Assistance working with Files in Python 3 - python

I am currently taking an introduction class to python scripting and am in need of help. The below variables are given
The file name -> P = test.txt
firstname -> F = 'Ruthy'
lastname -> L = 'Anderson'
new birthday-> B = 00000000
The objective is to search the file for the given first and last name and then replace the current birthday that is there with the 'B' variable. We are told that each record has a fixed length of 40.
Below is what the test.txt file contains
Adam Smith 11111985Theodore Anderson 03201990Monty Biscuit-Barrel 10181980Adam Smithers 11111900Ruthy Anderson 06062010
This is the code that I have thus far.
file1 = open(P, 'r')
data = file1.read()
file1.close()
file2 = open(P, 'w')
recordLength = 40
start = 0
records = []
while((len(data) - start) >= recordLength):
record = data[start:start + recordLength]
records.append(record)
start+= recordLength
for i in range(0, len(records)):
if re.seatch(F, data) and re.search(L, data):
data = re.sub('10101960', B, data)
file2.write(data)
file2.close()

IIUC my approach would be the following:
# P = 'test.txt'
# F = 'Ruthy'
# L = 'Anderson'
# B = '00000000'
with open(P, 'r+') as f:
while True:
rec = f.read(40)
if rec:
if rec.startswith(f'{F} {L}'):
pos = f.tell()
f.seek(pos-8)
f.write(B)
break
else:
break

Related

Syntax error calculating the average of student marks while reading from a text file

f = open('studMarks.txt', 'r')
marks = 0
# Sort out names, split the words then sort which order
for line in f:
words = line.split()
fname = words[0]
lname = words[1]
print(f"{lname},{fname}")
f.close()
f = open('studMarks.txt', 'r')
sum = 0
count = 0
for line in f:
count += 1
sum += float(line.split()[2])
n = []
average = sum/count
print(f"{average}")
When using the for loop it seems to display a value of 64.3, which I believe is for the total of the whole student list and average for all marks.
I need to produce the an output which displays the student names and average on the same line. I can do for the names but I cannot do it for the average as I keep getting errors. I don't know what to input in.
Below is the full solution. The with open line is a context manager and ensures that the file will get closed as soon as you exit the block. You should get used to using this style as it's the safe way to do I/O. The rest is just bog standard Python.
marks=dict()
with open('studMarks.txt', 'r') as f:
for line in f:
words = line.split()
fname = words[0]
lname = words[1]
score = int(words[2])
key = f'{fname} {lname}'
count_key = f'{fname} {lname}_count'
latest_score = score + (marks.get(key)[0] if marks.get(key) else 0)
latest_count = 1 + (marks.get(key)[1] if marks.get(key) else 0)
marks[key] = (latest_score, latest_count )
for name, value in marks.items():
print(f'{name} : {value[0]/value[1]}')
This is an interesting problem.
From what I understand you have a text file that looks like this:
Johnny Ly 90 100 Adam Best 80 30 Tim Smith 10 20 in a file called studentMarks2.txt
and want output like this:
Johnny_Ly 95.0 Adam_Best 55.0 Tim_Smith 15.0
if that is true then it can be done using code like this without pandas or csv
though those would make this a lot easier.
fileContents = []
with open('studMarks2.txt','r') as f:
fileContents = f.read().split()
students = dict()
names = []
for content in fileContents:
if content.isnumeric():
studentKey = '_'.join(names)
currentScore = students.get(studentKey,[])
newScore = currentScore + [float(content)]
students.update({studentKey:newScore})
else:
if len(names) == 2:
names.clear()
names.append(content)
else:
names.append(content)
for student,scores in students.items():
avg = sum(scores)/len(scores)
print(student,avg,end=' ')
Broken down
This part reads the contents and splits on white space
fileContents = []
with open('studMarks2.txt','r') as f:
fileContents = f.read().split()
this part then iterates through the contents
storing the names as keys in a dictionary and putting the scores in a list
students = dict()
names = []
for content in fileContents:
if content.isnumeric():
studentKey = '_'.join(names)
currentScore = students.get(studentKey,[])
newScore = currentScore + [float(content)]
students.update({studentKey:newScore})
else:
if len(names) == 2:
names.clear()
names.append(content)
else:
names.append(content)
Lastly it iterates over the dictionary and output the avg on one line
for student,scores in students.items():
avg = sum(scores)/len(scores)
print(student,avg,end=' ')

How to calculate moving average for temperature?

This is the output I need:
Temperature anomaly filename:SacramentoTemps.csv
Enter window size:60
1940,-0.2331
1941,-0.2169
1942,-0.2150
1943,-0.2228
1944,-0.2107
1945,-0.1796
1946,-0.1667
1947,-0.1582
1948,-0.1585
1949,-0.1492
1950,-0.1711
1951,-0.1688
1952,-0.1490
1953,-0.1556
1954,-0.1548
1955,-0.1580
1956,-0.1420
1957,-0.1101
1958,-0.1017
This is my code:
filename = input("Temperature anomaly filename:")
infile = open(filename, "r")
k = int(input("Enter window size:"))
infile.readline()
temp_list = []
for line in infile:
line = line.strip()
year,temp = line.split(",")
temp = float(temp)
temp_list.append(temp)
index = k
for index in range(index,len(temp_list)-1-index):
year = 1880 + index
ave = sum(temp_list[index:index+k]) / (2*index+1)
print(str(year)+","+"{:.4f}".format(ave))
infile.close()
My code currently prints out up until the year 1957 and it prints out the wrong averages for each year. What do I need to fix?
filename = "SacramentoTemps.csv"
infile = open(filename, "r")
k = int(input("Enter window size:"))
temp_list = []
for line in infile:
line = line.strip()
year, temp = line.split(",")
temp = float(temp)
temp_list.append(temp)
infile.close()
moving_average = []
for i, temp in enumerate(temp_list):
average = temp
if len(temp_list) - i < k:
break
for j in range(k):
average += temp_list[i+j]
moving_average.append(average/k)
print(str(year) + "," + "{:.4f}".format(average))
I coded in the direction of modifying your code as little as possible.
One thing to note is your file need to be longer than window size.
Using pandas would be most sane way to go:
import pandas as pd
filename = "SacramentoTemps.csv"
window = 2
data = pd.read_csv(filename)
data.temperature.rolling(window = window).mean().fillna(data.temperature)

How to randomly pair data in text file

I have two files: file(student) where there are 20 students and file(lecturer) where there are 3 lecturers. I want to pair the students and lecturers randomly. For example:
lecturer(1) = student(2),student(3),student(19)
lecturer(3) = student(20),student(23)......
This is the code I have tried. It is not behaving in the manner I had hoped for:
import random
lecturer = open("lecturer.txt", "r")
students = open("students.txt", "r")
spliti = lecturer.read().split("\n")
splitis = students.read().split("\n")
stud = (random.choice(splitis))
for stud in splitis:
file = open(stud + "txt","w")
for i in range():
questinss = random.choice(spliti)
file.write(lecturer + "\n")
files = open(students + ",txt", "r")
file.close()
lecturer.close()
students.close()
Here are some codes that you can use. Hope it can give you some thoughts.
import random
# get the students
with open('student.txt','r') as f:
students = f.read().split()
# get the lectures
with open('lecture.txt','r') as f:
lectures = f.read().spilt()
# since you only have three different lectures, we can sequently
# collect them as 0,1,2
reflist = []
for student in students:
reflist.append( lectures[ random.randrange(3) ] )
# prepare for the print
lecture_student = []
for lecture in lectures:
count = 0
ls = []
for ndx in reflist:
if lecture == ndx:
ls.append(students[count])
count += 1
lecture_student.append(ls)
# now to file them
with open('pro_lecture_student.txt','wt') as f:
count = 0
for lecture in lectures:
f.write(lecture)
f.write(': ')
for student in lecture_student[count]:
f.write(student)
f.write('\n\n')
count += 1

appending files in python

I have a homework assignment working with fixed length files:
You will be passed the filename P, firstname F, lastname L, and a new birthday B.
Load the fixed length record file in P, search for F,L in the first and change birthday to B.
P= sys.argv[1]
F= sys.argv[2]
L= sys.argv[3]
B= sys.argv[4]
recordlength = 40
record = [[]]
start = 0
file1 = open(P, 'r')
data = file1.read()
while( (len(data) - start) >= recordlength):
records= data[start:start + recordlength]
record.append(records)
start+= recordlength
for i in range(0,len(record)):
if F and L in record[i]:
rec = record[i]
rec = rec[:-8] + B
record[i] = rec
data = "".join(records)
file1 = open(P, 'a+')
file1.write(record[i])
file1.close()
I should get this output:
Adam Smith 11111985Theodore Anderson 03201990Monty Biscuit-Barrel 10181980Adam Smithers 00000000Ruthy Anderson 06062010
I get this output:
Adam Smith 11111985Theodore Anderson 03201990Monty Biscuit-Barrel 10181980Adam Smithers 10101960Ruthy Anderson 06062010Adam Smithers 00000000
Instead of replacing this line: Adam Smithers 10101960, with this line: Adam Smithers 00000000, it adds this line into the file, leaving the original line.
I'm not sure where my problem is, can someone point me in the right direction?
On line 8 you open the file but do not close before opening again on line 20. Try to close before line 20 or open with parameter "a" directly on line 8.

Python - Loop inside loop of two files with regex

Im trying to create a loop in order to check two files and compare with regex if a specific field matches.
avi file
TVShowName.S01E01.W.DVDRip.XviD.avi
TVShowName.S01E02.W.DVDRip.XviD.avi
TVShowName.S01E03.W.DVDRip.XviD.avi
srt
tvShowName.S01E01.episodename.DVDRip.XviD.srt
tvShowName.S01E02.episodename.DVDRip.XviD.srt
tvShowName.S01E03.episodename.DVDRip.XviD.srt
Without a loop I can match the file and make the magic happen. Although when I use the loop it only reaches the first line.
TVShowName.S01E01.W.DVDRip.XviD.avi
TVShowName.S01E01.W.DVDRip.XviD.srt
Code:
f1 = open('avi', 'r')
f2 = open('srt', 'r')
f3 = open ('merge', 'a')
for avi in f1:
m = re.search(".*([Ss][0-20].[eE][0-24].)+.*", avi )
for sub in f2:
n = re.search(".*([Ss][0-20].[eE][0-24].)+.*", sub )
if m.group(1) == n.group(1):
str_avi = str(m.group(0))
#print str_avi
ext_srt = str_srt.split('.')
ext_avi = str_avi.split('.')
#print ext_avi
#conv_str = str(m.group(0))
merge = str_avi.replace(ext_avi[-1],ext_srt[-1])
print merge
f3.write(merge)
f3.close()
I'm not entirely sure if this is the output you wanted. I can't add comments because I don't have enough reputation points.
import glob
import re
avifiles = []
srtfiles = []
for afile in glob.glob('*.avi'):
avifiles.append(afile)
for sfile in glob.glob('*.srt'):
srtfiles.append(sfile)
#f1 = open('avi', 'r')
#f2 = open('srt', 'r')
f3 = open ('merge', 'a')
for avi in avifiles:
m = re.search(".*([Ss][0-20].[eE][0-24].)+.*", avi )
for sub in srtfiles:
n = re.search(".*([Ss][0-20].[eE][0-24].)+.*", sub )
if m.group(1) == n.group(1):
str_avi = str(m.group(0))
str_srt = str(n.group(0))
ext_srt = str_srt.split('.')
ext_avi = str_avi.split('.')
#print ext_avi
#conv_str = str(m.group(0))
merge = str_avi.replace(ext_avi[-1],ext_srt[-1])
print merge
f3.write(merge+"\n")
f3.close()
I made the follow code and it seems working. My next step is add more video extentions. But it should be easy.
Thank you guys fot the helping!
import re, os, sys, itertools
str_avi = ''
split_avi = ''
global zzz
lista_avi = []
lista_srt = []
lista_final = []
os.chdir('.')
f1 = os.listdir(".")
for full in f1:
avi = re.search(".*([Ss][0-9].[eE][0-9].)+.*(...$)", full )
if avi:
if avi.group(2) == 'avi':
lista_avi.append(avi.group(0))
elif avi.group(2) == 'srt':
lista_srt.append(avi.group(0))
else:
pass
else:
print "Nenhum Arquivo localizado!"
for f,b in itertools.izip(lista_avi,lista_srt):
data_avi = f.split('.')
data_srt = b.split('.')
data_regx_avi = re.search(".*([Ss][0-9].[eE][0-9].)+.*(...$)", f )
data_regx_srt = re.search(".*([Ss][0-9].[eE][0-9].)+.*(...$)", b )
for x in lista_srt:
data_regx_srt = re.search(".*([Ss][0-9].[eE][0-9].)+.*(...$)", x )
if data_regx_avi.group(1) == data_regx_srt.group(1):
print 'Arquivo video:', data_regx_avi.group(0)
print 'Arquivo sub: ', f.replace(data_avi[-1],data_srt[-1])
#lista_final.append(f.replace(data_avi[-1],data_srt[-1]))
xx = f.replace(data_avi[-1],data_srt[-1])
os.rename(x, xx)

Categories