def test3(intervals, n):
count = 0
# 1. Loading IB-Tree
print "Loading IB-Tree..."
# 2. Insert buckets into IB-Tree
tree = IBTree()
tree.readMetaData()
# 2.1. Print IB-Tree
print "Done!"
#print "Printing IB-Tree..."
#tree.printIBTree()
# 3. Loading IB+-Tree
print "Loading IB+-Tree"
plusTree = IBPlusTree()
plusTree.readMetaData()
plusTree.setIBTree(tree)
print "Done!"
# 4. Query data for a given interval
for i in range(0, n):
listBuckets = ListBuckets()
listTuples = ListTuples()
tt = timer()
tt.start()
plusTree.search(listTuples, listBuckets, intervals[i])
tt.end()
# 5. Print result
print intervals[i]
print "Buckets (IB+-Tree): ", len(listBuckets.results)
print "Time1: ", tt.resultInSecond
#readDB(listBuckets.results, "ibPlusTreeDB.dat")
return
def test1():
count = 0
# 1. Loading IB-Tree
print "Loading IB-Tree..."
# 2. Insert buckets into IB-Tree
tree = IBTree()
tree.readMetaData()
# 2.1. Print IB-Tree
print "Done!"
#print "Printing IB-Tree..."
#tree.printIBTree()
# 3. Loading IB+-Tree
print "Loading IB+-Tree"
plusTree = IBPlusTree()
plusTree.readMetaData()
plusTree.setIBTree(tree)
print "Done!"
# 4. Query data for a given interval
listBuckets1 = ListBuckets()
listBuckets = ListBuckets()
listTuples = ListTuples()
plusTree.search(listTuples, listBuckets, [0, 0.15])
# 5. Print result
print "Buckets (IB+-Tree): ", listBuckets.results
tree.search(listBuckets1, [0, 0.15])
print "Buckets (IB-Tree): ", listBuckets1.results
return
def run_test3():
#Test IB-Tree
#1. Read data from listBuckets_2.txt
#2. Insert buckets into IB-Tree
#3. Print IB-Tree
#4. IB+-Tree = copy structure of IB-Tree
#5. Print structure of IB+-Tree
#1. Read data from listBuckets.txt
anEntry = IBEntry()
print "Reading data and inserting into IB-Tree..."
fin = open("listBuckets_2.txt", "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
number = input('Enter a number: ')
for line in fin:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (count >= number):
break
bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
#print "BucketID: " + str(bucketID) + "\t [" + str(interval[0]) + ", " + str(interval[1]) + "]"
#print "Inserting the bucketID: ", bucketID
tree.insertBucket(interval, bucketID)
count += 1
#3. Print IB-Tree
print "Done!"
print "Printing IB-Tree..."
tree.printIBTree()
fin.close()
print "Number of buckets: " + str(bucketID + 1)
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
#5. Print structure of IB+-Tree
plusTree.printIBPlusTree(False)
print "Finished!"
return
def test_ImprintsIBTree(initInput, initNum, input, numInput, queryInterval,
startID):
# 1. Read sorted data from InitImprintsIBTree_sorted_v3.dat file (around 1 000 000 rows = 1 000 buckets)
listPT = [0.0 for x in range(0, Constants.IMPRINTS_NUM_PT)]
ibTree = IBTree()
finput = open(initInput, "r")
counter = 0
numRows = 0
print("1. Read sorted data from InitImprintsIBTree_sorted_v3.dat")
print("2 & 3. Build imprints and insert into IBTree")
for line in finput:
listValues = line.split('\'')
lenList = len(listValues)
nValue = int(lenList / 2)
for i in range(0, nValue):
pt = float(listValues[i * 2 + 1])
listPT[numRows] = pt
numRows += 1
if (numRows == Constants.IMPRINTS_NUM_PT):
# 2. Build Imprints for these data
interval = imprintsBucket(listPT)
# 3. Insert these data into IBTree
ibTree.insertBucket(interval, startID)
numRows = 0
startID += 1
counter += 1
if (counter == initNum):
break
finput.close()
print("4. Copy IBTree structure to IB+-Tree")
# 4. Copy IBTree structure to IB+Tree
ibPlusTree = IBPlusTree(ibTree)
ibPlusTree.copyStructure(ibTree)
print("5. Read random data from IniImprintsIBTree_random_v4.data file")
print("6. Insert these data into IB+-Tree")
# 5. Read random data from InitImprintsIBTree_random_v4.data file (around 1 000 000 rows = 1 000 buckets)
fin = open(input, "r")
counter = 0
for line in fin:
listValues = line.split('\'')
lenList = len(listValues)
nValue = int(lenList / 2)
pts = []
for i in range(0, nValue):
pt = float(listValues[i * 2 + 1])
pts.append(pt)
#imprints = imprintsBucket(pts)
imprintMark = imprintsHash(pts) # skip at this moment
# 6. Insert these data into IB+-Tree and thus IB-Tree
ibPlusTree.insertTuple(imprintMark, str(pts))
counter += 1
if (counter == numInput):
break
fin.close()
print("7. Run the queries and obtain the results")
# 7. Run the queries to obtain the results
listBuckets = ListBuckets()
listTuples = ListTuples()
ibPlusTree.searchImprintsAll(listTuples, listBuckets, queryInterval)
print "Result: ", listBuckets.results
ibTree.printEvalInfo()
ibTree.evaluation.printEvalInfoToFile("ImprintsIBTree_output.txt")
#ibPlusTree.printEvalInfo()
#ibPlusTree.evaluation.printEvalInfoToFile()
return Constants.FUNC_TRUE
def run_loadData_DB(sortedFile, numRows, numTuples):
count = 0
# 1. Read data from listBuckets_sorted_2.txt
print "Reading data and inserting into IB-Tree..."
fin1 = open(sortedFile, "r")
# 2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
if (numRows <= 0):
number = input('Enter a number: ')
else:
number = numRows
for line in fin1:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (count >= number):
break
bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
tree.insertBucket(interval, bucketID)
count += 1
# 2.1. Print IB-Tree
print "Done!"
print "Printing IB-Tree..."
tree.printIBTree()
fin1.close()
print "Number of buckets: " + str(bucketID + 1)
# IB+-Tree
# 3. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree()
plusTree.copyStructure(tree)
#4. Read data from the database
#5. Insert data into the IBPlusTree
count = 0
print "Connecting to the database..."
try:
conn = psycopg2.connect(
"dbname='nyc-taxi-data' user='******' password='******' host='localhost' "
)
cursor = conn.cursor()
except:
print "Error: Cannot connect to the database!"
return
print "Connected!"
start = 0
end = 0
size = 250000
trace = 0
while (end < numTuples):
if ((numTuples - end) > size):
end = start + size
else:
end = start + (numTuples - end)
strQuery = "select * from trips where id >=" + str(
start) + " and id <" + str(end)
trace += 1
if (trace % 10 == 0):
print trace
cursor.execute(strQuery)
data = cursor.fetchall()
for row in data:
strValue = "%s\n" % ", ".join(map(str, row))
key = float(row[12])
plusTree.insertTuple(key, strValue)
start = end
#5. Write the metadata info file
plusTree.flush()
print "=================<<<<>>>>=================="
plusTree.writeMetaData()
#plusTree.readMetaData()
#tree.writeMetaData()
plusTree.ibTree.writeMetaData()
#tree.readMetaData()
return
def run_test4(inputNum=0, inputNum2=0):
#Test IBPlus-Tree
#1. Read data from listBuckets_sorted_2.txt
print "Reading data and inserting into IB-Tree..."
fin1 = open("listBuckets_sorted_2.txt", "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
if (inputNum <= 0):
number = input('Enter a number: ')
else:
number = inputNum
for line in fin1:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (count >= number):
break
bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
tree.insertBucket(interval, bucketID)
count += 1
#3. Print IB-Tree
print "Done!"
print "Printing IB-Tree..."
tree.printIBTree()
fin1.close()
print "Number of buckets: " + str(bucketID + 1)
#IB+-Tree
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
##5. Print structure of IB+-Tree
#plusTree.printIBPlusTree(False)
#6. Read tuples from listBuckets_2.txt
print "Reading data and inserting into IB+-Tree..."
fin2 = open("listBuckets_2.txt", "r")
count2 = 0
if (inputNum2 <= 0):
numberIBPlus = input(
'Please select number of tuples to be insert into IB+-Tree: ')
else:
numberIBPlus = inputNum2
#7. Insert these tuples into IB+-Tree
for line in fin2:
tokens = line.split(' ')
if ((tokens[0] == "interval") | (tokens[0] == "bucketID:")):
continue
if (re.match('^#.*$', line)):
continue
if (count2 >= numberIBPlus):
break
values = line.rstrip('\n').split(', ')
key = Decimal(values[12])
#print "Key: ", key
#print "Tuple: ", values
#print "Inserting tuple whose key " + str(key) + " into IB+-Tree..."
plusTree.insertTuple(key, values)
#print "Done!"
count2 += 1
print "Number of tuples: " + str(count2)
## 8. Print structure and all data in IB+-Tree
#plusTree.printIBPlusTree(True)
# 9. Query data for a given interval
listBuckets1 = ListBuckets()
listBuckets = ListBuckets()
listTuples = ListTuples()
plusTree.search(listTuples, listBuckets, [0, 0.15])
# 10. Print result
print "Buckets (IB+-Tree): ", listBuckets.results
tree.search(listBuckets1, [0, 0.15])
print "Buckets (IB-Tree): ", listBuckets1.results
#strTemp = ""
#for i in range(len(listTuples.results)):
# strTemp += str(listTuples.results[i][12]) + " "
# #print "Tuples: ", listTuples.results[i]
#print "Keys: ", strTemp
fin2.close()
print "=================<<<<>>>>=================="
plusTree.writeMetaData()
plusTree.readMetaData()
tree.writeMetaData()
tree.readMetaData()
#print "Printing IB-Tree..."
#tree.printIBTree()
#plusTree.ibTree.rootNode = tree.rootNode
# 9. Query data for a given interval
listBuckets1 = ListBuckets()
listBuckets = ListBuckets()
listTuples = ListTuples()
plusTree.search(listTuples, listBuckets, [0, 0.15])
# 10. Print result
print "Buckets (IB+-Tree): ", listBuckets.results
tree.search(listBuckets1, [0, 0.15])
print "Buckets (IB-Tree): ", listBuckets1.results
#strTemp = ""
#for i in range(len(listTuples.results)):
# strTemp += str(listTuples.results[i][12]) + " "
# #print "Tuples: ", listTuples.results[i]
#print "Keys: ", strTemp
#tree.printEvalInfo()
#tree.evaluation.printEvalInfoToFile(output)
print "Finished!"
return
def run_insertion_NYC(position):
#1. Connect to database
print "Connecting to the database..."
try:
conn = psycopg2.connect("dbname='nyc-taxi-data' user='******' password='******' host='localhost' ")
cursor = conn.cursor()
except:
print "Error: Cannot connect to the nyc-taxi-data database!"
return
print "Connected!"
#2. Initialize IB-Tree and IB+-Tree
#2.1 Get data from postgresql DB (1 000 000 rows)
strGetData = "select * from trips where id >= 1 and id <=1000000 order by trip_distance;"
cursor.execute(strGetData)
data = cursor.fetchall()
#strInsert = "INSERT INTO trips_bucket (bucketID, bucketData) VALUES (%s, %s)"
#2.2 Insert into IB-Tree and copy structure to IB+-Tree
index = 0
low = Constants.MAX_DISTANCE
high = Constants.MIN_DISTANCE
interval = [0.0 for x in range(2)]
bucketID = 10
tree = IBTree()
temp = ""
for row in data:
index += 1
distance = Decimal(row[12])
if(low > distance):
low = distance
if(high < distance):
high = distance
for j in range(0,len(row)):
temp += str(row[j])
if(index == 1000):
bucketID += 1
interval[0] = float(low)
interval[1] = float(high)
# Insert into IB-Tree
tree.insertBucket(interval, bucketID)
# Write data into postgresql (not necessary)
#cursor.execute(strInsert, (bucketID, temp))
#conn.commit()
index = 0
low = Constants.MAX_DISTANCE
high = Constants.MIN_DISTANCE
#print "Printing IB-Tree..."
#tree.printIBTree()
#IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
print "Finish initializing IB-Tree and IB+-Tree. Start to evaluate (20 times)...\n"
tree = None
tree1 = IBTree()
plusTree.ibTree = tree1
#3. Repeat 20 times, measuring the insert performance
t = timer()
#3.1 Get data from postgresql database
for j in range(0, 100):
strGetData = "select * from trips where id >= " + str((position)*1000000 + j * 10000)
strGetData += " and id < " + str((position)*1000000 + (j + 1)*10000) + ";"
#print strGetData
cursor.execute(strGetData)
data = cursor.fetchall()
#3.2 Insert into IB+-Tree and measure the time
t.start()
for row in data:
key = Decimal(row[12])
temp = ""
for k in range(0, len(row)):
temp += str(row[k])
plusTree.insertTuple(key, temp)
t.end()
if(j % 10 == 0):
print str(j)
print str(position) + "th -- execution time: " + str(t.getResult()) + "(s)"
print "Finished!"
def run_test(mapFile, inputfile, inputNum, inputNum2, queryInterval, output):
print "Loading the mapFile..."
fin1 = open(mapFile, 'r')
numBucket = 0
index = 0
listCTID = ["" for x in range(0, 60000)]
for line in fin1:
values = line.split(',', 1)
listCTID[index] = values[1]
index += 1
fin1.close()
#1. Read data from inputfile
print "Reading data and inserting into IB-Tree..."
fin2 = open(inputfile, "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
if (inputNum <= 0):
number = input('Enter a number: ')
else:
number = inputNum
for line in fin2:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (count >= number):
break
#bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
#print "BucketID: " + str(bucketID) + "\t [" + str(interval[0]) + ", " + str(interval[1]) + "]"
#print "Inserting the bucketID: ", bucketID
tree.insertBucket(interval, bucketID)
count += 1
bucketID += 1
#3. Print IB-Tree
print "Done!"
#print "Printing IB-Tree..."
#tree.printIBTree()
fin2.close()
print "Number of buckets: " + str(bucketID + 1)
#IB+-Tree
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
plusTree.ibPlusBuffer.setStartPointBucketID(bucketID)
#5. Print structure of IB+-Tree
#plusTree.printIBPlusTree(False)
#6. Read tuples from BigData_listMuonBuckets_100_200_2_1->23.txt
count2 = 0
if (inputNum2 <= 0):
numberIBPlus = input(
'Please select number of tuples to be insert into IB+-Tree: ')
else:
numberIBPlus = inputNum2
isStop = False
print "Reading data and inserting into IB+-Tree..."
for i in range(1, 24):
filename = "BigData_listMuonBuckets_100_200_2_" + str(i) + ".txt"
if (isStop):
break
fin2 = open(filename, "r")
#7. Insert these tuples into IB+-Tree
for line in fin2:
tokens = line.split(' ')
if ((tokens[0] == "interval") | (tokens[0] == "bucketID:")):
continue
if (re.match('^#.*$', line)):
continue
if (count2 >= numberIBPlus):
isStop = True
break
values1 = line.rstrip('\n').split(', ')
if (len(values1) < 5):
#print "##############Warning:", values1
continue
for j in range(0, len(values1)):
if (values1[j].find("u\'pt\'") != -1):
temp = values1[j].split(":")
key = Decimal(temp[1])
break
plusTree.insertTuple(key, values1)
#print "Done!"
count2 += 1
fin2.close()
print "Number of tuples: " + str(count2)
# 8. Print structure and all data in IB+-Tree
#plusTree.printIBPlusTree(True)
# 9. Query data for a given interval
#runQuery(plusTree, tree, [3.0, 3.3675], listCTID, output)
#runQuery(plusTree, tree, [3.0, 3.735], listCTID, output)
#runQuery(plusTree, tree, [3.0, 4.47], listCTID, output)
#runQuery(plusTree, tree, [3.0, 5.94], listCTID, output)
#runQuery(plusTree, tree, [3.0, 10.35], listCTID, output)
#10. Connect to DB
print "Connecting to the database..."
try:
conn = psycopg2.connect(
"dbname='BigDataTest' user='******' password='******' host='localhost' "
)
cursor = conn.cursor()
except:
print "Error: Cannot connect to the database!"
return
print "Connected!"
listBuckets = ListBuckets()
listTuples = ListTuples()
timeCalculator = timer()
timeCalculator.start()
plusTree.search(listTuples, listBuckets, queryInterval)
resultLength = len(listBuckets.results)
readQuery = ""
if (resultLength >= 1):
readQuery = "select * from MuonBucket where "
tempID = int(listBuckets.results[0])
tempCTID = listCTID[tempID].rstrip('\n')
strAdd = "CTID = \'" + str(tempCTID) + "\' "
readQuery += strAdd
for i in range(1, resultLength):
tempID = int(listBuckets.results[i])
tempCTID = listCTID[tempID].rstrip('\n')
if (tempCTID == ''):
continue
strAdd = "or CTID = \'" + str(tempCTID) + "\' "
readQuery += strAdd
cursor.execute(readQuery)
bufferData = cursor.fetchall()
timeCalculator.end()
# 10. Print result
tempString = "Buckets: " + str(listBuckets.results)
tempString += "\nList Bucket's length: " + str(resultLength)
tempString += "\nList Tuple's length: " + str(len(listTuples.results))
tempString += "\nExecution time (s): " + str(
timeCalculator.getResult()) + "\n"
print tempString
tree.printEvalInfo()
tree.evaluation.printEvalInfoToFile(output)
fout2 = open(output, 'a+')
fout2.write(tempString)
fout2.write(readQuery)
fout2.close()
print "Finished!"
return
def run_test4():
#Test IB-Tree
#1. Read data from listBuckets_2.txt
#2. Insert buckets into IB-Tree
#3. Print IB-Tree
#4. IB+-Tree = copy structure of IB-Tree
#5. Print structure of IB+-Tree
#6. Continue to read tuples from list_Buckets_2.txt
#7. Insert these tuples into IB+-Tree
#8. Print structure and all data in IB+-Tree
#9. Query data for a given interval
#10. Print result
########################################################
#1. Read data from listBuckets.txt
anEntry = IBEntry()
print "Reading data and inserting into IB-Tree..."
fin = open("listBuckets_2.txt", "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
countIB = 0
number = input('Select the number of buckets in IB-Tree: ')
for line in fin:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (countIB >= number):
break
bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
#print "BucketID: " + str(bucketID) + "\t [" + str(interval[0]) + ", " + str(interval[1]) + "]"
#print "Inserting the bucketID: ", bucketID
tree.insertBucket(interval, bucketID)
countIB += 1
#3. Print IB-Tree
print "Done!"
print "Printing IB-Tree..."
tree.printIBTree()
print "Number of buckets: " + str(bucketID + 1)
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
#5. Print structure of IB+-Tree
plusTree.printIBPlusTree(False)
#6. Continue to read tuples from list_Buckets_2.txt
#7. Insert these tuples into IB+-Tree
countIBPlus = 0
numberIBPlus = input(
'Select the number of tuples to insert into IB+-Tree: ')
for line in fin: #Continue to read tuples from file
tokens = line.split(' ')
if ((tokens[0] == "interval") | (tokens[0] == "bucketID:")):
continue
if (re.match('^#.*$', line)):
continue
if (countIBPlus >= numberIBPlus):
break
#print "Line: ", line
values = line.rstrip('\n').split(', ')
key = Decimal(values[12])
print "Key: ", key
print "Tuple: ", values
print "Inserting tuple whose key " + str(key) + " into IB+-Tree..."
plusTree.insertTuple(key, values)
print "Done!"
countIBPlus += 1
print "Number of tuples: " + str(countIBPlus)
#8. Print structure and all data in IB+-Tree
plusTree.printIBPlusTree(True)
#9. Query data for a given interval
listBuckets = ListBuckets()
listTuples = ListTuples()
plusTree.search(listTuples, listBuckets, [0.0, 0.5])
#10. Print result
print "Buckets: ", listBuckets.results
strTemp = ""
for i in range(len(listTuples.results)):
strTemp += str(listTuples.results[i][12]) + " "
print "Tuples: ", listTuples.results[i]
print "Keys: ", strTemp
#print "Created Tuples: " + str(plusTree.ibPlusBuffer.createdTuples)
#print "Released Tuples: " + str(plusTree.ibPlusBuffer.releasedTuples)
#print "Moved Tuples: " + str(plusTree.ibPlusBuffer.movedTuples)
fin.close()
print "Finished!"
return
def buildOutputIBPlusLayout(inputNum=0, start=0, inputNum2=0):
#Test IBPlus-Tree
#1. Read data from listBuckets_sorted_2.txt
print "Reading data and inserting into IB-Tree..."
fin1 = open("listBuckets_sorted_4.txt", "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
if(inputNum <= 0):
number = input('Enter a number: ')
else:
number = inputNum
numTuple = 0
min = 0.0
max = 0.0
for line in fin1:
tokens = line.split(' ')
if(count >= number): #reach limitation of number of bucket
break
if(re.match('^#.*$', line)):
continue
if((tokens[0] == "interval") | (tokens[0] == "bucketID:")):
continue
values = line.rstrip('\n').split(', ')
value = Decimal(values[12])
if(numTuple == 0):
min = max = value
numTuple += 1
else:
if(min > value):
min = value
if(max < value):
max = value
numTuple += 1
if(numTuple == 1000):
interval[0] = min
interval[1] = max
tree.insertBucket(interval, bucketID)
bucketID += 1
numTuple = 0
min = max = 0.0
count += 1
#3. Print IB-Tree
print "Done!"
#print "Printing IB-Tree..."
#tree.printIBTree()
fin1.close()
print "Number of buckets: " + str(bucketID)
#IB+-Tree
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
##5. Print structure of IB+-Tree
#plusTree.printIBPlusTree(False)
#6. Read tuples from listBuckets_2.txt
print "Reading data and inserting into IB+-Tree..."
fin2 = open("listBuckets_random_3.txt", "r")
count2 = 0
if(inputNum2 <= 0):
numberIBPlus = input('Please select number of tuples to be insert into IB+-Tree: ')
else:
numberIBPlus = inputNum2
#7. Insert these tuples into IB+-Tree
cStart = 0
for line in fin2:
tokens = line.split(' ')
if(count2 >= numberIBPlus):
break
if(re.match('^#.*$', line)):
continue
if((tokens[0] != "interval") & (tokens[0] != "bucketID:")):
cStart += 1
if(cStart < start):
continue
values = line.rstrip('\n').split(', ')
value = Decimal(values[12])
#tuple = Tuple()
#tuple.key = value
#tuple.data = [value]
plusTree.insertTuple(value, [value])
count2 += 1
print "Number of tuples: " + str(count2)
## 8. Print structure and all data in IB+-Tree
#plusTree.printIBPlusTree(True)
fin2.close()
plusTree.flush(tree)
print "Finished!"
return
def run_test(output, queryInterval, inputNum=50000, inputNum2=50000):
#Test IBPlus-Tree
#1. Read data from BigData_listBuckets_sorted.txt
print "Reading data and inserting into IB-Tree..."
fin1 = open("BigData_listBuckets_sorted.txt", "r")
#2. Insert buckets into IB-Tree
interval = [0.0 for x in range(2)]
bucketID = 0
tree = IBTree()
count = 0
if (inputNum <= 0):
number = input(
'Select the number of buckets to be inserted into IB-Tree: ')
else:
number = inputNum
for line in fin1:
tokens = line.split(' ')
if (tokens[0] == "interval"):
if (count >= number):
break
bucketID = int(tokens[1].replace(':', ''))
interval[0] = float(tokens[2])
interval[1] = float(tokens[3])
tree.insertBucket(interval, bucketID)
count += 1
#3. Print IB-Tree
print "Done!"
print "Printing IB-Tree..."
tree.printIBTree()
fin1.close()
print "Number of buckets: " + str(bucketID + 1)
#IB+-Tree
#4. IB+-Tree = copy structure of IB-Tree
plusTree = IBPlusTree(tree)
plusTree.copyStructure(tree)
#5. Print structure of IB+-Tree
plusTree.printIBPlusTree(False)
#6. Read tuples from BigData_listMuonBuckets_100_200_2_5->10.txt
print "Reading data and inserting into IB+-Tree..."
count2 = 0
if (inputNum2 <= 0):
numberIBPlus = input(
'Please select number of tuples to be insert into IB+-Tree: ')
else:
numberIBPlus = inputNum2
for j in range(5, 11):
filename = "BigData_listMuonBuckets_100_200_2_" + str(j) + ".txt"
fin2 = open(filename, "r")
#7. Insert these tuples into IB+-Tree
for line in fin2:
tokens = line.split(' ')
if ((tokens[0] == "interval") | (tokens[0] == "bucketID:")):
continue
if (re.match('^#.*$', line)):
continue
if (count2 >= numberIBPlus):
break
values = line.rstrip('\n').split(', ')
for i in range(0, len(values)):
if (values[i].find("u\'pt\'") != -1):
temp = values[i].split(":")
key = Decimal(temp[1])
break
#key = Decimal(values[12])
plusTree.insertTuple(key, values)
count2 += 1
fin2.close()
print "Number of tuples: " + str(count2)
# 8. Print structure and all data in IB+-Tree
#plusTree.printIBPlusTree(True)
# 9. Query data for a given interval
listBuckets = ListBuckets()
listTuples = ListTuples()
plusTree.search(listTuples, listBuckets, queryInterval)
# 10. Print result
print "Buckets: ", listBuckets.results
strTemp = ""
#for i in range(len(listTuples.results)):
# strTemp += str(listTuples.results[i][12]) + " "
# print "Tuples: ", listTuples.results[i]
#print "Keys: ", strTemp
tree.printEvalInfo()
tree.evaluation.printEvalInfoToFile(output)
print "Finished!"
return