# k3PMiner is and algorithm to discover top - k partial periodic patterns in a temporal database.
#
#
# **Importing this algorithm into a python program**
# --------------------------------------------------------
#
# import PAMI.partialPeriodicPattern.topk.k3PMiner as alg
#
# obj = alg.k3PMiner(iFile, k, periodicity)
#
# obj.mine()
#
# partialPeriodicPatterns = obj.getPatterns()
#
# print("Total number of top partial periodic Patterns:", len(partialPeriodicPatterns))
#
# 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 <https://www.gnu.org/licenses/>.
Copyright (C) 2021 Rage Uday Kiran
"""
from PAMI.partialPeriodicPattern.topk import abstract as _abstract
import validators as _validators
from urllib.request import urlopen as _urlopen
import sys as _sys
import pandas as pd
from deprecated import deprecated
[docs]
class k3PMiner(_abstract.partialPeriodicPatterns):
"""
:Description: k3PMiner is and algorithm to discover top - k partial periodic patterns in a temporal database.
:Reference: Palla Likhitha,Rage Uday Kiran, Discovering Top-K Partial Periodic Patterns in Big Temporal Databases https://dl.acm.org/doi/10.1007/978-3-031-39847-6_28
:param iFile: str :
Name of the Input file to mine complete set of periodic frequent pattern's
:param oFile: str :
Name of the output file to store complete set of periodic frequent pattern's
: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.
:param iFile: str :
Name of the Input file to mine complete set of frequent pattern's
:param oFile: str :
Name of the output file to store complete set of frequent patterns
:param period: str:
Minimum partial periodic...
: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:
iFile : str
Input file name or path of the input file
k: int
User specified count of top partial periodic patterns
sep : str
This variable is used to distinguish items from one another in a transaction. The default seperator is tab space or \t.
However, the users can override their default separator.
oFile : str
Name of the output file or the path of the output file
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
:Methods:
mine()
Mining process will start from here
getPatterns()
Complete set of patterns will be retrieved with this function
save(oFile)
Complete set of frequent patterns will be loaded in to a output file
getPatternsAsDataFrame()
Complete set of frequent patterns will be loaded in to a dataframe
getMemoryUSS()
Total amount of USS memory consumed by the mining process will be retrieved from this function
getMemoryRSS()
Total amount of RSS memory consumed by the mining process will be retrieved from this function
getRuntime()
Total amount of runtime taken by the mining process will be retrieved from this function
creatingItemSets()
Scans the dataset or dataframes and stores in list format
frequentOneItem()
Generates one frequent patterns
eclatGeneration(candidateList)
It will generate the combinations of frequent items
generateFrequentPatterns(tidList)
It will generate the combinations of frequent items from a list of items
**Executing the code on terminal:**
-------------------------------------
.. code-block:: console
Format:
python3 k3PMiner.py <iFile> <oFile> <k> <period>
Examples:
python3 k3PMiner.py sampleDB.txt patterns.txt 10 3
**Sample run of the importing code:**
--------------------------------------
... code-block:: python
import PAMI.partialPeriodicPattern.topk.k3PMiner as alg
obj = alg.Topk_PPPGrowth(iFile, k, period)
obj.mine()
partialPeriodicPatterns = obj.getPatterns()
print("Total number of top partial periodic Patterns:", len(partialPeriodicPatterns))
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()
_period = " "
_finalPatterns = {}
_iFile = " "
_oFile = " "
_sep = " "
_memoryUSS = float()
_memoryRSS = float()
_Database = []
_tidList = {}
_lno = int()
_minimum = int()
_mapSupport = {}
def _creatingItemSets(self):
"""
Storing the complete transactions of the database/input file in a database variable
"""
self._Database = []
if isinstance(self._iFile, _abstract._pd.DataFrame):
timeStamp, data = [], []
if self._iFile.empty:
print("its empty..")
i = self._iFile.columns.values.tolist()
if 'TS' in i:
timeStamp = self._iFile['TS'].tolist()
if 'Transactions' in i:
data = self._iFile['Transactions'].tolist()
for i in range(len(data)):
tr = [timeStamp[i]]
tr = tr + data[i]
self._Database.append(tr)
self._lno = len(self._Database)
# print(self.Database)
if isinstance(self._iFile, str):
if _validators.url(self._iFile):
data = _urlopen(self._iFile)
for line in data:
self._lno += 1
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:
self._lno += 1
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 given user specified value
:param value: user specified value
:return: converted value
"""
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 _frequentOneItem(self):
"""
Generating one frequent patterns
"""
self._mapSupport = {}
self._tidList = {}
self._period = self._convert(self._period)
self._k = int(self._convert(self._k))
for line in self._Database:
n = int(line[0])
for i in range(1, len(line)):
si = line[i]
if self._mapSupport.get(si) is None:
self._mapSupport[si] = [1, 0, n]
self._tidList[si] = [n]
else:
self._mapSupport[si][0] += 1
period = abs(n - self._mapSupport[si][2])
if period <= self._period:
self._mapSupport[si][1] += 1
self._mapSupport[si][2] = n
self._tidList[si].append(n)
for x, y in self._mapSupport.items():
period = abs(self._lno - self._mapSupport[x][2])
if period <= self._period:
self._mapSupport[x][1] += 1
self._mapSupport = {k: v[1] for k, v in self._mapSupport.items()}
#print(self._mapSupport)
plist = [key for key, value in sorted(self._mapSupport.items(), key=lambda x: x[1], reverse=True)]
#print(plist)
self._finalPatterns = {}
for i in plist:
if self._mapSupport[i] == 0:
continue
if len(self._finalPatterns) >= self._k:
break
else:
self._finalPatterns[i] = self._mapSupport[i]
#print(len(self._finalPatterns), self._k, self._periodicity)
#print(self._finalPatterns)
self._minimum = min([self._finalPatterns[i] for i in self._finalPatterns.keys()])
#print(self._minimum)
plist = list(self._finalPatterns.keys())
return plist
def _getSupportAndPeriod(self, timeStamps):
"""To calculate the periodicity and support
:param timeStamps: Timestamps of an item set
:return: support, periodicity
"""
timeStamps.sort()
sup = 0
for j in range(len(timeStamps) - 1):
per = abs(timeStamps[j + 1] - timeStamps[j])
if per <= self._period:
sup += 1
return sup
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
#print(prefix)
#print(self._minimum)
val = self._getSupportAndPeriod(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([self._finalPatterns[i] for i in self._finalPatterns.keys()])
#print(self._finalPatterns)
else:
#print(prefix, val)
for x, y in sorted(self._finalPatterns.items(), key=lambda x: x[1]):
if val > y:
#print("yes")
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([self._finalPatterns[i] for i in self._finalPatterns.keys()])
#print(self._finalPatterns)
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))
val = self._getSupportAndPeriod(y)
if val > 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)
[docs]
@deprecated("It is recommended to use mine() instead of mine() for mining process")
def startMine(self):
"""
Main function of the program
"""
self.mine()
[docs]
def mine(self):
"""
Main function of the program
"""
self._startTime = _abstract._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()
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))
val = self._getSupportAndPeriod(y1)
if val > self._minimum:
itemSets.append(itemJ)
tidSets.append(y1)
self._Generation(itemSetX, itemSets, tidSets)
print("TopK partial periodic patterns were generated successfully")
self._endTime = _abstract._time.time()
process = _abstract._psutil.Process(_abstract._os.getpid())
self._memoryUSS = float()
self._memoryRSS = float()
self._memoryUSS = process.memory_full_info().uss
self._memoryRSS = process.memory_info().rss
[docs]
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
[docs]
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
[docs]
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 = _abstract._pd.DataFrame(data, columns=['Patterns', 'Support'])
return dataFrame
[docs]
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)
[docs]
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
[docs]
def printResults(self):
""" This function is used to print the results
"""
print("Top K Partial Periodic 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(_sys.argv) == 5 or len(_sys.argv) == 6:
if len(_sys.argv) == 6:
_ap = k3PMiner(_sys.argv[1], _sys.argv[3], _sys.argv[4], _sys.argv[5])
if len(_sys.argv) == 5:
_ap = k3PMiner(_sys.argv[1], _sys.argv[3], _sys.argv[4])
_ap.mine()
print("Top K Partial Periodic Patterns:", len(_ap.getPatterns()))
_ap.save(_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")