This is what I have to do:
Read content of a text file, where two numbers separated by comma are on each line (like 10, 5\n, 12, 8\n, …)
Make a sum of those two numbers
Write into new text file two original numbers and the result of summation = like 10 + 5 = 15\n, 12 + 8 = 20\n, …
So far, I've got this:
import os
import sys
relative_path = "Homework 2.txt"
if not os.path.exists(relative_path):
print "not found"
sys.exit()
read_file = open(relative_path, "r")
lines = read_file.readlines()
read_file.close()
print lines
path_output = "data_result4.txt"
write_file = open(path_output, "w")
for line in lines:
line_array = line.split()
print line_array
You need to have a good understanding of python to understand this.
First, read the file, and get all of the lines by splitting it with a line feed (\n)
For each expression, calculate the answer and write it. Remember, you need to cast the numbers to integers so that they can be added together.
with open('Original.txt') as f:
lines = f.read().split('\n')
with open('answers.txt', 'w+') as f:
for expression in lines: # expression should be in format '12, 8'
nums = [int(i) for i in expression.split(', ')]
f.write('{} + {} = {}\n'.format(nums[0], nums[1], nums[0] + nums[1]))
# That should write '12 + 8 = 20\n'
Make your last for loop look like this:
for line in lines:
splitline = line.strip().split(",")
summation = sum(map(int, splitline))
write_file.write(" + ".join(splitline) + " = " + str(summation) + "\n")
One beautiful thing about that way is that you can have as many numbers as you want on a line, and it will still display correctly.
Seems like the input File is csv so just use the csv reader module in python.
Input File Homework 2.txt
1, 2
1,3
1,5
10,6
The script
import csv
f = open('Homework 2.txt', 'rb')
reader = csv.reader(f)
result = []
for line in list(reader):
nums = [int(i) for i in line]
result.append(["%(a)s + %(b)s = %(c)s" % {'a' : nums[0], 'b' : nums[1], 'c' : nums[0] + nums[1] }])
f = open('Homework 2 Output.txt', 'wb')
writer = csv.writer(f, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
for line in result:
writer.writerow(line)
The output file is then Homework 2 Output.txt
1 + 2 = 3
1 + 3 = 4
1 + 5 = 6
10 + 6 = 16
Related
I have a file I am reading from.
I need to output a copy of the file where line numbers are simply appended to the end of each line.
I tried the following code but couldn't get it to work:
with open('s.txt', 'r') as f, open("1.txt", "w") as out:
abc_list = [[float(n) for n in line.split()] for line in f]
for i,line in enumerate(abc_list):
out.write('{i+0:2}\n'.format(line.rstrip('\n')))
The input-file contains data similar to the following:
1 2
5 6
25 85
The shows what the contents of the output file should be:
1 2 1
5 6 2
25 85 3
I got the following error:
AttributeError: 'list' object has no attribute 'rstrip'
You don't need to call line.rstrip(). At that point line is a list of numbers, not a line from the input file. You should loop over the numbers and write each of them without a newline.
Then write i to the file at the end of the line.
If you want the line numbers to start at 1, use that as an argument to enumerate().
with open('s.txt', 'r') as f, open("1.txt", "w") as out:
abc_list = [[float(n) for n in line.split()] for line in f]
for i,nums in enumerate(abc_list, 1):
for n in nums:
out.write(str(n) + ' ')
out.write('{i:2}\n'.format(i))
You can also avoid creating the list of all lines.
with open('s.txt', 'r') as f, open("1.txt", "w") as out:
for i, line in enumerate(f, 1):
nums = [float(n) for n in line.split()]
for n in nums:
out.write(str(n) + ' ')
out.write('{i:2}\n'.format(i))
i got KeyError: 'i' with the answer of Barmar .. i fixed it now. Thanks for the help
with open('s.txt', 'r') as f, open("1.txt", "w") as out:
for i, line in enumerate(f, 1):
nums = [float(n) for n in line.split()]
for n in nums:
out.write(str(n) + ' ')
out.write(f'{i+0:2}\n')
The following function will append line numbers to the end of every line of a file:
def get_suffixed_iterator(rf, sep =" "):
sep = str(sep)
rf = iter(rf)
rf = map(str, rf)
rf = map(str.strip, rf)
for num, text in enumerate(rf, 1):
yield text + sep + str(num)
Below, we test the function:
f = ["orange\n\n", "eggs", "\n\napple\n\n\n"]
for lin in get_suffixed_iterator(f):
print(lin)
with open('readme.txt', 'r') as rf, open("writeme.txt", "w") as wf:
it = append_line_numbers(rf)
for line in it:
print(line, file=wf, end="\n")
I have a .txt file that is split into multiple lines, but each two of these lines I would like to merge into a single line of a list. How do I do that?
Thanks a lot!
What I have is organized like this:
[1 2 3 4
5 6]
[1 2 3 4
5 6 ]
while what I need would be:
[1 2 3 4 5 6]
[1 2 3 4 5 6]
data =[]
with open(r'<add file path here >','r') as file:
x = file.readlines()
for i in range(0,len(x),2):
data.append(x[i:i+2])
new =[' '.join(i) for i in data]
for i in range(len(new)):
new[i]=new[i].replace('\n','')
new_file_name = r'' #give new file path here
with open(new_file_name,'w+') as file:
for i in new:
file.write(i+'\n')
Try This
final_data = []
with open('file.txt') as a:
fdata= a.readlines()
for ln in range(0,len(fdata),2):
final_data.append(" ".join([fdata[ln].strip('\n'), fdata[ln+1].strip('\n')]))
print (final_data)
I feel you can use a regex for solving this scenario :
#! /usr/bin/env python2.7
import re
with open("textfilename.txt") as r:
text_data = r.read()
independent_lists = re.findall(r"\[(.+?)\]",r ,re.DOTALL)
#now that we have got each independent_list we can next work on
#turning it into a list
final_list_of_objects = [each_string.replace("\n"," ").split() for each_string in independent_lists]
print final_list_of_objects
However if you do not want them to be as a list object and rather just want the outcome without the newline characters inbetween the list then:
#! /usr/bin/env python2.7
import re
with open("textfilename.txt") as r:
text_data = r.read()
new_txt = ""
for each_char in text_data:
if each_char == "[":
bool_char = True
elif each_char == "]":
bool_char = False
elif each_char == "\n" and bool_char:
each_char = " "
new_txt += each_char
new_txt = re.sub(r"\s+", " ", new_txt) # to remove multiple space lines between numbers
You can do two things here:
1) If the text file was created by writing using numpy's savetxt function, you can simply use numpy.loadtxt function with appropriate delimiter.
2) Read file in a string and use a combination of replace and split functions.
file = open(filename,'r')
dataset = file.read()
dataset = dataset.replace('\n',' ').replace('] ',']\n').split('\n')
dataset = [x.replace('[','').replace(']','').split(' ') for x in dataset]
with open('test.txt') as file:
new_data = (" ".join(line.strip() for line in file).replace('] ',']\n').split('\n')) # ['[1 2 3 4 5 6]', ' [1 2 3 4 5 6 ]']
with open('test.txt','w+') as file:
for data in new_data:
file.write(data+'\n')
line.rstrip() removes just the trailing newline('\n') from the line.
you need to pass all read and stripped lines to ' '.join(), not
each line itself. Strings in python are sequences to, so the string
contained in line is interpreted as separate characters when passed on
it's own to ' '.join().
I have a file text delimited file which I am trying to make binary combination per each line and giving the number of line to each pairs.
Here is an example (you can download it here too if you want https://gist.github.com/anonymous/4107418c63b88c6da44281a8ae7a321f)
"A,B "
"AFD,DNGS,SGDH "
"NHYG,QHD,lkd,uyete"
"AFD,TTT"
I want to have it like this
A_1 B_1
AFD_2 DNGS_2
AFD_2 SGDH_2
DNGS_2 SGDH_2
NHYG_3 QHD_3
NHYG_3 lkd_3
NHYG_3 uyete_3
QHD_3 lkd_3
QHD_3 uyete_3
lkd_3 uyete_3
AFD_4 TTT_4
It means, A_1 and B_1 are coming from the first row
AFD_2 & DNGS_2 are coming from the second row , etc etc
I have tried to do it but I cannot figure it out
#!/usr/bin/python
import itertools
# make my output
out = {}
# give a name to my data
file_name = 'data.txt'
# read all the lines
for n, line in enumerate(open(file_name).readlines()):
# split each line by comma
item1 = line.split('\t')
# split each stirg from another one by a comma
item2 = item1.split(',')
# iterate over all combinations of 2 strings
for i in itertools.combinations(item2,2):
# save the data into out
out.write('\t'.join(i))
Output Answer 1
"A_1, B "_1
"AFD_2, DNGS_2
"AFD_2, SGDH "_2
DNGS_2, SGDH "_2
"NHYG_3, QHD_3
"NHYG_3, lkd_3
"NHYG_3, uyete"_3
QHD_3, lkd_3
QHD_3, uyete"_3
lkd_3, uyete"_3
"AFD_4, TTT"_4
answer 2
"A_1 B "_1
"AFD_2 DNGS_2
"AFD_2 SGDH "_2
DNGS_2 SGDH "_2
"NHYG_3 QHD_3
"NHYG_3 lkd_3
"NHYG_3 uyete"_3
QHD_3 lkd_3
QHD_3 uyete"_3
lkd_3 uyete"_3
"AFD_4 TTT"_4
Try this
#!/usr/bin/python
from itertools import combinations
with open('data1.txt') as f:
result = []
for n, line in enumerate(f, start=1):
items = line.strip().split(',')
x = [['%s_%d' % (x, n) for x in item] for item in combinations(items, 2)]
result.append(x)
for res in result:
for elem in res:
print(',\t'.join(elem))
You need a list of list of lists to represent each pair. You can build them using a list comprehension in a loop.
I wasn't sure what you wanted as your actual output format, but this prints your expected output.
If there are quotes in the input file, the simple fix is
items = line.replace("\"", "").strip().split(',')
For the above code. This would break if there were other double quotes in the data. So if you know there aren't its ok.
Otherwise, create a small function to strip the quotes. This example also writes to a file.
#!/usr/bin/python
from itertools import combinations
def remquotes(s):
beg, end = 0, len(s)
if s[0] == '"': beg = 1
if s[-1] == '"': end = -1
return s[beg:end]
with open('data1.txt') as f:
result = []
for n, line in enumerate(f, start=1):
items = remquotes(line.strip()).strip().split(',')
x = [['%s_%d' % (x, n) for x in item] for item in combinations(items, 2)]
result.append(x)
with open('out.txt', 'w') as fout:
for res in result:
for elem in res:
linestr = ',\t'.join(elem)
print(linestr)
fout.write(linestr + '\n')
Similar to the other answer provided adding that based on the comments it looks like you actually wish to write to a tab-delimited text file instead of a dictionary.
#!/usr/bin/python
import itertools
file_name = 'data.txt'
out_file = 'out.txt'
with open(file_name) as infile, open(out_file, "w") as out:
for n,line in enumerate(infile):
row = [i + "_" + str(n+1) for i in line.strip().split(",")]
for i in itertools.combinations(row,2):
out.write('\t'.join(i) + '\n')
The following seems to work with a minimal amount of code:
import itertools
input_filename = 'data.txt'
output_filename = 'split_data.txt'
with open(input_filename, 'rt') as inp, open(output_filename, 'wt') as outp:
for n, line in enumerate(inp, 1):
items = ('{}_{}'.format(x.strip(), n)
for x in line.replace('"', '').split(','))
for combo in itertools.combinations(items, 2):
outp.write('\t'.join(combo) + '\n')
I have a Python file with a few hundred lines of code. The longest line is 146 characters. How would I put # in column 200 down the whole file within Sublime Text? Preferably with one or two Sublime Text commands?
1 200
print("Hello world!") #
You can try something like this. Note that this writes to a new file: let me know if you want me to modify so that it overwrites the existing file:
data = []
with open('data.txt', 'r') as f:
data = [line[:-1] + ' ' * (200 - len(line)) + '#\n' for line in f]
with open('new_data.txt', 'w') as f:
f.writelines(data)
Note that this will have just append the "#" at the end of the line (regardless of column number) if the line length >= 200.
Here's a possible solution:
N = 200
output = [l.rstrip() for l in f]
output = ["{0}#{1}".format(
l[:len(l[:N])] + ' ' * (N - len(l[:N])), l[N:]) for l in output]
print("\n".join(output))
Or written differently:
N = 200
output = []
for l in f:
l = l.rstrip()
l1 = len(l[:N])
output.append("{0}#{1}".format(l[:l1] + ' ' * (N - l1), l[N:]))
print("\n".join(output))
I want use python to read specific multiply lines from txt files. For example ,read line 7 to 10, 17 to 20, 27 to 30 etc.
Here is the code I write, but it will only print out the first 3 lines numbers. Why? I am very new to use Python.
with open('OpenDR Data.txt', 'r') as f:
for poseNum in range(0, 4):
Data = f.readlines()[7+10*poseNum:10+10*poseNum]
for line in Data:
matAll = line.split()
MatList = map(float, matAll)
MatArray1D = np.array(MatList)
print MatArray1D
This simplifies the math a little to choose the relevant lines. You don't need to use readlines().
with open('OpenDR Data.txt', 'r') as fp:
for idx, line in enumerate(fp, 1):
if idx % 10 in [7,8,9,0]:
matAll = line.split()
MatList = map(float, matAll)
MatArray1D = np.array(MatList)
print MatArray1D
with open('OpenDR Data.txt') as f:
lines = f.readlines()
for poseNum in range(0, 4):
Data = lines[7+10*poseNum:10+10*poseNum]
You should only call readlines() once, so you should do it outside the loop:
with open('OpenDR Data.txt', 'r') as f:
lines = f.readlines()
for poseNum in range(0, 4):
Data = lines[7+10*poseNum:10+10*poseNum]
for line in Data:
matAll = line.split()
MatList = map(float, matAll)
MatArray1D = np.array(MatList)
print MatArray1D
You can use a combination list slicing and comprehension.
start = 7
end = 10
interval = 10
groups = 3
with open('data.txt') as f:
lines = f.readlines()
mult_lines = [lines[start-1 + interval*i:end + interval*i] for i in range(groups)]
This will return a list of lists containing each group of lines (i.e. 7 thru 10, 17 thru 20).