changes

PAMI/extras/DF2DB/DF2DB.py

@@ -32,8 +32,8 @@
      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.extras.DF2DB.DenseFormatDF2DB import *
-from PAMI.extras.DF2DB.SparseFormatDF2DB import *
+from PAMI.extras.DF2DB.denseDF2DB import *
+from PAMI.extras.DF2DB.sparseDF2DB import *
 import sys
 
 class DF2DB:
@@ -76,9 +76,9 @@ def __init__(self, inputDF, thresholdValue, condition, DFtype='sparse') -> None:
         self.condition = condition
         self.DFtype = DFtype.lower()
         if DFtype == 'sparse':
-            self.DF2DB = sparseFormatDF2DB(self.inputDF, self.condition, self.thresholdValue)
+            self.DF2DB = sparseDF2DB(self.inputDF, self.condition, self.thresholdValue)
         elif DFtype == 'dense':
-            self.DF2DB = DenseFormatDF2DB(self.inputDF, self.condition, self.thresholdValue)
+            self.DF2DB = denseDF2DB(self.inputDF, self.condition, self.thresholdValue)
         else:
             raise Exception('DF type should be sparse or dense')
 

PAMI/extras/DF2DB/DF2DBPlus.py

@@ -31,8 +31,8 @@
      along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
 
-from PAMI.extras.DF2DB.DenseFormatDF2DBPlus import *
-from PAMI.extras.DF2DB.sparseFormatDF2DBPlus import *
+from PAMI.extras.DF2DB.DenseFormatDFPlus import *
+from PAMI.extras.DF2DB.SparseFormatDFPlus import *
 import sys
 
 
@@ -72,9 +72,9 @@ def __init__(self, inputDF, thresholdConditionDF, DFtype='sparse') -> None:
         self.thresholdConditionDF = thresholdConditionDF
         self.DFtype = DFtype.lower()
         if DFtype == 'sparse':
-            self.DF2DB = sparseFormatDF2DBPlus(self.inputDF, self.thresholdConditionDF)
+            self.DF2DB = SparseFormatDFPlus(self.inputDF, self.thresholdConditionDF)
         elif DFtype == 'dense':
-            self.DF2DB = DenseFormatDF2DBPlus(self.inputDF, self.thresholdConditionDF)
+            self.DF2DB = DenseFormatDFPlus(self.inputDF, self.thresholdConditionDF)
         else:
             raise Exception('DF type should be sparse or dense')
 

PAMI/extras/DF2DB/DenseFormatDF2DB.py → PAMI/extras/DF2DB/DenseFormatDF.py

@@ -1,11 +1,11 @@
-# DenseFormatDF2DB in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
+# DenseFormatDF in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
 #
 # **Importing this algorithm into a python program**
 # --------------------------------------------------------
 #
-#     from PAMI.extras.DF2DB import DenseFormatDF2DB as db
+#     from PAMI.extras.DF2DB import DenseFormatDF as db
 #
-#     obj = db.DenseFormatDF2DB(idf, ">=", 16)
+#     obj = db.DenseFormatDF(idf, ">=", 16)
 #
 #     obj.save(oFile)
 #
@@ -49,7 +49,7 @@
 }
 
 
-class DenseFormatDF2DB:
+class DenseFormatDF:
     """
         :Description: This class create Data Base from DataFrame.
 
@@ -65,9 +65,9 @@ class DenseFormatDF2DB:
         --------------------------------------------------------
         .. code-block:: python
 
-        from PAMI.extras.DF2DB import DenseFormatDF2DB as db
+        from PAMI.extras.DF2DB import DenseFormatDF as db
 
-        obj = db.DenseFormatDF2DB(iDdf, ">=", 16 )
+        obj = db.DenseFormatDF(iDdf, ">=", 16 )
 
         obj.convert2TransactionalDatabase("outputFileName") # To create transactional database
 
@@ -266,7 +266,7 @@ def getFileName(self) -> str:
 # Dataframes do not run from a terminal
 
 # if __name__ == '__main__':
-#     obj = DenseFormatDF2DB(sys.argv[1], sys.argv[2], sys.argv[3])
+#     obj = DenseFormatDF(sys.argv[1], sys.argv[2], sys.argv[3])
 #     obj.convert2TransactionalDatabase(sys.argv[4])
 #     transactionalDB = obj.getFileName()
 #     print(transactionalDB)

PAMI/extras/DF2DB/SparseFormatDF2DB.py → PAMI/extras/DF2DB/SparseFormatDF.py

@@ -1,11 +1,11 @@
-# sparseFormatDF2DB in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
+# SparseFormatDF in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
 #
 # **Importing this algorithm into a python program**
 # --------------------------------------------------------
 #
-#     from PAMI.extras.DF2DB import sparseFormatDF2DB as db
+#     from PAMI.extras.DF2DB import SparseFormatDF as db
 #
-#     obj = db.sparseFormatDF2DB(idf, ">=", 16)
+#     obj = db.SparseFormatDF(idf, ">=", 16)
 #
 #     obj.save(oFile)
 #
@@ -38,7 +38,7 @@
 import pandas as pd
 import sys
 
-class sparseFormatDF2DB:
+class SparseFormatDF:
     """
             :Description:  This class create Data Base from DataFrame.
 
@@ -55,9 +55,9 @@ class sparseFormatDF2DB:
         --------------------------------------------------------
         .. code-block:: python
 
-        from PAMI.extras.DF2DB import sparseFormatDF2DB as db
+        from PAMI.extras.DF2DB import SparseFormatDF as db
 
-        obj = db.sparseFormatDF2DB(iDdf, ">=", 16)
+        obj = db.SparseFormatDF(iDdf, ">=", 16)
 
         obj.save(oFile)
 
@@ -155,6 +155,6 @@ def getFileName(self) -> str:
 
 if __name__ == '__main__':
 
-    obj = sparseFormatDF2DB(sys.argv[1], sys.argv[2])
+    obj = SparseFormatDF(sys.argv[1], sys.argv[2])
     obj.getFileName(sys.argv[3])
 

PAMI/extras/DF2DB/denseDF2DBPlus.py

@@ -1,11 +1,11 @@
-# DenseFormatDF2DBPlus in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
+# DenseFormatDFPlus in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
 #
 # **Importing this algorithm into a python program**
 # --------------------------------------------------------
 #
-#     from PAMI.extras.DF2DB import DenseFormatDF2DBPlus as db
+#     from PAMI.extras.DF2DB import DenseFormatDFPlus as db
 #
-#     obj = db.DenseFormatDF2DBPlus(idf, ">=", 16)
+#     obj = db.DenseFormatDFPlus(idf, ">=", 16)
 #
 #     obj.save(oFile)
 #
@@ -39,7 +39,7 @@
 import pandas as pd
 import sys
 
-class DenseFormatDF2DBPlus:
+class DenseFormatDFPlus:
     """
         :Description: This class create Data Base from DataFrame.
 
@@ -53,9 +53,9 @@ class DenseFormatDF2DBPlus:
         --------------------------------------------------------
         .. code-block:: python
 
-        from PAMI.extras.DF2DB import DenseFormatDF2DBPlus as db
+        from PAMI.extras.DF2DB import DenseFormatDFPlus as db
 
-        obj = db.DenseFormatDF2DBPlus(iDdf, ">=", 16)
+        obj = db.DenseFormatDFPlus(iDdf, ">=", 16)
 
         obj.save(oFile)
 
@@ -171,6 +171,6 @@ def getFileName(self) -> str:
         return self.outputFile
 
 if __name__ == '__main__':
-    a = DenseFormatDF2DBPlus(sys.argv[1], sys.argv[3])
-    a.DenseFormatDF2DBPlus()
+    a = DenseFormatDFPlus(sys.argv[1], sys.argv[3])
+    a.DenseFormatDFPlus()
 

PAMI/extras/DF2DB/denseDF2DB_dump.py

@@ -1,11 +1,11 @@
-# DenseFormatDF2DB_dump in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
+# DenseFormatDF_dump in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
 #
 # **Importing this algorithm into a python program**
 # --------------------------------------------------------
 #
-#     from PAMI.extras.DF2DB import DenseFormatDF2DB_dump as db
+#     from PAMI.extras.DF2DB import DenseFormatDF_dump as db
 #
-#     obj = db.DenseFormatDF2DB_dump(idf, ">=", 16)
+#     obj = db.DenseFormatDF_dump(idf, ">=", 16)
 #
 #     obj.save(oFile)
 #
@@ -38,7 +38,7 @@
 
 import pandas as pd
 import sys
-class DenseFormatDF2DB():
+class DenseFormatDF():
     """
         :Description: This class create Data Base from DataFrame.
 
@@ -53,9 +53,9 @@ class DenseFormatDF2DB():
         --------------------------------------------------------
         .. code-block:: python
 
-        from PAMI.extras.DF2DB import DenseFormatDF2DB_dump as db
+        from PAMI.extras.DF2DB import DenseFormatDF_dump as db
 
-        obj = db.DenseFormatDF2DB_dump(iDdf, ">=", 16)
+        obj = db.DenseFormatDF_dump(iDdf, ">=", 16)
 
         obj.save(oFile)
 
@@ -303,6 +303,6 @@ def getFileName(self) -> str:
 if __name__ == '__main__':
 
 
-    obj = DenseFormatDF2DB(sys.argv[1], sys.argv[2])
+    obj = DenseFormatDF(sys.argv[1], sys.argv[2])
     obj.getFileName(sys.argv[3])
 

PAMI/extras/DF2DB/sparseDF2DBPlus.py

@@ -1,11 +1,11 @@
-# sparseFormatDF2DBPlus in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
+# SparseFormatDFPlus in this code the dense dataframe is converting databases into different transactional, temporal, utility types.
 #
 # **Importing this algorithm into a python program**
 # --------------------------------------------------------
 #
-#     from PAMI.extras.DF2DB import sparseFormatDF2DBPlus as db
+#     from PAMI.extras.DF2DB import SparseFormatDFPlus as db
 #
-#     obj = db.sparseFormatDF2DBPlus(idf, ">=", 16)
+#     obj = db.SparseFormatDFPlus(idf, ">=", 16)
 #
 #     obj.save(oFile)
 #
@@ -38,7 +38,7 @@
 import pandas as pd
 import sys
 
-class sparseFormatDF2DBPlus:
+class SparseFormatDFPlus:
     """
             :Description: This class create Data Base from DataFrame.
 
@@ -52,9 +52,9 @@ class sparseFormatDF2DBPlus:
         --------------------------------------------------------
         .. code-block:: python
 
-        from PAMI.extras.DF2DB import sparseFormatDF2DBPlus as db
+        from PAMI.extras.DF2DB import SparseFormatDFPlus as db
 
-        obj = db.sparseFormatDF2DBPlus(iDdf, ">=", 16)
+        obj = db.SparseFormatDFPlus(iDdf, ">=", 16)
 
         obj.save(oFile)
 
@@ -151,5 +151,5 @@ def getFileName(self) -> str:
 
 
 if __name__ == '__main__':
-    obj = sparseFormatDF2DBPlus(sys.argv[1], sys.argv[2])
+    obj = SparseFormatDFPlus(sys.argv[1], sys.argv[2])
     obj.getFileName(sys.argv[3])

PAMI/extras/dbStats/TemporalDatabase.py

@@ -30,6 +30,7 @@
      You should have received a copy of the GNU General Public License
      along with this program.  If not, see <https://www.gnu.org/licenses/>.
 """
+
 import sys
 import statistics
 import pandas as pd
@@ -100,8 +101,7 @@ class TemporalDatabase:
 
     """
 
-
-    def __init__(self, inputFile: Union[str, pd.DataFrame], sep: str='\t') -> None:
+    def __init__(self, inputFile: Union[str, pd.DataFrame], sep: str = '\t') -> None:
         """
         :param inputFile: input file name or path
         :type inputFile: str
@@ -167,7 +167,7 @@ def readDatabase(self) -> None:
         for ts in timeStampList:
             self.periodList.append(int(ts) - preTimeStamp)
             preTimeStamp = ts
-            
+
         for x, y in self.database.items():
             for i in y:
                 if i not in self.periods:
@@ -277,31 +277,30 @@ def getSortedListOfItemFrequencies(self) -> Dict[str, int]:
                 itemFrequencies[item] = itemFrequencies.get(item, 0)
                 itemFrequencies[item] += 1
         return {k: v for k, v in sorted(itemFrequencies.items(), key=lambda x: x[1], reverse=True)}
-    
+
     def getFrequenciesInRange(self) -> Dict[int, int]:
         fre = self.getSortedListOfItemFrequencies()
         rangeFrequencies = {}
         maximum = max([i for i in fre.values()])
-        values = [int(i*maximum/6) for i in range(1,6)]
-        #print(maximum)
+        values = [int(i * maximum / 6) for i in range(1, 6)]
+        # print(maximum)
         va = len({key: val for key, val in fre.items() if val > 0 and val < values[0]})
         rangeFrequencies[va] = values[0]
-        for i in range(1,len(values)):
-
-            va = len({key: val for key, val in fre.items() if val < values[i] and val > values[i-1]})
+        for i in range(1, len(values)):
+            va = len({key: val for key, val in fre.items() if val < values[i] and val > values[i - 1]})
             rangeFrequencies[va] = values[i]
         return rangeFrequencies
-    
+
     def getPeriodsInRange(self) -> Dict[int, int]:
         fre = {k: v for k, v in sorted(self.periods.items(), key=lambda x: x[1])}
         rangePeriods = {}
         maximum = max([i for i in fre.values()])
-        values = [int(i*maximum/6) for i in range(1,6)]
-        #print(maximum)
+        values = [int(i * maximum / 6) for i in range(1, 6)]
+        # print(maximum)
         va = len({key: val for key, val in fre.items() if val > 0 and val < values[0]})
         rangePeriods[va] = values[0]
-        for i in range(1,len(values)):
-            va = len({key: val for key, val in fre.items() if val < values[i] and val > values[i-1]})
+        for i in range(1, len(values)):
+            va = len({key: val for key, val in fre.items() if val < values[i] and val > values[i - 1]})
             rangePeriods[va] = values[i]
         return rangePeriods
 
@@ -349,21 +348,21 @@ def getMaximumInterArrivalPeriod(self) -> int:
         :return: maximum inter arrival period
         """
         return max(self.periodList)
-    
+
     def getMinimumPeriodOfItem(self) -> int:
         """
         get the minimum period of the item
         :return: minimum period
         """
         return min([i for i in self.periods.values()])
-    
+
     def getAveragePeriodOfItem(self) -> float:
         """
         get the average period of the item
         :return: average period
         """
         return sum([i for i in self.periods.values()]) / len(self.periods)
-    
+
     def getMaximumPeriodOfItem(self) -> int:
         """
         get the maximum period of the item
@@ -385,7 +384,7 @@ def getNumberOfTransactionsPerTimestamp(self) -> Dict[int, int]:
         """
         maxTS = max(list(self.timeStampCount.keys()))
         return {ts: self.timeStampCount.get(ts, 0) for ts in range(1, maxTS + 1)}
-   
+
     def printStats(self) -> None:
         print(f'Database size : {self.getDatabaseSize()}')
         print(f'Number of items : {self.getTotalNumberOfItems()}')
@@ -401,14 +400,15 @@ def printStats(self) -> None:
         print(f'Standard Deviation Transaction Size : {self.getStandardDeviationTransactionLength()}')
         print(f'Variance : {self.getVarianceTransactionLength()}')
         print(f'Sparsity : {self.getSparsity()}')
-  
+
     def plotGraphs(self) -> None:
         itemFrequencies = self.getFrequenciesInRange()
         transactionLength = self.getTransanctionalLengthDistribution()
         plt.plotLineGraphFromDictionary(itemFrequencies, 100, 0, 'Frequency', 'no of items', 'frequency')
         plt.plotLineGraphFromDictionary(transactionLength, 100, 0, 'transaction length', 'transaction length',
                                         'frequency')
 
+
 if __name__ == '__main__':
     data = {'tid': [1, 2, 3, 4, 5, 6, 7],
 

docs/dataFrameCoversion.md

@@ -46,7 +46,7 @@ Key concepts in each link were briefly mentioned to save your valuable time. Cli
     Default separator used in PAMI is tab space. However, users can override the separator with their choice.
 
 1. [Converting Dataframes to Databases](df2db.html)
-   1. [Dense dataframe to database](DenseFormatDF2DB.html)
-   1. [Sparse dataframe to database](sparseFormatDF2DB.html)
+   1. [Dense dataframe to database](DenseFormatDF.html)
+   1. [Sparse dataframe to database](SparseFormatDF.html)
    1. [Spatiotemporal dataframe to databases](stDF2DB.html)