diff --git a/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT.py b/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT.py
index ae149967..c0960843 100644
--- a/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT.py
+++ b/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT.py
@@ -30,9 +30,6 @@
# print("Total ExecutionTime in seconds:", run)
#
-
-
-
__copyright__ = """
Copyright (C) 2021 Rage Uday Kiran
@@ -71,8 +68,6 @@ class SpatialECLAT(_ab._spatialFrequentPatterns):
Name of the output file to store complete set of Geo-referenced frequent patterns
:param 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.
- :param maxPer: float :
- The user can specify maxPer in count or proportion of database size. If the program detects the data type of maxPer is integer, then it treats maxPer is expressed in count.
:param nFile: str :
Name of the input file to mine complete set of Geo-referenced frequent patterns
:param sep: str :
@@ -132,7 +127,7 @@ class SpatialECLAT(_ab._spatialFrequentPatterns):
generateSpatialFrequentPatterns(tidList)
It will generate the combinations of frequent items from a list of items
convert(value)
- To convert the given user specified value
+ To convert the given user specified value
getNeighbourItems(keySet)
A function to get common neighbours of a itemSet
mapNeighbours(file)
@@ -160,7 +155,7 @@ class SpatialECLAT(_ab._spatialFrequentPatterns):
.. code-block:: python
from PAMI.georeferencedFrequentPattern.basic import SpatialECLAT as alg
-
+
obj = alg.SpatialECLAT("sampleTDB.txt", "sampleN.txt", 5)
obj.mine()
@@ -182,11 +177,6 @@ class SpatialECLAT(_ab._spatialFrequentPatterns):
run = obj.getRuntime()
print("Total ExecutionTime in seconds:", run)
-
-
- **Credits:**
- ----------------
- The complete program was written by B.Sai Chitra under the supervision of Professor Rage Uday Kiran.
"""
_minSup = float()
@@ -218,6 +208,7 @@ def _creatingItemSets(self):
self._Database = self._iFile['Transactions'].tolist()
if 'Patterns' in i:
self._Database = self._iFile['Patterns'].tolist()
+
if isinstance(self._iFile, str):
if _ab._validators.url(self._iFile):
data = _ab._urlopen(self._iFile)
@@ -239,21 +230,6 @@ def _creatingItemSets(self):
print("File Not Found")
quit()
- # function to get frequent one pattern
- def _frequentOneItem(self):
- """
- Generating one frequent patterns
- """
- self._finalPatterns = {}
- candidate = {}
- 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]] += [i]
- self._finalPatterns = {keys: value for keys, value in candidate.items() if len(value) >= self._minSup}
-
def _convert(self, value):
"""
To convert the given user specified value
@@ -275,101 +251,6 @@ def _convert(self, value):
value = int(value)
return value
- @staticmethod
- def _dictKeysToInt(iList):
- """
- Converting dictionary keys to integer elements
-
- :param iList: Dictionary with patterns as keys and their support count as a value
- :type iList: dict
- :returns: list of integer patterns to represent dictionary keys
- :rtype: list
- """
-
- temp = []
- for ite in iList.keys():
- ite = [int(i) for i in ite.strip('[]').split('\t')]
- temp.append(ite)
- # print(sorted(temp))
- return sorted(temp)
-
- def _eclatGeneration(self, cList):
- """It will generate the combinations of frequent items
-
- :param cList :it represents the items with their respective transaction identifiers
- :type cList: dictionary
- :return: returning transaction dictionary
- :rtype: dict
- """
- # to generate all
- tidList = {}
- key = list(cList.keys())
- for i in range(0, len(key)):
- NeighboursItems = self._getNeighbourItems(key[i])
- for j in range(i + 1, len(key)):
- # print(c[key[i]],c[key[j]])
- if not key[j] in NeighboursItems:
- continue
- intersectionList = list(set(cList[key[i]]).intersection(set(cList[key[j]])))
- itemList = []
- itemList += key[i]
- itemList += key[j]
- if len(intersectionList) >= self._minSup:
- itemList.sort()
- if tuple(itemList) not in tidList:
- tidList[tuple(set(itemList))] = intersectionList
- return tidList
-
- def _generateSpatialFrequentPatterns(self, tidList):
- """
- It will generate the combinations of frequent items from a list of items
-
- :param tidList: it represents the items with their respective transaction identifiers
- :type tidList: dictionary
- :return: returning transaction dictionary
- :rtype: dict
- """
- tidList1 = {}
- if len(tidList) == 0:
- print("There are no more candidate sets")
- else:
- key = list(tidList.keys())
- for i in range(0, len(key)):
- NeighboursItems = self._getNeighbourItems(key[i])
- for j in range(i + 1, len(key)):
- if not key[j] in NeighboursItems:
- continue
- intersectionList = list(set(tidList[key[i]]).intersection(set(tidList[key[j]])))
- itemList = []
- if len(intersectionList) >= self._minSup:
- itemList += key[i], key[j]
- itemList.sort()
- tidList1[tuple(itemList)] = intersectionList
-
- return tidList1
-
- def _getNeighbourItems(self, keySet):
- """
- A function to get Neighbours of a item
-
- :param keySet: itemSet
- :type keySet: str or tuple
- :return: set of common neighbours
- :rtype: set
- """
- itemNeighbours = self._NeighboursMap.keys()
- if isinstance(keySet, str):
- if self._NeighboursMap.get(keySet) is None:
- return []
- itemNeighbours = list(set(itemNeighbours).intersection(set(self._NeighboursMap.get(keySet))))
- if isinstance(keySet, tuple):
- keySet = list(keySet)
- # print(keySet)
- for j in range(0, len(keySet)):
- i = keySet[j]
- itemNeighbours = list(set(itemNeighbours).intersection(set(self._NeighboursMap.get(i))))
- return itemNeighbours
-
def _mapNeighbours(self):
"""
A function to map items to their Neighbours
@@ -386,7 +267,7 @@ def _mapNeighbours(self):
data = self._nFile['Neighbours'].tolist()
for k in range(len(items)):
self._NeighboursMap[items[k]] = data[k]
- # print(self.Database)
+
if isinstance(self._nFile, str):
if _ab._validators.url(self._nFile):
data = _ab._urlopen(self._nFile)
@@ -395,60 +276,114 @@ def _mapNeighbours(self):
line = line.decode("utf-8")
temp = [i.rstrip() for i in line.split(self._sep)]
temp = [x for x in temp if x]
- self._NeighboursMap[temp[0]] = temp[1:]
+ self._NeighboursMap[temp[0]] = set(temp[1:])
+ self._NeighboursMap[temp[0]].add(temp[0])
else:
try:
with open(self._nFile, '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._NeighboursMap[temp[0]] = temp[1:]
+ parts = line.strip().split(self._sep)
+ if len(parts) < 1: continue
+ item = parts[0]
+ # Optimization: Use Sets for O(1) lookup
+ neighbors = set(parts[1:])
+ neighbors.add(item)
+ self._NeighboursMap[item] = neighbors
except IOError:
print("File Not Found")
quit()
- @deprecated("It is recommended to use 'mine()' instead of 'mine()' for mining process. Starting from January 2025, 'mine()' will be completely terminated.")
+ def _getNeighbourItems(self, pattern):
+ """
+ Optimized function to get Neighbors of a item set
+ """
+ if not pattern: return set()
+
+ #Fast lookup using sets
+ common = self._NeighboursMap.get(pattern[0], set())
+ for i in range(1, len(pattern)):
+ neighs = self._NeighboursMap.get(pattern[i], set())
+ common = common.intersection(neighs)
+ if not common: break
+ return common
+
+ @deprecated(
+ "It is recommended to use 'mine()' instead of 'mine()' for mining process. Starting from January 2025, 'mine()' 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
"""
-
- # global items_sets, endTime, startTime
self._startTime = _ab._time.time()
+
if self._iFile is None:
raise Exception("Please enter the file path or file name:")
+
self._creatingItemSets()
self._minSup = self._convert(self._minSup)
self._mapNeighbours()
- self._finalPatterns = {}
- self._frequentOneItem()
- frequentSet = self._generateSpatialFrequentPatterns(self._finalPatterns)
- for x, y in frequentSet.items():
- if x not in self._finalPatterns:
- self._finalPatterns[x] = y
- while 1:
- frequentSet = self._eclatGeneration(frequentSet)
- for x, y in frequentSet.items():
- if x not in self._finalPatterns:
- self._finalPatterns[x] = y
- if len(frequentSet) == 0:
- break
+
+ # Use Sets for Vertical DB
+ tid_list = {}
+ for r_idx, trans in enumerate(self._Database):
+ for item in trans:
+ if item not in tid_list: tid_list[item] = set()
+ tid_list[item].add(r_idx)
+
+ frequent_1_items = {}
+ for item, tids in tid_list.items():
+ if len(tids) >= self._minSup:
+ frequent_1_items[(item,)] = tids
+ self._finalPatterns[(item,)] = len(tids)
+
+ # Start Optimized DFS
+ self._dfs(frequent_1_items)
+
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("Spatial Frequent patterns were generated successfully using SpatialECLAT algorithm")
+ def _dfs(self, current_level_patterns):
+ """
+ Recursive Depth First Search with Optimized Spatial Pruning
+ """
+ patterns = sorted(list(current_level_patterns.keys()))
+
+ for i in range(len(patterns)):
+ pattern_a = patterns[i]
+ tids_a = current_level_patterns[pattern_a]
+
+ # Spatial Pruning (Fastest check first)
+ valid_neighbors = self._getNeighbourItems(pattern_a)
+
+ for j in range(i + 1, len(patterns)):
+ pattern_b = patterns[j]
+
+ # Prefix Check
+ if pattern_a[:-1] != pattern_b[:-1]: continue
+
+ item_b = pattern_b[-1]
+
+ # Spatial Check (O(1) Lookup)
+ if item_b not in valid_neighbors: continue
+
+ # Support Check (Intersection)
+ tids_b = current_level_patterns[pattern_b]
+ intersection = tids_a.intersection(tids_b)
+ support = len(intersection)
+
+ if support >= self._minSup:
+ new_pattern = pattern_a + (item_b,)
+ self._finalPatterns[new_pattern] = support
+ self._dfs({new_pattern: intersection})
+
def getMemoryUSS(self):
"""
Total amount of USS memory consumed by the mining process will be retrieved from this function
@@ -456,7 +391,6 @@ def getMemoryUSS(self):
:return: returning USS memory consumed by the mining process
:rtype: float
"""
-
return self._memoryUSS
def getMemoryRSS(self):
@@ -466,7 +400,6 @@ def getMemoryRSS(self):
:return: returning RSS memory consumed by the mining process
:rtype: float
"""
-
return self._memoryRSS
def getRuntime(self):
@@ -476,7 +409,6 @@ def getRuntime(self):
:return: returning total amount of runtime taken by the mining process
:rtype: float
"""
-
return self._endTime - self._startTime
def getPatternsAsDataFrame(self):
@@ -486,7 +418,6 @@ def getPatternsAsDataFrame(self):
:return: returning frequent patterns in a dataframe
:rtype: pd.DataFrame
"""
-
dataFrame = {}
data = []
for a, b in self._finalPatterns.items():
@@ -496,6 +427,8 @@ def getPatternsAsDataFrame(self):
if type(a) == list:
for _ in a:
pat = pat + a + ' '
+ if type(a) == tuple:
+ pat = " ".join(a)
data.append([pat.strip(), b])
dataFrame = _ab._pd.DataFrame(data, columns=['Patterns', 'Support'])
return dataFrame
@@ -511,12 +444,11 @@ def save(self, outFile):
writer = open(self._oFile, 'w+')
for x, y in self._finalPatterns.items():
pat = str()
- if type(x) == str:
- pat = x
- if type(x) == list:
- for _ in x:
- pat = pat + x + '\t'
- patternsAndSupport = pat.strip() + ":" + str(len(y))
+ if isinstance(x, str):
+ pat = x
+ if isinstance(x, tuple) or isinstance(x, list):
+ pat = "\t".join(x)
+ patternsAndSupport = pat.strip() + ":" + str(y)
writer.write("%s \n" % patternsAndSupport)
def getPatterns(self):
@@ -535,7 +467,7 @@ def printResults(self):
print("Total number of Spatial 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())
+ print("Total ExecutionTime in ms:", self.getRuntime())
if __name__ == "__main__":
@@ -546,11 +478,10 @@ def printResults(self):
if len(_ab._sys.argv) == 5:
_ap = SpatialECLAT(_ab._sys.argv[1], _ab._sys.argv[3], _ab._sys.argv[4])
_ap.mine()
- _ap.mine()
print("Total number of Spatial 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 seconds:", _ap.getRuntime())
else:
- print("Error! The number of input parameters do not match the total number of parameters provided")
+ print("Error! The number of input parameters do not match the total number of parameters provided")
\ No newline at end of file
diff --git a/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT_old.py b/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT_old.py
new file mode 100644
index 00000000..0f012697
--- /dev/null
+++ b/PAMI/georeferencedFrequentPattern/basic/SpatialECLAT_old.py
@@ -0,0 +1,556 @@
+# SpatialEclat is an Extension of ECLAT algorithm,which stands for Equivalence Class Clustering and bottom-up
+# Lattice Traversal.It is one of the popular methods of Association Rule mining. It is a more efficient and
+# scalable version of the Apriori algorithm.
+#
+# **Importing this algorithm into a python program**
+# ---------------------------------------------------
+#
+# from PAMI.georeferencedFrequentPattern.basic import SpatialECLAT as alg
+#
+# obj = alg.SpatialECLAT("sampleTDB.txt", "sampleN.txt", 5)
+#
+# obj.mine()
+#
+# spatialFrequentPatterns = obj.getPatterns()
+#
+# print("Total number of Spatial Frequent Patterns:", len(spatialFrequentPatterns))
+#
+# obj.save("outFile")
+#
+# 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 .
+ Copyright (C) 2021 Rage Uday Kiran
+
+"""
+
+from PAMI.georeferencedFrequentPattern.basic import abstract as _ab
+from deprecated import deprecated
+
+
+class SpatialECLAT(_ab._spatialFrequentPatterns):
+ """
+ :Description: Spatial Eclat is a Extension of ECLAT algorithm,which stands for Equivalence Class Clustering and bottom-up
+ Lattice Traversal.It is one of the popular methods of Association Rule mining. It is a more efficient and
+ scalable version of the Apriori algorithm.
+
+ :Reference: Rage, Uday & Fournier Viger, Philippe & Zettsu, Koji & Toyoda, Masashi & Kitsuregawa, Masaru. (2020).
+ Discovering Frequent Spatial Patterns in Very Large Spatiotemporal Databases.
+
+ :param iFile: str :
+ Name of the Input file to mine complete set of Geo-referenced frequent patterns
+ :param oFile: str :
+ Name of the output file to store complete set of Geo-referenced frequent patterns
+ :param 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.
+ :param maxPer: float :
+ The user can specify maxPer in count or proportion of database size. If the program detects the data type of maxPer is integer, then it treats maxPer is expressed in count.
+ :param nFile: str :
+ Name of the input file to mine complete set of Geo-referenced frequent patterns
+ :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
+ nFile : str
+ Name of Neighbourhood file name
+ 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.
+ Example: minSup=10 will be treated as integer, while minSup=10.0 will be treated as float
+ 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
+ oFile : str
+ Name of the output file to store complete set of frequent patterns
+ 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 complete set of transactions available in the input database/file
+
+ :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(iFileName)
+ Storing the complete transactions of the database/input file in a database variable
+ frequentOneItem()
+ Generating one frequent patterns
+ dictKeysToInt(iList)
+ Converting dictionary keys to integer elements
+ eclatGeneration(cList)
+ It will generate the combinations of frequent items
+ generateSpatialFrequentPatterns(tidList)
+ It will generate the combinations of frequent items from a list of items
+ convert(value)
+ To convert the given user specified value
+ getNeighbourItems(keySet)
+ A function to get common neighbours of a itemSet
+ mapNeighbours(file)
+ A function to map items to their neighbours
+
+ **Executing the code on terminal :**
+ ----------------------------------------
+
+ .. code-block:: console
+
+ Format:
+
+ (.venv) $ python3 SpatialECLAT_old.py
+
+ Example Usage:
+
+ (.venv) $ python3 SpatialECLAT_old.py sampleTDB.txt output.txt sampleN.txt 0.5
+
+ .. note:: minSup will be considered in percentage of database transactions
+
+
+
+ **Sample run of importing the code :**
+ ------------------------------------------
+ .. code-block:: python
+
+ from PAMI.georeferencedFrequentPattern.basic import SpatialECLAT as alg
+
+ obj = alg.SpatialECLAT("sampleTDB.txt", "sampleN.txt", 5)
+
+ obj.mine()
+
+ spatialFrequentPatterns = obj.getPatterns()
+
+ print("Total number of Spatial Frequent Patterns:", len(spatialFrequentPatterns))
+
+ obj.save("outFile")
+
+ 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 B.Sai Chitra under the supervision of Professor Rage Uday Kiran.
+ """
+
+ _minSup = float()
+ _startTime = float()
+ _endTime = float()
+ _finalPatterns = {}
+ _iFile = " "
+ _oFile = " "
+ _nFile = " "
+ _memoryUSS = float()
+ _memoryRSS = float()
+ _Database = []
+ _sep = "\t"
+
+ def __init__(self, iFile, nFile, minSup, sep="\t"):
+ super().__init__(iFile, nFile, minSup, sep)
+ self._NeighboursMap = {}
+
+ 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 'Patterns' in i:
+ self._Database = self._iFile['Patterns'].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()
+
+ # function to get frequent one pattern
+ def _frequentOneItem(self):
+ """
+ Generating one frequent patterns
+ """
+ self._finalPatterns = {}
+ candidate = {}
+ 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]] += [i]
+ self._finalPatterns = {keys: value for keys, value in candidate.items() if len(value) >= self._minSup}
+
+ def _convert(self, value):
+ """
+ To convert the given user specified value
+
+ :param value: user specified value
+ :type value: int or float or str
+ :return: converted value
+ :rtype: float
+ """
+ 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
+
+ @staticmethod
+ def _dictKeysToInt(iList):
+ """
+ Converting dictionary keys to integer elements
+
+ :param iList: Dictionary with patterns as keys and their support count as a value
+ :type iList: dict
+ :returns: list of integer patterns to represent dictionary keys
+ :rtype: list
+ """
+
+ temp = []
+ for ite in iList.keys():
+ ite = [int(i) for i in ite.strip('[]').split('\t')]
+ temp.append(ite)
+ # print(sorted(temp))
+ return sorted(temp)
+
+ def _eclatGeneration(self, cList):
+ """It will generate the combinations of frequent items
+
+ :param cList :it represents the items with their respective transaction identifiers
+ :type cList: dictionary
+ :return: returning transaction dictionary
+ :rtype: dict
+ """
+ # to generate all
+ tidList = {}
+ key = list(cList.keys())
+ for i in range(0, len(key)):
+ NeighboursItems = self._getNeighbourItems(key[i])
+ for j in range(i + 1, len(key)):
+ # print(c[key[i]],c[key[j]])
+ if not key[j] in NeighboursItems:
+ continue
+ intersectionList = list(set(cList[key[i]]).intersection(set(cList[key[j]])))
+ itemList = []
+ itemList += key[i]
+ itemList += key[j]
+ if len(intersectionList) >= self._minSup:
+ itemList.sort()
+ if tuple(itemList) not in tidList:
+ tidList[tuple(set(itemList))] = intersectionList
+ return tidList
+
+ def _generateSpatialFrequentPatterns(self, tidList):
+ """
+ It will generate the combinations of frequent items from a list of items
+
+ :param tidList: it represents the items with their respective transaction identifiers
+ :type tidList: dictionary
+ :return: returning transaction dictionary
+ :rtype: dict
+ """
+ tidList1 = {}
+ if len(tidList) == 0:
+ print("There are no more candidate sets")
+ else:
+ key = list(tidList.keys())
+ for i in range(0, len(key)):
+ NeighboursItems = self._getNeighbourItems(key[i])
+ for j in range(i + 1, len(key)):
+ if not key[j] in NeighboursItems:
+ continue
+ intersectionList = list(set(tidList[key[i]]).intersection(set(tidList[key[j]])))
+ itemList = []
+ if len(intersectionList) >= self._minSup:
+ itemList += key[i], key[j]
+ itemList.sort()
+ tidList1[tuple(itemList)] = intersectionList
+
+ return tidList1
+
+ def _getNeighbourItems(self, keySet):
+ """
+ A function to get Neighbours of a item
+
+ :param keySet: itemSet
+ :type keySet: str or tuple
+ :return: set of common neighbours
+ :rtype: set
+ """
+ itemNeighbours = self._NeighboursMap.keys()
+ if isinstance(keySet, str):
+ if self._NeighboursMap.get(keySet) is None:
+ return []
+ itemNeighbours = list(set(itemNeighbours).intersection(set(self._NeighboursMap.get(keySet))))
+ if isinstance(keySet, tuple):
+ keySet = list(keySet)
+ # print(keySet)
+ for j in range(0, len(keySet)):
+ i = keySet[j]
+ itemNeighbours = list(set(itemNeighbours).intersection(set(self._NeighboursMap.get(i))))
+ return itemNeighbours
+
+ def _mapNeighbours(self):
+ """
+ A function to map items to their Neighbours
+ """
+ self._NeighboursMap = {}
+ if isinstance(self._nFile, _ab._pd.DataFrame):
+ data, items = [], []
+ if self._nFile.empty:
+ print("its empty..")
+ i = self._nFile.columns.values.tolist()
+ if 'item' in i:
+ items = self._nFile['items'].tolist()
+ if 'Neighbours' in i:
+ data = self._nFile['Neighbours'].tolist()
+ for k in range(len(items)):
+ self._NeighboursMap[items[k]] = data[k]
+ # print(self.Database)
+ if isinstance(self._nFile, str):
+ if _ab._validators.url(self._nFile):
+ data = _ab._urlopen(self._nFile)
+ 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._NeighboursMap[temp[0]] = temp[1:]
+ else:
+ try:
+ with open(self._nFile, '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._NeighboursMap[temp[0]] = temp[1:]
+ except IOError:
+ print("File Not Found")
+ quit()
+
+ @deprecated("It is recommended to use 'mine()' instead of 'mine()' for mining process. Starting from January 2025, 'mine()' 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
+ """
+
+ # global items_sets, endTime, startTime
+ self._startTime = _ab._time.time()
+ if self._iFile is None:
+ raise Exception("Please enter the file path or file name:")
+ self._creatingItemSets()
+ self._minSup = self._convert(self._minSup)
+ self._mapNeighbours()
+ self._finalPatterns = {}
+ self._frequentOneItem()
+ frequentSet = self._generateSpatialFrequentPatterns(self._finalPatterns)
+ for x, y in frequentSet.items():
+ if x not in self._finalPatterns:
+ self._finalPatterns[x] = y
+ while 1:
+ frequentSet = self._eclatGeneration(frequentSet)
+ for x, y in frequentSet.items():
+ if x not in self._finalPatterns:
+ self._finalPatterns[x] = y
+ if len(frequentSet) == 0:
+ break
+ 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("Spatial Frequent patterns were generated successfully using SpatialECLAT 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():
+ pat = str()
+ if type(a) == str:
+ pat = a
+ if type(a) == list:
+ for _ in a:
+ pat = pat + a + ' '
+ data.append([pat.strip(), 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 a output file
+
+ :param outFile: name of the output file
+ :type outFile: csv file
+ """
+ self._oFile = outFile
+ writer = open(self._oFile, 'w+')
+ for x, y in self._finalPatterns.items():
+ pat = str()
+ if type(x) == str:
+ pat = x
+ if type(x) == list:
+ for _ in x:
+ pat = pat + x + '\t'
+ patternsAndSupport = pat.strip() + ":" + str(len(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 printResults(self):
+ """
+ This function is used to print the results
+ """
+ print("Total number of Spatial 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) == 5 or len(_ab._sys.argv) == 6:
+ if len(_ab._sys.argv) == 6:
+ _ap = SpatialECLAT(_ab._sys.argv[1], _ab._sys.argv[3], _ab._sys.argv[4], _ab._sys.argv[5])
+ if len(_ab._sys.argv) == 5:
+ _ap = SpatialECLAT(_ab._sys.argv[1], _ab._sys.argv[3], _ab._sys.argv[4])
+ _ap.mine()
+ _ap.mine()
+ print("Total number of Spatial 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 seconds:", _ap.getRuntime())
+ else:
+ print("Error! The number of input parameters do not match the total number of parameters provided")
\ No newline at end of file