Untitled

Retrieving the top value in a dictionary that has multiple values under a single key

Name    Organism    Percent Match     Misc info

1        Human        100              xxx    

1        Goat          95              yyy

1        Pig           90              zzz

       

list = []  

if "1" in line:

    id = line

    bsp = id.split("t")

    uid = bsp[0]

    per = bsp[2]

 

    if not dict.has_key(uid):

        dict[uid] = []

    dict[uid].append(per)

    list = dict[uid]

    list.sort()

if list[0] in dict:

    print key

       

Name    Organism    Percent Match   Misc    info

1   Human   100 xxx

1   Goat    95  yyy

1   Pig 90  zzz

2   Mouse   95  yyy

2   Moose   90  zzz

2   Manatee 100 xxx

       

import csv

 

maxrows = {}

with open('test.dat', 'rb') as f:

    for row in csv.DictReader(f, delimiter = 't'):

        name = row['Name']

        percent = int(row['Percent Match'])

        if int(maxrows.get(name,row)['Percent Match']) <= percent:

            maxrows[name] = row

 

print(maxrows)

       

{'1': {'info': None, 'Percent Match': '100', 'Misc': 'xxx', 'Organism': 'Human', 'Name': '1'}, '2': {'info': None, 'Percent Match': '100', 'Misc': 'xxx', 'Organism': 'Manatee', 'Name': '2'}}

       

lines = []

with open('data.txt') as file:

    for line in file:

        if line.startswith('1'):

            lines.append(line.split())

 

best_match = max(lines, key=lambda k: int(k[2]))

       

>>> pprint.pprint(lines)

[['1', 'Human', '100', 'xxx'],

 ['1', 'Goat', '95', 'yyy'],

 ['1', 'Pig', '90', 'zzz']]

       

>>> max(lines, key=lambda k: int(k[2]))

['1', 'Human', '100', 'xxx']

       

with open('data.txt') as file:

    best_match = max((s.split() for s in file if s.startswith('1')),

                     key=lambda k: int(k[2]))

       

from collections import defaultdict

 

results = defaultdict(list)

with open('data.txt') as f:

    #next(f)      # you may need this so skip the header

    for line in f:

        splitted = line.split()

        results[splitted[0]].append(splitted[1:])

 

maxs = {}

for uid,data in results.items():

    maxs[uid] =  max(data, key=lambda k: int(k[1]))

       

Name    Organism    Percent Match     Misc info

1        Human        100              xxx    

1        Goat          95              yyy

1        Pig           90              zzz  

2        Pig           85              zzz  

2        Goat          70              yyy

       

{'1': ['Human', '100', 'xxx'], '2': ['Pig', '85', 'zzz']}

       

with open('datafile.txt', 'r') as f:

    lines = file.read().split('n')

 

matchDict = {}

 

for line in lines:

    if line[0] == '1':

        uid, organism, percent, misc = line.split('t')

        matchDict[int(percent)] = (organism, uid, misc)

 

highestMatch = max(matchDict.keys())

 

print('{0} is the highest match at {1} percent'.format(matchDict[highestMatch][0], highestMatch))