Develop Reference

write dictionary of lists to a tab delimited file in python, with dictionary key values as columns without Pandas

the dictionary I am using is:
dict={'item': [1,2,3], 'id':['a','b','c'], 'car':['sedan','truck','moped'], 'color': ['r','b','g'], 'speed': [2,4,10]}
I am trying to produce a tab delimited out put as such:
item id
1 a
2 b
3 c
The code I have written:
with open('file.txt', 'w') as tab_file:
dict_writer = DictWriter(tab_file, dict.keys(), delimiter = '\t')
dict_writer.writeheader()
dict_writer.writerows(dict)
specifically, I am struggling with writing to the file in a column based manner. Meaning, that the dictionary keys populate as the header, and the dictionary values populate vertically underneath the associated header. Also, I do NOT have the luxury of using Pandas

This solution will work for an ambiguous number of items and subitems in the dict:
d = {'item': [1, 2, 3], 'id': [4, 5, 6]}
for i in d:
print(i + "\t", end="")
numSubItems = len(d[i])
print()
for level in range(numSubItems):
for i in d:
print(str(d[i][level]) + "\t", end="")
print()
EDIT:
To implement this with writing to a text file:
d = {'item': [1, 2, 3], 'id': [4, 5, 6], 'test': [6, 7, 8]}
with open('file.txt', 'w') as f:
for i in d:
f.write(i + "\t")
numSubItems = len(d[i])
f.write("\n")
for level in range(numSubItems):
for i in d:
f.write(str(d[i][level]) + "\t")
f.write("\n")

Here's a way to do this using a one-off function and zip:
d = {
'item': [1, 2, 3],
'id': ['a', 'b', 'c'],
'car': ['sedan', 'truck', 'moped'],
'color': ['r', 'b', 'g'],
'speed': [2, 4, 10],
}
def row_printer(row):
print(*row, sep='\t')
row_printer(d.keys()) # Print header
for t in zip(*d.values()): # Print rows
row_printer(t)
To print to a file: print(..., file='file.txt')

You can use a simple loop with a zip:
d={'item': [1,2,3], 'id':["a","b","c"]}
print('item\tid')
for num, letter in zip(d['item'], d['id']):
print('\t'.join(str(num) + letter))
item id
1 a
2 b
3 c
EDIT:
If you don't want to hard code column names you can use this:
d={'item': [1,2,3], 'id':["a","b","c"]}
print('\t'.join(d.keys()))
for num, letter in zip(*d.values()):
print('\t'.join(str(num) + letter))
However the order of the columns is only guaranteed in python3.7+ if you use a dictionary. If you have a lower python version use an orderedDict instead, like this:
from collections import OrderedDict
d=OrderedDict({'item': [1,2,3], 'id':["a","b","c"]})
print('\t'.join(d.keys()))
for num, letter in zip(*d.values()):
print('\t'.join(str(num) + letter))

Instead of using csv.DictWriter you can also use a module like pandas for this:
import pandas as pd
df = pd.DataFrame.from_dict(d)
df.to_csv(“test.csv”, sep=“\t”, index=False)
Probably, you have to install it first by using
pip3 install pandas
See here for an example.

Python Dictionary to a specific format in .csv

I have a dictionary in python in this way
my_dict = {'1':['a','b','c'], '2':['d','e','f']}
and i want to write a csv file in which it is displayed as it follows
1, a b c
2, d e f
because it is parsed by another application in this specific format.
Is there any way to it?

This is a way to do it:
my_dict = {'1':['a','b','c'], '2':['d','e','f']}
with open('data.csv', 'w') as f:
f.write('\n'.join([("%s, %s" % (k,' '.join(my_dict[k]))) for k in my_dict])

my_dict = {'1':['a','b','c'], '2':['d','e','f']}
from operator import itemgetter
import csv
with open('data.csv','w') as f:
a = csv.writer(f, delimiter = ',', lineterminator='\n')
for k,v in sorted(my_dict.items(), key=itemgetter(0)):
a.writerow([k,' ' + ' '.join(v)])
data.csv
1, a b c
2, d e f

How to group array of the same name using Python?

I have over a thousand array categories in a text file, for example: Category A1 and Cateogry A2: (array in matlab code)
A1={[2,1,2]};
A1={[4,2,1,2,3]};
A2={[3,3,2,1]};
A2={[4,4,2,2]};
A2={[2,2,1,1,1]};
I would like to use Python to help me read the file and group them into:
A1=[{[2,1,2]} {[4,2,1,2,3]}];
A2=[{[3,3,2,1]} {[4,4,2,2]} {[2,2,1,1,1]}];

Use a dict to group, I presume you mean group as strings as they are not valid python containers coming from a .mat matlab file:
from collections import OrderedDict
od = OrderedDict()
with open("infile") as f:
for line in f:
name, data = line.split("=")
od.setdefault(name,[]).append(data.rstrip(";\n"))
from pprint import pprint as pp
pp((od.values()))
[['{[2,1,2]}', '{[4,2,1,2,3]}'],
['{[3,3,2,1]}', '{[4,4,2,2]}', '{[2,2,1,1,1]}']]
To group the data in your file just write the content:
with open("infile", "w") as f:
for k, v in od.items():
f.write("{}=[{}];\n".format(k, " ".join(v))))
Output:
A1=[{[2,1,2]} {[4,2,1,2,3]}];
A2=[{[3,3,2,1]} {[4,4,2,2]} {[2,2,1,1,1]}];
Which is actually your desired output with the semicolons removed from each sub array, the elements grouped and the semicolon added to the end of the group to keep the data valid in your matlab file.
The collections.OrderedDict will keep the order from your original file where using a normal dict will have no order.
A safer approach when updating a file is to write to a temp file then replace the original file with the updated using a NamedTemporaryFile and shutil.move:
from collections import OrderedDict
od = OrderedDict()
from tempfile import NamedTemporaryFile
from shutil import move
with open("infile") as f, NamedTemporaryFile(dir=".", delete=False) as temp:
for line in f:
name, data = line.split("=")
od.setdefault(name, []).append(data.rstrip("\n;"))
for k, v in od.items():
temp.write("{}=[{}];\n".format(k, " ".join(v)))
move(temp.name, "infile")
If the code errored in the loop or your comp crashed during the write, your original file would be preserved.

You can first loop over you lines and then split your lines with = then use ast.literal_eval and str.strip to extract the list within brackets and at last use a dictionary with a setdefault method to get your expected result :
import ast
d={}
with open('file_name') as f :
for line in f:
var,set_=line.split('=')
d.setdefault(var,[]).append(ast.literal_eval(set_.strip("{}\n;")))
print d
result :
{'A1': [[2, 1, 2], [4, 2, 1, 2, 3]], 'A2': [[3, 3, 2, 1], [4, 4, 2, 2], [2, 2, 1, 1, 1]]}
If you want the result to be exactly as your expected format you can do :
d={}
with open('ex.txt') as f,open('new','w')as out:
for line in f:
var,set_=line.split('=')
d.setdefault(var,[]).append(set_.strip(";\n"))
print d
for i,j in d.items():
out.write('{}=[{}];\n'.format(i,' '.join(j)))
At last you'll have the following result in new file :
A1=[{[2,1,2]} {[4,2,1,2,3]}];
A2=[{[3,3,2,1]} {[4,4,2,2]} {[2,2,1,1,1]}];

writing only dictionary values into a text file

I just want to write dictionary values into text file line wise line.I can write whole dictionary in to the file using:
log_disk={}
log=open('log.txt','w')
log.write(str(log_disk))
log.close()
Any help will be appreciated.In addition I want to avoid those keys which have value 'Empty' while writing into the file.

Just loop over the values then:
with open('log.txt','w') as log:
for value in log_disk.values():
log.write('{}\n'.format(value))

Write data as JSON unformatted string
You may dump the data as JSON, without formatting JSON data it is written on one line.
Do not forget to append newline:
>>> import json
>>> data = {}
>>> with open(fname, "a") as f:
... json.dump(data, f)
... f.write("\n")
...
Try with another data:
>>> data = {"a": "aha", "b": "bebe"}
>>> with open(fname, "a") as f:
... json.dump(data, f)
... f.write("\n")
...
It does not have to be dictionary, lists are working too:
>>> data = range(10)
>>> data
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
>>> with open(fname, "a") as f:
... json.dump(data, f)
... f.write("\n")
...
Reading data line by line
>>> with open(fname) as f:
... for line in f:
... print json.loads(line)
...
{}
{u'a': u'aha', u'b': u'bebe'}
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]

You just need to convert log_disk.values() to a list and you can write them directly
with open(filename) as openfile:
json.dump(list(log_disk.values()), file)

convert csv file to list of dictionaries

I have a csv file
col1, col2, col3
1, 2, 3
4, 5, 6
I want to create a list of dictionary from this csv.
output as :
a= [{'col1':1, 'col2':2, 'col3':3}, {'col1':4, 'col2':5, 'col3':6}]
How can I do this?

Use csv.DictReader:
import csv
with open('test.csv') as f:
a = [{k: int(v) for k, v in row.items()}
for row in csv.DictReader(f, skipinitialspace=True)]
Will result in :
[{'col2': 2, 'col3': 3, 'col1': 1}, {'col2': 5, 'col3': 6, 'col1': 4}]

Another simpler answer:
import csv
with open("configure_column_mapping_logic.csv", "r") as f:
reader = csv.DictReader(f)
a = list(reader)
print a

Using the csv module and a list comprehension:
import csv
with open('foo.csv') as f:
reader = csv.reader(f, skipinitialspace=True)
header = next(reader)
a = [dict(zip(header, map(int, row))) for row in reader]
print a
Output:
[{'col3': 3, 'col2': 2, 'col1': 1}, {'col3': 6, 'col2': 5, 'col1': 4}]

Answering here after long time as I don't see any updated/relevant answers.
df = pd.read_csv('Your csv file path')
data = df.to_dict('records')
print( data )

# similar solution via namedtuple:
import csv
from collections import namedtuple
with open('foo.csv') as f:
fh = csv.reader(open(f, "rU"), delimiter=',', dialect=csv.excel_tab)
headers = fh.next()
Row = namedtuple('Row', headers)
list_of_dicts = [Row._make(i)._asdict() for i in fh]

Well, while other people were out doing it the smart way, I implemented it naively. I suppose my approach has the benefit of not needing any external modules, although it will probably fail with weird configurations of values. Here it is just for reference:
a = []
with open("csv.txt") as myfile:
firstline = True
for line in myfile:
if firstline:
mykeys = "".join(line.split()).split(',')
firstline = False
else:
values = "".join(line.split()).split(',')
a.append({mykeys[n]:values[n] for n in range(0,len(mykeys))})

Simple method to parse CSV into list of dictionaries
with open('/home/mitul/Desktop/OPENEBS/test.csv', 'rb') as infile:
header = infile.readline().split(",")
for line in infile:
fields = line.split(",")
entry = {}
for i,value in enumerate(fields):
entry[header[i].strip()] = value.strip()
data.append(entry)