From 42f703a21a63d69a14a75ef75a80c3fce6f03ce3 Mon Sep 17 00:00:00 2001 From: Tarun Sreepada Date: Mon, 20 May 2024 11:14:43 +0900 Subject: [PATCH] minor optimization --- PAMI/frequentPattern/basic/ECLAT.py | 143 +++--- PAMI/frequentPattern/basic/ECLATDiffset.py | 116 +++-- PAMI/frequentPattern/basic/_ECLATDiffset.py | 402 +++++++++++++++++ PAMI/frequentPattern/topk/FAE.py | 12 +- PAMI/frequentPattern/topk/_FAE.py | 458 ++++++++++++++++++++ 5 files changed, 987 insertions(+), 144 deletions(-) create mode 100644 PAMI/frequentPattern/basic/_ECLATDiffset.py create mode 100644 PAMI/frequentPattern/topk/_FAE.py diff --git a/PAMI/frequentPattern/basic/ECLAT.py b/PAMI/frequentPattern/basic/ECLAT.py index c4466ccf..d7cafe5c 100644 --- a/PAMI/frequentPattern/basic/ECLAT.py +++ b/PAMI/frequentPattern/basic/ECLAT.py @@ -59,21 +59,21 @@ class ECLAT(_ab._frequentPatterns): About this algorithm ==================== - :**Description**: *ECLAT is one of the fundamental algorithm to discover frequent patterns in a transactional database.* + :**Description**: ECLAT is one of the fundamental algorithm to discover frequent patterns in a transactional database. :**Reference**: Mohammed Javeed Zaki: Scalable Algorithms for Association Mining. IEEE Trans. Knowl. Data Eng. 12(3): - 372-390 (2000), https://ieeexplore.ieee.org/document/846291 + 372-390 (2000), https://ieeexplore.ieee.org/document/846291 :**Parameters**: - **iFile** (*str or URL or dataFrame*) -- *Name of the Input file to mine complete set of frequent patterns.* - - **oFile** (*str*) -- *Name of the Output file to store the frequent patterns.* - - **minSup** (*int or float or str*) -- The user can specify minSup either in count or proportion of database size. If the program detects the data type of minSup is integer, then it treats minSup is expressed in count. - - **sep** (*str*) -- This variable is used to distinguish items from one another in a transaction. The default seperator is tab space. However, the users can override their default separator. + - **oFile** (*str*) -- *Name of the output file to store complete set of frequent patterns.* + - **minSup** (*int or float or str*) -- *The user can specify minSup either in count or proportion of database size. If the program detects the data type of minSup is integer, then it treats minSup is expressed in count. Otherwise, it will be treated as float.* + - **sep** (*str*) -- *This variable is used to distinguish items from one another in a transaction. The default seperator is tab space. However, the users can override their default separator.* :**Attributes**: - **startTime** (*float*) -- *To record the start time of the mining process.* - - **endTime** (*float*) -- *To record the end time of the mining process.* + - **endTime** (*float*) -- *To record the completion time of the mining process.* - **finalPatterns** (*dict*) -- *Storing the complete set of patterns in a dictionary variable.* - **memoryUSS** (*float*) -- *To store the total amount of USS memory consumed by the program.* - - **memoryRSS** *(float*) -- *To store the total amount of RSS memory consumed by the program.* + - **memoryRSS** (*float*) -- *To store the total amount of RSS memory consumed by the program.* - **Database** (*list*) -- *To store the transactions of a database in list.* Execution methods @@ -183,58 +183,6 @@ def _creatingItemSets(self) -> float: print("File Not Found") quit() - def _getUniqueItemList(self) -> list: - """ - - Generating one frequent patterns - - :return: list of unique patterns - :rtype: list - """ - self._finalPatterns = {} - candidate = {} - uniqueItem = [] - for i in range(len(self._Database)): - for j in range(len(self._Database[i])): - if self._Database[i][j] not in candidate: - candidate[self._Database[i][j]] = {i} - else: - candidate[self._Database[i][j]].add(i) - for key, value in candidate.items(): - supp = len(value) - if supp >= self._minSup: - self._finalPatterns[key] = [value] - uniqueItem.append(key) - uniqueItem.sort() - return uniqueItem - - def _generateFrequentPatterns(self, candidateFrequent: list) -> None: - """ - - It will generate the combinations of frequent items - - :param candidateFrequent :it represents the items with their respective transaction identifiers - :type candidateFrequent: list - :return: None - """ - new_freqList = [] - for i in range(0, len(candidateFrequent)): - item1 = candidateFrequent[i] - i1_list = item1.split() - for j in range(i + 1, len(candidateFrequent)): - item2 = candidateFrequent[j] - i2_list = item2.split() - if i1_list[:-1] == i2_list[:-1]: - interSet = self._finalPatterns[item1][0].intersection(self._finalPatterns[item2][0]) - if len(interSet) >= self._minSup: - newKey = item1 + "\t" + i2_list[-1] - self._finalPatterns[newKey] = [interSet] - new_freqList.append(newKey) - else: break - - if len(new_freqList) > 0: - self._generateFrequentPatterns(new_freqList) - def _convert(self, value) -> float: """ @@ -264,6 +212,30 @@ def startMine(self) -> None: self.mine() + def __recursive(self, items, cands): + """ + + This function generates new candidates by taking input as original candidates. + + :param items: A dictionary containing items and their corresponding support values. + :type items: dict + :param cands: A list of candidate itemsets. + :type cands: list + :return: None + """ + + for i in range(len(cands)): + newCands = [] + for j in range(i + 1, len(cands)): + intersection = items[cands[i]].intersection(items[cands[j]]) + if len(intersection) >= self._minSup: + newCand = tuple(cands[i] + tuple([cands[j][-1]])) + newCands.append(newCand) + items[newCand] = intersection + self._finalPatterns[newCand] = len(intersection) + if len(newCands) > 1: + self.__recursive(items, newCands) + def mine(self) -> None: """ Frequent pattern mining process will start from here @@ -275,11 +247,29 @@ def mine(self) -> None: if self._minSup is None: raise Exception("Please enter the Minimum Support") self._creatingItemSets() + self._minSup = self._convert(self._minSup) - uniqueItemList = self._getUniqueItemList() - self._generateFrequentPatterns(uniqueItemList) - for x, y in self._finalPatterns.items(): - self._finalPatterns[x] = len(y[0]) + + + items = {} + index = 0 + for line in self._Database: + for item in line: + if item not in items: + items[item] = [] + items[item].append(index) + index += 1 + + items = {tuple([k]): set(v) for k, v in items.items() if len(v) >= self._minSup} + items = {k: v for k, v in sorted(items.items(), key=lambda item: len(item[1]), reverse=False)} + for k, v in items.items(): + self._finalPatterns[k] = len(v) + + cands = list(items.keys()) + + self.__recursive(items, cands) + + self._endTime = _ab._time.time() process = _ab._psutil.Process(_ab._os.getpid()) self._memoryUSS = float() @@ -329,11 +319,18 @@ def getPatternsAsDataFrame(self) -> _ab._pd.DataFrame: :rtype: pd.DataFrame """ - dataFrame = {} - data = [] - for a, b in self._finalPatterns.items(): - data.append([a.replace('\t', ' '), b]) - dataFrame = _ab._pd.DataFrame(data, columns=['Patterns', 'Support']) + # time = _ab._time.time() + # dataFrame = {} + # data = [] + # for a, b in self._finalPatterns.items(): + # # data.append([a.replace('\t', ' '), b]) + # data.append([" ".join(a), b]) + # dataFrame = _ab._pd.DataFrame(data, columns=['Patterns', 'Support']) + # print("Time taken to convert the frequent patterns into DataFrame is: ", _ab._time.time() - time) + + + dataFrame = _ab._pd.DataFrame(list(self._finalPatterns.items()), columns=['Patterns', 'Support']) + return dataFrame def save(self, outFile: str) -> None: @@ -345,15 +342,13 @@ def save(self, outFile: str) -> None: :type outFile: csvfile :return: None """ - self._oFile = outFile - writer = open(self._oFile, 'w+') - for x, y in self._finalPatterns.items(): - patternsAndSupport = x.strip() + ":" + str(y) - writer.write("%s \n" % patternsAndSupport) + with open(outFile, 'w') as f: + for x, y in self._finalPatterns.items(): + x = self._sep.join(x) + f.write(f"{x}:{y}\n") def getPatterns(self) -> dict: """ - Function to send the set of frequent patterns after completion of the mining process :return: returning frequent patterns diff --git a/PAMI/frequentPattern/basic/ECLATDiffset.py b/PAMI/frequentPattern/basic/ECLATDiffset.py index b9970a1a..8e69a9f9 100644 --- a/PAMI/frequentPattern/basic/ECLATDiffset.py +++ b/PAMI/frequentPattern/basic/ECLATDiffset.py @@ -203,65 +203,6 @@ def _convert(self, value): value = int(value) return value - def _getUniqueItemList(self): - - # tidSets will store all the initial tids - tidSets = {} - # uniqueItem will store all frequent 1 items - uniqueItem = [] - for line in self._Database: - transNum = 0 - # Database = [set([i.rstrip() for i in transaction.split('\t')]) for transaction in f] - for transaction in self._Database: - transNum += 1 - self._trans_set.add(transNum) - for item in transaction: - if item in tidSets: - tidSets[item].add(transNum) - else: - tidSets[item] = {transNum} - for key, value in tidSets.items(): - supp = len(value) - if supp >= self._minSup: - self._diffSets[key] = [supp, self._trans_set.difference(value)] - uniqueItem.append(key) - # for x, y in self._diffSets.items(): - # print(x, y) - uniqueItem.sort() - # print() - return uniqueItem - - def _runDeclat(self, candidateList): - """ - - It will generate the combinations of frequent items - - :param candidateList :it represents the items with their respective transaction identifiers - :type candidateList: list - :return: returning transaction dictionary - :rtype: dict - """ - - newList = [] - for i in range(0, len(candidateList)): - item1 = candidateList[i] - iList = item1.split() - for j in range(i + 1, len(candidateList)): - item2 = candidateList[j] - jList = item2.split() - if iList[:-1] == jList[:-1]: - unionDiffSet = self._diffSets[item2][1].difference(self._diffSets[item1][1]) - unionSup = self._diffSets[item1][0] - len(unionDiffSet) - if unionSup >= self._minSup: - newKey = item1 + "\t" + jList[-1] - self._diffSets[newKey] = [unionSup, unionDiffSet] - newList.append(newKey) - else: - break - - if len(newList) > 0: - self._runDeclat(newList) - @deprecated("It is recommended to use 'mine()' instead of 'startMine()' for mining process. Starting from January 2025, 'startMine()' will be completely terminated.") def startMine(self): """ @@ -269,6 +210,31 @@ def startMine(self): """ self.mine() + def __recursive(self, items, cands): + """ + + This function generates new candidates by taking input as original candidates. + + :param items: A dictionary containing items and their corresponding support values. + :type items: dict + :param cands: A list of candidate itemsets. + :type cands: list + :return: None + """ + + for i in range(len(cands)): + newCands = [] + for j in range(i + 1, len(cands)): + intersection = items[cands[i]] | items[cands[j]] + supp = len(self._db - intersection) + if supp >= self._minSup: + newCand = tuple(cands[i] + tuple([cands[j][-1]])) + newCands.append(newCand) + items[newCand] = intersection + self._finalPatterns[newCand] = supp + if len(newCands) > 1: + self.__recursive(items, newCands) + def mine(self): """ Frequent pattern mining process will start from here @@ -286,11 +252,33 @@ def mine(self): self._creatingItemSets() #print(len(self._Database)) self._minSup = self._convert(self._minSup) - uniqueItemList = [] - uniqueItemList = self._getUniqueItemList() - self._runDeclat(uniqueItemList) - self._finalPatterns = self._diffSets - #print(len(self._finalPatterns), len(uniqueItemList)) + + items = {} + db = set([i for i in range(len(self._Database))]) + for i in range(len(self._Database)): + for item in self._Database[i]: + if tuple([item]) in items: + items[tuple([item])].append(i) + else: + items[tuple([item])] = [i] + + items = dict(sorted(items.items(), key=lambda x: len(x[1]), reverse=True)) + + keys = [] + for item in list(items.keys()): + if len(items[item]) < self._minSup: + del items[item] + continue + self._finalPatterns[item] = len(items[item]) + # print(item, len(items[item])) + items[item] = db - set(items[item]) + # print(item, len(items[item])) + keys.append(item) + + self._db = db + + self.__recursive(items, keys) + self._endTime = _ab._time.time() process = _ab._psutil.Process(_ab._os.getpid()) self._memoryUSS = float() diff --git a/PAMI/frequentPattern/basic/_ECLATDiffset.py b/PAMI/frequentPattern/basic/_ECLATDiffset.py new file mode 100644 index 00000000..b9970a1a --- /dev/null +++ b/PAMI/frequentPattern/basic/_ECLATDiffset.py @@ -0,0 +1,402 @@ +# ECLATDiffest uses diffset to extract the frequent patterns in a transactional database. +# +# **Importing this algorithm into a python program** +# +# import PAMI.frequentPattern.basic.ECLATDiffset as alg +# +# iFile = 'sampleDB.txt' +# +# minSup = 10 # can also be specified between 0 and 1 +# +# obj = alg.ECLATDiffset(iFile, minSup) +# +# obj.mine() +# +# frequentPatterns = obj.getPatterns() +# +# print("Total number of Frequent Patterns:", len(frequentPatterns)) +# +# obj.savePatterns(oFile) +# +# Df = obj.getPatternInDataFrame() +# +# memUSS = obj.getMemoryUSS() +# +# print("Total Memory in USS:", memUSS) +# +# memRSS = obj.getMemoryRSS() +# +# print("Total Memory in RSS", memRSS) +# +# run = obj.getRuntime() +# +# print("Total ExecutionTime in seconds:", run) +# + + +__copyright__ = """ +Copyright (C) 2021 Rage Uday Kiran + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +""" + + +# from abstract import * + +from PAMI.frequentPattern.basic import abstract as _ab +from deprecated import deprecated + + +class ECLATDiffset(_ab._frequentPatterns): + """ + :**Description**: ECLATDiffset uses diffset to extract the frequent patterns in a transactional database. + + :**Reference**: KDD '03: Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining + August 2003 Pages 326–335 https://doi.org/10.1145/956750.956788 + + :**Parameters**: - **iFile** (*str or URL or dataFrame*) -- *Name of the Input file to mine complete set of frequent patterns.* + - **oFile** (*str*) -- *Name of the output file to store complete set of frequent patterns* + - **minSup** (*int or float or str*) -- *The user can specify minSup either in count or proportion of database size. If the program detects the data type of minSup is integer, then it treats minSup is expressed in count.* + - **sep** (*str*) -- **This variable is used to distinguish items from one another in a transaction. The default seperator is tab space. However, the users can override their default separator.** + + :**Attributes**: - **startTime** (*float*) -- *To record the start time of the mining process.* + - **endTime** (*float*) -- *To record the end time of the mining process.* + - **finalPatterns** (*dict*) -- *Storing the complete set of patterns in a dictionary variable.* + - **memoryUSS** (*float*) -- *To store the total amount of USS memory consumed by the program.* + - **memoryRSS** *(float*) -- *To store the total amount of RSS memory consumed by the program.* + - **Database** (*list*) -- *To store the transactions of a database in list.* + + + Execution methods + ================= + + **Terminal command** + + .. code-block:: console + + Format: + + (.venv) $ python3 ECLATDiffset.py + + Example Usage: + + (.venv) $ python3 ECLATDiffset.py sampleDB.txt patterns.txt 10.0 + + .. note:: minSup can be specified in support count or a value between 0 and 1. + + + **Calling from a python program** + + .. code-block:: python + + import PAMI.frequentPattern.basic.ECLATDiffset as alg + + iFile = 'sampleDB.txt' + + minSup = 10 # can also be specified between 0 and 1 + + obj = alg.ECLATDiffset(iFile, minSup) + + obj.mine() + + frequentPatterns = obj.getPatterns() + + print("Total number of Frequent Patterns:", len(frequentPatterns)) + + obj.savePatterns(oFile) + + Df = obj.getPatternInDataFrame() + + memUSS = obj.getMemoryUSS() + + print("Total Memory in USS:", memUSS) + + memRSS = obj.getMemoryRSS() + + print("Total Memory in RSS", memRSS) + + run = obj.getRuntime() + + print("Total ExecutionTime in seconds:", run) + + + Credits: + ======== + + The complete program was written by Kundai and revised by Tarun Sreepada under the supervision of Professor Rage Uday Kiran. + + """ + + _minSup = float() + _startTime = float() + _endTime = float() + _finalPatterns = {} + _iFile = " " + _oFile = " " + _sep = " " + _memoryUSS = float() + _memoryRSS = float() + _Database = [] + _diffSets = {} + _trans_set = set() + + def _creatingItemSets(self): + """ + Storing the complete transactions of the database/input file in a database variable + """ + self._Database = [] + if isinstance(self._iFile, _ab._pd.DataFrame): + if self._iFile.empty: + print("its empty..") + i = self._iFile.columns.values.tolist() + if 'Transactions' in i: + self._Database = self._iFile['Transactions'].tolist() + if isinstance(self._iFile, str): + if _ab._validators.url(self._iFile): + data = _ab._urlopen(self._iFile) + for line in data: + line.strip() + line = line.decode("utf-8") + temp = [i.rstrip() for i in line.split(self._sep)] + temp = [x for x in temp if x] + self._Database.append(temp) + else: + try: + with open(self._iFile, 'r', encoding='utf-8') as f: + for line in f: + line.strip() + temp = [i.rstrip() for i in line.split(self._sep)] + temp = [x for x in temp if x] + self._Database.append(temp) + except IOError: + print("File Not Found") + quit() + + def _convert(self, value): + """ + + To convert the user specified minSup value + + :param value: user specified minSup value + :return: converted type + """ + if type(value) is int: + value = int(value) + if type(value) is float: + value = (len(self._Database) * value) + if type(value) is str: + if '.' in value: + value = float(value) + value = (len(self._Database) * value) + else: + value = int(value) + return value + + def _getUniqueItemList(self): + + # tidSets will store all the initial tids + tidSets = {} + # uniqueItem will store all frequent 1 items + uniqueItem = [] + for line in self._Database: + transNum = 0 + # Database = [set([i.rstrip() for i in transaction.split('\t')]) for transaction in f] + for transaction in self._Database: + transNum += 1 + self._trans_set.add(transNum) + for item in transaction: + if item in tidSets: + tidSets[item].add(transNum) + else: + tidSets[item] = {transNum} + for key, value in tidSets.items(): + supp = len(value) + if supp >= self._minSup: + self._diffSets[key] = [supp, self._trans_set.difference(value)] + uniqueItem.append(key) + # for x, y in self._diffSets.items(): + # print(x, y) + uniqueItem.sort() + # print() + return uniqueItem + + def _runDeclat(self, candidateList): + """ + + It will generate the combinations of frequent items + + :param candidateList :it represents the items with their respective transaction identifiers + :type candidateList: list + :return: returning transaction dictionary + :rtype: dict + """ + + newList = [] + for i in range(0, len(candidateList)): + item1 = candidateList[i] + iList = item1.split() + for j in range(i + 1, len(candidateList)): + item2 = candidateList[j] + jList = item2.split() + if iList[:-1] == jList[:-1]: + unionDiffSet = self._diffSets[item2][1].difference(self._diffSets[item1][1]) + unionSup = self._diffSets[item1][0] - len(unionDiffSet) + if unionSup >= self._minSup: + newKey = item1 + "\t" + jList[-1] + self._diffSets[newKey] = [unionSup, unionDiffSet] + newList.append(newKey) + else: + break + + if len(newList) > 0: + self._runDeclat(newList) + + @deprecated("It is recommended to use 'mine()' instead of 'startMine()' for mining process. Starting from January 2025, 'startMine()' will be completely terminated.") + def startMine(self): + """ + Frequent pattern mining process will start from here + """ + self.mine() + + def mine(self): + """ + Frequent pattern mining process will start from here + """ + + self._startTime = _ab._time.time() + self._Database = [] + self._finalPatterns = {} + self._diffSets = {} + self._trans_set = set() + if self._iFile is None: + raise Exception("Please enter the file path or file name:") + if self._minSup is None: + raise Exception("Please enter the Minimum Support") + self._creatingItemSets() + #print(len(self._Database)) + self._minSup = self._convert(self._minSup) + uniqueItemList = [] + uniqueItemList = self._getUniqueItemList() + self._runDeclat(uniqueItemList) + self._finalPatterns = self._diffSets + #print(len(self._finalPatterns), len(uniqueItemList)) + self._endTime = _ab._time.time() + process = _ab._psutil.Process(_ab._os.getpid()) + self._memoryUSS = float() + self._memoryRSS = float() + self._memoryUSS = process.memory_full_info().uss + self._memoryRSS = process.memory_info().rss + print("Frequent patterns were generated successfully using ECLAT Diffset algorithm") + + def getMemoryUSS(self): + """ + + Total amount of USS memory consumed by the mining process will be retrieved from this function + + :return: returning USS memory consumed by the mining process + :rtype: float + """ + + return self._memoryUSS + + def getMemoryRSS(self): + """ + + Total amount of RSS memory consumed by the mining process will be retrieved from this function + + :return: returning RSS memory consumed by the mining process + :rtype: float + """ + + return self._memoryRSS + + def getRuntime(self): + """ + + Calculating the total amount of runtime taken by the mining process + + :return: returning total amount of runtime taken by the mining process + :rtype: float + """ + + return self._endTime - self._startTime + + def getPatternsAsDataFrame(self): + """ + + Storing final frequent patterns in a dataframe + + :return: returning frequent patterns in a dataframe + :rtype: pd.DataFrame + """ + + dataFrame = {} + data = [] + for a, b in self._finalPatterns.items(): + data.append([a.replace('\t', ' '), b[0]]) + dataFrame = _ab._pd.DataFrame(data, columns=['Patterns', 'Support']) + return dataFrame + + def save(self, outFile): + """ + + Complete set of frequent patterns will be loaded in to an output file + + :param outFile: name of the output file + :type outFile: csvfile + """ + self._oFile = outFile + writer = open(self._oFile, 'w+') + for x, y in self._finalPatterns.items(): + patternsAndSupport = x.strip() + ":" + str(y[0]) + writer.write("%s \n" % patternsAndSupport) + + def getPatterns(self): + """ + + Function to send the set of frequent patterns after completion of the mining process + + :return: returning frequent patterns + :rtype: dict + """ + return self._finalPatterns + + def printResults(self): + """ + This function is used to print the results + """ + print("Total number of Frequent Patterns:", len(self.getPatterns())) + print("Total Memory in USS:", self.getMemoryUSS()) + print("Total Memory in RSS", self.getMemoryRSS()) + print("Total ExecutionTime in ms:", self.getRuntime()) + + +if __name__ == "__main__": + _ap = str() + if len(_ab._sys.argv) == 4 or len(_ab._sys.argv) == 5: + if len(_ab._sys.argv) == 5: + _ap = ECLATDiffset(_ab._sys.argv[1], _ab._sys.argv[3], _ab._sys.argv[4]) + if len(_ab._sys.argv) == 4: + _ap = ECLATDiffset(_ab._sys.argv[1], _ab._sys.argv[3]) + _ap.startMine() + _ap.mine() + print("Total number of Frequent Patterns:", len(_ap.getPatterns())) + _ap.save(_ab._sys.argv[2]) + print(_ap.getPatternsAsDataFrame()) + print("Total Memory in USS:", _ap.getMemoryUSS()) + print("Total Memory in RSS", _ap.getMemoryRSS()) + print("Total ExecutionTime in ms:", _ap.getRuntime()) + else: + print("Error! The number of input parameters do not match the total number of parameters provided") + diff --git a/PAMI/frequentPattern/topk/FAE.py b/PAMI/frequentPattern/topk/FAE.py index 44026d62..d4991f90 100644 --- a/PAMI/frequentPattern/topk/FAE.py +++ b/PAMI/frequentPattern/topk/FAE.py @@ -216,6 +216,7 @@ def _frequentOneItem(self): self._tidList[j].append(i) self._finalPatterns = {} plist = [key for key, value in sorted(candidate.items(), key=lambda x: x[1], reverse=True)] + self._tidList = {k: frozenset(v) for k, v in self._tidList.items()} for i in plist: if len(self._finalPatterns) >= self._k: break @@ -242,8 +243,9 @@ def _save(self, prefix, suffix, tidSetI): prefix = prefix + suffix val = len(tidSetI) sample = str() - for i in prefix: - sample = sample + i + "\t" + # for i in prefix: + # sample = sample + i + "\t" + sample = "\t".join(prefix) if len(self._finalPatterns) < self._k: if val > self._minimum: self._finalPatterns[sample] = val @@ -289,7 +291,7 @@ def _Generation(self, prefix, itemSets, tidSets): for j in range(i + 1, len(itemSets)): itemJ = itemSets[j] tidSetJ = tidSets[j] - y = list(set(tidSetI).intersection(tidSetJ)) + y = tidSetI.intersection(tidSetJ) if len(y) >= self._minimum: classItemSets.append(itemJ) classTidSets.append(y) @@ -344,7 +346,7 @@ def mine(self): for j in range(i + 1, len(plist)): itemJ = plist[j] tidSetJ = self._tidList[itemJ] - y1 = list(set(tidSetI).intersection(tidSetJ)) + y1 = tidSetI.intersection(tidSetJ) if len(y1) >= self._minimum: itemSets.append(itemJ) tidSets.append(y1) @@ -456,5 +458,3 @@ def printTOPK(self): print("Total ExecutionTime in ms:", _ap.getRuntime()) else: print("Error! The number of input parameters do not match the total number of parameters provided") - - diff --git a/PAMI/frequentPattern/topk/_FAE.py b/PAMI/frequentPattern/topk/_FAE.py new file mode 100644 index 00000000..88a165ad --- /dev/null +++ b/PAMI/frequentPattern/topk/_FAE.py @@ -0,0 +1,458 @@ +# Top - K is and algorithm to discover top frequent patterns in a transactional database. +# +# **Importing this algorithm into a python program** +# --------------------------------------------------------- +# +# import PAMI.frequentPattern.topK.FAE as alg +# +# obj = alg.FAE(iFile, K) +# +# obj.mine() +# +# topKFrequentPatterns = obj.getPatterns() +# +# print("Total number of Frequent Patterns:", len(topKFrequentPatterns)) +# +# obj.save(oFile) +# +# Df = obj.getPatternInDataFrame() +# +# memUSS = obj.getMemoryUSS() +# +# print("Total Memory in USS:", memUSS) +# +# memRSS = obj.getMemoryRSS() +# +# print("Total Memory in RSS", memRSS) +# +# run = obj.getRuntime() +# +# print("Total ExecutionTime in seconds:", run) +# + + + + + +__copyright__ = """ +Copyright (C) 2021 Rage Uday Kiran + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see . +""" + +from PAMI.frequentPattern.topk import abstract as _ab +from deprecated import deprecated + + +class FAE(_ab._frequentPatterns): + """ + :Description: Top - K is and algorithm to discover top frequent patterns in a transactional database. + + + :Reference: Zhi-Hong Deng, Guo-Dong Fang: Mining Top-Rank-K Frequent Patterns: DOI: 10.1109/ICMLC.2007.4370261 · Source: IEEE Xplore + https://ieeexplore.ieee.org/document/4370261 + + :param iFile: str : + Name of the Input file to mine complete set of frequent patterns + :param oFile: str : + Name of the output file to store complete set of frequent patterns + :param k: int : + User specified count of top frequent patterns + :param minimum: int : + Minimum number of frequent patterns to consider in analysis + + :param sep: str : + This variable is used to distinguish items from one another in a transaction. The default seperator is tab space. However, the users can override their default separator. + + + + :Attributes: + + startTime : float + To record the start time of the mining process + + endTime : float + To record the completion time of the mining process + + finalPatterns : dict + Storing the complete set of patterns in a dictionary variable + + memoryUSS : float + To store the total amount of USS memory consumed by the program + + memoryRSS : float + To store the total amount of RSS memory consumed by the program + + finalPatterns : dict + it represents to store the patterns + + + **Methods to execute code on terminal** + ------------------------------------------- + + .. code-block:: console + + Format: + + (.venv) $ python3 FAE.py + + Example Usage: + + (.venv) $ python3 FAE.py sampleDB.txt patterns.txt 10 + + .. note:: k will be considered as count of top frequent patterns to consider in analysis + + + + **Importing this algorithm into a python program** + --------------------------------------------------------- + .. code-block:: python + + import PAMI.frequentPattern.topK.FAE as alg + + obj = alg.FAE(iFile, K) + + obj.mine() + + topKFrequentPatterns = obj.getPatterns() + + print("Total number of Frequent Patterns:", len(topKFrequentPatterns)) + + obj.save(oFile) + + Df = obj.getPatternInDataFrame() + + memUSS = obj.getMemoryUSS() + + print("Total Memory in USS:", memUSS) + + memRSS = obj.getMemoryRSS() + + print("Total Memory in RSS", memRSS) + + run = obj.getRuntime() + + print("Total ExecutionTime in seconds:", run) + + Credits: + -------- + The complete program was written by P.Likhitha under the supervision of Professor Rage Uday Kiran. + + """ + + _startTime = float() + _endTime = float() + _k = int() + _finalPatterns = {} + _iFile = " " + _oFile = " " + _sep = " " + _memoryUSS = float() + _memoryRSS = float() + _Database = [] + _tidList = {} + _minimum = int() + + def _creatingItemSets(self): + """ + Storing the complete transactions of the database/input file in a database variable + + """ + + self._Database = [] + if isinstance(self._iFile, _ab._pd.DataFrame): + if self._iFile.empty: + print("its empty..") + i = self._iFile.columns.values.tolist() + if 'Transactions' in i: + self._Database = self._iFile['Transactions'].tolist() + + # print(self.Database) + if isinstance(self._iFile, str): + if _ab._validators.url(self._iFile): + data = _ab._urlopen(self._iFile) + for line in data: + line.strip() + line = line.decode("utf-8") + temp = [i.rstrip() for i in line.split(self._sep)] + temp = [x for x in temp if x] + self._Database.append(temp) + else: + try: + with open(self._iFile, 'r', encoding='utf-8') as f: + for line in f: + line.strip() + temp = [i.rstrip() for i in line.split(self._sep)] + temp = [x for x in temp if x] + self._Database.append(temp) + except IOError: + print("File Not Found") + quit() + + def _frequentOneItem(self): + """ + Generating one frequent patterns + """ + candidate = {} + self._tidList = {} + for i in range(len(self._Database)): + for j in self._Database[i]: + if j not in candidate: + candidate[j] = 1 + self._tidList[j] = [i] + else: + candidate[j] += 1 + self._tidList[j].append(i) + self._finalPatterns = {} + plist = [key for key, value in sorted(candidate.items(), key=lambda x: x[1], reverse=True)] + for i in plist: + if len(self._finalPatterns) >= self._k: + break + else: + self._finalPatterns[i] = candidate[i] + self._minimum = min([self._finalPatterns[i] for i in self._finalPatterns.keys()]) + plist = list(self._finalPatterns.keys()) + return plist + + def _save(self, prefix, suffix, tidSetI): + """Saves the patterns that satisfy the periodic frequent property. + + :param prefix: the prefix of a pattern + :type prefix: list + :param suffix: the suffix of a patterns + :type suffix: list + :param tidSetI: the timestamp of a patterns + :type tidSetI: list + """ + + if prefix is None: + prefix = suffix + else: + prefix = prefix + suffix + val = len(tidSetI) + sample = str() + for i in prefix: + sample = sample + i + "\t" + if len(self._finalPatterns) < self._k: + if val > self._minimum: + self._finalPatterns[sample] = val + self._finalPatterns = {k: v for k, v in sorted(self._finalPatterns.items(), key=lambda item: item[1], reverse=True)} + self._minimum = min([i for i in self._finalPatterns.values()]) + else: + for x, y in sorted(self._finalPatterns.items(), key=lambda x: x[1]): + if val > y: + del self._finalPatterns[x] + self._finalPatterns[sample] = val + self._finalPatterns = {k: v for k, v in + sorted(self._finalPatterns.items(), key=lambda item: item[1], + reverse=True)} + self._minimum = min([i for i in self._finalPatterns.values()]) + return + + def _Generation(self, prefix, itemSets, tidSets): + """Equivalence class is followed and checks for the patterns generated for periodic-frequent patterns. + + :param prefix: main equivalence prefix + :type prefix: periodic-frequent item or pattern + :param itemSets: patterns which are items combined with prefix and satisfying the periodicity + and frequent with their timestamps + :type itemSets: list + :param tidSets: timestamps of the items in the argument itemSets + :type tidSets: list + + + """ + if len(itemSets) == 1: + i = itemSets[0] + tidI = tidSets[0] + self._save(prefix, [i], tidI) + return + for i in range(len(itemSets)): + itemI = itemSets[i] + if itemI is None: + continue + tidSetI = tidSets[i] + classItemSets = [] + classTidSets = [] + itemSetX = [itemI] + for j in range(i + 1, len(itemSets)): + itemJ = itemSets[j] + tidSetJ = tidSets[j] + y = list(set(tidSetI).intersection(tidSetJ)) + if len(y) >= self._minimum: + classItemSets.append(itemJ) + classTidSets.append(y) + newPrefix = list(set(itemSetX)) + prefix + self._Generation(newPrefix, classItemSets, classTidSets) + self._save(prefix, list(set(itemSetX)), tidSetI) + + def _convert(self, value): + """ + to convert the type of user specified minSup value + :param value: user specified minSup value + :type value: int or float or str + :return: converted type + """ + if type(value) is int: + value = int(value) + if type(value) is float: + value = (len(self._Database) * value) + if type(value) is str: + if '.' in value: + value = float(value) + value = ((len(self._Database)) * value) + else: + value = int(value) + return value + + @deprecated("It is recommended to use 'mine()' instead of 'startMine()' for mining process. Starting from January 2025, 'startMine()' will be completely terminated.") + def startMine(self): + """ + Main function of the program + """ + self.mine() + + def mine(self): + """ + Main function of the program + """ + self._startTime = _ab._time.time() + if self._iFile is None: + raise Exception("Please enter the file path or file name:") + if self._k is None: + raise Exception("Please enter the Minimum Support") + self._creatingItemSets() + self._k = self._convert(self._k) + plist = self._frequentOneItem() + for i in range(len(plist)): + itemI = plist[i] + tidSetI = self._tidList[itemI] + itemSetX = [itemI] + itemSets = [] + tidSets = [] + for j in range(i + 1, len(plist)): + itemJ = plist[j] + tidSetJ = self._tidList[itemJ] + y1 = list(set(tidSetI).intersection(tidSetJ)) + if len(y1) >= self._minimum: + itemSets.append(itemJ) + tidSets.append(y1) + self._Generation(itemSetX, itemSets, tidSets) + print(" TopK frequent patterns were successfully generated using FAE algorithm.") + self._endTime = _ab._time.time() + self._memoryUSS = float() + self._memoryRSS = float() + process = _ab._psutil.Process(_ab._os.getpid()) + self._memoryUSS = process.memory_full_info().uss + self._memoryRSS = process.memory_info().rss + + def getMemoryUSS(self): + """ + Total amount of USS memory consumed by the mining process will be retrieved from this function + + :return: returning USS memory consumed by the mining process + + :rtype: float + """ + + return self._memoryUSS + + def getMemoryRSS(self): + """ + Total amount of RSS memory consumed by the mining process will be retrieved from this function + + :return: returning RSS memory consumed by the mining process + + :rtype: float + """ + + return self._memoryRSS + + def getRuntime(self): + """ + Calculating the total amount of runtime taken by the mining process + + :return: returning total amount of runtime taken by the mining process + + :rtype: float + """ + + return self._endTime - self._startTime + + def getPatternsAsDataFrame(self): + """ + Storing final frequent patterns in a dataframe + + :return: returning frequent patterns in a dataframe + + :rtype: pd.DataFrame + """ + + dataFrame = {} + data = [] + for a, b in self._finalPatterns.items(): + data.append([a.replace('\t', ' '), b]) + dataFrame = _ab._pd.DataFrame(data, columns=['Patterns', 'Support']) + return dataFrame + + def save(self, outFile): + """ + Complete set of frequent patterns will be loaded in to an output file + + :param outFile: name of the output file + + :type outFile: file + """ + self._oFile = outFile + writer = open(self._oFile, 'w+') + for x, y in self._finalPatterns.items(): + patternsAndSupport = x.strip() + ":" + str(y) + writer.write("%s \n" % patternsAndSupport) + + def getPatterns(self): + """ + Function to send the set of frequent patterns after completion of the mining process + + :return: returning frequent patterns + + :rtype: dict + """ + return self._finalPatterns + + def printTOPK(self): + """ + This function is used to print the results + """ + print("Top K Frequent Patterns:", len(self.getPatterns())) + print("Total Memory in USS:", self.getMemoryUSS()) + print("Total Memory in RSS", self.getMemoryRSS()) + print("Total ExecutionTime in ms:", self.getRuntime()) + + +if __name__ == "__main__": + _ap = str() + if len(_ab._sys.argv) == 4 or len(_ab._sys.argv) == 5: + if len(_ab._sys.argv) == 5: + _ap = FAE(_ab._sys.argv[1], _ab._sys.argv[3], _ab._sys.argv[4]) + if len(_ab._sys.argv) == 4: + _ap = FAE(_ab._sys.argv[1], _ab._sys.argv[3]) + _ap.startMine() + _ap.mine() + print("Top K Frequent Patterns:", len(_ap.getPatterns())) + _ap.save(_ab._sys.argv[2]) + print("Total Memory in USS:", _ap.getMemoryUSS()) + print("Total Memory in RSS", _ap.getMemoryRSS()) + print("Total ExecutionTime in ms:", _ap.getRuntime()) + else: + print("Error! The number of input parameters do not match the total number of parameters provided")