I want to convert all json files of directory to text files through this command: but I got error. How can I change it?
import pandas as pd
df = pd.read_json(r"/media/New Volume/a3d/pdb/json_parser/ *.json ")
df.to_csv(r"/media/New Volume/a3d/pdb/json_parser/ *.txt ", index = False)
import os
import pandas as pd
# Get the list of json files, which are in the folder:
str_address = r"/media/New Volume/a3d/pdb/json_parser/"
lst_files = [i for i in os.listdir(str_address) if i.endswith(".json")]
# Loop through the json files
for file_ in lst_files:
df = pd.read_json(str_address + file_)
df.to_csv(str_address+ file_+ ".txt", index = False)
I'm new to python and hoping for some help to read in csv files from a folder and converting each file to a html folder...this is what I have so far:
import pandas as pd
import os
import glob
path = "htmlplots"
csv_files = glob.glob(os.path.join(path, "*.csv"))
for file in csv_files:
# read the csv file
df = pd.read_csv(file)
# print the filename
print('File Name:', file.split("\\")[-1])
# print the content
display(df)
Ideally I then need to create html files from the resulting csv files that have a 'next' and 'previous' link from one to two, two to three (next) and three to two, two to one (previous).
Use:
import pandas as pd
import os
import glob
path = ""
csv_files = glob.glob(os.path.join(path, "*.csv"))
for i, file in enumerate(csv_files):
df = pd.read_csv(file, header = None)
name = file.split('.')[-1]
if i>0:
prev = csv_files[i-1]
df.loc['prev',:]=f'http://{prev}'
else:
df.loc['prev',:]=''
if i!=len(csv_files)-1:
next = csv_files[i+1]
df.loc['next',:]=f'http://{next}'
else:
df.loc['next',:]=''
df.to_html(f"{file}.html", render_links = True)
Input csv file:
Output html:
I have a folder with 50 .csv files. The .csv files are auto-generated and a results/ output from a process-based model (long and automatically named). For example, sandbox_username_vetch_scaleup_IA_1.csv; sandbox_username_vetch_scaleup_IA_2.csv, and it continues till sandbox_username_vetch_scaleup_IA_50.csv.
I am trying to shorten the file names in a way so that the files are names are IA_1, IA_2 ...up to IA_50 and subsequently the new .csv file name gets added as a column to the data frame. Here is what I have tried so far
# import necessary libraries
import pandas as pd
import os
import glob
import sys
from pathlib import Path
import re
data_p = "/Users/Username/Documents/HV_Scale/CWAD"
output_p = "/Users/Username/Documents/HV_Scale/CWAD"
retval = os.getcwd()
print (retval) # see in which folder you are
os.chdir(data_p) # move to the folder with your data
os.getcwd()
filenames = sorted(glob.glob('*.csv'))
fnames = list(filenames) # get the names of all your files
#print(fnames)
#Loop over
for f in range(len(fnames)):
print(f'fname: {fnames[f]}\n')
pfile = pd.read_csv(fnames[f], delimiter=",") # read in file
#extract filename
filename = fnames[f]
parts = filename.split(".") # giving you the number in file name and .csv
only_id = parts[0].split("_") # if there is a bracket included
# get IA from your file
filestate = pfile["IA"][0] # assuming this is on the first row
filestate = str(filestate)
# get new filename
newfilename = only_id[0]+"-"+filestate+parts[1]
# save your file (don't put a slash at the end of your directories on top)
pfile.to_csv(output_p+"/"+newfilename, index = False, header = True)
Here is the code for adding the csv file name as a column
import glob
import os
import shutil
import sys
import pandas as pd
path = '/Users/Username/Documents/HV_Scale/IA_CWAD/short'
all_files = glob.glob(os.path.join(path, "*.csv"))
names = [os.path.basename(x) for x in glob.glob(path+'\*.csv')]
df = pd.DataFrame()
for file_ in all_files:
file_df = pd.read_csv(file_,sep=';', parse_dates=[0], infer_datetime_format=True,header=None )
file_df['file_name'] = file_
df = df.append(file_df)
#However, this adds the old csv file name and not the renamed one
In order to rename and move these files, all you need is:
import glob
import os
import shutil
import sys
SOURCE = '<Your source directory>'
TARGET = '<Your target directory>'
for file in glob.glob(os.path.join(SOURCE, '*_IA_*.csv')):
idx = file.index('_IA_')
filename = file[idx+1:]
target = os.path.join(TARGET, filename)
if os.path.exists(target):
print(f'Target file {target} already exists', file=sys.stderr)
else:
shutil.copy(file, target)
As there's nothing in the OP's question that tries to handle modification of the CSV files, that is left as an exercise for the OP.
Source and target directories should be different otherwise this can lead to ambiguous results
I am trying to read a xlsx file, compare all the reference numbers from a column to files inside a folder and if they correspond, rename them to an email associate with the reference number.
Excel File has fields such as:
Reference EmailAddress
1123 bob.smith#yahoo.com
1233 john.drako#gmail.com
1334 samuel.manuel#yahoo.com
... .....
My folder applicants just contains doc files named as the Reference column:
How can I compare the contents of the applicantsCVs folder, to the Reference field inside my excel file and if it matches, rename all of the files as the corresponding email address ?
Here is What I've tried so far:
import os
import pandas as pd
dfOne = pd.read_excel('Book2.xlsx', na_values=['NA'], usecols = "A:D")
references = dfOne['Reference']
emailAddress = dfOne['EmailAddress']
cleanedEmailList = [x for x in emailAddress if str(x) != 'nan']
print(cleanedEmailList)
excelArray = []
filesArray = []
for root, dirs, files in os.walk("applicantCVs"):
for filename in files:
print(filename) #Original file name with type 1233.doc
reworkedFile = os.path.splitext(filename)[0]
filesArray.append(reworkedFile)
for entry in references:
excelArray.append(str(entry))
for i in excelArray:
if i in filesArray:
print(i, "corresponds to the file names")
I compare the reference names to the folder contents and print it out if it's the same:
for i in excelArray:
if i in filesArray:
print(i, "corresponds to the file names")
I've tried to rename it with os.rename(filename, cleanedEmailList ) but it didn't work because cleanedEmailList is an array of emails.
How can I match and rename the files?
Update:
from os.path import dirname
import pandas as pd
from pathlib import Path
import os
dfOne = pd.read_excel('Book2.xlsx', na_values=['NA'], usecols = "A:D")
emailAddress = dfOne['EmailAddress']
reference = dfOne['Reference'] = dfOne.references.astype(str)
references = dict(dfOne.dropna(subset=[reference, "EmailAddress"]).set_index(reference)["EmailAddress"])
print(references)
files = Path("applicantCVs").glob("*")
for file in files:
new_name = references.get(file.stem, file.stem)
file.rename(file.with_name(f"{new_name}{file.suffix}"))
based on sample data:
Reference EmailAddress
1123 bob.smith#yahoo.com
1233 john.drako#gmail.com
nan jane.smith#example.com
1334 samuel.manuel#yahoo.com
First you assemble a dict with the set of references as keys and the new names as values:
references = dict(df.dropna(subset=["Reference","EmailAddress"]).set_index("Reference")["EmailAddress"])
{'1123': 'bob.smith#yahoo.com',
'1233': 'john.drako#gmail.com',
'1334': 'samuel.manuel#yahoo.com'}
Note that the references are strs here. If they aren't in your original database, you can use astype(str)
Then you use pathlib.Path to look for all the files in the data directory:
files = Path("../data/renames").glob("*")
[WindowsPath('../data/renames/1123.docx'),
WindowsPath('../data/renames/1156.pptx'),
WindowsPath('../data/renames/1233.txt')]
The renaming can be made very simple:
for file in files:
new_name = references.get(file.stem, file.stem )
file.rename(file.with_name(f"{new_name}{file.suffix}"))
The references.get asks for the new filename, and if it doesn't find it, use the original stem.
[WindowsPath('../data/renames/1156.pptx'),
WindowsPath('../data/renames/bob.smith#yahoo.com.docx'),
WindowsPath('../data/renames/john.drako#gmail.com.txt')]
How about adding the "email associate" (your new name i guess?) into an dictionary, where the keys are your reference numbers?
This could look something like:
cor_dict = {}
for i in excelArray:
if i in filesArray:
cor_dict[i] =dfOne['EmailAddress'].at[dfOne.Reference == i]
for entry in cor_dict.items():
path = 'path to file...'
filename = str(entry[0])+'.doc'
new_filename = str(entry[1]).replace('#','_') + '_.doc'
filepath = os.path.join(path, filename)
new_filepath = os.path.join(path,new_filename)
os.rename(filename, new_filename)
This is one approach using a simple iteration.
Ex:
import os
#Sample Data#
#dfOne = pd.DataFrame({'Reference': [1123, 1233, 1334, 4444, 5555],'EmailAddress': ["bob.smith#yahoo.com", "john.drako#gmail.com", "samuel.manuel#yahoo.com", np.nan, "samuel.manuel#yahoo.com"]})
dfOne = pd.read_excel('Book2.xlsx', na_values=['NA'], usecols = "A:D")
dfOne.dropna(inplace=True) #Drop rows with NaN
for root, dirs, files in os.walk("applicantsCVs"):
for file in files:
file_name, ext = os.path.splitext(file)
email = dfOne[dfOne['Reference'].astype(str).str.contains(file_name)]["EmailAddress"]
if email.values:
os.rename(os.path.join(root, file), os.path.join(root, email.values[0]+ext))
Or if you have only .docx file to rename
import os
dfOne = pd.read_excel('Book2.xlsx', na_values=['NA'], usecols = "A:D")
dfOne["Reference"] = dfOne["Reference"].astype(str)
dfOne.dropna(inplace=True) #Drop rows with NaN
ext = ".docx"
for root, dirs, files in os.walk("applicantsCVs"):
files = r"\b" + "|".join(os.path.splitext(i)[0] for i in files) + r"\b"
for email, ref in dfOne[dfOne['Reference'].astype(str).str.contains(files, regex=True)].values:
os.rename(os.path.join(root, ref+ext), os.path.join(root, email+ext))
You could do it directly in your dataframe using df.apply():
import glob
import os.path
#Filter out null addresses
df = df.dropna(subset=['EmailAddress'])
#Add a column to check if file exists
df2['Existing_file'] = df2.apply(lambda row: glob.glob("applicantsCVs/{}.*".format(row['Reference'])), axis=1)
df2.apply(lambda row: os.rename(row.Existing_file[0], 'applicantsCVs/{}.{}'.format( row.EmailAddress, row.Existing_file[0].split('.')[-1])) if len(row.Existing_file) else None, axis = 1)
print(df2.Existing_file.map(len), "existing files renamed")
EDIT :
works now with any extension (.doc, .docx) by using glob module
Let consider our sample data in excel sheet is following:
Reference EmailAddress
1123 bob.smith#yahoo.com
1233 john.drako#gmail.com
1334 samuel.manuel#yahoo.com
nan python#gmail.com
There are following steps involved to solve this problem.
Step 1
import the data properly from excel sheet "my.xlsx". Here I am using the sample data
import pandas as pd
import os
#import data from excel sheet and drop rows with nan
df = pd.read_excel('my.xlsx').dropna()
#check the head of data if the data is in desirable format
df.head()
You will see that the data type in the references are in float type here
Step 2
Change the data type in the reference column to integer and then into string
df['Reference']=df.Reference.astype(int, inplace=True)
df = df.astype(str,inplace=True)
df.head()
Now the data is in desirable format
Step 3
Renaming the files in the desired folder. Zip the lists of 'Reference' and 'EmailAddress' to use in for loop.
#absolute path to folder. I consider you have the folder "application cv" in the home directory
path_to_files='/home/applicant cv/'
for ref,email in zip(list(df['Reference']),list(df['EmailAddress'])):
try:
os.rename(path_to_files+ref+'.doc',path_to_files+email+'.doc')
except:
print ("File name doesn't exist in the list, I am leaving it as it is")
Step 1: import the data from excel sheet "Book1.xlsx"
import pandas as pd
df = pd.read_excel (r'path of your file here\Book1.xlsx')
print (df)
Step 2: Choose path that your ".docx" files are in and store their names.
Get only relevent part of filename to compare.
mypath = r'path of docx files\doc files'
from os import listdir,rename
from os.path import isfile, join
onlyfiles = [f for f in listdir(mypath) if isfile(join(mypath, f))]
#print(onlyfiles)
currentfilename=onlyfiles[0].split(".")[0]
This is how I stored the files
Step 3: Run loop to check if name matches with the Reference. And just use rename(src,dest) function from os
for i in range(3):
#print(currentfilename,df['ref'][i])
if str(currentfilename)==str(df['Reference'][i]):
corrosponding_email=df['EmailAddress'][i]
#print(mypath+"\\"+corrosponding_email)
rename(mypath+"\\"+str(currentfilename)+".docx",mypath+"\\"+corrosponding_email+".docx")
checkout the code with example:https://github.com/Vineet-Dhaimodker
I have multiple directories, each of which containing any number of .xls files.
I'd like to take the files in any given directory and combine them into one .xls file, using the file names as the tab names.
For example if there are the files NAME.xls, AGE.xls, LOCATION.xls, I'd like to combine them into a new file with the data from NAME.xls on a tab called NAME, the data from AGE.xls on a tab called AGE and so on.
Each source .xls file only has one column of data with no headers.
This is what I have so far, and well it's not working.
Any help would be greatly appreciated (I'm fairly new to Python and I've never had to do anything like this before).
wkbk = xlwt.Workbook()
xlsfiles = glob.glob(os.path.join(path, "*.xls"))
onlyfiles = [f for f in listdir(path) if isfile(join(path, f))]
tabNames = []
for OF in onlyfiles:
if str(OF)[-4:] == ".xls":
sheetName = str(OF)[:-4]
tabNames.append(sheetName)
else:
pass
for TN in tabNames:
outsheet = wkbk.add_sheet(str(TN))
data = pd.read_excel(path + "\\" + TN + ".xls", sheet_name="data")
data.to_excel(path + "\\" + "Combined" + ".xls", sheet_name = str(TN))
Here is a small helper function - it supports both .xls and .xlsx files:
import pandas as pd
try:
from pathlib import Path
except ImportError: # Python 2
from pathlib2 import Path
def merge_excel_files(dir_name, out_filename='result.xlsx', **kwargs):
p = Path(dir_name)
with pd.ExcelWriter(out_filename) as xls:
_ = [pd.read_excel(f, header=None, **kwargs)
.to_excel(xls, sheet_name=f.stem, index=False, header=None)
for f in p.glob('*.xls*')]
Usage:
merge_excel_files(r'D:\temp\xls_directory', 'd:/temp/out.xls')
merge_excel_files(r'D:\temp\xlsx_directory', 'd:/temp/out.xlsx')
Can you try
import pandas as pd
import glob
path = 'YourPath\ToYour\Files\\' # Note the \\ at the end
# Create a list with only .xls files
list_xls = glob.glob1(path,"*.xls")
# Create a writer for pandas
writer = pd.ExcelWriter(path + "Combined.xls", engine = 'xlwt')
# Loop on all the files
for xls_file in list_xls:
# Read the xls file and the sheet named data
df_data = pd.read_excel(io = path + xls_file, sheet_name="data")
# Are the sheet containing data in all your xls file named "data" ?
# Write the data into a sheet named after the file
df_data.to_excel(writer, sheet_name = xls_file[:-4])
# Save and close your Combined.xls
writer.save()
writer.close()
Let me know if it works for you, I never tried engine = 'xlwt' as I don't work with .xls file but .xlsx