Geek asks and answers

Python: combining call data

Good - I’m sure that this question was answered earlier, but I can’t find it ....

My problem: I have a list of lists with this composition.

0.2 A

0.1 A

0.3 A

0.3 B

0.2 C

0.5 C

My goal is to deduce the following:

0.6 A

0.3 B

0.7 C

In other words, I need to combine data from several rows together.

Here is the code I'm using:

unique_percents = []

for line in percents:
    new_percent = float(line[0])
    for inner_line in percents:
        if line[1] == inner_line[1]:
           new_percent += float(inner_line[0])
        else:
            temp = []
            temp.append(new_percent)
            temp.append(line[1])
            unique_percents.append(temp)
            break

I think it should work, but it does not add interest and still has duplicates. Perhaps I don’t understand how the “break” works?

I will also offer the best loop structure or algorithm to use. Thanks, David.

+3
source share
11 answers

dict, collections.defaultdict , , dict - 0.0:

import collections

lines = [[0.2, 'A'], [0.1, 'A'], [0.3, 'A'], [0.3, 'B'], [0.2, 'C'], [0.5, 'C']]
amounts = collections.defaultdict(float)
for amount, letter in lines:
    amounts[letter] += amount

for letter, amount in sorted(amounts.iteritems()):
    print amount, letter
+6

:

result = {}
for line in percents:
    value, key = line
    result[key] = result.get(key, 0) + float(value)
+3
total = {}
data = [('0.1', 'A'), ('0.2', 'A'), ('.3', 'B'), ('.4', 'B'), ('-10', 'C')]
for amount, key in data:
    total[key] = total.get(key, 0.0) + float(amount)

for key, amount in total.items():
    print key, amount
+2

, itertools.groupby( , , ):

data = [
    [0.2, 'A'],
    [0.1, 'A'],
    [0.3, 'A'],
    [0.3, 'B'],
    [0.2, 'C'],
    [0.5, 'C'],
]

from itertools import groupby

summary = dict((k, sum(i[0] for i in items)) 
                for k,items in groupby(data, key=lambda x:x[1]))

print summary

:

{'A': 0.60000000000000009, 'C': 0.69999999999999996, 'B': 0.29999999999999999}
+2

: [ [0.2, A], [0.1, A], ...] ( :)

res_dict = {}

for pair in lst:
    letter = pair[1]
    val = pair[0]
    try:
        res_dict[letter] += val
    except KeyError:
        res_dict[letter] = val

res_lst = [(val, letter) for letter, val in res_dict] # note, a list of tuples!
+1

collections.defaultdict ( d):

>>> s=collections.defaultdict(float)
>>> for ln in d:
...     v,k=ln.split()
...     s[k] += float(v)
>>> s
defaultdict(<type 'float'>, {'A': 0.60000000000000009, 'C': 0.69999999999999996, 'B': 0.29999999999999999})
>>> ["%s %s" % (v,k) for k,v in s.iteritems()]
['0.6 A', '0.7 C', '0.3 B']
>>>
+1

Python 3.1 , collections.Counter. decimal.Decimal floats:

# Counter requires python 3.1 and newer
from collections import Counter
from decimal import Decimal

lines = ["0.2 A", "0.1 A", "0.3 A", "0.3 B", "0.2 C", "0.5 C"]
results = Counter()
for line in lines:
    percent, label = line.split()
    results[label] += Decimal(percent)
print(results)

:

Counter ({'C': decimal ('0.7'), 'A': decimal ('0.6'), 'B': decimal ('0.3')})

+1
source

This is verbosity, but it works:

# Python 2.7
lines = """0.2 A
0.1 A
0.3 A
0.3 B
0.2 C
0.5 C"""

lines = lines.split('\n')
#print(lines)
pctg2total = {}
thing2index = {}
index = 0
for line in lines:
    pctg, thing = line.split()
    pctg = float(pctg)
    if thing not in thing2index:
        thing2index[thing] = index
        index = index + 1
        pctg2total[thing] = pctg
    else:
        pctg2total[thing] = pctg2total[thing] + pctg
output = ((pctg2total[thing], thing) for thing in pctg2total)
# Let sort by the first occurrence.
output = list(sorted(output, key = lambda thing: thing2index[thing[1]]))
print(output)

>>> 
[(0.60000000000000009, 'A'), (0.29999999999999999, 'B'), (0.69999999999999996, 'C')]
0
source 
letters = {}
for line in open("data", "r"):
    lineStrip = line.strip().split()
    percent = float(lineStrip[0])
    letter = lineStrip[1]
    if letter in letters:
        letters[letter] = percent + letters[letter]
    else:
        letters[letter] = percent

for letter, percent in letters.items():
    print letter, percent

A 0.6
C 0.7
B 0.3
0
source 
>>> from itertools import groupby, imap
>>> from operator import itemgetter
>>> data = [['0.2', 'A'], ['0.1', 'A'], ['0.3', 'A'], ['0.3', 'B'], ['0.2', 'C'], ['0.5', 'C']]
>>> # data = sorted(data, key=itemgetter(1))
... 
>>> for k, g in groupby(data, key=itemgetter(1)):
...     print sum(imap(float, imap(itemgetter(0), g))), k
... 
0.6 A
0.3 B
0.7 C
>>>
0
source

Let's say we have this

data =[(b, float(a)) for a,b in 
    (line.split() for line in
        """
        0.2 A
        0.1 A
        0.3 A
        0.3 B
        0.2 C
        0.5 C""".splitlines()
        if line)]
print data 
# [('A', 0.2), ('A', 0.1), ('A', 0.3), ('B', 0.3), ('C', 0.2), ('C', 0.5)]

Now you can just go and summarize

counter = {}
for letter, val in data:
    if letter in counter:
        counter[letter]+=val
    else:
        counter[letter]=val

print counter.items()

Or group values ​​together and use the sum:

from itertools import groupby
# you want the name and the sum of the values
print [(name, sum(value for k,value in grp)) 
    # from each group
    for name, grp in 
    # where the group name of a item `p` is given by `p[0]`
    groupby(sorted(data), key=lambda p:p[0])]
0
source

More articles:


All Articles