I am a beginner. I have a log file like the below for ~ 1000 cycle loops,
"CycleSTART#1
Temp=26C
Fan=3000
CycleSTART#2
Temp=27C
Fan=3200
.
.
.
."
My objective is to read the Temp & fan values corresponding to cycle count. Basically I want to put everything in a table. And I tried with the simple programming
string1 = 'CycleSTART#'
string2 = 'Temp'
string3 = 'Fan'
import pandas as pd
filepath = "XXX<location of txt file>"
with open(filepath) as fp:
line=fp.readline()
cnt = 1
while line:
cnt += 1
flag = 0
index = 0
for line in fp:
if string1 in line:
flag = 1
break
if flag == 1:
lword=len(line)
extracted_string1 = line[11:11+lword]
for line in fp:
if string2 in line:
flag = 2
break
if flag == 2:
lword=len(line)
extracted_string2 = line[6:6+lword]
for line in fp:
if string3 in line:
flag = 3
break
if flag == 3:
lword=len(line)
extracted_string3 = line[5:5+lword]
data = {'cycle': [extracted_string1],
'temp' : [extracted_string2],
'Fan' : [extracted_string3],
df = pd.DataFrame(data, columns = ['cycle', 'temp', 'Fan']
print (df)
f.close()
Tried with this but every time, I get the first cycle value and its not looping to the next cycles.
I would rewrite a little bit and use splits to stay away from regex.
import pandas as pd
def add_to_dict(item, key, dic):
if dic.get(item, False):
dic[item].append(item)
else:
dic[item] = [item]
filepath = "XXX<location of txt file>"
data_container = {}
with open(filepath, "r") as f:
for indx, line in enumerate(f):
if indx % 3 == 0:
value = int(line.split("#")[-1]) # Split on # and then convert to number
key = "cycle"
elif indx % 3 == 1:
temp = float(temp.split("=")[-1][:-1]) # Split on = and then remove the C to hold the temperature value
key = "temp"
elif indx % 3 == 2:
fan = int(fan.split("=")[-1]) # Almost same as above, split on = to get the numerical value at the end and convert it to int
key = "Fan"
add_to_dict(value, key, data_container)
dataframe = pd.DataFrame.from_dict(data_container)
Related
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=' ')
For changing the values from 10 to 18, 19 or 20, I am splitting the string, access the substrings and then trying to change it. Its working but just not changing the values. Here is the solution I am trying to implement:
oldFileName = 'tryout.hmo'
newFileName = 'tryout_NEW.hmo'
topoFileName = 'Density.topo'
readme = open( oldFileName, "r" )
oldLines = readme.readlines()
readme = open(topoFileName, "r")
Lines = readme.readlines()
readme.close()
newFile = open(newFileName,"w")
for row in oldLines:
for line in Lines:
tmp = line.split()
list = row.rstrip()
tmp1 = list.split()
newFile.write(row)
if row.find("BEG_ELEM_DATA") > -1:
if tmp[0] == tmp1[0]:
if tmp[2] == 1 and tmp[3] == 0:
# it is magnet, value 18
newFile.write(tmp1.replace(tmp1[1], "18"))
elif tmp[2] == 1 and tmp[3] == 1:
# it is iron, value 19
newFile.write(tmp1.replace(tmp1[1], "19"))
else:
# it is air, value 20
newFile.write(tmp1.replace(tmp1[1], "20"))
newFile.close()
I would really appreciate it if you could able to solve this problem in above script, then I guess it should work.
I'm also still a beginner in Python, but I tried to solve your problem and here is my solution:
I guess there are way better ways to do it because here you have to import all data to a dataframe before comparing it.
Also I don't know if you can read your data with pd.read_csv to a dataframe because I don't know *.hmo and *.topo
import pandas as pd
df = pd.read_csv('tryout.csv', delimiter=';')
df2 = pd.read_csv('density.csv', delimiter=';')
for idx, row in df.iterrows():
for idx2, row2 in df2.iterrows():
if row[0] == row2[0]:
if row2[2] == 1 and row2[3] == 0 :
# it is magnet, value 18
row[1] = 18
elif row2[2] == 1 and row2[3] == 1 :
# it is iron, value 19
row[1] = 19
else:
# it is air, value 20
row[1] = 20
df.to_csv('new_tryout.csv')
What my code is doing here, it loads both files to dataframes. Then iterate over every line to compare where the ID in both files is the same (e.g 3749).
If true there are the 3 if statements whether it is magnet/iron/air and change the value in df to the right number.
At the end save the new df to a new file 'new_tryout.csv'
I created 2 testfiles for it and it worked the way it should.
Finally, here is the solution you were searching for.
import pandas as pd
df2 = pd.read_csv('Density.topo', header = 0, names = list('ABCD'), delimiter=r'\s+', skiprows=1)
df2[['C', 'D']]= df2[['C', 'D']].round()
new_file_content=''
with open('tryout.hmo', 'r') as f:
for line in f:
if line[11:13] == '10':
if line[3].isspace():
ID_to_search_for = line[4:8] # number with 4 digits
else:
ID_to_search_for = line[3:8] # number with 5 digits
search_idx = df2[df2['A'] == ID_to_search_for].index[0]
if df2['C'][search_idx] == 1 and df2['D'][search_idx] == 0:
change = '18' #magnet
new_line = line[:11] + change + line[13:]
elif df2['C'][search_idx] == 1 and df2['D'][search_idx] == 1:
change = '19' #iron
new_line = line[:11] + change + line[13:]
else:
change = '20' #air
new_line = line[:11] + change + line[13:]
new_file_content += new_line
else:
new_file_content += line
with open('tryout_changed.hmo', 'w') as f:
f.write(new_file_content)
if you don't want to use dataframes, you can do it like this:
with open('density.topo') as f:
lists_of_list = [line.rstrip().split() for line in f]
new_file_content=''
with open('tryout_test.hmo', 'r') as f:
for line in f:
if line[11:13] == '10':
if line[3].isspace():
ID_to_search_for = line[4:8] # number with 4 digits
else:
ID_to_search_for = line[3:8] # number with 5 digits
for idx, sublist in enumerate(lists_of_list):
if sublist[0] == ID_to_search_for:
if lists_of_list[idx][2] == 1 and lists_of_list[idx][3] == 0:
change = '18' #magnet
new_line = line[:11] + change + line[13:]
elif lists_of_list[idx][2] == 1 and lists_of_list[idx][3] == 1:
change = '19' #iron
new_line = line[:11] + change + line[13:]
else:
change = '20' #air
new_line = line[:11] + change + line[13:]
new_file_content += new_line
else:
new_file_content += line
with open('tryout_changed.hmo', 'w') as f:
f.write(new_file_content)
ok, here is my final answer. It does (again) all things you were searching for. Please debug your code in your IDE if there is a problem. You should start using context manager instead of open and closing files step by step.
I wrote the new code around your code in the question and added some comments to it.
oldFileName = 'tryout.hmo'
newFileName = 'tryout_NEW.hmo'
topoFileName = 'Density.topo'
readme = open( oldFileName, "r" )
oldLines = readme.readlines()
m = int(oldLines[3])
print(m)
new_m = m+3
m1 = str(m)
new_m1 = str(new_m)
Phrase = "END_COMP_DATA"
#n = "Phrase not found" #not used --> not needed
with open(oldFileName,"r") as oldFile:
for number, lin in enumerate(oldFile):
if Phrase in lin:
n = number
#insert 3 lines to tryout_new at the right position (--> row n)
magnet = f" {m+1} "'" topo_magnet"'"\n"
iron = f" {m+2} "'" topo_iron"'"\n"
air = f" {m+3} "'" topo_air"'"\n"
oldLines[n:n] = [magnet, iron, air]
newFile = open(newFileName,"w")
flag = 0
with open('density.topo') as f:
data_density = [line.rstrip().split() for line in f]
for idx, row in enumerate(oldLines):
lst = row.rstrip() #I think you shouldn't name a variable like a class in python (list). use 'lst' or something like that
tmp_tryout = lst.split()
if row.find("BEG_ELEM_DATA") > -1:
flag = 1
if flag == 1 and len(tmp_tryout)>1:
# if the column has more than 2 columns (after split), check for the "10"
if tmp_tryout[1] == '10':
# density_idx_line searchs in density.topo for a match with tmp_tryout[0] (e.g. 3749) and stores the whole line
density_idx_line = list(filter(lambda x: x[0] == tmp_tryout[0], data_density))
if len(density_idx_line) >0:
if density_idx_line[0][2] == '1.0' and density_idx_line[0][3] == '1e-05':
# the ' 10 ' is the 10 with a whitespace before and after it. Only like this only the 10 gets replaced (and not e.g. 3104 to 3184)
newFile.write(row.replace(' 10 ', ' 18 '))
elif density_idx_line[0][2] == '1.0' and density_idx_line[0][3] == '1.0':
newFile.write(row.replace(' 10 ', ' 19 '))
else:
newFile.write(row.replace(' 10 ', ' 20 '))
else:
newFile.write(row)
else:
if idx == 3:
newFile.write(row.replace(m1, new_m1))
else:
newFile.write(row)
newFile.close()
print ("script terminated successfully!")
ok, here is another solution. For anybody else who reads this: this is still only a temporary solution but #Sagar and me both don't know to do it better.
import pandas as pd
df = pd.read_csv('tryout.hmo', header = 0, names = list('ABCDEFGHIJKLM'), delimiter=r'\s+', skiprows=[i for i in range(52362)])
df2 = pd.read_csv('Density.topo', header = 0, names = list('ANOP'), delimiter=r'\s+', skiprows=1)
df2 = df2.iloc[:-3, :]
df3 = df.merge(df2, how='outer', on='A')
df3[['O','P']] = df3[['O','P']].fillna(-1).astype(int).replace(-1, np.nan)
df3['B']= df3.apply(lambda x: 18 if x['B']==10 and x['O']==1 and x['P']==0 else (
19 if x['B']==10 and x['O']==1 and x['P']==1 else (
20 if x['B']==10 and x['O']==0 and x['P']==0 else x['B'])), axis=1)
df3.to_csv('new_tryout.csv')
It finished the code in less than a second, so it is far better than iterrows or itertuples.
The new csv file includes both the tryout file and the density file. They are merged together by the first column of tryout file (ID i guess)
I didn't check all of this very big file but from the few random points I checked, it seems as this way works.
I am working with some data that for a specific column can only formatted in 1 of three ways:
3884932039484 (this is randomly generated from my program)
0 (this is static and will never change)
-1 (this is static and will never change)
I want the program to randomly pick between option 1,2 or 3 and insert one of three options. This is what I currently have:
file = open(r'I:\PythonDataFiles\StandardFeedInput\standardfeed_test.tsv', 'r')
all_lines = file.readlines()
#date_time_answer = input('Please input a date and time(2015-09-15 00:00:00): ')
#if date_time_answer == '':
date_time_answer = '{:%Y-%m-%d %H:%M:%S}'.format(datetime.datetime.now() - datetime.timedelta(days = 1))
date_time = 1
is_imp = 16
person_id = 19
aid = 44
line_id = 49
cid = 50
is_click = 60
app_id = 0
prev_app_id = ''
new_file = open(r'I:\PythonDataFiles\Standard Feed Output\test2.txt', 'w')
for line in all_lines:
row = line.split('\t')
row[date_time] = date_time_answer
row[person_id] = str((random.randint(1000000000, 9999999999)), 0, -1)
if row[app_id] == str(prev_app_id):
row[is_imp] = str(0)
row[is_click] = str(1)
else:
row[is_imp] = str(1)
prev_app_id = app_id
print(row)
new_file.write('\t'.join(row))
Use random.choice() to pick one of the three options:
random.choice([random.randint(1000000000, 9999999999), 0, -1])
This is the which i am doing
import csv
output = open('output.txt' , 'wb')
# this functions return the min for num.txt
def get_min(num):
return int(open('%s.txt' % num, 'r+').readlines()[0])
# temporary variables
last_line = ''
input_list = []
#iterate over input.txt in sort the input in a list of tuples
for i, line in enumerate(open('input.txt', 'r+').readlines()):
if i%2 == 0:
last_line = line
else:
input_list.append((last_line, line))
filtered = [(header, data[:get_min(header[-2])] + '\n' ) for (header, data) in input_list]
[output.write(''.join(data)) for data in filtered]
output.close()
In this code input.txt is something like this
>012|013|0|3|M
AFDSFASDFASDFA
>005|5|67|0|6
ACCTCTGACC
>029|032|4|5|S
GGCAGGGAGCAGGCCTGTA
and num.txt is something like this
M 4
P 10
I want that in above input.txt check the amount of value from the num.txt by looking at its last column which is same like in num.txt and cut its character according to that values
I think the error in my code is that it only accept the integer text file , where it should also accept file which contain alphabets
The totally revised version, after a long chat with the OP;
import os
import re
# Fetch all hashes and counts
file_c = open('num.txt')
file_c = file_c.read()
lines = re.findall(r'\w+\.txt \d+', file_c)
numbers = {}
for line in lines:
line_split = line.split('.txt ')
hash_name = line_split[0]
count = line_split[1]
numbers[hash_name] = count
#print(numbers)
# The input file
file_i = open('input.txt')
file_i = file_i.read()
for hash_name, count in numbers.iteritems():
regex = '(' + hash_name.strip() + ')'
result = re.findall(r'>.*\|(' + regex + ')(.*?)>', file_i, re.S)
if len(result) > 0:
data_original = result[0][2]
stripped_data = result[0][2][int(count):]
file_i = file_i.replace(data_original, '\n' + stripped_data)
#print(data_original)
#print(stripped_data)
#print(file_i)
# Write the input file to new input_new.txt
f = open('input_new.txt', 'wt')
f.write(file_i)
You can do it like so;
import re
min_count = 4 # this variable will contain that count integer from where to start removing
str_to_match = 'EOG6CC67M' # this variable will contain the filename you read
input = '' # The file input (input.txt) will go in here
counter = 0
def callback_f(e):
global min_count
global counter
counter += 1
# Check your input
print(str(counter) + ' >>> ' + e.group())
# Only replace the value with nothing (remove it) after a certain count
if counter > min_count:
return '' # replace with nothing
result = re.sub(r''+str_to_match, callback_f, input)
With this tactic you can keep count with a global counter and there's no need to do hard line-loops with complex structures.
Update
More detailed version with file access;
import os
import re
def callback_f(e):
global counter
counter += 1
# Check your input
print(str(counter) + ' >>> ' + e.group())
# Fetch all hash-file names and their content (count)
num_files = os.listdir('./num_files')
numbers = {}
for file in num_files:
if file[0] != '.':
file_c = open('./num_files/' + file)
file_c = file_c.read()
numbers[file.split('.')[0]] = file_c
# Now the CSV files
csv_files = os.listdir('./csv_files')
for file in csv_files:
if file[0] != '.':
for hash_name, min_count in numbers.iteritems():
file_c = open('./csv_files/' + file)
file_c = file_c.read()
counter = 0
result = re.sub(r''+hash_name, callback_f, file_c)
# Write the replaced content back to the file here
Considered directory/file structure;
+ Projects
+ Project_folder
+ csv_files
- input1.csv
- input2.csv
~ etc.
+ num_files
- EOG6CC67M.txt
- EOG62JQZP.txt
~ etc.
- python_file.py
The CSV files contain the big chunks of text you state in your original question.
The Num files contain the hash-files with an Integer in them
What happens in this script;
Collect all Hash files (in a dictionary) and it's inner count number
Loop through all CSV files
Subloop through the collected numbers for each CSV file
Replace/remove (based on what you do in callback_f()) hashes after a certain count
Write the output back (it's the last comment in the script, would contain the file.write() functionality)
I am doing text processing and using 'readline()' function as follows:
ifd = open(...)
for line in ifd:
while (condition)
do something...
line = ifd.readline()
condition = ....
#Here when the condition becomes false I need to rewind the pointer so that the 'for' loop read the same line again.
ifd.fseek() followed by readline is giving me a '\n' character. How to rewind the pointer so that the whole line is read again.
>>> ifd.seek(-1,1)
>>> line = ifd.readline()
>>> line
'\n'
Here is my code
labtestnames = sorted(tmp)
#Now read each line in the inFile and write into outFile
ifd = open(inFile, "r")
ofd = open(outFile, "w")
#read the header
header = ifd.readline() #Do nothing with this line. Skip
#Write header into the output file
nl = "mrn\tspecimen_id\tlab_number\tlogin_dt\tfluid"
offset = len(nl.split("\t"))
nl = nl + "\t" + "\t".join(labtestnames)
ofd.write(nl+"\n")
lenFields = len(nl.split("\t"))
print "Reading the input file and converting into modified file for further processing (correlation analysis etc..)"
prevTup = (0,0,0)
rowComplete = 0
k=0
for line in ifd:
k=k+1
if (k==200): break
items = line.rstrip("\n").split("\t")
if((items[0] =='')):
continue
newline= list('' for i in range(lenFields))
newline[0],newline[1],newline[3],newline[2],newline[4] = items[0], items[1], items[3], items[2], items[4]
ltests = []
ltvals = []
while(cmp(prevTup, (items[0], items[1], items[3])) == 0): # If the same mrn, lab_number and specimen_id then fill the same row. else create a new row.
ltests.append(items[6])
ltvals.append(items[7])
pos = ifd.tell()
line = ifd.readline()
prevTup = (items[0], items[1], items[3])
items = line.rstrip("\n").split("\t")
rowComplete = 1
if (rowComplete == 1): #If the row is completed, prepare newline and write into outfile
indices = [labtestnames.index(x) for x in ltests]
j=0
ifd.seek(pos)
for i in indices:
newline[i+offset] = ltvals[j]
j=j+1
if (rowComplete == 0): #
currTup = (items[0], items[1], items[3])
ltests = items[6]
ltvals = items[7]
pos = ifd.tell()
line = ifd.readline()
items = line.rstrip("\n").split("\t")
newTup = (items[0], items[1], items[3])
if(cmp(currTup, newTup) == 0):
prevTup = currTup
ifd.seek(pos)
continue
else:
indices = labtestnames.index(ltests)
newline[indices+offset] = ltvals
ofd.write(newline+"\n")
The problem can be handled more simply using itertools.groupby. groupby can cluster all the contiguous lines that deal with the same mrn, specimen_id, and lab_num.
The code that does this is
for key, group in IT.groupby(reader, key = mykey):
where reader iterates over the lines of the input file, and mykey is defined by
def mykey(row):
return (row['mrn'], row['specimen_id'], row['lab_num'])
Each row from reader is passed to mykey, and all rows with the same key are clustered together in the same group.
While we're at it, we might as well use the csv module to read each line into a dict (which I call row). This frees us from having to deal with low-level string manipulation like line.rstrip("\n").split("\t") and instead of referring to columns by index numbers (e.g. row[3]) we can write code that speaks in higher-level terms such as row['lab_num'].
import itertools as IT
import csv
inFile = 'curious.dat'
outFile = 'curious.out'
def mykey(row):
return (row['mrn'], row['specimen_id'], row['lab_num'])
fieldnames = 'mrn specimen_id date lab_num Bilirubin Lipase Calcium Magnesium Phosphate'.split()
with open(inFile, 'rb') as ifd:
reader = csv.DictReader(ifd, delimiter = '\t')
with open(outFile, 'wb') as ofd:
writer = csv.DictWriter(
ofd, fieldnames, delimiter = '\t', lineterminator = '\n', )
writer.writeheader()
for key, group in IT.groupby(reader, key = mykey):
new = {}
row = next(group)
for key in ('mrn', 'specimen_id', 'date', 'lab_num'):
new[key] = row[key]
new[row['labtest']] = row['result_val']
for row in group:
new[row['labtest']] = row['result_val']
writer.writerow(new)
yields
mrn specimen_id date lab_num Bilirubin Lipase Calcium Magnesium Phosphate
4419529 1614487 26.2675 5802791G 0.1
3319529 1614487 26.2675 5802791G 0.3 153 8.1 2.1 4
5713871 682571 56.0779 9732266E 4.1
This seems to be a perfect use case for yield expressions. Consider the following example that prints lines from a file, repeating some of them at random:
def buflines(fp):
r = None
while True:
r = yield r or next(fp)
if r:
yield None
from random import randint
with open('filename') as fp:
buf = buflines(fp)
for line in buf:
print line
if randint(1, 100) > 80:
print 'ONCE AGAIN::'
buf.send(line)
Basically, if you want to process an item once again, you send it back to the generator. On the next iteration you will be reading the same item once again.