Add CM-SPADE Algorithm for sequential pattern mining by lubimoemestechko · Pull Request #703 · Desbordante/desbordante-core

lubimoemestechko · 2026-03-18T19:00:37Z

This pull request adds a new algorithm for vertical mining of sequential patterns. The following functionalities have been developed:

the core CM-SPADE algorithm and the structures it uses;
a parser for handling sequences where the symbol -1 indicates the start of a new itemset and the symbol -2 indicates the end of a sequence;
Python bindings to use the algorithm from Python.

github-actions

clang-tidy made some suggestions

github-actions · 2026-03-18T19:06:37Z

+            EquivalenceClass& child_y = (i == j) ? child_x : eq_members[j];
+            Int item_y = child_y.GetClassIdentifier()->GetLastElement().GetItem().GetId();
+
+            bool do_not_explore_XY = false, do_not_explore_YX = false;


warning: invalid case style for variable 'do_not_explore_XY' [readability-identifier-naming]

Suggested change

bool do_not_explore_XY = false, do_not_explore_YX = false;

bool do_not_explore_xy = false, do_not_explore_YX = false;

src/core/algorithms/cmspade/cmspade.cpp:111:

- do_not_explore_XY = (count1 < minsup_absolute_); + do_not_explore_xy = (count1 < minsup_absolute_);

src/core/algorithms/cmspade/cmspade.cpp:113:

- do_not_explore_XY = true; + do_not_explore_xy = true;

src/core/algorithms/cmspade/cmspade.cpp:116:

- do_not_explore_XY = true; + do_not_explore_xy = true;

src/core/algorithms/cmspade/cmspade.cpp:133:

- do_not_explore_XY = true; + do_not_explore_xy = true;

src/core/algorithms/cmspade/cmspade.cpp:168:

- if (do_not_explore_XY && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_Y_X){ + if (do_not_explore_xy && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_Y_X){

src/core/algorithms/cmspade/cmspade.cpp:173:

- minsup_absolute_, do_not_explore_XY, do_not_explore_YX, + minsup_absolute_, do_not_explore_xy, do_not_explore_YX,

github-actions · 2026-03-18T19:06:37Z

+            EquivalenceClass& child_y = (i == j) ? child_x : eq_members[j];
+            Int item_y = child_y.GetClassIdentifier()->GetLastElement().GetItem().GetId();
+
+            bool do_not_explore_XY = false, do_not_explore_YX = false;


warning: invalid case style for variable 'do_not_explore_YX' [readability-identifier-naming]

Suggested change

bool do_not_explore_XY = false, do_not_explore_YX = false;

bool do_not_explore_XY = false, do_not_explore_yx = false;

src/core/algorithms/cmspade/cmspade.cpp:125:

- do_not_explore_YX = (count2 < minsup_absolute_); + do_not_explore_yx = (count2 < minsup_absolute_);

src/core/algorithms/cmspade/cmspade.cpp:127:

- do_not_explore_YX = true; + do_not_explore_yx = true;

src/core/algorithms/cmspade/cmspade.cpp:130:

- do_not_explore_YX = true; + do_not_explore_yx = true;

src/core/algorithms/cmspade/cmspade.cpp:134:

- do_not_explore_YX = true; + do_not_explore_yx = true;

src/core/algorithms/cmspade/cmspade.cpp:168:

- if (do_not_explore_XY && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_Y_X){ + if (do_not_explore_XY && do_not_explore_yx && do_not_explore_X_Y && do_not_explore_Y_X){

src/core/algorithms/cmspade/cmspade.cpp:173:

- minsup_absolute_, do_not_explore_XY, do_not_explore_YX, + minsup_absolute_, do_not_explore_XY, do_not_explore_yx,

github-actions · 2026-03-18T19:06:37Z

+            Int item_y = child_y.GetClassIdentifier()->GetLastElement().GetItem().GetId();
+
+            bool do_not_explore_XY = false, do_not_explore_YX = false;
+            bool do_not_explore_X_Y = false, do_not_explore_Y_X = false;


warning: invalid case style for variable 'do_not_explore_X_Y' [readability-identifier-naming]

Suggested change

bool do_not_explore_X_Y = false, do_not_explore_Y_X = false;

bool do_not_explore_x_y = false, do_not_explore_Y_X = false;

src/core/algorithms/cmspade/cmspade.cpp:142:

- do_not_explore_X_Y = (count1 < minsup_absolute_); + do_not_explore_x_y = (count1 < minsup_absolute_);

src/core/algorithms/cmspade/cmspade.cpp:144:

- do_not_explore_X_Y = true; + do_not_explore_x_y = true;

src/core/algorithms/cmspade/cmspade.cpp:147:

- do_not_explore_X_Y = true; + do_not_explore_x_y = true;

src/core/algorithms/cmspade/cmspade.cpp:164:

- do_not_explore_X_Y = true; + do_not_explore_x_y = true;

src/core/algorithms/cmspade/cmspade.cpp:168:

- if (do_not_explore_XY && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_Y_X){ + if (do_not_explore_XY && do_not_explore_YX && do_not_explore_x_y && do_not_explore_Y_X){

src/core/algorithms/cmspade/cmspade.cpp:174:

- do_not_explore_X_Y, do_not_explore_Y_X); + do_not_explore_x_y, do_not_explore_Y_X);

github-actions · 2026-03-18T19:06:38Z

+            Int item_y = child_y.GetClassIdentifier()->GetLastElement().GetItem().GetId();
+
+            bool do_not_explore_XY = false, do_not_explore_YX = false;
+            bool do_not_explore_X_Y = false, do_not_explore_Y_X = false;


warning: invalid case style for variable 'do_not_explore_Y_X' [readability-identifier-naming]

Suggested change

bool do_not_explore_X_Y = false, do_not_explore_Y_X = false;

bool do_not_explore_X_Y = false, do_not_explore_y_x = false;

src/core/algorithms/cmspade/cmspade.cpp:156:

- do_not_explore_Y_X = (count2 < minsup_absolute_); + do_not_explore_y_x = (count2 < minsup_absolute_);

src/core/algorithms/cmspade/cmspade.cpp:158:

- do_not_explore_Y_X = true; + do_not_explore_y_x = true;

src/core/algorithms/cmspade/cmspade.cpp:161:

- do_not_explore_Y_X = true; + do_not_explore_y_x = true;

src/core/algorithms/cmspade/cmspade.cpp:165:

- do_not_explore_Y_X = true; + do_not_explore_y_x = true;

src/core/algorithms/cmspade/cmspade.cpp:168:

- if (do_not_explore_XY && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_Y_X){ + if (do_not_explore_XY && do_not_explore_YX && do_not_explore_X_Y && do_not_explore_y_x){

src/core/algorithms/cmspade/cmspade.cpp:174:

- do_not_explore_X_Y, do_not_explore_Y_X); + do_not_explore_X_Y, do_not_explore_y_x);

github-actions · 2026-03-18T19:06:38Z

+    const std::vector<Item> &GetItems() const { return items_; }
+    Item GetItem(int index) const { return items_[index]; }
+
+    std::size_t size() const { return items_.size(); }


warning: invalid case style for function 'size' [readability-identifier-naming]

Suggested change

std::size_t size() const { return items_.size(); }

std::size_t Size() const { return items_.size(); }

github-actions · 2026-03-18T19:06:38Z

+    Item GetItem(int index) const { return items_[index]; }
+
+    std::size_t size() const { return items_.size(); }
+    bool empty() const { return items_.empty(); }


warning: invalid case style for function 'empty' [readability-identifier-naming]

Suggested change

bool empty() const { return items_.empty(); }

bool Empty() const { return items_.empty(); }

github-actions · 2026-03-18T19:06:38Z

+
+    const std::vector<std::unique_ptr<Itemset>>& GetItemsets() const { return itemsets_; }
+
+    size_t size() const { return itemsets_.size(); }


warning: invalid case style for function 'size' [readability-identifier-naming]

Suggested change

size_t size() const { return itemsets_.size(); }

size_t Size() const { return itemsets_.size(); }

github-actions · 2026-03-18T19:06:38Z

+    const std::vector<std::unique_ptr<Itemset>>& GetItemsets() const { return itemsets_; }
+
+    size_t size() const { return itemsets_.size(); }
+    int length() const { return number_of_items_; }


warning: invalid case style for function 'length' [readability-identifier-naming]

Suggested change

int length() const { return number_of_items_; }

int Length() const { return number_of_items_; }

github-actions · 2026-03-18T19:06:38Z

+        }
+    }
+
+    if (!current_itemset->empty()) {


warning: Dereference of null smart pointer 'current_itemset' of type 'std::unique_ptr' [clang-analyzer-cplusplus.Move]

if (!current_itemset->empty()) { ^

Additional context

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:22: Calling 'CMSpadeParser::ParseNextSequence'

while (ParseNextSequence(sequence_id, sequence)) { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:35: Loop condition is true. Entering loop body

while (std::getline(file_, line)) { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Assuming the condition is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Left side of '||' is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Assuming the condition is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Left side of '||' is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Assuming the condition is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Left side of '||' is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Assuming the condition is false

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:36: Taking false branch

if (line.empty() || line[0] == '#' || line[0] == '%' || line[0] == '@') { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:40: Calling 'CMSpadeParser::ParseSequenceLine'

ParseSequenceLine(line, sequence_id, sequence); ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:55: Loop condition is true. Entering loop body

while(iss >> token){ ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:56: Assuming the condition is false

if (token[0] == '<'){ ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:56: Taking false branch

if (token[0] == '<'){ ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:60: Taking false branch

if (token == "-1"){ ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:67: Taking true branch

else if (token == "-2"){ ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:68: Assuming the condition is true

if (!current_itemset->empty()) { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:68: Taking true branch

if (!current_itemset->empty()) { ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:69: Smart pointer 'current_itemset' of type 'std::unique_ptr' is reset to null when moved from

sequence->AddItemset(std::move(current_itemset)); ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:72: Execution continues on line 83

break; ^

src/core/algorithms/cmspade/parser/cmspade_parser.cpp:82: Dereference of null smart pointer 'current_itemset' of type 'std::unique_ptr'

if (!current_itemset->empty()) { ^

github-actions · 2026-03-18T19:06:38Z

+
+class CMSpadeInternalTest : public ::testing::Test {
+protected:
+    TestableCMSpade algo;


warning: invalid case style for protected member 'algo' [readability-identifier-naming]

Suggested change

TestableCMSpade algo;

TestableCMSpade algo_;

src/tests/unit/test_cmspade.cpp:215:

- algo.SetPath(file.GetPath()); - algo.LoadDataInternal(); - algo.BuildCMap(); + algo_.SetPath(file.GetPath()); + algo_.LoadDataInternal(); + algo_.BuildCMap();

src/tests/unit/test_cmspade.cpp:219:

- auto cmap_eq = algo.cmap_equal_; + auto cmap_eq = algo_.cmap_equal_;

src/tests/unit/test_cmspade.cpp:227:

- algo.SetPath(file.GetPath()); - algo.LoadDataInternal(); - algo.BuildCMap(); + algo_.SetPath(file.GetPath()); + algo_.LoadDataInternal(); + algo_.BuildCMap();

src/tests/unit/test_cmspade.cpp:231:

- auto cmap_after = algo.cmap_after_; + auto cmap_after = algo_.cmap_after_;

src/tests/unit/test_cmspade.cpp:244:

- auto candidates = algo.Generator(&p1, &p2, 1, false, false, false, false); + auto candidates = algo_.Generator(&p1, &p2, 1, false, false, false, false);

src/tests/unit/test_cmspade.cpp:254:

- auto candidates = algo.Generator(&p1, &p2, 1, true, true, true, true); + auto candidates = algo_.Generator(&p1, &p2, 1, true, true, true, true);

src/tests/unit/test_cmspade.cpp:260:

- algo.SetPath(file.GetPath()); - algo.LoadDataInternal(); + algo_.SetPath(file.GetPath()); + algo_.LoadDataInternal();

src/tests/unit/test_cmspade.cpp:263:

- algo.itemset_counts_ = std::make_shared<std::vector<ItemsetId>>(std::vector<ItemsetId>{1, 1}); - algo.BuildFrequentItems(2); - algo.RemoveInfrequentItemsFromSequences(); + algo_.itemset_counts_ = std::make_shared<std::vector<ItemsetId>>(std::vector<ItemsetId>{1, 1}); + algo_.BuildFrequentItems(2); + algo_.RemoveInfrequentItemsFromSequences();

src/tests/unit/test_cmspade.cpp:267:

- auto& seqs = algo.sequences_; + auto& seqs = algo_.sequences_;

github-actions

clang-tidy made some suggestions

github-actions · 2026-05-11T17:27:46Z

+}
+
+TEST(CMSpadeExecuteTest, RemoveEmptySequences) {
+    TestableCMSpade algo_;


warning: invalid case style for variable 'algo_' [readability-identifier-naming]

Suggested change

TestableCMSpade algo_;

TestableCMSpade algo;

src/tests/unit/test_cmspade.cpp:288:

- algo_.SetPath(file.GetPath()); - algo_.LoadDataInternal(); - algo_.itemset_counts_ = + algo.SetPath(file.GetPath()); + algo.LoadDataInternal(); + algo.itemset_counts_ =

src/tests/unit/test_cmspade.cpp:293:

- algo_.minsup_absolute_ = 2; - algo_.BuildFrequentItems(); - algo_.RemoveInfrequentItemsFromSequences(); - algo_.RemoveEmptySequences(); + algo.minsup_absolute_ = 2; + algo.BuildFrequentItems(); + algo.RemoveInfrequentItemsFromSequences(); + algo.RemoveEmptySequences();

src/tests/unit/test_cmspade.cpp:298:

- EXPECT_EQ(algo_.sequences_.size(), 2); + EXPECT_EQ(algo.sequences_.size(), 2);

github-actions Bot reviewed Mar 18, 2026

View reviewed changes

lubimoemestechko marked this pull request as draft March 18, 2026 19:38

lubimoemestechko marked this pull request as ready for review April 20, 2026 18:13

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

ac17660

lubimoemestechko force-pushed the feature-cmspade branch from bc62c9b to ac17660 Compare May 11, 2026 16:31

lubimoemestechko added 2 commits May 11, 2026 17:09

med

46a3802

med

bf702d8

github-actions Bot reviewed May 11, 2026

View reviewed changes

	bool do_not_explore_XY = false, do_not_explore_YX = false;
	bool do_not_explore_xy = false, do_not_explore_YX = false;

	bool do_not_explore_X_Y = false, do_not_explore_Y_X = false;
	bool do_not_explore_x_y = false, do_not_explore_Y_X = false;

	std::size_t size() const { return items_.size(); }
	std::size_t Size() const { return items_.size(); }

	bool empty() const { return items_.empty(); }
	bool Empty() const { return items_.empty(); }


		const std::vector<std::unique_ptr<Itemset>>& GetItemsets() const { return itemsets_; }

		size_t size() const { return itemsets_.size(); }

	int length() const { return number_of_items_; }
	int Length() const { return number_of_items_; }

Conversation

lubimoemestechko commented Mar 18, 2026

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot Mar 18, 2026

Choose a reason for hiding this comment

Uh oh!

github-actions Bot left a comment

Choose a reason for hiding this comment

Uh oh!

github-actions Bot May 11, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant