Develop Reference

is there a way to only have a value in a list if the key appears multiple times in a file?

I'm trying to make a dictionary from items in a file. What I have now works but I was wondering if there is a way to only have a list if the key is a duplicate that has different value.so, if I have this
micheal math 2
jim chem 3
jim math 3
pam cs 4
expected output:
{micheal:[math,2],jim: [[chem,3], [math,3]], pam: [cs,4]}
actual output:
{micheal:[[math,2]],jim: [[chem,3], [math,3]], pam: [[cs,4]]}
current code:
example_dict = {}
for line in dictionary:
line = (line.strip()).split(' ')
key = line[0]
if key not in example_dict
example_dict[key] = []
example_dict[key].append(line[1:])
return example_dict

With your current solution, go over your example_dict afterward and flatten values that only have one element, e.x.:
...
example_dict = {k: (v if len(v) > 1 else v[0]) for k, v in example_dict.items()}
return example_dict

It seems like it would make a lot of sense to use dictionaries instead of tuple lists as values.
example_dict = {}
for line in dictionary:
name, subject, grade = line.strip().split() # optional, but cleaner
if name not in example_dict:
example_dict[name] = {}
example_dict[name][subject] = grade
Result:
{'micheal': {'math': '2'},
'jim': {'chem': '3', 'math': '3'},
'pam': {'cs': '4'}}

Problem of incorrect output for dictionary returned from file

File contains student ID and ID of the solved problem.
Example:
1,2
1,4
1,3
2,1
2,2
2,3
2,4
The task is to write a function which will take a filename as an argument and return a dictionary with a student ID and amount of solved tasks.
Example output:
{1:3, 2:4}
My code which doesn't support the correct output. Please, help me find a mistake and a solution.
import collections
def solved_tasks(filename):
with open(filename) as f:
for line in f.readlines():
key,value = line.strip().split(',')
dictionary = {key: collections.Counter(str(value))}
return dictionary

Since you only care about the sum, not the individual exercises, you can use a Counter on the first column:
def solved_tasks(filename):
with open(filename) as in_stream:
counts = collections.Counter(
line.partition(',')[0] # first column ...
for line in in_stream if line # ... of every non-empty row
)
return {int(key): value for key, value in counts.items()}

Assuming that you want to save the repeated instances of student id, you can use a defaultdict and save the problems solved by each student as a list in your dictionary:
import collections
dictionary = collections.defaultdict(list)
def solved_tasks(filename):
with open(filename) as f:
for line in f.readlines():
key,value = line.strip().split(',')
dictionary[key].append(value)
return dictionary
Output:
defaultdict(<type 'list'>, {'1': ['2', '4', '3'], '2': ['1', '2', '3', '4']})
If you want the sum:
def solved_tasks(filename):
with open(filename) as f:
for line in f.readlines():
key,value = line.strip().split(',')
dictionary[key] += 1
return dictionary
Output:
defaultdict(<type 'int'>, {'1': 3, '2': 4})

you can count how often a key appears
marks = """1,2
"1,4
"1,3
"2,1
"2,2
"2,3
"2,4
"2,4"""
dict = {}
for line in marks.split("\n"):
key,value = line.strip().split(",")
dict[key] = dict.get(key,[]) + [value]
for key in dict:
dict[key] = len(set(dict[key])) # eliminate duplicates
the dict.get(key,[]) method returns an empty list if the key doesn't exist in the dict as a default parameter.
#Edit: You said there may contain duplicates. This method would eliminate all duplicates.
#Edit: Added multilines with """

def solved_tasks(filename):
res = {}
values=""
with open(filename, "r") as f:
for line in f.readlines():
values += line.strip()[0] #take only the first value and concatinate with the values string
value = values[0] #take the first value
res[int(value)] = values.count(value) #put it in the dict
for i in values: #loop the values
if i != value: # if the value is not the first value, then the value is the new found value
value = i
res[int(value)] = values.count(value) #add the new value to the dict
return res

Replace values in Python dict

I have 2 files, The first only has 2 columns
A 2
B 5
C 6
And the second has the letters as a first column.
A cat
B dog
C house
I want to replace the letters in the second file with the numbers that correspond to them in the first file so I would get.
2 cat
5 dog
6 house
I created a dict from the first and read the second. I tried a few things but none worked. I can't seem to replace the values.
import csv
with open('filea.txt','rU') as f:
reader = csv.reader(f, delimiter="\t")
for i in reader:
print i[0] #reads only first column
a_data = (i[0])
dictList = []
with open('file2.txt', 'r') as d:
for line in d:
elements = line.rstrip().split("\t")[0:]
dictList.append(dict(zip(elements[::1], elements[0::1])))
for key, value in dictList.items():
if value == "A":
dictList[key] = "cat"

The issue appears to be on your last lines:
for key, value in dictList.items():
if value == "A":
dictList[key] = "cat"
This should be:
for key, value in dictList.items():
if key in a_data:
dictList[a_data[key]] = dictList[key]
del dictList[key]
d1 = {'A': 2, 'B': 5, 'C': 6}
d2 = {'A': 'cat', 'B': 'dog', 'C': 'house', 'D': 'car'}
for key, value in d2.items():
if key in d1:
d2[d1[key]] = d2[key]
del d2[key]
>>> d2
{2: 'cat', 5: 'dog', 6: 'house', 'D': 'car'}
Notice that this method allows for items in the second dictionary which don't have a key from the first dictionary.
Wrapped up in a conditional dictionary comprehension format:
>>> {d1[k] if k in d1 else k: d2[k] for k in d2}
{2: 'cat', 5: 'dog', 6: 'house', 'D': 'car'}
I believe this code will get you your desired result:
with open('filea.txt', 'rU') as f:
reader = csv.reader(f, delimiter="\t")
d1 = {}
for line in reader:
if line[1] != "":
d1[line[0]] = int(line[1])
with open('fileb.txt', 'rU') as f:
reader = csv.reader(f, delimiter="\t")
reader.next() # Skip header row.
d2 = {}
for line in reader:
d2[line[0]] = [float(i) for i in line[1:]]
d3 = {d1[k] if k in d1 else k: d2[k] for k in d2}

You could use dictionary comprehension:
d1 = {'A':2,'B':5,'C':6}
d2 = {'A':'cat','B':'dog','C':'house'}
In [23]: {d1[k]:d2[k] for k in d1.keys()}
Out[23]: {2: 'cat', 5: 'dog', 6: 'house'}

If the two dictionaries are called a and b, you can construct a new dictionary this way:
composed_dict = {a[k]:b[k] for k in a}
This will take all the keys in a, and read the corresponding values from a and b to construct a new dictionary.
Regarding your code:
The variable a_data has no purpose. You read the first file, pront the first column, and do nothing else with the data in it
zip(elements[::1], elements[0::1]) will just construct pairs like [1,2,3] -> [(1,1),(2,2),(3,3)], I think that's not what you want
After all you have a list of dictionaries, and at the last line you just put strings in that list. I think that is not intentional.

import re
d1 = dict()
with open('filea.txt', 'r') as fl:
for f in fl:
key, val = re.findall('\w+', f)
d1[key] = val
d2 = dict()
with open('file2.txt', 'r') as fl:
for f in fl:
key, val = re.findall('\w+', f)
d2[key] = val
with open('file3.txt', 'wb') as f:
for k, v in d1.items():
f.write("{a}\t{b}\n".format(a=v, b=d2[k]))

Problems with Python Dictionarys and nested Lists

I am trying to create a dictionary that has a nested list inside of it.
The goal would be to have it be:
key : [x,y,z]
I am pulling the information from a csv file and counting the number of times a certain key shows up in each column. However I am getting the below error
> d[key][i] = 1
KeyError: 'owner'
Where owner is the title of my column.
if __name__ == '__main__':
d = {}
with open ('sample.csv','r') as f:
reader = csv.reader(f)
for i in range(0,3):
for row in reader:
key = row[0]
if key in d:
d[key][i] +=1
else:
d[key][i] = 1
for key,value in d.iteritems():
print key,value
What do I tweak in this loop to have it create a key if it doesn't exist and then add to it if it does?

The problem is, that you try to use a list ([i]) where no list is.
So you have to replace
d[key][i] = 1
with
d[key] = [0,0,0]
d[key][i] = 1
This would first create the list with three entries (so you can use [0], [1] and [2] afterward without error) and then assigns one to the correct entry in the list.

You can use defaultdict:
from collections import defaultdict
ncols = 3
d = defaultdict(lambda: [0 for i in range(ncols)])

Use a try, catch block to append a list to the new key, then increment as needed
if __name__ == '__main__':
d = {}
with open ('sample.csv','r') as f:
reader = csv.reader(f)
for i in xrange(0,3):
for row in reader:
key = row[i]
try: d[key][i] += 1
except KeyError:
d[key] = [0, 0, 0]
d[key][i] = 1
for key,value in d.iteritems():
print key,value

Using defaultdict and Counter you can come up with a dict that allows you to easily measure how many times a key appeared in a position (in this case 1st, 2nd or 3rd, by the slice)
csv = [
['a','b','c','d'],
['e','f','g', 4 ],
['a','b','c','d']
]
from collections import Counter, defaultdict
d = defaultdict(Counter)
for row in csv:
for idx, value in enumerate(row[0:3]):
d[value][idx] += 1
example usage:
print d
print d['a'][0] #number of times 'a' has been found in the 1st position
print d['b'][2] #number of times 'b' found in the 3rd position
print d['f'][1] #number of times 'f' found in 2nd position
print [d['a'][n] for n in xrange(3)] # to match the format requested in your post
defaultdict(<class 'collections.Counter'>, {'a': Counter({0: 2}), 'c': Counter({2: 2}), 'b': Counter({1: 2}), 'e': Counter({0: 1}), 'g': Counter({2: 1}), 'f': Counter({1: 1})})
2
0
1
[2, 0, 0]
Or put into a function:
def occurrences(key):
return [d[key][n] for n in xrange(3)]
print occurrences('a') # [2, 0, 0]

Update dictionary while parsing CSV file

I have csv file like this:
item,#RGB
item1,#ffcc00
item1,#ffcc00
item1,#ff00cc
item2,#00ffcc
item2,#ffcc00
item2,#ffcc00
item2,#ffcc00
....
and I want to make dictionary d, with item name as key and RGB value and count as tuples in list as dictionary value, like:
d[item] = [ (#RGB, count) ]
so for "item1" as in example, I would like to get:
d['item1'] = [ ('#ffcc00', 2), ('#ff00cc', 1) ]
I imagine some Pythonic iterator can do this in one line, but I can't understand how at this moment. So far I've made this:
d={}
with open('data.csv', 'rb') as f:
reader = csv.reader(f)
try:
for row in reader:
try:
if d[(row[0], row[1])]:
i +=1
except KeyError:
i = 1
d[(row[0], row[1])] = i
except csv.Error, e:
sys.exit('file %s, line %d: %s' % (filename, reader.line_num, e))
which gives me:
d[(item, #RGB)] = count
Any better way? Or am I doing this wrongly from start?

how about:
a = {}
for row in reader:
a.setdefault(row[0], {}).setdefault(row[1], 0)
a[row[0]][row[1]] += 1
This creates a dictionary like
{'item2': {'#00ffcc': 1, '#ffcc00': 3},
'item1': {'#ffcc00': 2, '#ff00cc': 1}}
I find it more convenient than your structure, but you can convert it to tuples if needed:
b = dict((k, v.items()) for k, v in a.items())

import csv
from collections import defaultdict, Counter
from itertools import islice
with open('infile.txt') as f:
d=defaultdict(Counter)
for k,v in islice(csv.reader(f),1,None):
d[k].update((v,))
print d
prints
defaultdict(<class 'collections.Counter'>, {'item2': Counter({'#ffcc00': 3, '#00ffcc': 1}), 'item1': Counter({'#ffcc00': 2, '#ff00cc': 1})})