Presentation

CMakeLists.txt

@@ -4,11 +4,6 @@ project(sequence_miner LANGUAGES CXX)
 
 set(CMAKE_CXX_STANDARD 17)
 
-set(CATCH_INCLUDE_DIR ${CMAKE_CURRENT_SOURCE_DIR}/extern/catch2)
-add_library(Catch2::Catch IMPORTED INTERFACE)
-set_property(TARGET Catch2::Catch PROPERTY INTERFACE_INCLUDE_DIRECTORIES "${CATCH_INCLUDE_DIR}")
-
 add_subdirectory(extern/yaml)
 add_subdirectory(src)
 add_subdirectory(app)
-add_subdirectory(tests)

data/config_fifa.yaml

@@ -0,0 +1,20 @@
+# file with input data, full path should be provided
+input_file: ./data/fifa.spmf
+# minimum support for the sequence
+min_support: 4000
+# separator between sequence_id, time_id and the sequence data
+input_ids_separator: " "
+# separator between sequence items in one time point
+input_items_separator: ", "
+# file to write frequent sequences
+output_file: ./data/out.txt
+# separator between items in output files
+output_items_separator: " "
+# separator between itemsets in output files
+output_events_separator: "-1"
+# algorithm to detect sequences, possible values: spade, prefixspan
+algorithm: prefixspan
+# if true spade uses DFS, BFS otherwise
+spade_dfs: false
+# maximum number of sequences to read from the input, if -1 whole file is read
+input_limit: 20000

data/config_paper.yaml

@@ -0,0 +1,20 @@
+# file with input data, full path should be provided
+input_file: ./data/input_prefixspan_paper.txt
+# minimum support for the sequence
+min_support: 1
+# separator between sequence_id, time_id and the sequence data
+input_ids_separator: " "
+# separator between sequence items in one time point
+input_items_separator: ", "
+# file to write frequent sequences
+output_file: ./data/out.txt
+# separator between items in output files
+output_items_separator: " "
+# separator between itemsets in output files
+output_events_separator: "|"
+# algorithm to detect sequences, possible values: spade, prefixspan
+algorithm: spade
+# if true spade uses DFS, BFS otherwise
+spade_dfs: false
+# maximum number of sequences to read from the input, if -1 whole file is read
+input_limit: 20000

data/config_simple.yaml

@@ -0,0 +1,20 @@
+# file with input data, full path should be provided
+input_file: ./data/simple_input.txt
+# minimum support for the sequence
+min_support: 2
+# separator between sequence_id, time_id and the sequence data
+input_ids_separator: " "
+# separator between sequence items in one time point
+input_items_separator: ", "
+# file to write frequent sequences
+output_file: ./data/out.txt
+# separator between items in output files
+output_items_separator: " "
+# separator between itemsets in output files
+output_events_separator: "|"
+# algorithm to detect sequences, possible values: spade, prefixspan
+algorithm: prefixspan
+# if true spade uses DFS, BFS otherwise
+spade_dfs: false
+# maximum number of sequences to read from the input, if -1 whole file is read
+input_limit: -1

data/config_string.yaml

@@ -0,0 +1,20 @@
+# file with input data, full path should be provided
+input_file: ./data/simple_string_input.txt
+# minimum support for the sequence
+min_support: 1
+# separator between sequence_id, time_id and the sequence data
+input_ids_separator: " "
+# separator between sequence items in one time point
+input_items_separator: ", "
+# file to write frequent sequences
+output_file: ./data/out.txt
+# separator between items in output files
+output_items_separator: " "
+# separator between itemsets in output files
+output_events_separator: "|"
+# algorithm to detect sequences, possible values: spade, prefixspan
+algorithm: spade
+# if true spade uses DFS, BFS otherwise
+spade_dfs: false
+# maximum number of sequences to read from the input, if -1 whole file is read
+input_limit: 20000