Add core algorithm, parser, models, test and python bindings

Author: lubimoemestechko

examples/basic/mining_frequent_patterns.py

@@ -0,0 +1,9 @@
+import desbordante
+Database = 'examples/datasets/cmspade/cmspade_simple_test.txt'
+algo = desbordante.cmspade.algorithms.CMSpade()
+algo.load_data(sequence_database = Database, minsup = 0.75)
+algo.execute()
+result = algo.get_frequent_patterns()
+print(f'Found {len(result)} frequent patterns \n')
+for p in result:
+    print(p)

examples/datasets/cmspade/cmspade_simple_test.txt

@@ -0,0 +1,4 @@
+1 2 -1 3 -1 6 7 -1 7 -1 5 -1 -2
+1 -1 2 -1 6 -1 5 -1 -2
+2 -1 6 7 -1 -2
+1 4 -1 3 -1 2 -1 1 2 5 6 -1 -2

src/core/algorithms/CMakeLists.txt

@@ -2,6 +2,7 @@ set(SUBDIRS
     algebraic_constraints
     association_rules
     cfd
+    cmspade
     dc
     dd
     fd
@@ -41,6 +42,7 @@ target_link_libraries(
               ${DESBORDANTE_PREFIX}::ar
               ${DESBORDANTE_PREFIX}::cfd
               ${DESBORDANTE_PREFIX}::cfd::verifier
+              ${DESBORDANTE_PREFIX}::cmspade
               ${DESBORDANTE_PREFIX}::datastats
               ${DESBORDANTE_PREFIX}::dd::split
               ${DESBORDANTE_PREFIX}::fd::aid

src/core/algorithms/algorithm_types.h

@@ -11,7 +11,7 @@ using AlgorithmTypes =
                    fd_verifier::FDVerifier, HyUCC, PyroUCC, HPIValid, cfd::FDFirstAlgorithm,
                    ACAlgorithm, UCCVerifier, Faida, Spider, Mind, INDVerifier, Fastod, GfdValidator,
                    EGfdValidator, NaiveGfdValidator, order::Order, dd::Split, Cords, hymd::HyMD,
-                   PFDVerifier, cfd_verifier::CFDVerifier>;
+                   PFDVerifier, cfd_verifier::CFDVerifier, cmspade::CMSpade>;
 
 // clang-format off
 /* Enumeration of all supported non-pipeline algorithms. If you implement a new
@@ -96,7 +96,10 @@ BETTER_ENUM(AlgorithmType, char,
     pfd_verifier,
 
 /* CFD verifier algorithm */
-    cfd_verifier
+    cfd_verifier,
+
+/* Frequent patterns mining algorithm */
+    cmspade
 )
 // clang-format on
 

src/core/algorithms/algorithms.h

@@ -4,6 +4,7 @@
 #include "core/algorithms/association_rules/mining_algorithms.h"
 #include "core/algorithms/cfd/cfd_verifier/cfd_verifier.h"
 #include "core/algorithms/cfd/mining_algorithms.h"
+#include "core/algorithms/cmspade/cmspade.h"
 #include "core/algorithms/dd/mining_algorithms.h"
 #include "core/algorithms/fd/mining_algorithms.h"
 #include "core/algorithms/fd/sfd/cords.h"
@@ -18,4 +19,4 @@
 #include "core/algorithms/od/mining_algorithms.h"
 #include "core/algorithms/statistics/algorithms.h"
 #include "core/algorithms/ucc/mining_algorithms.h"
-#include "core/algorithms/ucc/verification_algorithms.h"
+#include "core/algorithms/ucc/verification_algorithms.h" 

src/core/algorithms/cmspade/CMakeLists.txt

@@ -0,0 +1,21 @@
+add_subdirectory(model)
+add_subdirectory(parser)
+
+set(NAME cmspade)
+desbordante_add_lib(NAME)
+
+target_sources(
+    ${NAME}
+    PRIVATE cmspade.cpp
+    PUBLIC FILE_SET HEADERS BASE_DIRS "${PROJECT_SOURCE_DIR}/src"
+)
+
+target_link_libraries(
+    ${NAME}
+    PUBLIC
+        ${DESBORDANTE_PREFIX}::cmspade::model
+        ${DESBORDANTE_PREFIX}::cmspade::parser
+        Boost::headers
+    PRIVATE
+        ${DESBORDANTE_PREFIX}::algos better-enums
+)