return top results from list

[kdt]

Hi,

With a list of fixed length strings, I want to count the occurrences of each characters at each of 9 positions. I then want to return the top 2 results for each position. The result has to be a list for the function I am passing this too. The code I have so far has two rather big problems (1) it is too slow and (2) it gives the wrong results :(

[CODE=python]
dd ={'.LEA.....':7 7,'R....L...':8 ,'.L....DA.':5, '.L.R.V..L':4,' A....S.SA':55,' QL..L....':5,'M .SC.SE..':77}


def positionalWeigh ts(dd, topx=2):
posList = [[] for i in range(9)]

for key in dd.keys():
for i, item in enumerate(key):
if item != '.':
if posList[i]==[]:
posList[i].append([item, 1])
else:
for c in posList[i]:
if c[0] != item:
posList[i].append([item,1])
else:
c[1] += 1

for i in posList:
for j in i:
j.sort()

y =[]
for i in posList:
x = topx
for j, k in enumerate(i):
z=[]
while x > 0:
z.append(k[1])
x-=1
y.append(z)
return y

pw= positionalWeigh ts(dd)
print pw


>>>
[['A', 'A'], [], [], [], [], [], [], [], ['L', 'L'], ['S', 'S'], [], ['R', 'R'], [], [], [], ['L', 'L'], ['S', 'S'], [], [], [], [], [], [], ['D', 'D'], [], ['S', 'S'], [], ['A', 'A'], []]

[/CODE]

Please help!

[KaezarRex]

I think I got the first part working:
[CODE=python]posList = [[] for i in range(9)]

for key in dd.keys():
for i, item in enumerate(key):
if item != '.':
if posList[i]==[]:
posList[i].append([item, 1])
else:
found = False
for c in posList[i]:
if c[0] == item:
c[1] += 1
found = True
if not found:
posList[i].append([item,1])[/CODE]
You wern't checking every list in a posList index before you inserted a new list.

[kdt]

I think I got the first part working:
[CODE=python]posList = [[] for i in range(9)]

for key in dd.keys():
for i, item in enumerate(key):
if item != '.':
if posList[i]==[]:
posList[i].append([item, 1])
else:
found = False
for c in posList[i]:
if c[0] == item:
c[1] += 1
found = True
if not found:
posList[i].append([item,1])[/CODE]
You wern't checking every list in a posList index before you inserted a new list.

cheers mate, made quite a few mistakes in this one. Finally got it working now- yipee! Still if anyone can propose speed tips, I'm using psyco, and it doesn't seem to be making much difference :S

[CODE=python]
def positionalWeigh ts(dd, topx=2):
posList = [[] for i in range(9)]

for key in dd.keys():
for i, item in enumerate(key):
if item != '.':
if posList[i]==[]:
posList[i].append([1, item])
else:
found = False
for c in posList[i]:
if c[1] == item:
c[0] += 1
found = True
if not found:
posList[i].append([1, item])

for i in posList:
i.sort()
i.reverse()

y =[]
for i in posList:
x = topx
z=[]
while x>0:
z.append(i[x][1])
x-=1
print z
y.append(z)
return y

>>>
['Y', 'M']
['V', 'M']
['L', 'M']
['Y', 'E']
['L', 'K']
['F', 'L']
['L', 'Y']
['L', 'Y']
['I', 'L']
[['Y', 'M'], ['V', 'M'], ['L', 'M'], ['Y', 'E'], ['L', 'K'], ['F', 'L'], ['L', 'Y'], ['L', 'Y'], ['I', 'L']]
[/CODE]

[bvdet]

See if this helps any:[code=Python]def positionalWeigh ts(dd, topx=2):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while True:
try:
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
except: break

result = []

for dd in posDict:
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
print a
try:
result.append([[a[0][0], a[0][1]]])
for i in range(topx-1):
result[-1].append([a[i+1][0], a[i+1][1]])
except IndexError, e:
pass

return result

s = positionalWeigh ts(dd, 2)

for i, item in enumerate(s):
for j in item:
print 'Position %d: %s = %d' % (i, j[1], j[0])

[/code]
Output:
>>> [(1, 'R'), (1, 'Q'), (1, 'M'), (1, 'A')]
[(4, 'L')]
[(1, 'S'), (1, 'E')]
[(1, 'R'), (1, 'C'), (1, 'A')]
[(1, 'L')]
[(2, 'S'), (1, 'V'), (1, 'L')]
[(1, 'E'), (1, 'D')]
[(1, 'S'), (1, 'A')]
[(1, 'L'), (1, 'A')]
Position 0: R = 1
Position 0: Q = 1
Position 1: L = 4
Position 2: S = 1
Position 2: E = 1
Position 3: R = 1
Position 3: C = 1
Position 4: L = 1
Position 5: S = 2
Position 5: V = 1
Position 6: E = 1
Position 6: D = 1
Position 7: S = 1
Position 7: A = 1
Position 8: L = 1
Position 8: A = 1
>>>

[kdt]

See if this helps any:[code=Python]def positionalWeigh ts(dd, topx=2):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while True:
try:
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
except: break

result = []

for dd in posDict:
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
print a
try:
result.append([[a[0][0], a[0][1]]])
for i in range(topx-1):
result[-1].append([a[i+1][0], a[i+1][1]])
except IndexError, e:
pass

return result

s = positionalWeigh ts(dd, 2)

for i, item in enumerate(s):
for j in item:
print 'Position %d: %s = %d' % (i, j[1], j[0])

[/code]
Output:
>>> [(1, 'R'), (1, 'Q'), (1, 'M'), (1, 'A')]
[(4, 'L')]
[(1, 'S'), (1, 'E')]
[(1, 'R'), (1, 'C'), (1, 'A')]
[(1, 'L')]
[(2, 'S'), (1, 'V'), (1, 'L')]
[(1, 'E'), (1, 'D')]
[(1, 'S'), (1, 'A')]
[(1, 'L'), (1, 'A')]
Position 0: R = 1
Position 0: Q = 1
Position 1: L = 4
Position 2: S = 1
Position 2: E = 1
Position 3: R = 1
Position 3: C = 1
Position 4: L = 1
Position 5: S = 2
Position 5: V = 1
Position 6: E = 1
Position 6: D = 1
Position 7: S = 1
Position 7: A = 1
Position 8: L = 1
Position 8: A = 1
>>>

Thanks mate, it looks like the speed issue is from another part of the program. I'll definately use parts of this (especially for learning, I need to use try: except more) :)

[bvdet]

I eliminated one of the try/except blocks by substituting 'while True' for 'while len(item)' and modified the way 'result' is compiled:[code=Python]def positionalWeigh ts(dd, topx=2):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while len(item):
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
result = [[] for i in range(len(dd.ke ys()[0]))]
for j, dd in enumerate(posDi ct):
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
try:
for i in range(topx):
result[j].append([a[i][0], a[i][1]])
except IndexError, e:
pass
return result[/code]I am sure it can be improved.

[kdt]

I eliminated one of the try/except blocks by substituting 'while True' for 'while len(item)' and modified the way 'result' is compiled:[code=Python]def positionalWeigh ts(dd, topx=2):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while len(item):
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
result = [[] for i in range(len(dd.ke ys()[0]))]
for j, dd in enumerate(posDi ct):
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
try:
for i in range(topx):
result[j].append([a[i][0], a[i][1]])
except IndexError, e:
pass
return result[/code]I am sure it can be improved.

Thanks bvdet, definately more concise than my attempt. Had to make some slight changes to it to get the output I wanted. However, there is a really strange property of it, in it that it doesn't return the top topx results, instead it will only return the top 1 for each position regardless of the value of topx. You can however add y to topx where y = top number of results you want -1. Strange indeed!

[CODE=python]
def positionalWeigh ts(dd,topx =5):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while len(item):
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
result = [[] for i in range(len(dd.ke ys()[0]))]
for j, dd in enumerate(posDi ct):
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
try:
for i in range(topx+1): # need to add 1 to return top 2
result[j].append(a[i][1]) # changed for top topx results, no counts required
except IndexError, e:
pass
return result

>>>
[['F', 'M'], ['L', 'M'], ['A', 'M'], ['F', 'E'], ['Y', 'K'], ['I', 'L'], ['F', 'Y'], ['S', 'Y'], ['V', 'L']]

[/CODE]

[bvdet]

This code seems to work correctly without adding 1 to 'topx':[code=Python]def positionalWeigh ts(dd, topx=2):
posDict = [{} for i in range(len(dd.ke ys()[0]))]
for item in dd.keys():
item = list(item)
pos = 0
while len(item):
s = item.pop(0)
if s != '.':
if posDict[pos].has_key(s):
posDict[pos][s] += 1
else:
posDict[pos][s] = 1
pos += 1
print posDict
result = [[] for i in range(len(dd.ke ys()[0]))]
for j, dd in enumerate(posDi ct):
a = sorted(zip(dd.v alues(), dd.keys()), reverse=True)
print a
try:
for i in range(topx):
# with counts
# result[j].append([a[i][0], a[i][1]])
# without counts
result[j].append(a[i][1])
except IndexError, e:
pass
return result

dd ={'.LEA.....':7 7,'R....L...':8 ,'.L....DA.':5, '.L.R.V..L':4,\
'A....S.SA':55, 'QL..L....':5,' M.SC.SE..':77, '.LEADER..':5,\
'..LEADER.':5, '.LL..TT..':5, 'AZR..TFGG':5}

s = positionalWeigh ts(dd, 3)
print s[/code]Output:

>>> [{'A': 2, 'Q': 1, 'R': 1, 'M': 1}, {'Z': 1, 'L': 6}, {'S': 1, 'R': 1, 'E': 2, 'L': 2}, {'A': 2, 'C': 1, 'R': 1, 'E': 1}, {'A': 1, 'D': 1, 'L': 1}, {'E': 1, 'D': 1, 'L': 1, 'S': 2, 'T': 2, 'V': 1}, {'F': 1, 'R': 1, 'E': 2, 'D': 1, 'T': 1}, {'A': 1, 'S': 1, 'R': 1, 'G': 1}, {'A': 1, 'L': 1, 'G': 1}]
[(2, 'A'), (1, 'R'), (1, 'Q'), (1, 'M')]
[(6, 'L'), (1, 'Z')]
[(2, 'L'), (2, 'E'), (1, 'S'), (1, 'R')]
[(2, 'A'), (1, 'R'), (1, 'E'), (1, 'C')]
[(1, 'L'), (1, 'D'), (1, 'A')]
[(2, 'T'), (2, 'S'), (1, 'V'), (1, 'L'), (1, 'E'), (1, 'D')]
[(2, 'E'), (1, 'T'), (1, 'R'), (1, 'F'), (1, 'D')]
[(1, 'S'), (1, 'R'), (1, 'G'), (1, 'A')]
[(1, 'L'), (1, 'G'), (1, 'A')]
[['A', 'R', 'Q'], ['L', 'Z'], ['L', 'E', 'S'], ['A', 'R', 'E'], ['L', 'D', 'A'], ['T', 'S', 'V'], ['E', 'T', 'R'], ['S', 'R', 'G'], ['L', 'G', 'A']]
>>>

[kdt]

sorry, please disregard my last post, I was being silly again - passing the wrong values to the function. All's good now

Thanks