A library for working with phylogenetic and population genetic data.
v0.27.0
sequence/functions/stats.hpp
Go to the documentation of this file.
1 #ifndef GENESIS_SEQUENCE_FUNCTIONS_STATS_H_
2 #define GENESIS_SEQUENCE_FUNCTIONS_STATS_H_
3 
4 /*
5  Genesis - A toolkit for working with phylogenetic data.
6  Copyright (C) 2014-2017 Lucas Czech
7 
8  This program is free software: you can redistribute it and/or modify
9  it under the terms of the GNU General Public License as published by
10  the Free Software Foundation, either version 3 of the License, or
11  (at your option) any later version.
12 
13  This program is distributed in the hope that it will be useful,
14  but WITHOUT ANY WARRANTY; without even the implied warranty of
15  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16  GNU General Public License for more details.
17 
18  You should have received a copy of the GNU General Public License
19  along with this program. If not, see <http://www.gnu.org/licenses/>.
20 
21  Contact:
22  Lucas Czech <lucas.czech@h-its.org>
23  Exelixis Lab, Heidelberg Institute for Theoretical Studies
24  Schloss-Wolfsbrunnenweg 35, D-69118 Heidelberg, Germany
25 */
26 
34 #include <map>
35 #include <string>
36 #include <vector>
37 
38 namespace genesis {
39 namespace sequence {
40 
41 // =================================================================================================
42 // Forwad Declarations
43 // =================================================================================================
44 
45 class Sequence;
46 class SiteCounts;
47 class SequenceSet;
48 
49 // =================================================================================================
50 // Characteristics
51 // =================================================================================================
52 
59 std::map<char, size_t> site_histogram( Sequence const& seq );
60 
67 std::map<char, size_t> site_histogram( SequenceSet const& set );
68 
79 std::map<char, double> base_frequencies( Sequence const& seq, std::string const& plain_chars );
80 
86 std::map<char, double> base_frequencies( SequenceSet const& set, std::string const& plain_chars );
87 
98 size_t count_chars( SequenceSet const& set, std::string const& chars );
99 
111 double gapyness( SequenceSet const& set, std::string const& gap_chars );
112 
113 size_t gap_site_count( SiteCounts const& counts );
114 
115 } // namespace sequence
116 } // namespace genesis
117 
118 #endif // include guard
genesis::sequence::gap_site_count
size_t gap_site_count(SiteCounts const &counts)
Definition: sequence/functions/stats.cpp:190
genesis
Container namespace for all symbols of genesis in order to keep them separate when used as a library.
Definition: placement/formats/edge_color.cpp:42
genesis::sequence::base_frequencies
std::map< char, double > base_frequencies(Sequence const &seq, std::string const &plain_chars)
Get the base frequencies of the sites in a Sequence given the base chars.
Definition: sequence/functions/stats.cpp:135
genesis::sequence::count_chars
size_t count_chars(SequenceSet const &set, std::string const &chars)
Count the number of occurrences of the given chars within the sites of the SequenceSet.
Definition: sequence/functions/stats.cpp:151
genesis::sequence::gapyness
double gapyness(SequenceSet const &set, std::string const &gap_chars)
Return the "gapyness" of the Sequences, i.e., the proportion of gap chars and other completely undete...
Definition: sequence/functions/stats.cpp:177
genesis::sequence::site_histogram
std::map< char, size_t > site_histogram(Sequence const &seq)
Get a histogram of the occurrences of particular sites, given a Sequence.
Definition: sequence/functions/stats.cpp:53