#2 updated the UtilityDatabase.py

PAMI/extras/syntheticDataGenerator/GeoReferentialTransactionalDatabase.py

@@ -1,15 +1,15 @@
 # generateTransactionalDatabase is a code used to convert the database into Temporal database.
 #
 #  **Importing this algorithm into a python program**
-#  --------------------------------------------------------
+#
 #     from PAMI.extras.generateDatabase import generateTransactionalDatabase as db
 #     obj = db(10, 5, 10)
 #     obj.create()
 #     obj.save('db.txt')
 #     print(obj.getTransactions()) to get the transactional database as a pandas dataframe
 
 # **Running the code from the command line**
-# --------------------------------------------------------
+#
 #     python generateDatabase.py 10 5 10 db.txt
 #     cat db.txt
 #
@@ -121,16 +121,15 @@ def tuning(self, array, sumRes) -> list:
         """
 
         while np.sum(array) != sumRes:
-            # get index of largest value
-            randIndex = np.random.randint(0, len(array))
-            # if sum is too large, decrease the largest value
+
             if np.sum(array) > sumRes:
-                array[randIndex] -= 1
-            # if sum is too small, increase the smallest value
+                maxIndex = np.argmax(array)
+                array[maxIndex] -= 1
+                # if sum is too small, increase the smallest value
             else:
                 minIndex = np.argmin(array)
-                array[randIndex] += 1
-        return array
+                array[minIndex] += 1
+            return array
 
     def generateArray(self, nums, avg, maxItems) -> list:
         """
@@ -154,7 +153,7 @@ def generateArray(self, nums, avg, maxItems) -> list:
         """
 
         # generate n random values
-        values = np.random.randint(1, maxItems, nums)
+        values = np.random.randint(1, avg * 1.5, nums)
 
         sumRes = nums * avg
 

PAMI/extras/syntheticDataGenerator/GeoreferentialTemporalDatabase.py

@@ -57,6 +57,7 @@ def __init__(
         self.seperator = sep
         self.occurrenceProbabilityOfSameTimestamp = occurrenceProbabilityOfSameTimestamp
         self.occurrenceProbabilityToSkipSubsequentTimestamp = occurrenceProbabilityToSkipSubsequentTimestamp
+        self.current_timestamp = int()
         self._startTime = float()
         self._endTime = float()
         self._memoryUSS = float()
@@ -76,7 +77,7 @@ def __init__(
 
     def getPoint(self, x1, y1, x2, y2):
 
-        return (np.random.randint(x1, x2), np.random.randint(y1, y2))
+        return (np.random.randint(x1, x2),np.random.randint(y1, y2))
 
     def performCoinFlip(self, probability: float) -> bool:
         """
@@ -86,7 +87,7 @@ def performCoinFlip(self, probability: float) -> bool:
         :return: True if the coin lands heads, False otherwise.
         """
         result = np.random.choice([0, 1], p=[1 - probability, probability])
-        return result == 1
+        return result
 
     def tuning(self, array, sumRes) -> list:
         """
@@ -106,16 +107,14 @@ def tuning(self, array, sumRes) -> list:
         """
 
         while np.sum(array) != sumRes:
-            # get index of largest value
-            randIndex = np.random.randint(0, len(array))
-            # if sum is too large, decrease the largest value
             if np.sum(array) > sumRes:
-                array[randIndex] -= 1
-            # if sum is too small, increase the smallest value
+                maxIndex = np.argmax(array)
+                array[maxIndex] -= 1
+                # if sum is too small, increase the smallest value
             else:
                 minIndex = np.argmin(array)
-                array[randIndex] += 1
-        return array
+                array[minIndex] += 1
+            return array
 
     def generateArray(self, nums, avg, maxItems) -> list:
         """
@@ -139,7 +138,7 @@ def generateArray(self, nums, avg, maxItems) -> list:
         """
 
         # generate n random values
-        values = np.random.randint(1, maxItems, nums)
+        values = np.random.randint(1, avg*1.5, nums)
 
         sumRes = nums * avg
 
@@ -172,39 +171,29 @@ def create(self) -> None:
         """
         self._startTime = time.time()
         db = set()
-        lineSize = [] #may be error. need to check it.
-        sumRes = self.databaseSize * self.avgItemsPerTransaction  # Total number of items
+
+        values = self.generateArray(self.databaseSize, self.avgItemsPerTransaction, self.numItems)
 
         for i in range(self.databaseSize):
             # Determine the timestamp
             if self.performCoinFlip(self.occurrenceProbabilityOfSameTimestamp):
                 timestamp = self.current_timestamp
             else:
-                if self.performCoinFlip(self.occurrenceProbabilityToSkipSubsequentTimestamp):
+                if self.performCoinFlip(self.occurrenceProbabilityToSkipSubsequentTimestamp)==1:
                     self.current_timestamp += 2
                 else:
                     self.current_timestamp += 1
                 timestamp = self.current_timestamp
 
             self.db.append([timestamp])  # Start the transaction with the timestamp
 
-            lineSize.append([i, 0])  # Initialize lineSize with 0 for each transaction
-
-        # Adjust lineSize to ensure sum of sizes equals sumRes
-        lineSize = self.tuning(lineSize, sumRes)
-
         # For each transaction, generate items
-        for i in tqdm.tqdm(range(len(lineSize))):
-            transaction_index = lineSize[i][0]
-            num_items = lineSize[i][1]
-
-            if num_items > self.numItems:
-                raise ValueError(
-                    "Error: Either increase numItems or decrease avgItemsPerTransaction or modify percentage")
-            items = np.random.choice(range(1, self.numItems + 1), num_items, replace=False)
-            self.db[transaction_index].extend(items)
+        for i in tqdm.tqdm(range(self.databaseSize)):
+            items = np.random.choice(range(1, self.numItems + 1), values[i], replace=False)
+            nline = [self.itemPoint[i] for i in items]
+            self.db[i].extend(nline)
 
-        self._runTime = time.time() - self._startTime
+        self._endTime = time.time()
         process = psutil.Process(os.getpid())
         self._memoryUSS = process.memory_full_info().uss
         self._memoryRSS = process.memory_info().rss

PAMI/extras/syntheticDataGenerator/utilityDatabase.py → PAMI/extras/syntheticDataGenerator/UtilityDatabase.py

@@ -1,51 +1,73 @@
 import numpy as np
 import pandas as pd
 import random
+import psutil, os, time
 
 
-class UtilityDataGenerator:
-    def __init__(self, databaseSize, numberOfItems, averageLengthOfTransaction,
-                 minimumInternalUtilityValue, maximumInternalUtilityValue,
-                 minimumExternalUtilityValue, maximumExternalUtilityValue):
+class UtilityDatabase:
+    def __init__(self, databaseSize, numItems, avgItemsPerTransaction,
+                 minInternalUtilityValue, maxInternalUtilityValue,
+                 minExternalUtilityValue, maxExternalUtilityValue):
         self.databaseSize = databaseSize
-        self.numberOfItems = numberOfItems
-        self.averageLengthOfTransaction = averageLengthOfTransaction
-        self.minInternalUtilityValue = minimumInternalUtilityValue
-        self.maxInternalUtilityValue = maximumInternalUtilityValue
-        self.minExternalUtilityValue = minimumExternalUtilityValue
-        self.maxExternalUtilityValue = maximumExternalUtilityValue
+        self.numItems = numItems
+        self.avgItemsPerTransaction = avgItemsPerTransaction
+        self.minInternalUtilityValue = minInternalUtilityValue
+        self.maxInternalUtilityValue = maxInternalUtilityValue
+        self.minExternalUtilityValue = minExternalUtilityValue
+        self.maxExternalUtilityValue = maxExternalUtilityValue
         self.entries = []
         self.ExternalUtilityData = self.GenerateExternalUtilityData()
+        self._startTime = float()
+        self._endTime = float()
+        self._memoryUSS = float()
+        self._memoryRSS = float()
 
     def GenerateExternalUtilityData(self):
-        items = range(1, self.numberOfItems + 1)
+        items = range(1, self.numItems + 1)
         ExternalUtilityData = {f'item{item}': random.randint(100, 900) for item in items}
         return ExternalUtilityData
 
-    def Generate(self):
+    def create(self):
+        self._startTime = time.time()
         for entry_id in range(1, self.databaseSize + 1):
-            entry_length = np.random.randint(1, self.averageLengthOfTransaction * 2)
+            entry_length = np.random.randint(1, self.avgItemsPerTransaction * 2)
             entry = np.random.randint(self.minInternalUtilityValue, self.maxInternalUtilityValue + 1,
-                                      size=self.numberOfItems)
+                                      size=self.numItems)
             entry_sum = entry.sum()
             self.entries.append((entry, entry_sum))
+        self._endTime = time.time()
 
-    def Save(self, fileName):
+    def save(self, fileName):
         with open(fileName, 'w') as file:
             for idx, (entry, entry_sum) in enumerate(self.entries, start=1):
                 entry_str = '\t'.join(map(str, entry))
                 file.write(f'{idx}\t{entry_str}\t{entry_sum}\n')
 
+    def getMemoryUSS(self) -> float:
+
+        process = psutil.Process(os.getpid())
+        self._memoryUSS = process.memory_full_info().uss
+        return self._memoryUSS
+
+    def getMemoryRSS(self) -> float:
+
+        process = psutil.Process(os.getpid())
+        self._memoryRSS = process.memory_info().rss
+        return self._memoryRSS
+
+    def getRuntime(self) -> float:
+        return self._endTime - self._startTime
+
     def SaveItemsInternalUtilityValues(self, fileName):
-        items = random.sample(range(1, self.numberOfItems + 1), self.numberOfItems)
+        items = random.sample(range(1, self.numItems + 1), self.numItems)
         internal_utility_data = [np.random.randint(self.minInternalUtilityValue, self.maxInternalUtilityValue + 1) for _
                                  in items]
         data = {'Item': items, 'Internal Utility Value': internal_utility_data}
         df = pd.DataFrame(data)
         df.to_csv(fileName, sep='\t', index=False)
 
     def Saveitemsexternalutilityvalues(self, fileName):
-        items = random.sample(range(1, self.numberOfItems + 1), self.numberOfItems)
+        items = random.sample(range(1, self.numItems + 1), self.numItems)
         data = {'Item': [f'item{item}' for item in items],
                 'External Utility Value': list(self.ExternalUtilityData.values())}
         df = pd.DataFrame(data)
@@ -59,22 +81,22 @@ def GetUtilityData(self):
         return df
 
     def GetInternalUtilityData(self):
-        items = random.sample(range(1, self.numberOfItems + 1), self.numberOfItems)
+        items = random.sample(range(1, self.numItems + 1), self.numItems)
         InternalUtilityData = [np.random.randint(self.minInternalUtilityValue, self.maxInternalUtilityValue + 1) for _
                                  in items]
         data = {'Item': items, 'Internal Utility Value': InternalUtilityData}
         df = pd.DataFrame(data)
         return df
 
     def GetExternalUtilityData(self):
-        items = random.sample(range(1, self.numberOfItems + 1), self.numberOfItems)
+        items = random.sample(range(1, self.numItems + 1), self.numItems)
         data = {'Item': [f'item{item}' for item in items],
                 'External Utility Value': list(self.ExternalUtilityData.values())}
         df = pd.DataFrame(data)
         return df
 
     def GenerateAndPrintItemPairs(self):
-        items = random.sample(range(1, self.numberOfItems + 1), 2)
+        items = random.sample(range(1, self.numItems + 1), 2)
         item1_id = f'item{items[0]}'
         item2_id = f'item{items[1]}'
         item1_value = self.ExternalUtilityData[item1_id]
@@ -87,12 +109,15 @@ def GenerateAndPrintItemPairs(self):
 
 
 if __name__ == "__main__":
-    data_generator = UtilityDataGenerator(100000, 2000, 10, 1, 100, 1, 10)
-    data_generator.Generate()
-    data_generator.Save("utility_data-6.csv")
+    data_generator = UtilityDatabase(100000, 2000, 10, 1, 100, 1, 10)
+    data_generator.create()
+    data_generator.save("utility_data-6.csv")
     data_generator.SaveItemsInternalUtilityValues("items_internal_utility.csv")
     data_generator.Saveitemsexternalutilityvalues("items_external_utility.csv")
-    utility_data = data_generator.GetUtilityData()
+    utilityDataFrame = data_generator.GetUtilityData()
+    print('Runtime: ' + str(data_generator.getRuntime()))
+    print('Memory (RSS): ' + str(data_generator.getMemoryRSS()))
+    print('Memory (USS): ' + str(data_generator.getMemoryUSS()))
     InternalUtilityData = data_generator.GetInternalUtilityData()
     ExternalUtilityData = data_generator.GetExternalUtilityData()