Merge branch 'UdayLab:main' into main

PAMI/contiguousFrequentPattern/basic/PositionMining.py

@@ -34,27 +34,10 @@
 import pandas as pd
 import numpy as np
 import math
-from PAMI.contigousFrequentPattern.basic import abstract as _ab
+from PAMI.contiguousFrequentPattern import abstract as _ab
 from deprecated import deprecated
 
 
-__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/>.
-"""
-
 class Node:
     def __init__(self,symbol,leaf=False):
         self._val=symbol
@@ -96,9 +79,10 @@ class PositionMining:
 
     """
 
-    def __init__(self,minsup,datapath):
+    def __init__(self,minsup,datapath,maxlength=20):
         self.min_sup=minsup
         self.datapath=datapath
+        self.maxlength=maxlength
 
 
     def readData(self):
@@ -110,6 +94,7 @@ def readData(self):
         # for i in range(1,len(vals)):
         #     self.seq_prefixes[vals[i]]
         self.data=vals
+        # print(self.data)
 
     def getfreqs(self):
         """
@@ -272,7 +257,7 @@ def mineNext_candidates(self):
         """
         Mining frequent patterns along with their positions from length 1 frequent candidates
         """
-        while self.current_candidate<5:
+        while self.current_candidate<self.maxlength-1:
             curr=self.table[self.current_candidate]
             self.join(curr,self.current_candidate)
             self.current_candidate+=1
@@ -291,7 +276,7 @@ def mine(self):
         """
         # pass
         self._startTime = _ab._time.time()
-        self.table = {i: {} for i in range(1, 6)}
+        self.table = {i: {} for i in range(1, self.maxlength)}
         self.readData()
 
         self.getfreqs()
@@ -310,24 +295,4 @@ def mine(self):
         self._memoryUSS = float()
         self._memoryRSS = float()
         self._memoryUSS = process.memory_full_info().uss
-        self._memoryRSS = process.memory_info().rss
-
-
-# """Driver code"""
-
-# df=pd.read_csv("data/D1.csv")
-# data=df._values[:,1:]
-# c=0
-# for i in data:
-#     c+=len(i[1])
-
-# obj = PositionMining(minsup=400,data=data)
-# obj.mine()
-# interestingPatterns = obj.getPatterns()
-# print(interestingPatterns)
-# print("Total number of interesting patterns:", len(interestingPatterns))
-# obj.save("result.csv")
-
-
-# print()
-# print()
+        self._memoryRSS = process.memory_info().rss

PAMI/extras/csvConverter/csvParquet.py → PAMI/extras/converters/CSV2Parquet.py

@@ -38,7 +38,7 @@
 import pandas as pd
 import numpy as np
 
-class csvParquet():
+class CSV2Parquet():
     """
 
     :Description:   csvParquet is a code used to convert temporal and utility types into sparse and dense format
@@ -67,7 +67,7 @@ def __init__(self, iFile: str, sep: str='\t'):
         self._iFile = iFile
         self._sep = sep
 
-def csvParquet(csv_file: str, sep: str, inputType: str, outputType: str) -> None:
+def CSV2Parquet(csv_file: str, sep: str, inputType: str, outputType: str) -> None:
     inputTypes = ["temporal", "utility"]
     outputTypes = ["sparse", "dense"]
 

PAMI/extras/graph/flatTransactions.py → PAMI/extras/converters/Subgraphs2FlatTransactions.py

@@ -11,10 +11,11 @@
 #
 #   obj.saveFlatTransactions(oFile)
 
-class FlatTransactions:
+class Subgraphs2FlatTransactions:
 
     def __init__(self):
         self.flatTransactions = {}
+
     def getFlatTransactions(self, fidGidDictMap):
         """
         fidGidMap is a list of dictionaries with keys 'FID' and 'GIDs'
@@ -44,4 +45,4 @@ def saveFlatTransactions(self, oFile):
         """
         with open(oFile, 'w') as f:
             for _, fids in self.flatTransactions.items():
-                f.write(f"{' '.join(map(str, fids))}\n")
+                f.write(f"{' '.join(map(str, fids))}\n")

PAMI/GraphTransactionalCoveragePattern/basic/GTCP.py → PAMI/graphTransactionalCoveragePattern/basic/GTCP.py

@@ -58,7 +58,7 @@ def __init__(self,iFile,minsup,minGTC,minGTPC,maxOR=0.2):
         gsp_obj.mine()
         self.Sf=gsp_obj.getSubgraphGraphMapping()
         self.GetFIDBasedFlatTransactions()
-        # print("Subgraph mining completed")
+        print("Subgraph mining completed")
 
     def mine(self):
         """
@@ -236,4 +236,6 @@ def getRuntime(self):
         :return: returning total amount of runtime taken by the mining process
         :rtype: float
         """
-        return self._endTime-self._startTime
+        return self._endTime-self._startTime
+
+

PAMI/graphTransactionalCoveragePattern/basic/graph_gen.py

@@ -0,0 +1,30 @@
+import random
+def generate_random_graph(n, m, max_label,f):
+    vertices = [(f"v {i}", random.randint(1, max_label)) for i in range(n)]
+    edges = set()
+
+    while len(edges) < m:
+        u = random.randint(0, n - 1)
+        v = random.randint(0, n - 1)
+        label = random.randint(1, max_label)
+
+        if u != v and (u, v, label) not in edges:
+            edges.add((u, v, label))
+
+    for vertex in vertices:
+        s=f"{vertex[0]} {vertex[1]}\n"
+        f.write(s)
+
+    for edge in edges:
+        s=f"e {edge[0]} {edge[1]} {edge[2]}\n"
+        f.write(s)
+
+
+def generate(path, transactions):
+    f=open(path,"w+")
+    for t in range(transactions):
+        f.write("t # {}\n".format(t))
+        generate_random_graph(random.randint(10,20),random.randint(20,30),3,f)
+
+    f.write("t # -1")
+    f.close()

PAMI/sequentialPattern/basic/PrefixSpan.py

@@ -13,8 +13,7 @@
 #
 #      You should have received a copy of the GNU General Public License
 #      along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-from PAMI.sequentialPatternMining.basic import abstract as _ab
+from PAMI.sequentialPattern.basic import abstract as _ab
 import sys
 sys.setrecursionlimit(10000)
 

PAMI/sequentialPattern/basic/SPADE.py

@@ -58,7 +58,7 @@
 import pandas as pd
 from deprecated import deprecated
 
-from PAMI.sequentialPatternMining.basic import abstract as _ab
+from PAMI.sequentialPattern.basic import abstract as _ab
 
 _ab._sys.setrecursionlimit(10000)
 

PAMI/sequentialPattern/basic/SPAM.py

@@ -57,7 +57,7 @@
 import pandas as pd
 from deprecated import deprecated
 
-from PAMI.sequentialPatternMining.basic import abstract as _ab
+from PAMI.sequentialPattern.basic import abstract as _ab
 _ab._sys.setrecursionlimit(10000)
 
 class SPAM(_ab._sequentialPatterns):

PAMI/subgraphMining/topK/tkg.py

@@ -385,7 +385,7 @@ def registerAsCandidate(self, subgraph):
     def isCanonical(self, c: _ab.DfsCode):
         canC = _ab.DfsCode()
         for i in range(c.size):
-            extensions = self.rightMostPathExtensionsFromSingle(canC, _ab.Graph(c))
+            extensions = self.rightMostPathExtensionsFromSingle(canC, _ab.Graph(-1, None, c))
             minEe = None
             for ee in extensions.keys():
                 if minEe is None or ee.smallerThan(minEe):

README.md

@@ -11,6 +11,9 @@
 [![Downloads](https://static.pepy.tech/badge/pami)](https://pepy.tech/project/pami)
 [![Downloads](https://static.pepy.tech/badge/pami/month)](https://pepy.tech/project/pami)
 [![Downloads](https://static.pepy.tech/badge/pami/week)](https://pepy.tech/project/pami)
+[![pages-build-deployment](https://github.com/UdayLab/PAMI/actions/workflows/pages/pages-build-deployment/badge.svg)](https://github.com/UdayLab/PAMI/actions/workflows/pages/pages-build-deployment)
+[![Dependabot Updates](https://github.com/UdayLab/PAMI/actions/workflows/dependabot/dependabot-updates/badge.svg)](https://github.com/UdayLab/PAMI/actions/workflows/dependabot/dependabot-updates)
+[![CodeQL](https://github.com/UdayLab/PAMI/actions/workflows/github-code-scanning/codeql/badge.svg)](https://github.com/UdayLab/PAMI/actions/workflows/github-code-scanning/codeql)
 
 [Click here for more information](https://pepy.tech/project/pami)
 
@@ -560,6 +563,11 @@ We invite and encourage all community members to contribute, report bugs, fix bu
 |--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
  | Gspan <a target="_blank" href="https://colab.research.google.com/github/UdayLab/PAMI/blob/main/notebooks/subgraphMining/basic/gspan.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> | TKG <a target="_blank" href="https://colab.research.google.com/github/UdayLab/PAMI/blob/main/notebooks/subgraphMining/topk/tkg.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> |
 
+#### 11.2. Graph transactional coverage pattern mining
+| Basic                                                                                                                                                                                                                                                       |
+|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| GTCP<a target="_blank" href="https://colab.research.google.com/github/UdayLab/PAMI/blob/main/notebooks/graphTransactionalCoveragePatterns/basic/GTCP.ipynb"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/> </a> |
+
 ## 12. Additional Features
 
 #### 12.1. Creation of synthetic databases
@@ -590,6 +598,16 @@ We invite and encourage all community members to contribute, report bugs, fix bu
 | Temporal database <a target="_blank" href="https://colab.research.google.com/github/UdayLab/PAMI/blob/main/notebooks/extras/stats/TemporalDatabase.ipynb"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>           |
 | Utility database (coming soon)                                                                                                                                                                                                                                    |
 
+#### 12.4. Convertors
+| Approaches                 |
+|----------------------------|
+| Subgraphs2FlatTransactions |
+| CSV2Parquet                |
+| CSV2BitInteger             |
+| CSV2Integer                |
+
+
+
 #### 12.4. Generating Latex code for the experimental results
 | Approaches               |
 |--------------------------|

notebooks/graphTransactionalCoveragePatterns/basic/GTCP.ipynb

@@ -0,0 +1,37 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    ""
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}