Develop Reference

How to change smiles to images(png) using RDKit in python script

How to save image files after generate image file in python script?
def mols_to_pngs(mols, basename = "test"):
filenames = []
for i, mol in enumerate(mols):
filename = "%s%d.png" % (basename, i)
Draw.MolToFile(mol,filename)
filenames.append(filename)
return filenames
and I want to this process automatically using csv file and python script

To automatically save image files generated from a python script using a csv file, you need to read the data from the csv file and process it in your script. Here's a basic example:
import csv
import sys
def mols_to_pngs(mols, basename = "test"):
filenames = []
for i, mol in enumerate(mols):
filename = "%s%d.png" % (basename, i)
Draw.MolToFile(mol,filename)
filenames.append(filename)
return filenames
# Read the csv file
try:
with open('data.csv', 'r') as file:
reader = csv.reader(file)
# Skip the header row
next(reader)
mols = []
for row in reader:
# Process the data from the csv file
mol = process_data(row)
mols.append(mol)
except IOError:
print("Could not read file:", file)
sys.exit()
# Save the image files
filenames = mols_to_pngs(mols)
print("Saved the following files:", filenames)
Note that you need to replace the process_data function with your own implementation to process the data from the csv file and create the mol objects. Additionally, you may need to modify the code to match your specific use case.

how to read text from multiple files in python

I have many text files around 3000 files in a folder and in each file the 193rd line is the only line which has important information. How can i read all these files into 1 single text file using python.

There is a function named list dir in the os module. this function returns a list of all files in a given directory. Then you can access each file using a for a loop.
This tutorial will be helpful for listdir function. https://www.geeksforgeeks.org/python-os-listdir-method/
The example code is below.
import os
# your file path
path = ""
# to store the files or you can give this direct to the for loop like below
# for file in os.listdir(path)
dir_files = []
dir_files = os.listdir(path)
# to store your important text files.
# this list stores your important text line (193th line) in each file
texts = []
for file in dir_files:
with open(path + '\\' + file) as f:
# this t varialble store your 192th line in each cycle
t = f.read().split('\n')[192]
# this file append each file into texts list
texts.append(t)
# to print each important line
for text in texts:
print(text)

You will need to list the directory and read each file like so:
import os
for filename in os.listdir("/path/to/folder"):
with open(f"/path/to/folder/{filename}", "r") as f:
desired_line = f.readlines()[193]
... # Do whatever you need with the line

You can loop through your file paths, read the text from every file and then split lines using the line seperator in your OS.
import os
file_paths = [f"/path/to/file{i}.ext" for i in range(3000)]
info = []
for p in file_paths:
with open(p, "r") as file:
text = file.read(p)
line_list = text.split(os.linesep)
info.append(line_list[192])

You could try that, if its what you want:
import os
important_lines = []
for textfile in os.listdir('data'):
text_from_file = open( os.path.join('data', textfile) ).readlines()
if len(text_from_file) >= 192:
important_line = text_from_file[192]
important_lines.append(important_line)
#list of 192th lines from files

How to unzip all folders/files that end in .zip and extract “file.txt” file from each zipped folder

My code currently unzips one zip folder and finds the file called file.txt and extracts it. Now I need to unzip multiple folders that have the extension .zip. I have tried to use code similar to what I need it to do but the problem is that now I have to find a file called file.txt in each of those .zip folders and extract that file only . Also to store file.txt into a separate folder that has the same name where it came from. Thank you in advance for your time.
import re
import os
from zipfile import ZipFile
def pain():
print("\t\t\tinput_files.zip has been unzipped")
with ZipFile('input_files.zip', 'r') as zipObj:
zipObj.extractall()
listOfFileNames = zipObj.namelist()
for fileName in listOfFileNames:
if fileName.endswith('.txt'):
zipObj.extract(fileName, 'storage')
outfile = "output2.txt" #this will be the filename that the code will write to
baconFile = open(outfile,"wt")
file_name1 = "file.txt"
print('Filename\tLine\tnumber of numbers\tstring separated by a comma\twhite space found\ttab found\tcarriage return found\n') #This prints the master column in the python shell and this is the way the code should collect the data
baconFile.write('Filename\tLine\tnumber of numbers\tstring separated by a comma\twhite space found\ttab found\tcarriage return found\n') #This prints the master column in the output file and this is the way the code should collect the data
#for filename in os.listdir(os.getcwd() + "/input_files"):
for filename in os.listdir('C:\Users\M29858\Desktop\TestPy\Version10\input_files'):
with open("input_files/" + filename, 'r') as f:
if file_name1 in filename:
output_contents(filename, f, baconFile)
baconFile.close() #closes the for loop that the code is writing to
def output_contents(filename, f, baconFile): #using open() function to open the file inside the directory
index = 0
for line in f:
#create a list of all of the numerical values in our line
content = line.split(',') #this will be used to count the amount numbers before and after comma
whitespace_found = False
tab_found = False
false_string = "False (end of file)"
carriage_found = false_string
sigfigs = ""
index += 1 #adds 1 for every line if it finds what the command wants
if " " in line: #checking for whitespace
whitespace_found = True
if "\t" in line: #checking for tabs return
tab_found = True
if '\n' in line: #checking if there is a newline after the end of each line
carriage_found = True
sigfigs = (','.join(str(len(g)) for g in re.findall(r'\d+\.?(\d+)?', line ))) #counts the sigsfigs after decimal point
print(filename + "\t{0:<4}\t{1:<17}\t{2:<27}\t{3:17}\t{4:9}\t{5:21}"
.format(index, len(content), sigfigs, str(whitespace_found), str(tab_found), str(carriage_found))) #whatever is inside the .format() is the way it the data is stored into
baconFile.write('\n')
baconFile.write( filename + "\t{0:<4}\t{1:<17}\t{2:<27}\t{3:17}\t{4:9}\t{5:21}"
.format(index, len(content), sigfigs, str(whitespace_found), str(tab_found), str(carriage_found)))
if __name__ == '__main__':
pain()
#THIS WORKS

import glob
import os
from zipfile import ZipFile
def main():
for fname in glob.glob("*.zip"): # get all the zip files
with ZipFile(fname) as archive:
# if there's no file.txt, ignore and go on to the next zip file
if 'file.txt' not in archive.namelist(): continue
# make a new directory named after the zip file
dirname = fname.rsplit('.',1)[0]
os.mkdir(dirname)
extract file.txt into the directory you just created
archive.extract('file.txt', path=dirname)

Is there a way to load data from all files in a directory using Python?

My question: Is there a way to load data from all files in a directory using Python
Input: Get all files in a given directory of mine (wow.txt, testting.txt,etc.)
Process: I want to run all the files through a def function
Output: I want the output to be all the files names and their respective content below it.For example:
/home/file/wow.txt
"all of its content"
/home/file/www.txt
"all of its content"
Here is my code:
# Import Functions
import os
import sys
# Define the file path
path="/home/my_files"
file_name="wow.txt"
#Load Data Function
def load_data(path,file_name):
"""
Input : path and file_name
Purpose: loading text file
Output : list of paragraphs/documents and
title(initial 100 words considered as title of document)
"""
documents_list = []
titles=[]
with open( os.path.join(path, file_name) ,"rt", encoding='latin-1') as fin:
for line in fin.readlines():
text = line.strip()
documents_list.append(text)
print("Total Number of Documents:",len(documents_list))
titles.append( text[0:min(len(text),100)] )
return documents_list,titles
#Output
load_data(path,file_name)
Here is my output:
My Problem is that my output only takes one file and shows its content. Obviously, i defined the path and file name in my code to one file but I am confused as to how to write the path in a way to load all the files and output each of its contents separately. Any suggestions?

Using glob:
import glob
files = glob.glob("*.txt") # get all the .txt files
for file in files: # iterate over the list of files
with open(file, "r") as fin: # open the file
# rest of the code
Using os.listdir():
import os
arr = os.listdir()
files = [x for x in arr if x.endswith('.txt')]
for file in files: # iterate over the list of files
with open(file, "r") as fin: # open the file
# rest of the code

Try this:
import glob
for file in glob.glob("test/*.xyz"):
print(file)
if my directory name was "test" and I had lots of xyz files in them...

You can use glob and pandas
import pandas as pd
import glob
path = r'some_directory' # use your path
all_files = glob.glob(path + "/*.txt")
li = []
for filename in all_files:
#read file here
# if you decide to use pandas you might need to use the 'sep' paramaeter as well
df = pd.read_csv(filename, index_col=None, header=0)
li.append(df)
# get it all together
frame = pd.concat(li, axis=0, ignore_index=True)

I will take advantage of the function you have already written, so use the following:
data = []
path="/home/my_files"
dirs = os.listdir( path )
for file in dirs:
data.append(load_data(path, file))
In this case you will have all data in the list data.

Hi you can use a for loop on a listdir:
os.listdir(<path of your directory>)
this gives you the list of files in your directory, but this gives you also the name of folders in that directory

Try generating a file list first, then passing that to a modified version of your function.
def dir_recursive(dirName):
import os
import re
fileList = list()
for (dir, _, files) in os.walk(dirName):
for f in files:
path = os.path.join(dir, f)
if os.path.exists(path):
fileList.append(path)
fList = list()
prog = re.compile('.txt$')
for k in range(len(fileList)):
binMatch = prog.search(fileList[k])
if binMatch:
fList.append(binMatch.string)
return fList
def load_data2(file_list):
documents_list = []
titles=[]
for file_path in file_list:
with open( file_path ,"rt", encoding='latin-1') as fin:
for line in fin.readlines():
text = line.strip()
documents_list.append(text)
print("Total Number of Documents:",len(documents_list))
titles.append( text[0:min(len(text),100)] )
return documents_list,titles
# Generate a file list & load the data from it
file_list = dir_recursive(path)
documents_list, titles = load_data2(file_list)

How do I apply my python code to all of the files in a folder at once, and how do I create a new name for each subsequent output file?

The code I am working with takes in a .pdf file, and outputs a .txt file. My question is, how do I create a loop (probably a for loop) which runs the code over and over again on all files in a folder which end in ".pdf"? Furthermore, how do I change the output each time the loop runs so that I can write a new file each time, that has the same name as the input file (ie. 1_pet.pdf > 1_pet.txt, 2_pet.pdf > 2_pet.txt, etc.)
Here is the code so far:
path="2_pet.pdf"
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()

The following script solve your problem:
import os
sourcedir = 'pdfdir'
dl = os.listdir('pdfdir')
for f in dl:
fs = f.split(".")
if fs[1] == "pdf":
path_in = os.path.join(dl,f)
content = getPDFContent(path_in)
encoded = content.encode("utf-8")
path_out = os.path.join(dl,fs[0] + ".txt")
text_file = open(path_out, 'w')
text_file.write(encoded)
text_file.close()

Create a function that encapsulates what you want to do to each file.
import os.path
def parse_pdf(filename):
"Parse a pdf into text"
content = getPDFContent(filename)
encoded = content.encode("utf-8")
## split of the pdf extension to add .txt instead.
(root, _) = os.path.splitext(filename)
text_file = open(root + ".txt", "w")
text_file.write(encoded)
text_file.close()
Then apply this function to a list of filenames, like so:
for f in files:
parse_pdf(f)

One way to operate on all PDF files in a directory is to invoke glob.glob() and iterate over the results:
import glob
for path in glob.glob('*.pdf')
content = getPDFContent(path)
encoded = content.encode("utf-8")
text_file = open("Output.txt", "w")
text_file.write(encoded)
text_file.close()
Another way is to allow the user to specify the files:
import sys
for path in sys.argv[1:]:
...
Then the user runs your script like python foo.py *.pdf.

You could use a recursive function to search the folders and all subfolders for files that end with pdf. Than take those files and then create a text file for it.
It could be something like:
import os
def convert_PDF(path, func):
d = os.path.basename(path)
if os.path.isdir(path):
[convert_PDF(os.path.join(path,x), func) for x in os.listdir(path)]
elif d[-4:] == '.pdf':
funct(path)
# based entirely on your example code
def convert_to_txt(path):
content = getPDFContent(path)
encoded = content.encode("utf-8")
file_path = os.path.dirname(path)
# replace pdf with txt extension
file_name = os.path.basename(path)[:-4]+'.txt'
text_file = open(file_path +'/'+file_name, "w")
text_file.write(encoded)
text_file.close()
convert_PDF('path/to/files', convert_to_txt)
Because the actual operation is changeable, you can replace the function with whatever operation you need to perform (like using a different library, converting to a different type, etc.)