def inclose4path(file, process, threshold=1):
NB_CHECKS = 0
NB_SUB_CHECKS = 0
NB_COL_CHECKS = 0
supports, n_rows, n_cols = compute_supports(file)
max_todo_size = 0
todo = deque()
todo.append((set(range(0, n_rows)), set(), set(), 0))
while len(todo) != 0:
max_todo_size = max(max_todo_size, len(todo))
rows, cols, P, y = todo.pop()
P = set(P) # copy before modifying
todo_inside = []
for j in range(y, n_cols):
if j not in cols and j not in P:
NB_COL_CHECKS += 1
g = rows.intersection(supports[j])
if len(g) == 0:
P.add(j)
elif len(g) == len(rows):
cols.add(j)
else:
if len(g) < threshold:
continue
NB_CHECKS += 1
found_one = False
if not found_one:
for A, _, _, _ in todo:
NB_SUB_CHECKS += 1
if g.issubset(A):
found_one = True
break
if not found_one:
for A, _ in todo_inside:
NB_SUB_CHECKS += 1
if g.issubset(A):
found_one = True
break
if not found_one:
todo_inside.append((g, j))
process(rows, cols)
for g, j in todo_inside:
h = cols.union({j})
todo.append((g, h, P, j+1))
return NB_CHECKS, NB_SUB_CHECKS, NB_COL_CHECKS
def inclose5(file, process, threshold=1):
def is_canonical(supports, g: Set[int], cols: Set[int], j):
is_canonical.n_checks += 1
for jj in range(0, j):
if jj not in cols:
is_canonical.n_sub_checks += 1
if g.issubset(supports[jj]):
return jj
return -1
is_canonical.n_checks = 0
is_canonical.n_sub_checks = 0
NB_COL_CHECKS = 0
supports, n_rows, n_cols = compute_supports(file)
max_todo_size = 0
todo = deque()
todo.append((set(range(0, n_rows)), set(), set(), 0))
while len(todo) != 0:
max_todo_size = max(max_todo_size, len(todo))
rows, cols, P, y = todo.pop()
P = set(P) # copy before modifying
todo_inside = []
for j in range(y, n_cols):
if j not in cols and j not in P:
NB_COL_CHECKS += 1
g = rows.intersection(supports[j])
if len(g) == 0:
P.add(j)
elif len(g) == len(rows):
cols.add(j)
else:
if len(g) < threshold:
continue
canonical = is_canonical(supports, g, cols, j)
if canonical == -1:
todo_inside.append((g, j))
elif canonical < y:
P.add(j)
process(rows, cols)
#todo_inside = reversed(todo_inside)
for g, j in todo_inside:
h = cols.union({j})
todo.append((g, h, P, j + 1))
#print("MAX SIZE", max_todo_size)
return is_canonical.n_checks, is_canonical.n_sub_checks, NB_COL_CHECKS
def inclose2(file, process, threshold=1):
def is_canonical(supports, g: Set[int], cols: Set[int], j):
is_canonical.n_checks += 1
for jj in range(0, j):
if jj not in cols:
is_canonical.n_sub_checks += 1
if g.issubset(supports[jj]):
return False
return True
is_canonical.n_checks = 0
is_canonical.n_sub_checks = 0
NB_COL_CHECKS = 0
supports, n_rows, n_cols = compute_supports(file)
max_todo_size = 0
todo = deque()
todo.append((set(range(0, n_rows)), set(), 0))
while len(todo) != 0:
max_todo_size = max(max_todo_size, len(todo))
rows, cols, y = todo.pop()
todo_inside = []
for j in range(y, n_cols):
if j not in cols:
NB_COL_CHECKS += 1
g = rows.intersection(supports[j])
if len(g) == len(rows):
cols.add(j)
else:
if len(g) < threshold:
continue
canonical = is_canonical(supports, g, cols, j)
if canonical:
todo_inside.append((g, j))
if len(rows) != 0:
process(rows, cols)
#todo_inside = reversed(todo_inside)
for g, j in todo_inside:
h = cols.union({j})
todo.append((g, h, j + 1))
return is_canonical.n_checks, is_canonical.n_sub_checks, NB_COL_CHECKS
#Computing the support of each pattern encountered in the first class in the second class
nrowN = dfN.size
# Create the dataframe of emerging patterns
emerging_patterns = frequent_itemsets_T[['itemsets', 'length', 'support']]
#Changing the name of the columns
emerging_patterns.columns = ['Pattern', 'Size', 'supportT']
#One way to insert new columns
#emerging_patterns = emerging_patterns.reindex(columns=['Pattern', 'Size', 'supportT', 'supportN', 'GrowthRatio'])
emerging_patterns = emerging_patterns.assign(supportN=0.0, GrowthRatio=np.inf)
for pattern in emerging_patterns.itertuples():
supportN = compute_supports(pattern.Pattern, dfN)
if supportN > 0:
emerging_patterns.at[pattern.Index, 'supportN'] = supportN
emerging_patterns.at[pattern.Index,
'GrowthRatio'] = emerging_patterns.at[
pattern.Index, 'supportT'] / supportN
#Sort the patterns by their support values and then by their sizes
emerging_patterns.sort_values(['GrowthRatio', 'supportT', 'Size'],
ascending=[False, False, False],
inplace=True)
emerging_patterns.to_csv("../results/emerging_patterns.csv", index=False)
print("Done!")
def fcbo(matrix, process):
NB_CANON = 0
NB_INCL = 0
NB_COLCHECK = 0
n = matrix.shape[0]
m = matrix.shape[1]
supports = compute_supports(matrix)
def canon_check(Nj, B, j):
nonlocal NB_INCL
NB_INCL += 1
for i in range(0, j):
if i in Nj and i not in B:
return False
return True
def canon_check_eq(B, D, j):
nonlocal NB_INCL
NB_INCL += 1
for i in range(0, j):
if (i in B) != (i in D):
return False
return True
def supported(A):
nonlocal NB_CANON
nonlocal NB_INCL
NB_CANON += 1
cols = set()
for j in range(0, m):
NB_INCL += 1
if all(matrix[i, j] != 0 for i in A):
cols.add(j)
return cols
def compute(A, B, y, N):
nonlocal NB_COLCHECK
if len(A) != 0:
process(A, B)
M = [s for s in N]
todo = []
for j in range(y, m):
if j not in B:
NB_COLCHECK += 1
if canon_check(N[j], B, j):
C = A.intersection(supports[j])
D = supported(C)
if canon_check_eq(B, D, j):
todo.append((C, D, j))
else:
M[j] = D
for C, D, j in todo:
compute(C, D, j+1, M)
compute(set(range(0, n)), supported(set(range(0, n))), 0, [set() for _ in range(0, m)])
return NB_CANON, NB_INCL, NB_COLCHECK