def createShingles(inputDocument):
documentLength = len(inputDocument)
shingles = []
hashedShingles = []
beginIndex = 0;
endSliceIndex = beginIndex + shingleLength;
while endSliceIndex <= documentLength:
# Slice ends at n-1 in python
shingle = inputDocument[beginIndex:endSliceIndex]
shingles.append(shingle)
hashedShingles.append(hash(shingle))
beginIndex = beginIndex + 1
endSliceIndex = beginIndex + shingleLength;
Common.printVector(shingles)
Common.printVector(hashedShingles)
import Common
p = [5, 4, 6, 2, 7]
length = len(p) - 1
m = [[0 for _ in range(length)] for _ in range(length)]
s = [[0 for _ in range(length)] for _ in range(length)]
def computeMatrix():
for currentLength in range(length):
print("Current Length={0}".format(currentLength))
for i in range(0, length - currentLength, 1):
j = i + currentLength
print("i={0},j={1}".format(i, j))
for k in range(i, j, 1):
print(" k={0}".format(k))
num = m[i][k] + m[k+1][j] + p[i]*p[k + 1]*p[j + 1]
if (m[i][j] == 0 or num < m[i][j]):
m[i][j] = num
s[i][j] = k
Common.printVector(p, label="Vector p")
computeMatrix()
Common.printMatrix(m, label="Optimal Cost", r="Row Size", c="Column Size")
Common.printMatrix(s, label="Partition", r="Row Size", c="Column Size")
for column in range(0, columns):
currentRowNumber = referenceNumbers[row]
currentColumnSum = column + 1
if currentColumnSum < currentRowNumber:
if row == 0:
m[row][column] = False
else:
# Copy previous row value
m[row][column] = m[row - 1][column]
elif currentColumnSum == currentRowNumber:
m[row][column] = True
else:
m[row][column] = m[row - 1][column] or m[row - 1][column - currentRowNumber]
def backTrack():
row = rows - 1
column = columns - 1
while column >= 0 and row >= 0:
currentRowValue = m[row][column]
previousRowValue = m[row - 1][column] if row - 1 >= 0 else False
if currentRowValue == previousRowValue:
row = row - 1
else:
backtrack.insert(0, referenceNumbers[row])
column = column - referenceNumbers[row]
Common.printVector(referenceNumbers, label="Vector referenceNumbers")
computeMatrix()
Common.printMatrix(m, label="Matrix", r="Row Size", c="Column Size")
backTrack()
Common.printVector(backtrack, label="Backtrack numbers")
# Max of previous column or row
m[row][column] = 0
def backtrack():
# Find the max element
maxValue = 0
maxRowIndex = 0
maxColumnIndex = 0
for row in range(1, rows):
rowMax = max(m[row])
if rowMax > maxValue:
maxValue = rowMax
maxRowIndex = row
maxColumnIndex = m[row].index(maxValue)
while maxRowIndex > 0 and maxColumnIndex > 0:
diagonal = m[maxRowIndex - 1][maxColumnIndex - 1]
if diagonal == maxValue - 1:
seq.insert(0, word1[maxColumnIndex - 1])
maxValue = diagonal
maxRowIndex = maxRowIndex - 1
maxColumnIndex = maxColumnIndex - 1
else:
break;
Common.printVector(word1, label="word1")
Common.printVector(word2, label="word2")
longestCommon()
Common.printMatrix(m, r="word2", c="word1")
backtrack()
Common.printVector(seq, label="Common Substring")
if char1 == char2:
# Diagonal + 1
diagonal = m[row - 1][column - 1]
m[row][column] = diagonal + 1
else:
# Max of previous column or row
m[row][column] = max(m[row][column - 1], m[row - 1][column])
def backtrack():
column = columns - 1
row = rows - 1
while column > 0 and row > 0:
current = m[row][column]
prevRow = m[row - 1][column]
prevColumn = m[row][column - 1]
prevDiagonal = m[row - 1][column - 1]
if current == prevColumn:
column = column - 1
elif current == prevRow:
row = row - 1
elif current == prevDiagonal + 1:
seq.append(word1[column - 1])
column = column - 1
row = row - 1
Common.printVector(word1, label="word1")
Common.printVector(word2, label="word2")
commonSubsequence()
Common.printMatrix(m, r="word2", c="word1")
backtrack()
Common.printVector(seq, label="Common Subsequence")
