PAMI.frequentPattern.pyspark package

Submodules

PAMI.frequentPattern.pyspark.abstract module

PAMI.frequentPattern.pyspark.parallelApriori module

class PAMI.frequentPattern.pyspark.parallelApriori.parallelApriori(iFile, minSup, numWorkers, sep='\t')

Bases: _frequentPatterns

Description:

Parallel Apriori is an algorithm to discover frequent patterns in a transactional database. This program employs parallel apriori property (or downward closure property) to reduce the search space effectively.

Reference:

N. Li, L. Zeng, Q. He and Z. Shi, “Parallel Implementation of Apriori Algorithm Based on MapReduce,” 2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing, Kyoto, Japan, 2012, pp. 236-241, doi: 10.1109/SNPD.2012.31.

Parameters:

• iFile – str : 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 : 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.

• numPartitions – int : The number of partitions. On each worker node, an executor process is started and this process performs processing.The processing unit of worker node is partition

Attributes:

startTimefloat

To record the start time of the mining process

endTimefloat

To record the completion time of the mining process

finalPatternsdict

Storing the complete set of patterns in a dictionary variable

memoryUSSfloat

To store the total amount of USS memory consumed by the program

memoryRSSfloat

To store the total amount of RSS memory consumed by the program

lnoint

the number of transactions

Methods to execute code on terminal

Format:

(.venv) $ python3 parallelApriori.py <inputFile> <outputFile> <minSup> <numWorkers>

Example Usage:

(.venv) $ python3 parallelApriori.py sampleDB.txt patterns.txt 10.0 3

Note

minSup will be considered in percentage of database transactions

Importing this algorithm into a python program

import PAMI.frequentPattern.pyspark.parallelApriori as alg

obj = alg.parallelApriori(iFile, minSup, numWorkers)

obj.mine()

frequentPatterns = obj.getPatterns()

print("Total number of Frequent Patterns:", len(frequentPatterns))

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 Yudai Masu under the supervision of Professor Rage Uday Kiran.

getMemoryRSS()

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

getMemoryUSS()

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

getPatterns()

Function to send the set of frequent patterns after completion of the mining process :return: returning frequent patterns :rtype: dict

getPatternsAsDataFrame()

Storing final frequent patterns in a dataframe :return: returning frequent patterns in a dataframe :rtype: pd.DataFrame

getRuntime()

Calculating the total amount of runtime taken by the mining process :return: returning total amount of runtime taken by the mining process :rtype: float

mine()

Frequent pattern mining process will start from here

printResults()

This method prints all the stats

save(outFile)

Complete set of frequent patterns will be loaded in to an output file :param outFile: name of the output file :type outFile: csvfile

mine()

Frequent pattern mining process will start from here

PAMI.frequentPattern.pyspark.parallelECLAT module

class PAMI.frequentPattern.pyspark.parallelECLAT.parallelECLAT(iFile, minSup, numWorkers, sep='\t')

Bases: _frequentPatterns

Description:

ParallelEclat is an algorithm to discover frequent patterns in a transactional database. This program employs parallel apriori property (or downward closure property) to reduce the search space effectively.

Reference:

Parameters:

• iFile – str : 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 : 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.

• numPartitions – int : The number of partitions. On each worker node, an executor process is started and this process performs processing.The processing unit of worker node is partition

Attributes:

startTimefloat

To record the start time of the mining process

endTimefloat

To record the completion time of the mining process

finalPatternsdict

Storing the complete set of patterns in a dictionary variable

memoryUSSfloat

To store the total amount of USS memory consumed by the program

memoryRSSfloat

To store the total amount of RSS memory consumed by the program

lnoint

the number of transactions

Methods to execute code on terminal

Format:

(.venv) $ python3 parallelECLAT.py <inputFile> <outputFile> <minSup> <numWorkers>

Example Usage:

(.venv) $ python3 parallelECLAT.py sampleDB.txt patterns.txt 10.0 3

Note

minSup will be considered in percentage of database transactions

Importing this algorithm into a python program

import PAMI.frequentPattern.pyspark.parallelECLAT as alg

obj = alg.parallelECLAT(iFile, minSup, numWorkers)

obj.mine()

frequentPatterns = obj.getPatterns()

print("Total number of Frequent Patterns:", len(frequentPatterns))

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 Yudai Masu under the supervision of Professor Rage Uday Kiran.

getMemoryRSS()

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

getMemoryUSS()

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

getPatterns()

Function to send the set of frequent patterns after completion of the mining process :return: returning frequent patterns :rtype: dict

getPatternsAsDataFrame()

Storing final frequent patterns in a dataframe :return: returning frequent patterns in a dataframe :rtype: pd.DataFrame

getRuntime()

Calculating the total amount of runtime taken by the mining process :return: returning total amount of runtime taken by the mining process :rtype: float

mine()

Frequent pattern mining process will start from here

printResults()

This function is used to print the results

save(outFile)

Complete set of frequent patterns will be loaded in to an output file :param outFile: name of the output file :type outFile: csvfile

mine()

Frequent pattern mining process will start from here

PAMI.frequentPattern.pyspark.parallelFPGrowth module

class PAMI.frequentPattern.pyspark.parallelFPGrowth.Node(item, prefix)

Bases: object

Attribute:

itemint

Storing item of a node

countint

To maintain the support count of node

childrendict

To maintain the children of node

prefixlist

To maintain the prefix of node

class PAMI.frequentPattern.pyspark.parallelFPGrowth.Tree

Bases: object

Attribute:

rootNode

The first node of the tree set to Null

nodeLinkdict

Store nodes that have the same item

Methods:

addTransaction(transaction, count)

Create tree from transaction and count

addNodeToNodeLink(node)

Add nodes that have the same item to self.nodeLink

generateConditionalTree(item)

Create conditional pattern base of item

addNodeToNodeLink(node)

Add node to self.nodeLink :param node: Node to add :type node: Node

addTransaction(transaction, count)

Add transaction to tree :param transaction: Transaction to add :type transaction: list :param count: Number of nodes :type count: int

generateConditionalTree(item)

Generate conditional tree based on item :param item: Item to be considered as a condition :type item: str or int :return: Tree

class PAMI.frequentPattern.pyspark.parallelFPGrowth.parallelFPGrowth(iFile, minSup, numWorkers, sep='\t')

Bases: _frequentPatterns

Description:

Parallel FPGrowth is one of the fundamental algorithm to discover frequent patterns in a transactional database. It stores the database in compressed fp-tree decreasing the memory usage and extracts the patterns from tree.It employs downward closure property to reduce the search space effectively.

Reference:

Li, Haoyuan et al. “Pfp: parallel fp-growth for query recommendation.” ACM Conference on Recommender Systems (2008).

Parameters:

• iFile – str : 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 : 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.

• numPartitions – int : The number of partitions. On each worker node, an executor process is started and this process performs processing.The processing unit of worker node is partition

Attributes:

startTimefloat

To record the start time of the mining process

endTimefloat

To record the completion time of the mining process

finalPatternsdict

Storing the complete set of patterns in a dictionary variable

memoryUSSfloat

To store the total amount of USS memory consumed by the program

memoryRSSfloat

To store the total amount of RSS memory consumed by the program

lnoint

the number of transactions

Methods to execute code on terminal

Format:

(.venv) $ python3 parallelFPGrowth.py <inputFile> <outputFile> <minSup> <numWorkers>

Example Usage:

(.venv) $ python3 parallelFPGrowth.py sampleDB.txt patterns.txt 10.0 3

Note

minSup will be considered in percentage of database transactions

Importing this algorithm into a python program

import PAMI.frequentPattern.pyspark.parallelFPGrowth as alg

obj = alg.parallelFPGrowth(iFile, minSup, numWorkers)

obj.mine()

frequentPatterns = obj.getPatterns()

print("Total number of Frequent Patterns:", len(frequentPatterns))

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 Yudai Masu under the supervision of Professor Rage Uday Kiran.

static buildTree(tree, data)

Build tree from data :param tree: tree to build :type tree: Tree :param data: data to build :type data: list :return: tree

genAllFrequentPatterns(tree_tuple)

Generate all frequent patterns :param tree_tuple: (partition id, tree) :type tree_tuple: tuple :return: dict

genCondTransaction(trans, rank)

Generate conditional transactions from transaction :param trans : transactions to generate conditional transactions :type trans: list :param rank: rank of conditional transactions to generate conditional transactions :type rank: dict :return: list

genFreqPatterns(item, prefix, tree)

Generate new frequent patterns based on item. :param item: item :type item: int :param prefix: prefix frequent pattern :type prefix: str :param tree: tree to generate patterns :type tree: Tree :return:

getMemoryRSS()

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

getMemoryUSS()

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

getPartitionId(value)

Get partition id of item :param value: value to get partition id :type value: int :return: integer

getPatterns()

Function to send the set of frequent patterns after completion of the mining process :return: returning frequent patterns :rtype: dict

getPatternsAsDataFrame()

Storing final frequent patterns in a dataframe :return: returning frequent patterns in a dataframe :rtype: pd.DataFrame

getRuntime()

Calculating the total amount of runtime taken by the mining process :return: returning total amount of runtime taken by the mining process :rtype: float

mine()

Frequent pattern mining process will start from here

printResults()

This function is used to print the results

save(outFile)

Complete set of frequent patterns will be loaded in to an output file :param outFile: name of the output file :type outFile: csvfile

startMine()

Frequent pattern mining process will start from here

Module contents