We Keep Coding

transform for in loop to while loop

i have this assignment in a basic programming course where i need to transform this code using while loop instead of for loop, but i dont know how to doit
this is my code so far
def read_txt(file_txt):
file = open(file_txt, "r")
lines = file.readlines()
file.close()
return lines
file_txt = input("file: ")
lines = read_txt(file_txt)
for l in lines:
asd = l.split(",")
length = len(asd)
score = 0
for i in range(1, length):
score += int(asd[i])
average = score / (length-1)
print(asd[0], average)
file text is like this
edward,4,3,1,2
sara,5,4,1,0

def read_txt(file_txt):
file = open(file_txt, "r")
lines = file.readlines()
file.close()
return lines
file_txt = input("file: ")
lines = read_txt(file_txt)
lines.reverse()
while lines:
l = lines.pop()
asd = l.split(",")
length = len(asd)
score = 0
i = 1
while i < length:
score += int(asd[i])
i += 1
average = score / (length-1)
print(asd[0], average)
Now in this while loop, it will iterate through lines until lines is empty. it will pop out items one by one.

For loops are more suitable for iterating over lines in files than while loops. Few improvements here are, (1) use the builtin sum instead of manually adding up scores, and (2) don't read all lines in file at once if the files are too big.
file_txt = input("file: ")
with open(file_txt) as f:
while True:
line = f.readline()
if not line:
break
name, scores = line.split(',', maxsplit=1)
scores = scores.split(',')
avg = sum(int(s) for s in scores) / len(scores)
print(f'{name} {avg}')
As you see above the check for if not line to determine if we have reached the end of file in a while loop, this is not needed in for loop as that implements the __iter__ protocol.
Python 3.8 walrus operator makes that slightly easier with::
file_txt = input("file: ")
with open(file_txt) as f:
while line := f.readline():
name, scores = line.split(',', maxsplit=1)
scores = scores.split(',')
avg = sum(int(s) for s in scores) / len(scores)
print(f'{name} {avg}')

The following gives the exact same output without using any for loop.
filename = input("file: ")
with open(filename) as f:
f = f.readlines()
n = []
while f:
v = f.pop()
if v[-1] == '\n':
n.append(v.strip('\n'))
else:
n.append(v)
d = {}
while n:
v = n.pop()
v = v.split(',')
d[v[0]] = v[1:]
d_k = list(d.keys())
d_k.sort(reverse=True)
while d_k:
v = d_k.pop()
p = d[v]
n = []
while p:
a = p.pop()
a = int(a)
n.append(a)
print(str(v), str(sum(n)/len(n)))
Output:
edward 2.5
sara 2.5

reading and deleting lines in python

I am trying to read all the lines in a specific file, and it prints the number of the line as an index.
What I am trying to do is to delete the line by inputting the number of the line by the user.
As far as it is now, it prints all the lines with the number of that line, but when I enter the number of the line to be deleted, it's not deleted.
This is the code of the delete function:
def deleteorders ():
index = 0
fh = open ('orders.txt', 'r')
lines = fh.readlines()
for line in lines:
lines = fh.readlines()
index = index+1
print (str(index) + ' ' + line)
try:
indexinp = int(input('Enter the number of the order to be deleted, or "B" to go back: '))
if indexinp == 'B':
return
else:
del line[indexinp]
print (line)
fh = open ('orders.txt', 'w')
fh.writelines(line)
fh.close()
except:
print ('The entered number is not in the range')
return

This should work (you'll need to add the error handling back in):
lines = enumerate(open('orders.txt'))
for i, line in lines:
print i, line
i = int(input(">"))
open('orders.txt', 'w').write(''.join((v for k, v in lines if k != i)))

Python coding for opening and saving data to a file

I am having an issue getting the train function to work correctly in python. I can not modify the def function. I am at the point where I need to get the second file to read lines one at a time for PosList and i need to match the value of movieWordCount[z] in OpenPos. If the file is there, then I am good to incrment column 2 by one of t hat line (segmented by a space). If it is not, then I need the else to append it to the file end. It does not work. It does not append the values if it is missing and I am not sure if it will find the value if it is there. I have been stuck getting thsi to work for two days.
Here is my code segment I am working with:
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
#Now use tokenize to split it apart by space and set to new array for me to call column2
else:
print "not found"
lines.append(movieWordCount[z] + " 1" + "\n")
Here is my full code:
#!/usr/bin/python
#Import Counter
import collections
from collections import Counter
#Was already here but pickle is used for data input and export
import math, os, pickle, re
class Bayes_Classifier:
def __init__(self, trainDirectory = "movie_reviews/"):
#If file listing exists skip to train
if os.path.isfile('iFileList'):
print "file found"
self.train()
#self.classify()
#If file listing does not exist skip to train
if not os.path.isfile('iFileList'):
print "no file"
newfile = 'iFileList'
tempList = set()
subDir = './movie_reviews'
for filenames in os.listdir(subDir):
my_sub_path = os.path.join(os.sep,subDir,filenames)
tempList.add(filenames)
self.save("filenames", "try3")
f = []
for fFileObj in os.walk("movie_reviews/"):
f.extend(fFileObj)
break
pickle.dump(f, open( "save.p", "wb" ))
self.save(f, "try4")
with open(newfile, 'wb') as fi:
pickle.dump(tempList, fi)
#print tempList
self.train()
#self.classify()
def train(self):
'''Trains the Naive Bayes Sentiment Classifier.'''
print "File ready for training"
#Open iFileList to use as input for opening movie files
x = 0
OpenIFileList = open('iFileList','r')
print "iFileList now Open"
#Loop through the file
for line in OpenIFileList:
#print "Ready to read lines"
#print "reading line " + line
if x > 4:
if x % 2 == 0:
#print line
s = line
if '-' in s:
comp = s.split("'")
#print comp[2]
print comp[1] #This is What you need for t he movie file
compValue1 = comp[1]
#Determine Positive/Negative.
#compType is the variable I am storing it to.
compType = compValue1.split("-",2)[1]
#print compType #Prints that middle value like 5 or 1
# This will do the work based on the value.
if compType == '5':
# print "you have a five" #Confirms the loop I am in.
#If file does not exists create it
if not os.path.exists('PosList'):
print "no file"
file('PosList', 'w').close()
#Open file that needs to be reviewed for word count
compValue2 = "movie_reviews/" + compValue1
print compValue2 #Prints the directory and file path
OpenMovieList = open(compValue2,'r')
for commentLine in OpenMovieList:
commentPositive = commentLine.split(" ")
commentPositiveCounter = Counter(commentPositive)
#print commentPositiveCounter # " Comment Pos goes here"
#if commentLine != '' or commentLine != ' ':
#Get first word, second word, ....
if commentLine and (not commentLine.isspace()):
movieWordCount = self.tokenize(commentLine)
y = len(movieWordCount) #determines length of string
print y
z = 0
#print movieWordCount[0] # Shows the zero position in the file.
while z < y:
print "position " + str(z) + " word is " + movieWordCount[z] # Shows the word we are at and position id
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
else:
print "not found"
lines.append(movieWordCount)
z = z + 1
#Close the files
OpenMovieList.close()
OpenPos.close()
x += 1
#for line2 in OpenIFileList.readlines():
#for line in open('myfile','r').readlines():
#do_something(line)
#Save results
#Close the File List
OpenIFileList.close()
def loadFile(self, sFilename):
'''Given a file name, return the contents of the file as a string.'''
f = open(sFilename, "r")
sTxt = f.read()
f.close()
return sTxt
def save(self, dObj, sFilename):
'''Given an object and a file name, write the object to the file using pickle.'''
f = open(sFilename, "w")
p = pickle.Pickler(f)
p.dump(dObj)
f.close()
def load(self, sFilename):
'''Given a file name, load and return the object stored in the file.'''
f = open(sFilename, "r")
u = pickle.Unpickler(f)
dObj = u.load()
f.close()
return dObj
def tokenize(self, sText):
'''Given a string of text sText, returns a list of the individual tokens that
occur in that string (in order).'''
lTokens = []
sToken = ""
for c in sText:
if re.match("[a-zA-Z0-9]", str(c)) != None or c == "\'" or c == "_" or c == '-':
sToken += c
else:
if sToken != "":
lTokens.append(sToken)
sToken = ""
if c.strip() != "":
lTokens.append(str(c.strip()))
if sToken != "":
lTokens.append(sToken)
return lTokens

To open a file for writing, you can use
with open('PosList', 'w') as Open_Pos
As you are using the with form, you do not need to close the file; Python will do that for you at the end of the with-block.
So assuming that the way you add data to the lines variable is correct, you could remove the superfluous code OpenMovieList.close() and OpenPos.close(), and append 2 lines to your code:
with open("PosList") as OpenPos:
lines = OpenPos.readlines()
print lines
if movieWordCount[z] in lines:
print "found"
else:
print "not found"
lines.append(movieWordCount)
with open("PosList", "w") as OpenPos:
OpenPos.write(lines)

Searching a file for matches between two values and outputting search hits in Python

I am (attempting) to write a program that searches through a hex file for instances of a hex string between two values, eg. Between D4135B and D414AC, incrementing between the first value until the second is reached- D4135B, D4135C, D4135D etc etc.
I have managed to get it to increment etc, but it’s the search part I am having trouble with.
This is the code I have so far, it's been cobbled together from other places and I need to make it somehow output all search hits into the output file (file_out)
I have exceeded the limit of my Python understanding and I'm sure there's probably a much easier way of doing this. I would be very grateful for any help.
def search_process(hx): # searching for two binary strings
global FLAG
while threeByteHexPlusOne != threeByteHex2: #Keep incrementing until second value reached
If Flag:
if hx.find(threeByteHex2) != -1:
FLAG = False #If threeByteHex = ThreeByteHexPlusOne, end search
Print (“Reached the end of the search”,hx.find(threeByteHexPlusOne))
Else:
If hx.find(threeByteHexPlusOne) != -1:
FLAG = True
Return -1 #If no results found
if __name__ == '__main__':
try:
file_in = open(FILE_IN, "r") #opening input file
file_out = open(FILE_OUT, 'w') #opening output file
hx_read = file_in.read #read from input file
tmp = ''
found = ''
while hx_read: #reading from file till file is empty
hx_read = tmp + hx_read
pos = search_process(hx_read)
while pos != -1:
hex_read = hx_read[pos:]
if FLAG:
found = found + hx_read
pos = search_process(hx_read)
tmp = bytes_read[]
hx_read = file_in.read
file_out.write(found) #writing to output file
except IOError:
print('FILE NOT FOUND!!! Check your filename or directory/PATH')

Here's a program that looks through a hex string from a file 3 bytes at a time and if the 3-byte hex string is between the given hex bounds, it writes it to another file. It makes use of generators to make getting the bytes from the hex string a little cleaner.
import base64
import sys
_usage_string = 'Usage: python {} <input_file> <output_file>'.format(sys.argv[0])
def _to_base_10_int(value):
return int(value, 16)
def get_bytes(hex_str):
# Two characters equals one byte
for i in range(0, len(hex_str), 2):
yield hex_str[i:i+2]
def get_three_byte_hexes(hex_str):
bytes = get_bytes(hex_str)
while True:
try:
three_byte_hex = next(bytes) + next(bytes) + next(bytes)
except StopIteration:
break
yield three_byte_hex
def find_hexes_in_range(hex_str, lower_bound_hex, upper_bound_hex):
lower_bound = _to_base_10_int(lower_bound_hex)
upper_bound = _to_base_10_int(upper_bound_hex)
found = []
for three_byte_hex in get_three_byte_hexes(hex_str):
hex_value = _to_base_10_int(three_byte_hex)
if lower_bound <= hex_value < upper_bound:
found.append(three_byte_hex)
return found
if __name__ == "__main__":
try:
assert(len(sys.argv) == 3)
except AssertionError:
print _usage_string
sys.exit(2)
file_contents = open(sys.argv[1], 'rb').read()
hex_str = base64.decodestring(file_contents).encode('hex')
found = find_hexes_in_range(hex_str, 'D4135B', 'D414AC')
print('Found:')
print(found)
if found:
with open(sys.argv[2], 'wb') as fout:
for _hex in found:
fout.write(_hex)
Check out some more info on generators here

find a alpha-numeric entry in tab delimited file with python

I'm trying to perform a GOs annotation using the SIMAP database which is
Blast2GO annotated. Everything is fine, but I have problems when I try
to find the accession number in the file where entry numbers are
associated with their GOs. The problem is that the script does not find
the number in the input file when really there is. I tried several things
without good results (re.match, insert in a list and then extract the element, etc)
File where the GOs are associated with entry numbers has this structure (accession number, GO term, blats2go score):
1f0ba1d119f52ff28e907d2b5ea450db GO:0007154 79
1f0ba1d119f52ff28e907d2b5ea450db GO:0005605 99
The python code:
import re
from Bio.Blast import NCBIXML
from Bio import SeqIO
input_file = open('/home/fpiston/Desktop/test_go/test2.fasta', 'rU')
result_handle = open('/home/fpiston/Desktop/test_go/test2.xml', 'rU')
save_file = open('/home/fpiston/Desktop/test_go/test2.out', 'w')
fh = open('/home/fpiston/Desktop/test_go/Os_Bd_Ta_blat2go_fake', 'rU')
q_dict = SeqIO.to_dict(SeqIO.parse(input_file, "fasta"))
blast_records = NCBIXML.parse(result_handle)
hits = []
for blast_record in blast_records:
if blast_record.alignments:
list = (blast_record.query).split()
if re.match('ENA|\w*|\w*', list[0]) != None:
list2 = list[0].split("|")
save_file.write('%s\t' % list2[1])
else:
save_file.write('%s\t' % list[0])
for alignment in blast_record.alignments:
for hsp in alignment.hsps:
h = alignment.hit_def
for l in fh:
ls = l.split() #at this point all right
if h in ls: #here, 'h' in not found in 'fh'
print h
print 'ok'
save_file.write('%s\t' % ls[1])
save_file.write('\n')
hits.append(blast_record.query.split()[0])
misses =set(q_dict.keys()) - set(hits)
for i in misses:
list = i.split("|")
if len(list) > 1:
save_file.write('%s\t' % list[1])
else:
save_file.write('%s\t' % list)
save_file.write('%s\n' % 'no_match')
save_file.close()
This is the code with the correction of martineau (fh.seek(0)):
#!/usr/bin/env python
import sys
import re
from Bio.Blast import NCBIXML
from Bio import SeqIO
input_file = sys.argv[1] #queries sequences in fasta format
out_blast_file = sys.argv[2] #name of the blast results file
output_file = sys.argv[3] #name of the output file
result_handle = open(out_blast_file, 'rU')
fh = open('/home/fpiston/Desktop/test_go/Os_Bd_Ta_blat2go', 'rU')
q_dict = SeqIO.to_dict(SeqIO.parse(open(input_file), "fasta"))
blast_records = NCBIXML.parse(result_handle)
save_file = open(output_file, 'w')
hits = []
for blast_record in blast_records:
if blast_record.alignments:
list = (blast_record.query).split()
if re.match('ENA|\w*|\w*', list[0]) != None:
list2 = list[0].split("|")
save_file.write('\n%s\t' % list2[1])
else:
save_file.write('\n%s\t' % list[0])
for alignment in blast_record.alignments:
for hsp in alignment.hsps:
hit = alignment.hit_def
save_file.write('%s\t' % hit)
fh.seek(0)
for l in fh:
ls = l.split()
if ls[0] in hit:
save_file.write('%s\t' % ls[1])
hits.append(blast_record.query.split()[0])
misses =set(q_dict.keys()) - set(hits)
for i in misses:
list = i.split("|")
if len(list) > 1:
save_file.write('\n%s\t' % list[1])
else:
save_file.write('\n%s\t' % list)
save_file.write('%s' % 'no_match')
save_file.close()

I really have no idea what you're talking about here, but noticed that within the outer for blast_record in blast_records: and for alignment in blast_record.alignments: loops you have a for l in fh: but never rewind the file with a fh.seek(0) anywhere, which means it only reads the lines in the file the first time it's executed -- which seems illogical.
You could fix this by adding the fh.seek(0) just before the inner loop. Although unnecessary the very first time the inner loop executes, it's need all the following times and doing it one extra time won't hurt anything.