list.DoubleArrayList;
4		import cern.jet.stat.Descriptive;
5
6		/**
7		* Miscellaneous functions used for statistical analysis. Some are optimized or specialized versions of methods that can
8		* be found elsewhere.
9		*
10		* @see <a href="http://hoschek.home.cern.ch/hoschek/colt/V1.0.3/doc/cern/jet/math/package-summary.html">cern.jet.math
11		* </a>
12		* @see <a href="http://hoschek.home.cern.ch/hoschek/colt/V1.0.3/doc/cern/jet/stat/package-summary.html">cern.jet.stat
13		* </a>
14		* <p>
15		* Copyright (c) 2004
16		* </p>
17		* <p>
18		* Columbia University
19		* </p>
20		* @author Paul Pavlidis
21		* @version $Id: Stats.java,v 1.10 2004/07/27 03:18:58 pavlidis Exp $
22		*/
23		public class Stats {
24
25	0	private Stats() { /* block instantiation */
26		};
27
28		/**
29		* Test whether a value is a valid fractional or probability value.
30		*
31		* @param value
32		* @return true if the value is in the interval 0 to 1.
33		*/
34	23	public static boolean isValidFraction( double value ) {
35	23	if ( value > 1.0 \|\| value < 0.0 ) {
36	2	return false;
37		}
38	21	return true;
39		}
40
41		/**
42		* Compute the coefficient of variation of an array (standard deviation / mean)
43		*
44		* @param data DoubleArrayList
45		* @return the cv
46		* @todo offer a regularized version of this function.
47		*/
48	1	public static double cv( DoubleArrayList data ) {
49	1	double mean = DescriptiveWithMissing.mean( data );
50	1	return mean
51		/ Math.sqrt( DescriptiveWithMissing.sampleVariance( data, mean ) );
52		}
53
54		/**
55		* Convert an array into a cumulative array. Summing is from the left hand side. Use this to make CDFs where the
56		* concern is the left tail.
57		*
58		* @param x DoubleArrayList
59		* @return cern.colt.list.DoubleArrayList
60		*/
61	1	public static DoubleArrayList cumulate( DoubleArrayList x ) {
62	1	if ( x.size() == 0 ) {
63	0	return new DoubleArrayList( 0 );
64		}
65
66	1	DoubleArrayList r = new DoubleArrayList();
67
68	1	double sum = 0.0;
69	1	for ( int i = 0; i < x.size(); i++ ) {
70	5	sum += x.get( i );
71	5	r.add( sum );
72		}
73	1	return r;
74		}
75
76		/**
77		* Convert an array into a cumulative array. Summing is from the right hand side. This is useful for creating
78		* upper-tail cumulative density histograms from count histograms, where the upper tail is expected to have very
79		* small numbers that could be lost to rounding.
80		*
81		* @param x the array of data to be cumulated.
82		* @return cern.colt.list.DoubleArrayList
83		*/
84	2	public static DoubleArrayList cumulateRight( DoubleArrayList x ) {
85	2	if ( x.size() == 0 ) {
86	0	return new DoubleArrayList( 0 );
87		}
88
89	2	DoubleArrayList r = new DoubleArrayList( new double[x.size()] );
90
91	2	double sum = 0.0;
92	2	for ( int i = x.size() - 1; i >= 0; i-- ) {
93	10	sum += x.get( i );
94	10	r.set( i, sum );
95		}
96	2	return r;
97		}
98
99		/**
100		* Convert an array into a cumulative density function (CDF). This assumes that the input contains counts
101		* representing the distribution in question.
102		*
103		* @param x The input of counts (i.e. a histogram).
104		* @return DoubleArrayList the CDF.
105		*/
106	1	public static DoubleArrayList cdf( DoubleArrayList x ) {
107	1	return cumulateRight( normalize( x ) );
108		}
109
110		/**
111		* Divide the elements of an array by a given factor.
112		*
113		* @param x Input array.
114		* @param normfactor double
115		* @return Normalized array.
116		*/
117	3	public static DoubleArrayList normalize( DoubleArrayList x, double normfactor ) {
118	3	if ( x.size() == 0 ) {
119	0	return new DoubleArrayList( 0 );
120		}
121
122	3	DoubleArrayList r = new DoubleArrayList();
123
124	3	for ( int i = 0; i < x.size(); i++ ) {
125	15	r.add( x.get( i ) / normfactor );
126		}
127	3	return r;
128
129		}
130
131		/**
132		* Adjust the elements of an array so they total to 1.0.
133		*
134		* @param x Input array.
135		* @return Normalized array.
136		*/
137	2	public static DoubleArrayList normalize( DoubleArrayList x ) {
138	2	return normalize( x, Descriptive.sum( x ) );
139		}
140
141		/**
142		* calculate the mean of the values above (NOT greater or equal to) a particular index rank of an array. Quantile
143		* must be a value from 0 to 100.
144		*
145		* @see DescriptiveWithMissing#meanAboveQuantile
146		* @param index the rank of the value we wish to average above.
147		* @param array Array for which we want to get the quantile.
148		* @param effectiveSize The size of the array, not including NaNs.
149		* @return double
150		*/
151	1	public static double meanAboveQuantile( int index, double[] array,
152		int effectiveSize ) {
153
154	1	double[] temp = new double[effectiveSize];
155	1	double median;
156	1	double returnvalue = 0.0;
157	1	int k = 0;
158
159	1	temp = array;
160	1	median = quantile( index, array, effectiveSize );
161
162	1	for ( int i = 0; i < effectiveSize; i++ ) {
163	50	if ( temp[i] > median ) {
164	24	returnvalue += temp[i];
165	24	k++;
166		}
167		}
168	1	return ( returnvalue / k );
169		}
170
171		/**
172		* Compute the range of an array.
173		*
174		* @param data DoubleArrayList
175		* @return double
176		*/
177	1	public static double range( DoubleArrayList data ) {
178	1	return Descriptive.max( data ) - Descriptive.min( data );
179		}
180
181		/**
182		* Given a double array, calculate the quantile requested. Note that no interpolation is done.
183		*
184		* @see DescriptiveWithMissing#quantile
185		* @param index - the rank of the value we wish to get. Thus if we have 200 items in the array, and want the median,
186		* we should enter 100.
187		* @param values double[] - array of data we want quantile of
188		* @param effectiveSize int the effective size of the array
189		* @return double the value at the requested quantile
190		*/
191	23	public static double quantile( int index, double[] values, int effectiveSize ) {
192	23	double pivot = -1.0;
193	23	if ( index == 0 ) {
194	3	double ans = values[0];
195	3	for ( int i = 1; i < effectiveSize; i++ ) {
196	3	if ( ans > values[i] ) {
197	1	ans = values[i];
198		}
199		}
200	3	return ans;
201		}
202
203	20	double[] temp = new double[effectiveSize];
204
205	20	for ( int i = 0; i < effectiveSize; i++ ) {
206	456	temp[i] = values[i];
207		}
208
209	20	pivot = temp[0];
210
211	20	double[] smaller = new double[effectiveSize];
212	20	double[] bigger = new double[effectiveSize];
213	20	int itrSm = 0;
214	20	int itrBg = 0;
215	20	for ( int i = 1; i < effectiveSize; i++ ) {
216	436	if ( temp[i] <= pivot ) {
217	313	smaller[itrSm] = temp[i];
218	313	itrSm++;
219	123	} else if ( temp[i] > pivot ) {
220	123	bigger[itrBg] = temp[i];
221	123	itrBg++;
222		}
223		}
224	20	if ( itrSm > index ) { // quantile must be in the 'smaller' array
225	11	return quantile( index, smaller, itrSm );
226	9	} else if ( itrSm < index ) { // quantile is in the 'bigger' array
227	9	return quantile( index - itrSm - 1, bigger, itrBg );
228		} else {
229	0	return pivot;
230		}
231
232		}
233
234		}