Merge pull request #428 from Tarun-Sreepada/main

standard format
UdayLab · May 29, 2024 · 04a903d · 04a903d
2 parents 449b28e + 7be754c
commit 04a903d
Show file tree

Hide file tree

Showing 12 changed files with 39 additions and 7 deletions.
diff --git a/PAMI/correlatedPattern/basic/CoMine.py b/PAMI/correlatedPattern/basic/CoMine.py
@@ -247,6 +247,9 @@ def _creatingItemSets(self) -> None:
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/correlatedPattern/basic/CoMinePlus.py b/PAMI/correlatedPattern/basic/CoMinePlus.py
@@ -247,6 +247,9 @@ def _creatingItemSets(self) -> None:
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/extras/syntheticDataGenerator/TransactionalDatabase.py b/PAMI/extras/syntheticDataGenerator/TransactionalDatabase.py
@@ -173,7 +173,7 @@ def save(self, filename) -> None:
             for line in self.db:
                 f.write(str(self.seperator).join(map(str, line)) + '\n')
 
-    def getTransactions(self) -> pd.DataFrame:
+    def getTransactions(self, sep = "\t") -> pd.DataFrame:
         """
         Get the transactional database in dataFrame format
 
@@ -182,8 +182,7 @@ def getTransactions(self) -> pd.DataFrame:
         """
         column = "Transactions"
         db = pd.DataFrame(columns=[column])
-        temp = ["\t".join([str(a) for a in x]) for x in self.db]
-        db[column] = temp
+        db[column] = [sep.join(map(str, line)) for line in self.db]
         return db
 
 

diff --git a/PAMI/frequentPattern/basic/Apriori.py b/PAMI/frequentPattern/basic/Apriori.py
@@ -161,10 +161,10 @@ def _creatingItemSets(self) -> None:
                 print("its empty..")
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
-                temp = self._iFile['Transactions'].tolist()
-
-            for k in temp:
-                self._Database.append(set(k))
+                self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/frequentPattern/basic/Aprioribitset.py b/PAMI/frequentPattern/basic/Aprioribitset.py
@@ -191,6 +191,9 @@ def _creatingItemSets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
 
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):

diff --git a/PAMI/frequentPattern/basic/ECLAT.py b/PAMI/frequentPattern/basic/ECLAT.py
@@ -162,6 +162,9 @@ def _creatingItemSets(self) -> float:
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/frequentPattern/basic/ECLATDiffset.py b/PAMI/frequentPattern/basic/ECLATDiffset.py
@@ -161,6 +161,9 @@ def _creatingItemSets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/frequentPattern/basic/ECLATbitset.py b/PAMI/frequentPattern/basic/ECLATbitset.py
@@ -178,6 +178,9 @@ def _creatingItemSets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
 
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):

diff --git a/PAMI/frequentPattern/basic/FPGrowth.py b/PAMI/frequentPattern/basic/FPGrowth.py
@@ -227,6 +227,10 @@ def __creatingItemSets(self) -> None:
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self.__Database = self._iFile['Transactions'].tolist()
+                self.__Database = [x.split(self._sep) for x in self.__Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
+
 
             #print(self.Database)
         if isinstance(self._iFile, str):

diff --git a/PAMI/frequentPattern/closed/CHARM.py b/PAMI/frequentPattern/closed/CHARM.py
@@ -193,6 +193,10 @@ def _creatingItemsets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [i.split(self._sep) for i in self._Database]
+
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
             for i in self._Database:
                 self._lno += 1
                 for j in i:

diff --git a/PAMI/frequentPattern/maximal/MaxFPGrowth.py b/PAMI/frequentPattern/maximal/MaxFPGrowth.py
@@ -533,6 +533,10 @@ def _creatingItemSets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
+
         if isinstance(self._iFile, str):
             if _ab._validators.url(self._iFile):
                 data = _ab._urlopen(self._iFile)

diff --git a/PAMI/frequentPattern/topk/FAE.py b/PAMI/frequentPattern/topk/FAE.py
@@ -160,6 +160,9 @@ def _creatingItemSets(self):
             i = self._iFile.columns.values.tolist()
             if 'Transactions' in i:
                 self._Database = self._iFile['Transactions'].tolist()
+                self._Database = [x.split(self._sep) for x in self._Database]
+            else:
+                print("The column name should be Transactions and each line should be separated by tab space or a seperator specified by the user")
 
             # print(self.Database)
         if isinstance(self._iFile, str):