|
0
|
1 .\" Automatically generated by Pod::Man 2.25 (Pod::Simple 3.22)
|
|
|
2 .\"
|
|
|
3 .\" Standard preamble:
|
|
|
4 .\" ========================================================================
|
|
|
5 .de Sp \" Vertical space (when we can't use .PP)
|
|
|
6 .if t .sp .5v
|
|
|
7 .if n .sp
|
|
|
8 ..
|
|
|
9 .de Vb \" Begin verbatim text
|
|
|
10 .ft CW
|
|
|
11 .nf
|
|
|
12 .ne \\$1
|
|
|
13 ..
|
|
|
14 .de Ve \" End verbatim text
|
|
|
15 .ft R
|
|
|
16 .fi
|
|
|
17 ..
|
|
|
18 .\" Set up some character translations and predefined strings. \*(-- will
|
|
|
19 .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
|
|
|
20 .\" double quote, and \*(R" will give a right double quote. \*(C+ will
|
|
|
21 .\" give a nicer C++. Capital omega is used to do unbreakable dashes and
|
|
|
22 .\" therefore won't be available. \*(C` and \*(C' expand to `' in nroff,
|
|
|
23 .\" nothing in troff, for use with C<>.
|
|
|
24 .tr \(*W-
|
|
|
25 .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
|
|
|
26 .ie n \{\
|
|
|
27 . ds -- \(*W-
|
|
|
28 . ds PI pi
|
|
|
29 . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
|
|
|
30 . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch
|
|
|
31 . ds L" ""
|
|
|
32 . ds R" ""
|
|
|
33 . ds C` ""
|
|
|
34 . ds C' ""
|
|
|
35 'br\}
|
|
|
36 .el\{\
|
|
|
37 . ds -- \|\(em\|
|
|
|
38 . ds PI \(*p
|
|
|
39 . ds L" ``
|
|
|
40 . ds R" ''
|
|
|
41 'br\}
|
|
|
42 .\"
|
|
|
43 .\" Escape single quotes in literal strings from groff's Unicode transform.
|
|
|
44 .ie \n(.g .ds Aq \(aq
|
|
|
45 .el .ds Aq '
|
|
|
46 .\"
|
|
|
47 .\" If the F register is turned on, we'll generate index entries on stderr for
|
|
|
48 .\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
|
|
|
49 .\" entries marked with X<> in POD. Of course, you'll have to process the
|
|
|
50 .\" output yourself in some meaningful fashion.
|
|
|
51 .ie \nF \{\
|
|
|
52 . de IX
|
|
|
53 . tm Index:\\$1\t\\n%\t"\\$2"
|
|
|
54 ..
|
|
|
55 . nr % 0
|
|
|
56 . rr F
|
|
|
57 .\}
|
|
|
58 .el \{\
|
|
|
59 . de IX
|
|
|
60 ..
|
|
|
61 .\}
|
|
|
62 .\"
|
|
|
63 .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
|
|
|
64 .\" Fear. Run. Save yourself. No user-serviceable parts.
|
|
|
65 . \" fudge factors for nroff and troff
|
|
|
66 .if n \{\
|
|
|
67 . ds #H 0
|
|
|
68 . ds #V .8m
|
|
|
69 . ds #F .3m
|
|
|
70 . ds #[ \f1
|
|
|
71 . ds #] \fP
|
|
|
72 .\}
|
|
|
73 .if t \{\
|
|
|
74 . ds #H ((1u-(\\\\n(.fu%2u))*.13m)
|
|
|
75 . ds #V .6m
|
|
|
76 . ds #F 0
|
|
|
77 . ds #[ \&
|
|
|
78 . ds #] \&
|
|
|
79 .\}
|
|
|
80 . \" simple accents for nroff and troff
|
|
|
81 .if n \{\
|
|
|
82 . ds ' \&
|
|
|
83 . ds ` \&
|
|
|
84 . ds ^ \&
|
|
|
85 . ds , \&
|
|
|
86 . ds ~ ~
|
|
|
87 . ds /
|
|
|
88 .\}
|
|
|
89 .if t \{\
|
|
|
90 . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
|
|
|
91 . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
|
|
|
92 . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
|
|
|
93 . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
|
|
|
94 . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
|
|
|
95 . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
|
|
|
96 .\}
|
|
|
97 . \" troff and (daisy-wheel) nroff accents
|
|
|
98 .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
|
|
|
99 .ds 8 \h'\*(#H'\(*b\h'-\*(#H'
|
|
|
100 .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
|
|
|
101 .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
|
|
|
102 .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
|
|
|
103 .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
|
|
|
104 .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
|
|
|
105 .ds ae a\h'-(\w'a'u*4/10)'e
|
|
|
106 .ds Ae A\h'-(\w'A'u*4/10)'E
|
|
|
107 . \" corrections for vroff
|
|
|
108 .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
|
|
|
109 .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
|
|
|
110 . \" for low resolution devices (crt and lpr)
|
|
|
111 .if \n(.H>23 .if \n(.V>19 \
|
|
|
112 \{\
|
|
|
113 . ds : e
|
|
|
114 . ds 8 ss
|
|
|
115 . ds o a
|
|
|
116 . ds d- d\h'-1'\(ga
|
|
|
117 . ds D- D\h'-1'\(hy
|
|
|
118 . ds th \o'bp'
|
|
|
119 . ds Th \o'LP'
|
|
|
120 . ds ae ae
|
|
|
121 . ds Ae AE
|
|
|
122 .\}
|
|
|
123 .rm #[ #] #H #V #F C
|
|
|
124 .\" ========================================================================
|
|
|
125 .\"
|
|
|
126 .IX Title "ANALYZETEXTFILESDATA 1"
|
|
|
127 .TH ANALYZETEXTFILESDATA 1 "2015-03-29" "perl v5.14.2" "MayaChemTools"
|
|
|
128 .\" For nroff, turn off justification. Always turn off hyphenation; it makes
|
|
|
129 .\" way too many mistakes in technical documents.
|
|
|
130 .if n .ad l
|
|
|
131 .nh
|
|
|
132 .SH "NAME"
|
|
|
133 AnalyzeTextFilesData.pl \- Analyze numerical coulmn data in TextFile(s)
|
|
|
134 .SH "SYNOPSIS"
|
|
|
135 .IX Header "SYNOPSIS"
|
|
|
136 AnalyzeTextFilesData.pl TextFile(s)...
|
|
|
137 .PP
|
|
|
138 AnalyzeTextFilesData.pl [\fB\-c, \-\-colmode\fR colnum | collabel] [\fB\-\-columns\fR \*(L"colnum,[colnum,...]\*(R" | \*(L"collabel,[collabel,...]\*(R" | All]
|
|
|
139 [\fB\-\-columnpairs\fR \*(L"colnum,colnum,[colnum,colnum]...\*(R" | \*(L"collabel,collabel,[collabel,collabel]...\*(R" | AllPairs]
|
|
|
140 [\fB\-d, \-\-detail\fR infolevel] [\fB\-f, \-\-fast\fR] [\fB\-\-frequencybins\fR number | \*(L"number,number,[number,...]\*(R"] [\fB\-h, \-\-help\fR]
|
|
|
141 [\fB\-\-indelim\fR comma | semicolon] [\fB\-\-klargest\fR number] [\fB\-\-ksmallest\fR number]
|
|
|
142 [\fB\-m, \-\-mode\fR DescriptiveStatisticsBasic | DescriptiveStatisticsAll | All | \*(L"function1, [function2,...]\*(R"]
|
|
|
143 [\fB\-o, \-\-overwrite\fR] [\fB\-\-outdelim\fR comma | tab | semicolon] [\fB\-p, \-\-precision\fR number]
|
|
|
144 [\fB\-q, \-\-quote\fR yes | no] [\fB\-r, \-\-root\fR rootname] [\fB\-\-trimfraction\fR number] [\fB\-w, \-\-workingdir\fR dirname] TextFiles(s)...
|
|
|
145 .SH "DESCRIPTION"
|
|
|
146 .IX Header "DESCRIPTION"
|
|
|
147 Anaylze numerical column data in \fITextFile(s)\fR using a combination of various statistical
|
|
|
148 functions; Non-numerical values are simply ignored. For \fICorrelation, RSquare, and Covariance\fR
|
|
|
149 analysis, the count of valid values in specifed column pair must be same; otherwise, column
|
|
|
150 pair is ignored. The file names are separated by space. The valid file extensions are \fI.csv\fR
|
|
|
151 and \fI.tsv\fR for comma/semicolon and tab delimited text files respectively. All other
|
|
|
152 file names are ignored. All the text files in a current directory can be specified by
|
|
|
153 \&\fI*.csv\fR, \fI*.tsv\fR, or the current directory name. The \fB\-\-indelim\fR option determines
|
|
|
154 the format of \fITextFile(s)\fR. Any file which doesn't correspond to the format indicated
|
|
|
155 by \fB\-\-indelim\fR option is ignored.
|
|
|
156 .SH "OPTIONS"
|
|
|
157 .IX Header "OPTIONS"
|
|
|
158 .IP "\fB\-c, \-\-colmode\fR \fIcolnum | collabel\fR" 4
|
|
|
159 .IX Item "-c, --colmode colnum | collabel"
|
|
|
160 Specify how columns are identified in TextFile(s): using column number or column
|
|
|
161 label. Possible values: \fIcolnum or collabel\fR. Default value: \fIcolnum\fR.
|
|
|
162 .ie n .IP "\fB\-\-columns\fR \fI""colnum,[colnum,...]"" | ""collabel,[collabel]..."" | All\fR" 4
|
|
|
163 .el .IP "\fB\-\-columns\fR \fI``colnum,[colnum,...]'' | ``collabel,[collabel]...'' | All\fR" 4
|
|
|
164 .IX Item "--columns colnum,[colnum,...] | collabel,[collabel]... | All"
|
|
|
165 This value is mode specific. It's a list of comma delimited columns to use
|
|
|
166 for data analysis. Default value: \fIFirst column\fR.
|
|
|
167 .Sp
|
|
|
168 This value is ignored during \fICorrelation/Pearson Correlation\fR and \fICovariance\fR
|
|
|
169 data analysis; \fB\-coulmnparis\fR option is used instead.
|
|
|
170 .Sp
|
|
|
171 For \fIcolnum\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
172 \&\fIcolnum,colnum,...\fR. Example:
|
|
|
173 .Sp
|
|
|
174 .Vb 1
|
|
|
175 \& 1,3,5
|
|
|
176 .Ve
|
|
|
177 .Sp
|
|
|
178 For \fIcollabel\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
179 \&\fIcollabel,collabel,..\fR. Example:
|
|
|
180 .Sp
|
|
|
181 .Vb 1
|
|
|
182 \& ALogP,MolWeight,EC50
|
|
|
183 .Ve
|
|
|
184 .ie n .IP "\fB\-\-columnpairs\fR \fI""colnum,colnum,[colnum,colnum,...]"" | ""collabel,collabel,[collabel,collabel,...]"" | AllPairs\fR" 4
|
|
|
185 .el .IP "\fB\-\-columnpairs\fR \fI``colnum,colnum,[colnum,colnum,...]'' | ``collabel,collabel,[collabel,collabel,...]'' | AllPairs\fR" 4
|
|
|
186 .IX Item "--columnpairs colnum,colnum,[colnum,colnum,...] | collabel,collabel,[collabel,collabel,...] | AllPairs"
|
|
|
187 This value is mode specific and is only used for \fICorrelation, PearsonCorrelation, or
|
|
|
188 Covariance\fR value of \fB\-m, \-\-mode\fR option. It is a comma delimited list of column pairs
|
|
|
189 to use for data analysis during \fICorrelation\fR and \fICovariance\fR calculations. Default value:
|
|
|
190 \&\fIFirst column, Second column\fR.
|
|
|
191 .Sp
|
|
|
192 For \fIcolnum\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
193 \&\fIcolnum,colnum,[colnum,colnum]...\fR. Example:
|
|
|
194 .Sp
|
|
|
195 .Vb 1
|
|
|
196 \& 1,3,5,6,1,6
|
|
|
197 .Ve
|
|
|
198 .Sp
|
|
|
199 For \fIcollabel\fR value of \fB\-c, \-\-colmode\fR option, input values format is:
|
|
|
200 \&\fIcollabel,collabel,[collabel,collabel]..\fR. Example:
|
|
|
201 .Sp
|
|
|
202 .Vb 1
|
|
|
203 \& MolWeight,EC50,NumN+O,PSA
|
|
|
204 .Ve
|
|
|
205 .Sp
|
|
|
206 For \fIAllPairs\fR value of \fB\-\-columnparis\fR option, all column pairs are used for \fICorrelation\fR
|
|
|
207 and \fICovariance\fR calculations.
|
|
|
208 .IP "\fB\-d, \-\-detail\fR \fIinfolevel\fR" 4
|
|
|
209 .IX Item "-d, --detail infolevel"
|
|
|
210 Level of information to print about column values being ignored. Default: \fI1\fR. Possible values:
|
|
|
211 1, 2, 3, or 4.
|
|
|
212 .IP "\fB\-f, \-\-fast\fR" 4
|
|
|
213 .IX Item "-f, --fast"
|
|
|
214 In this mode, all the columns specified for analysis are assumed to contain numerical
|
|
|
215 data and no checking is performed before analysis. By default, only numerical data is
|
|
|
216 used for analysis; other types of column data is ignored.
|
|
|
217 .ie n .IP "\fB\-\-frequencybins\fR \fInumber | ""number,number,[number,...]""\fR" 4
|
|
|
218 .el .IP "\fB\-\-frequencybins\fR \fInumber | ``number,number,[number,...]''\fR" 4
|
|
|
219 .IX Item "--frequencybins number | number,number,[number,...]"
|
|
|
220 Specify number of bins or bin range to use for frequency analysis. Default value: \fI10\fR
|
|
|
221 .Sp
|
|
|
222 Number of bins value along with the smallest and largest value for a column is used to
|
|
|
223 group the column values into different groups.
|
|
|
224 .Sp
|
|
|
225 The bin range list is used to group values for a column into different groups; It must contain
|
|
|
226 values in ascending order. Examples:
|
|
|
227 .Sp
|
|
|
228 .Vb 2
|
|
|
229 \& 10,20,30
|
|
|
230 \& 0.1,0.2,0.3,0.4,0.5
|
|
|
231 .Ve
|
|
|
232 .Sp
|
|
|
233 The frequency value calculated for a specific bin corresponds to all the column values
|
|
|
234 which are greater than the previous bin value and less than or equal to the current bin value.
|
|
|
235 .IP "\fB\-h, \-\-help\fR" 4
|
|
|
236 .IX Item "-h, --help"
|
|
|
237 Print this help message.
|
|
|
238 .IP "\fB\-\-indelim\fR \fIcomma | semicolon\fR" 4
|
|
|
239 .IX Item "--indelim comma | semicolon"
|
|
|
240 Input delimiter for \s-1CSV\s0 \fITextFile(s)\fR. Possible values: \fIcomma or semicolon\fR.
|
|
|
241 Default value: \fIcomma\fR. For \s-1TSV\s0 files, this option is ignored and \fItab\fR is used as a
|
|
|
242 delimiter.
|
|
|
243 .IP "\fB\-\-klargest\fR \fInumber\fR" 4
|
|
|
244 .IX Item "--klargest number"
|
|
|
245 Kth largest value to find by \fIKLargest\fR function. Default value: \fI2\fR Valid values: positive
|
|
|
246 integers.
|
|
|
247 .IP "\fB\-\-ksmallest\fR \fInumber\fR" 4
|
|
|
248 .IX Item "--ksmallest number"
|
|
|
249 Kth smallest value to find by \fIKSmallest\fR function. Default value: \fI2\fR. Valid values: positive
|
|
|
250 integers.
|
|
|
251 .ie n .IP "\fB\-m, \-\-mode\fR \fIDescriptiveStatisticsBasic | DescriptiveStatisticsAll | All | ""function1, [function2,...]""\fR" 4
|
|
|
252 .el .IP "\fB\-m, \-\-mode\fR \fIDescriptiveStatisticsBasic | DescriptiveStatisticsAll | All | ``function1, [function2,...]''\fR" 4
|
|
|
253 .IX Item "-m, --mode DescriptiveStatisticsBasic | DescriptiveStatisticsAll | All | function1, [function2,...]"
|
|
|
254 Specify how to analyze data in TextFile(s): calculate basic or all descriptive statistics; or
|
|
|
255 use a comma delimited list of supported statistical functions. Possible values:
|
|
|
256 \&\fIDescriptiveStatisticsBasic | DescriptiveStatisticsAll | \*(L"function1,[function2]...\*(R"\fR. Default
|
|
|
257 value: \fIDescriptiveStatisticsBasic\fR
|
|
|
258 .Sp
|
|
|
259 \&\fIDescriptiveStatisticsBasic\fR includes these functions: \fICount, Maximum, Minimum, Mean,
|
|
|
260 Median, Sum, StandardDeviation, StandardError, Variance\fR.
|
|
|
261 .Sp
|
|
|
262 \&\fIDescriptiveStatisticsAll\fR, in addition to \fIDescriptiveStatisticsBasic\fR functions, includes:
|
|
|
263 \&\fIGeometricMean, Frequency, HarmonicMean, KLargest, KSmallest, Kurtosis, Mode, RSquare,
|
|
|
264 Skewness, TrimMean\fR.
|
|
|
265 .Sp
|
|
|
266 \&\fIAll\fR uses complete list of supported functions: \fIAverage, AverageDeviation, Correlation,
|
|
|
267 Count, Covariance, GeometricMean, Frequency, HarmonicMean, KLargest, KSmallest, Kurtosis,
|
|
|
268 Maximum, Minimum, Mean, Median, Mode, RSquare, Skewness, Sum,
|
|
|
269 SumOfSquares, StandardDeviation, StandardDeviationN, StandardError, StandardScores,
|
|
|
270 StandardScoresN, TrimMean, Variance, VarianceN\fR. The function names ending with N
|
|
|
271 calculate corresponding values assuming an entire population instead of a population sample.
|
|
|
272 .Sp
|
|
|
273 Here are the formulas for these functions:
|
|
|
274 .Sp
|
|
|
275 Average: See Mean
|
|
|
276 .Sp
|
|
|
277 AverageDeviation: \s-1SUM\s0( \s-1ABS\s0(x[i] \- Xmean) ) / n
|
|
|
278 .Sp
|
|
|
279 Correlation: See Pearson Correlation
|
|
|
280 .Sp
|
|
|
281 Covariance: \s-1SUM\s0( (x[i] \- Xmean)(y[i] \- Ymean) ) / n
|
|
|
282 .Sp
|
|
|
283 GeometricMean: NthROOT( \s-1PRODUCT\s0(x[i]) )
|
|
|
284 .Sp
|
|
|
285 HarmonicMean: 1 / ( \s-1SUM\s0(1/x[i]) / n )
|
|
|
286 .Sp
|
|
|
287 Mean: \s-1SUM\s0( x[i] ) / n
|
|
|
288 .Sp
|
|
|
289 Median: Xsorted[(n \- 1)/2 + 1] for even values of n; (Xsorted[n/2] + Xsorted[n/2 + 1])/2
|
|
|
290 for odd values of n.
|
|
|
291 .Sp
|
|
|
292 Kurtosis: [ {n(n + 1)/(n \- 1)(n \- 2)(n \- 3)} SUM{ ((x[i] \- Xmean)/STDDEV)^4 } ] \-
|
|
|
293 {3((n \- 1)^2)}/{(n \- 2)(n\-3)}
|
|
|
294 .Sp
|
|
|
295 PearsonCorrelation: \s-1SUM\s0( (x[i] \- Xmean)(y[i] \- Ymean) ) / \s-1SQRT\s0( \s-1SUM\s0( (x[i] \- Xmean)^2 )
|
|
|
296 (\s-1SUM\s0( (y[i] \- Ymean)^2 )) )
|
|
|
297 .Sp
|
|
|
298 RSquare: PearsonCorrelation^2
|
|
|
299 .Sp
|
|
|
300 Skewness: {n/(n \- 1)(n \- 2)} SUM{ ((x[i] \- Xmean)/STDDEV)^3 }
|
|
|
301 .Sp
|
|
|
302 StandardDeviation: \s-1SQRT\s0 ( \s-1SUM\s0( (x[i] \- Mean)^2 ) / (n \- 1) )
|
|
|
303 .Sp
|
|
|
304 StandardDeviationN: \s-1SQRT\s0 ( \s-1SUM\s0( (x[i] \- Mean)^2 ) / n )
|
|
|
305 .Sp
|
|
|
306 StandardError: StandardDeviation / \s-1SQRT\s0( n )
|
|
|
307 .Sp
|
|
|
308 StandardScore: (x[i] \- Mean) / (n \- 1)
|
|
|
309 .Sp
|
|
|
310 StandardScoreN: (x[i] \- Mean) / n
|
|
|
311 .Sp
|
|
|
312 Variance: \s-1SUM\s0( (x[i] \- Xmean)^2 / (n \- 1) )
|
|
|
313 .Sp
|
|
|
314 VarianceN: \s-1SUM\s0( (x[i] \- Xmean)^2 / n )
|
|
|
315 .IP "\fB\-o, \-\-overwrite\fR" 4
|
|
|
316 .IX Item "-o, --overwrite"
|
|
|
317 Overwrite existing files.
|
|
|
318 .IP "\fB\-\-outdelim\fR \fIcomma | tab | semicolon\fR" 4
|
|
|
319 .IX Item "--outdelim comma | tab | semicolon"
|
|
|
320 Output text file delimiter. Possible values: \fIcomma, tab, or semicolon\fR
|
|
|
321 Default value: \fIcomma\fR.
|
|
|
322 .IP "\fB\-p, \-\-precision\fR \fInumber\fR" 4
|
|
|
323 .IX Item "-p, --precision number"
|
|
|
324 Precision of calculated values in the output file. Default: up to \fI2\fR decimal places.
|
|
|
325 Valid values: positive integers.
|
|
|
326 .IP "\fB\-q, \-\-quote\fR \fIyes | no\fR" 4
|
|
|
327 .IX Item "-q, --quote yes | no"
|
|
|
328 Put quotes around column values in output text file. Possible values: \fIyes or
|
|
|
329 no\fR. Default value: \fIyes\fR.
|
|
|
330 .IP "\fB\-r, \-\-root\fR \fIrootname\fR" 4
|
|
|
331 .IX Item "-r, --root rootname"
|
|
|
332 New text file name is generated using the root: <Root>.<Ext>. Default new file
|
|
|
333 name: <InitialTextFileName><Mode>.<Ext>. Based on the specified analysis,
|
|
|
334 <Mode> corresponds to one of these values: DescriptiveStatisticsBasic,
|
|
|
335 DescriptiveStatisticsAll, AllStatistics, SpecifiedStatistics, Covariance, Correlation,
|
|
|
336 Frequency, or StandardScores. The csv, and tsv <Ext> values are used for
|
|
|
337 comma/semicolon, and tab delimited text files respectively. This option is ignored for
|
|
|
338 multiple input files.
|
|
|
339 .IP "\fB\-\-trimfraction\fR \fInumber\fR" 4
|
|
|
340 .IX Item "--trimfraction number"
|
|
|
341 Fraction of data to exclude from the top and bottom of the data set during
|
|
|
342 \&\fITrimMean\fR calculation. Default value: \fI0.1\fR. Valid values: > 0 and < 1.
|
|
|
343 .IP "\fB\-w \-\-workingdir\fR \fItext\fR" 4
|
|
|
344 .IX Item "-w --workingdir text"
|
|
|
345 Location of working directory. Default: current directory.
|
|
|
346 .SH "EXAMPLES"
|
|
|
347 .IX Header "EXAMPLES"
|
|
|
348 To calculate basic statistics for data in first column and generate a
|
|
|
349 NewSample1DescriptiveStatisticsBasic.csv file, type:
|
|
|
350 .PP
|
|
|
351 .Vb 1
|
|
|
352 \& % AnalyzeTextFilesData.pl \-o \-r NewSample1 Sample1.csv
|
|
|
353 .Ve
|
|
|
354 .PP
|
|
|
355 To calculate basic statistics for data in third column and generate a
|
|
|
356 NewSample1DescriptiveStatisticsBasic.csv file, type:
|
|
|
357 .PP
|
|
|
358 .Vb 1
|
|
|
359 \& % AnalyzeTextFilesData.pl \-\-columns 3 \-o \-r NewSample1 Sample1.csv
|
|
|
360 .Ve
|
|
|
361 .PP
|
|
|
362 To calculate basic statistics for data in MolWeight column and generate a
|
|
|
363 NewSample1DescriptiveStatisticsBasic.csv file, type:
|
|
|
364 .PP
|
|
|
365 .Vb 2
|
|
|
366 \& % AnalyzeTextFilesData.pl \-colmode collabel \-\-columns MolWeight \-o
|
|
|
367 \& \-r NewSample1 Sample1.csv
|
|
|
368 .Ve
|
|
|
369 .PP
|
|
|
370 To calculate all available statistics for data in third column and all column pairs,
|
|
|
371 and generate NewSample1DescriptiveStatisticsAll.csv, NewSample1CorrelationMatrix.csv,
|
|
|
372 NewSample1CorrelationMatrix.csv, and NewSample1MolWeightFrequencyAnalysis.csv files,
|
|
|
373 type:
|
|
|
374 .PP
|
|
|
375 .Vb 2
|
|
|
376 \& % AnalyzeTextFilesData.pl \-m DescriptiveStatisticsAll \-\-columns 3 \-o
|
|
|
377 \& \-\-columnpairs AllPairs \-r NewSample1 Sample1.csv
|
|
|
378 .Ve
|
|
|
379 .PP
|
|
|
380 To compute frequency distribution of data in third column into five bins and
|
|
|
381 generate NewSample1MolWeightFrequencyAnalysis.csv, type:
|
|
|
382 .PP
|
|
|
383 .Vb 2
|
|
|
384 \& % AnalyzeTextFilesData.pl \-m Frequency \-\-frequencybins 5 \-\-columns 3
|
|
|
385 \& \-o \-r NewSample1 Sample1.csv
|
|
|
386 .Ve
|
|
|
387 .PP
|
|
|
388 To compute frequency distribution of data in third column into specified bin range
|
|
|
389 values, and generate NewSample1MolWeightFrequencyAnalysis.csv, type:
|
|
|
390 .PP
|
|
|
391 .Vb 2
|
|
|
392 \& % AnalyzeTextFilesData.pl \-m Frequency \-\-frequencybins "100,200,400"
|
|
|
393 \& \-\-columns 3 \-o \-r NewSample1 Sample1.csv
|
|
|
394 .Ve
|
|
|
395 .PP
|
|
|
396 To calculate all available statistics for data in all columns and column pairs, type:
|
|
|
397 .PP
|
|
|
398 .Vb 2
|
|
|
399 \& % AnalyzeTextFilesData.pl \-m All \-\-columns All \-\-columnpairs
|
|
|
400 \& AllPairs \-o \-r NewSample1 Sample1.csv
|
|
|
401 .Ve
|
|
|
402 .SH "AUTHOR"
|
|
|
403 .IX Header "AUTHOR"
|
|
|
404 Manish Sud <msud@san.rr.com>
|
|
|
405 .SH "SEE ALSO"
|
|
|
406 .IX Header "SEE ALSO"
|
|
|
407 JoinTextFiles.pl, MergeTextFilesWithSD.pl, ModifyTextFilesFormat.pl, SplitTextFiles.pl, TextFilesToHTML.pl
|
|
|
408 .SH "COPYRIGHT"
|
|
|
409 .IX Header "COPYRIGHT"
|
|
|
410 Copyright (C) 2015 Manish Sud. All rights reserved.
|
|
|
411 .PP
|
|
|
412 This file is part of MayaChemTools.
|
|
|
413 .PP
|
|
|
414 MayaChemTools is free software; you can redistribute it and/or modify it under
|
|
|
415 the terms of the \s-1GNU\s0 Lesser General Public License as published by the Free
|
|
|
416 Software Foundation; either version 3 of the License, or (at your option)
|
|
|
417 any later version.
|
