Develop Reference

How to save words that occur no more than 3 times in a text? Reading and writing files

I am working on a text file right now that is called "dracula.txt", and I have to do the following in python:
Save words that occur no more than 3 times in descending order in a file called less_common_words.txt. Each word with its count should be saved on a separate line.
I would appreciate any help! I've been working on this for too long.
I have already tokenized my file and counted the words. This is my code so far:
file = open("C:/Users/17733/Downloads/dracula.txt", 'r', encoding = 'utf-8-sig')
data = file.read()
data
data_list = data.split('\n')
data_list
new_list = []
for i in data_list:
if i !='':
ans_here = i.split(' ')
new_list.extend(ans_here)
new_list
import string
import re
puncs = list(string.punctuation)
puncs.append('"')
puncs.append('[')
puncs.append('.')
puncs.append('-')
puncs.append('_')
#append each seperately
new_2 = []
for i in new_list:
for p in puncs:
if p in i:
i_new = i.replace(p, ' ')
new_2.append(i_new)
new_2
new_2 = [i.replace(' ', ' ').strip().lower() for i in new_2]
new_2

from pathlib import Path
from collections import Counter
import string
filepath = Path('test.txt')
output_filepath = Path('outfile.txt')
# print(filepath.exists())
with open(filepath) as f:
content = f.readlines()
word_list = sum((
(s.lower().strip('\n').translate(str.maketrans('', '', string.punctuation))).split(' ')
for s in content
), [])
less_common_words = sorted([
key for key, value in Counter(word_list).items() if value <= 3
],reverse=True)
with open(output_filepath, mode='wt', encoding='utf-8') as myfile:
myfile.write('\n'.join(less_common_words))

This should exactly be what you need- I fixed my previous error by flattening the entire txt into a 2d list:
book_open = open('frankenstein.txt', 'r').readlines()
beauty_book = [i.split() for i in book_open]
flatten = []
for sublist in beauty_book:
for val in sublist:
flatten.append(val)
foo = 0
for i in flatten:
list_open = open('less_common_words.txt', 'r').readlines()
beauty_list = [i.replace('\n', '') for i in list_open]
count = flatten.count(flatten[foo])
compile = str((flatten[foo], count))
if count <= 3:
if compile not in beauty_list:
file = open('less_common_words.txt', 'a+')
file.write('\n'+compile)
file.close()
foo += 1

Turning Text file to dictionary

I have a text file that has following structure:
mom:2
dad:3
mom:4
dad:2
me:4
And I need to make a dictionary that would display each name only once, but adding the numeric values together. In this case it would look like this:
{dad':5, 'me':4, 'mom':6}
How I should approach this problem?
I've tried
d = {}
try:
file = open(file.txt, "r")
for line in file:
(a, b) = line.split(":")
d[a] = float(b)
except IOError:
print()
but i haven't found a way to count up the values.

with open('file.txt', 'r') as f:
fp = f.readlines()
t = [l.strip().split(':') for l in fp if l != '\n']
d = {}
for l in t:
d[l[0]] = d.setdefault(l[0], 0) + int(l[1])

trying to create a dictionary from a text file but

so, I have text file (a paragraph) and I need to read the file and create a dictionary containing each different word from the file as a key and the corresponding value for each key will be an integer showing the frequency of the word in the text file.
an example of what the dictionary should look like:
{'and':2, 'all':1, 'be':1, 'is':3} etc.
so far I have this,
def create_word_frequency_dictionary () :
filename = 'dictionary.txt'
infile = open(filename, 'r')
line = infile.readline()
my_dictionary = {}
frequency = 0
while line != '' :
row = line.lower()
word_list = row.split()
print(word_list)
print (word_list[0])
words = word_list[0]
my_dictionary[words] = frequency+1
line = infile.readline()
infile.close()
print (my_dictionary)
create_word_frequency_dictionary()
any help would be appreciated thanks.

Documentation defines collections module as "High-performance container datatypes". Consider using collections.Counter instead of re-inventing the wheel.
from collections import Counter
filename = 'dictionary.txt'
infile = open(filename, 'r')
text = str(infile.read())
print(Counter(text.split()))
Update:
Okay, I fixed your code and now it works, but Counter is still a better option:
def create_word_frequency_dictionary () :
filename = 'dictionary.txt'
infile = open(filename, 'r')
lines = infile.readlines()
my_dictionary = {}
for line in lines:
row = str(line.lower())
for word in row.split():
if word in my_dictionary:
my_dictionary[word] = my_dictionary[word] + 1
else:
my_dictionary[word] = 1
infile.close()
print (my_dictionary)
create_word_frequency_dictionary()

If you are not using version of python which has Counter:
>>> import collections
>>> words = ["a", "b", "a", "c"]
>>> word_frequency = collections.defaultdict(int)
>>> for w in words:
... word_frequency[w] += 1
...
>>> print word_frequency
defaultdict(<type 'int'>, {'a': 2, 'c': 1, 'b': 1})

Just replace my_dictionary[words] = frequency+1 with my_dictionary[words] = my_dictionary[words]+1.

How to read from file after some 'mark'?

For example, if I have some text / log file with very simple structure, where here is a few different parts of it, with different structure, and splitted by some mark line, e.g.:
0x23499 0x234234 0x234234
...
0x34534 0x353454 0x345464
$$$NEW_SECTION$$$
4345-34534-345-345345-3453
3453-34534-346-766788-3534
...
So, how I can read file by these parts? E.g. read file in one variable before that $$$NEW_SECTION$$$ mark, and after it (without using regexps, etc). Are here any simple solutions for that?

Here is the solution without reading the whole file into memory:
data1 = []
pos = 0
with open('data.txt', 'r') as f:
line = f.readline()
while line and not line.startswith('$$$'):
data1.append(line)
line = f.readline()
pos = f.tell()
data2 = []
with open('data.txt', 'r') as f:
f.seek(pos)
for line in f:
data2.append(line)
print data1
print data2
The first iteration can't be made with for line in f not to spoil the accurate position in the file.

The simplest solution is str.split
>>> s = filecontents.split("$$$NEW_SECTION$$$")
>>> s[0]
'0x23499 0x234234 0x234234\n\n0x34534 0x353454 0x345464\n'
>>> s[1]
'\n4345-34534-345-345345-3453\n3453-34534-346-766788-3534'

Solution 1:
If file is not very-big then:
with open('your_log.txt') as f:
parts = f.read().split('$$$NEW_SECTION$$$')
if len(parts) > 0:
part1 = parts[0]
...
Solution 2:
def FileParser(filepath):
with open(filepath) as f:
part = ''
while(line = f.readline()):
part += line
if (line != '$$$NEW_SECTION$$$'):
returnpart = part
part = ''
yield returnpart
for segment in FileParser('your_log.txt'):
print segment
Note: it is untested code so please validate before using it

Solution:
def sec(file_, sentinel):
with open(file_) as f:
section = []
for i in iter(f.readline, ''):
if i.rstrip() == sentinel:
yield section
section = []
else:
section.append(i)
yield section
and use:
>>> from pprint import pprint
>>> pprint(list(sec('file.txt')))
[['0x23499 0x234234 0x234234\n', '0x34534 0x353454 0x345464\n'],
['4345-34534-345-345345-3453\n',
'3453-34534-346-766788-3534\n',
'3453-34534-346-746788-3534\n']]
>>>
sections to variables or best sections to dict:
>>> sections = {}
>>> for n, section in enumerate(sec('file.txt')):
... sections[n] = section
>>>

Finding a line in a file then reading next few lines in Python

I have a plain text file with the following data:
id=1
name=Scott
occupation=Truck driver
age=23
id=2
name=Dave
occupation=Waiter
age=16
id=3
name=Susan
occupation=Computer programmer
age=29
I'm trying to work out the best way to get to any point in the file given an id string, then grab the rows underneath to extract the data for use in my program. I can do something like:
def get_person_by_id(id):
file = open('rooms', 'r')
for line in file:
if ("id=" + id) in line:
print(id + " found")
But I'm not sure how I can now go through the next bunch of lines and do line.split("=") or similar to extract the info (put into a list or dict or whatever) that I can use my program. Any pointers?

One option would be to load the entire thing into memory, which would save you from reading the file every time:
with open('rooms') as f:
chunks = f.read().split('\n\n')
people_by_id = {}
for chunk in chunks:
data = dict(row.split('=', 1) for row in chunk.split('\n'))
people_by_id[data['id']] = data
del data['id']
def get_person_by_id(id):
return people_by_id.get(id)

How about exiting from a for loop after finding the correct line:
def get_person_by_id(id):
file = open('rooms', 'r')
for line in file:
if ("id=" + id) in line:
print(id + " found")
break
#now you can continue processing your file:
next_line = file.readline()

Maybe:
d = dict()
with open(filename) as f:
for line in f:
k,v = line.split('=')
if 'id=' in line:
d[v] = {}
d[d.keys()[-1]][k] = v

And here is an iterative solution.
objects = []
current_object = None
with open("info.txt", "rb") as f:
for line in f:
line = line.strip("\r\n")
if not line:
current_object = None
continue
if current_object is None:
current_object = {}
objects.append(current_object)
key,_,value = line.partition('=')
current_object[key] = value
print objects

Another example of an iterative parser:
from itertools import takewhile
def entries(f):
e = {}
def read_one():
one = {}
for line in takewhile(lambda x: '=' in x, f):
key, val = line.strip().split('=')
one[key] = val
return one
while True:
one = read_one()
if not one:
break
else:
e[one.pop('id')] = one
return e
Example:
>>> with open('data.txt') as f:
..: print entries(f)['2']
{'age': '16', 'occupation': 'Waiter', 'name': 'Dave'}

Get all the person's attributes and values (i.e. id, name, occupation, age, etc..), till you find
an empy line.
def get_person_by_id(id):
person = {}
file = open('rooms', 'r')
for line in file:
if found == True:
if line.strip():
attr, value = line.split("="):
else:
return person
elif ("id=" + id) in line:
print(id + " found")
found = True
attr, value = line.split("=")
person[attr] = value
return person

This solution is a bit more forgiving of empty lines within records.
def read_persons(it):
person = dict()
for l in it:
try:
k, v = l.strip('\n').split('=', 1)
except ValueError:
pass
else:
if k == 'id': # New record
if person:
yield person
person = dict()
person[k] = v
if person:
yield person