We Keep Coding

pandas creates 2 copies of files in a loop

I have a dataframe like as below
import numpy as np
import pandas as pd
from numpy.random import default_rng
rng = default_rng(100)
cdf = pd.DataFrame({'Id':[1,2,3,4,5],
'customer': rng.choice(list('ACD'),size=(5)),
'region': rng.choice(list('PQRS'),size=(5)),
'dumeel': rng.choice(list('QWER'),size=(5)),
'dumma': rng.choice((1234),size=(5)),
'target': rng.choice([0,1],size=(5))
})
I am trying to split the dataframe based on Customer and store it in a folder. Not necessary to understand the full code. The issue is in the last line.
i = 0
for k, v in df.groupby(['Customer']):
print(k.split('#')[0])
LM = k.split('#')[0]
i = i+1
unique_cust_names = '_'.join(v['Customer'].astype(str).unique())
unique_ids = '_'.join(v['Id'].astype(str).unique())
unique_location = '_'.join(v['dumeel'].astype(str).unique())
filename = '_'.join([unique_ids, unique_cust_names, unique_location, LM])
print(filename)
with pd.ExcelWriter(f"{filename}.xlsx", engine='xlsxwriter') as writer:
v.to_excel(writer,columns=col_list,index=False)
wb = load_workbook(filename = 'format_sheet.xlsx')
sheet_from =wb.worksheets[0]
wb1 = load_workbook(filename = f"{filename}.xlsx")
sheet_to = wb1.worksheets[0]
copy_styles(sheet_from, sheet_to)
#wb.close()
tab = Table(displayName = "Table1", ref = "A1:" + get_column_letter(wb1.worksheets[0].max_column) + str(wb1.worksheets[0].max_row) )
style = TableStyleInfo(name="TableStyleMedium2", showFirstColumn=False, showLastColumn=False, showRowStripes=True, showColumnStripes=False)
tab.tableStyleInfo = style
wb1.worksheets[0].add_table(tab)
#wb1.worksheets[0].parent.save(f"{filename}.xlsx")
wb1.save("test_files/" + f"{filename}.xlsx") # issue is here
wb1.close()
print("Total number of customers to be emailed is ", i)
Though the code works fine, the issue is in the below line I guess
wb1.save("test_files/" + f"{filename}.xlsx") # issue is here
This creates two copies of files.. One in the current folder as jupyter notebook file and other one inside the test_files folder.
For ex: I see two files called test1.xlsx one in the current folder and one inside the test_files folder (path is test_files/test1.xlsx)
How can I avoid this?
I expect my output to generate/save only 1 file for each customer inside the test_files folder?

The issue is happening because you are referencing 2 different file names one with the prefix "test_files/" and once without it. Best way to handle it will be to define file name as follows
dir_filename = "test_files/" + f"{filename}.xlsx"
and then reference it in the following places
with pd.ExcelWriter(f"{filename}.xlsx", engine='xlsxwriter') as writer:
v.to_excel(writer,columns=col_list,index=False)
##
wb1 = load_workbook(filename = f"{filename}.xlsx")
##
wb1.save("test_files/" + f"{filename}.xlsx")
Hope it helps

Open multiple Excel files to separate Pandas dataframes

Brand new to Python and could use some help importing multiple Excel files to separate Pandas dataframes. I have successfully implemented the following code, but of course it imports everything into one frame. I would like to import them into df1, df2, df3, df4, df5, etc.
Anything helps, thank you!
import pandas as pd
import glob
def get_files():
directory_path = input('Enter directory path: ')
filenames = glob.glob(directory_path + '/*.xlsx')
number_of_files = len(filenames)
df = pd.DataFrame()
for f in filenames:
data = pd.read_excel(f, 'Sheet1')
df = df.append(data)
print(df)
print(number_of_files)
get_files()

The easiest way to do that is to use a list. Each element of the list is a dataframe
def get_files():
directory_path = input('Enter directory path: ')
filenames = glob.glob(directory_path + '/*.xlsx')
number_of_files = len(filenames)
df_list = []
for f in filenames:
data = pd.read_excel(f, 'Sheet1')
df_list.append(data)
print(df_list)
print(number_of_files)
return df_list
get_files()
You can then access your dataframes with df_list[0], df_list[1]...

Just as another option by Jezrael answer here https://stackoverflow.com/a/52074347/13160821 but modified for your code.
from os.path import basename
def get_files():
directory_path = input('Enter directory path: ')
filenames = glob.glob(directory_path + '/*.xlsx')
number_of_files = len(filenames)
df_list = {basename(f) : pd.read_excel(f, 'Sheet1') for f in filenames}
print(number_of_files)
return df_list
get_files()
Which can then be accessed by the filename eg. dfs['file_name1.xlsx'] or dfs['some_file.xlsx']. You can also do things like splitext to remove the xlsx from the key or use just part of the filename.

Loop through multiple CSV files and run a script

I have a script which pulls in data from a csv file, does some manipulations to it and creates an output excel file. But, its a tedious process as I need to do it for multiple files.
Question: Is there a way for me to run this script across multiple csv files together and create a separate excel file output for each input file?
I'm not sure what to try out here. I've read that I need to use a module called glob but I'm not sure how to go about it.
This script works for a single file:
# Import libraries
import pandas as pd
import xlsxwriter
# Set system paths
INPUT_PATH = 'SystemPath//Downloads//'
INPUT_FILE = 'rawData.csv'
OUTPUT_PATH = 'SystemPath//Downloads//Output//'
OUTPUT_FILE = 'rawDataOutput.xlsx'
# Get data
df = pd.read_csv(INPUT_PATH + INPUT_FILE)
# Clean data
cleanedData = df[['State','Campaigns','Type','Start date','Impressions','Clicks','Spend(INR)',
'Orders','Sales(INR)','NTB orders','NTB sales']]
cleanedData = cleanedData[cleanedData['Impressions'] != 0].sort_values('Impressions',
ascending= False).reset_index()
cleanedData.loc['Total'] = cleanedData.select_dtypes(pd.np.number).sum()
cleanedData['CTR(%)'] = (cleanedData['Clicks'] /
cleanedData['Impressions']).astype(float).map("{:.2%}".format)
cleanedData['CPC(INR)'] = (cleanedData['Spend(INR)'] / cleanedData['Clicks'])
cleanedData['ACOS(%)'] = (cleanedData['Spend(INR)'] /
cleanedData['Sales(INR)']).astype(float).map("{:.2%}".format)
cleanedData['% of orders NTB'] = (cleanedData['NTB orders'] /
cleanedData['Orders']).astype(float).map("{:.2%}".format)
cleanedData['% of sales NTB'] = (cleanedData['NTB sales'] /
cleanedData['Sales(INR)']).astype(float).map("{:.2%}".format)
cleanedData = cleanedData[['State','Campaigns','Type','Start date','Impressions','Clicks','CTR(%)',
'Spend(INR)','CPC(INR)','Orders','Sales(INR)','ACOS(%)',
'NTB orders','% of orders NTB','NTB sales','% of sales NTB']]
# Create summary
summaryData = cleanedData.groupby(['Type'])[['Spend(INR)','Sales(INR)']].agg('sum')
summaryData.loc['Overall Snapshot'] = summaryData.select_dtypes(pd.np.number).sum()
summaryData['ROI'] = summaryData['Sales(INR)'] / summaryData['Spend(INR)']
# Push to excel
writer = pd.ExcelWriter(OUTPUT_PATH + OUTPUT_FILE, engine='xlsxwriter')
summaryData.to_excel(writer, sheet_name='Summary')
cleanedData.to_excel(writer, sheet_name='Overall Report')
writer.save()
I've never tried anything like this before and I would appreciate your help trying to figure this out

You can use Python's glob.glob() to get all of the CSV files from a given folder. For each filename that is returned, you could derive a suitable output filename. The file processing could be moved into a function as follows:
# Import libraries
import pandas as pd
import xlsxwriter
import glob
import os
def process_csv(input_filename, output_filename):
# Get data
df = pd.read_csv(input_filename)
# Clean data
cleanedData = df[['State','Campaigns','Type','Start date','Impressions','Clicks','Spend(INR)',
'Orders','Sales(INR)','NTB orders','NTB sales']]
cleanedData = cleanedData[cleanedData['Impressions'] != 0].sort_values('Impressions',
ascending= False).reset_index()
cleanedData.loc['Total'] = cleanedData.select_dtypes(pd.np.number).sum()
cleanedData['CTR(%)'] = (cleanedData['Clicks'] /
cleanedData['Impressions']).astype(float).map("{:.2%}".format)
cleanedData['CPC(INR)'] = (cleanedData['Spend(INR)'] / cleanedData['Clicks'])
cleanedData['ACOS(%)'] = (cleanedData['Spend(INR)'] /
cleanedData['Sales(INR)']).astype(float).map("{:.2%}".format)
cleanedData['% of orders NTB'] = (cleanedData['NTB orders'] /
cleanedData['Orders']).astype(float).map("{:.2%}".format)
cleanedData['% of sales NTB'] = (cleanedData['NTB sales'] /
cleanedData['Sales(INR)']).astype(float).map("{:.2%}".format)
cleanedData = cleanedData[['State','Campaigns','Type','Start date','Impressions','Clicks','CTR(%)',
'Spend(INR)','CPC(INR)','Orders','Sales(INR)','ACOS(%)',
'NTB orders','% of orders NTB','NTB sales','% of sales NTB']]
# Create summary
summaryData = cleanedData.groupby(['Type'])[['Spend(INR)','Sales(INR)']].agg('sum')
summaryData.loc['Overall Snapshot'] = summaryData.select_dtypes(pd.np.number).sum()
summaryData['ROI'] = summaryData['Sales(INR)'] / summaryData['Spend(INR)']
# Push to excel
writer = pd.ExcelWriter(output_filename, engine='xlsxwriter')
summaryData.to_excel(writer, sheet_name='Summary')
cleanedData.to_excel(writer, sheet_name='Overall Report')
writer.save()
# Set system paths
INPUT_PATH = 'SystemPath//Downloads//'
OUTPUT_PATH = 'SystemPath//Downloads//Output//'
for csv_filename in glob.glob(os.path.join(INPUT_PATH, "*.csv")):
name, ext = os.path.splitext(os.path.basename(csv_filename))
# Create an output filename based on the input filename
output_filename = os.path.join(OUTPUT_PATH, f"{name}Output.xlsx")
process_csv(csv_filename, output_filename)
os.path.join() can be used as a safer way to join file paths together.

Something like:
import os
import glob
import pandas as pd
os.chdir(r'path\to\folder') #changes folder path to working dir
filelist=glob.glob('*.csv') #creates a list of all csv files
for file in filelist: #loops through the files
df=pd.read_csv(file,...)
#Do something and create a final_df
final_df.to_excel(file[:-4],+'_output.xlsx',index=False) #excel with same name+ouput

you can run this scrip inside a for loop:
for file in os.listdir(INPUT_PATH):
if file.endswith('.csv') or file.endswith('.CSV'):
INPUT_FILE = INPUT_PATH + '/' + file
OUTPUT_FILE = INPUT_PATH + '/Outputs/' + file.[:-4] + 'xlsx'

try this:
import glob
files = glob.glob(INPUT_PATH + "*.csv")
for file in files:
# Get data
df = pd.read_csv(file)
# Clean data
#your cleaning code
# Push to excel
writer = pd.ExcelWriter(OUTPUT_PATH + file.split("/")[-1].replace(".csv","_OUTPUT.xlxs", engine='xlsxwriter')

Taking Same Worksheet from a Folder of xlsm Files with Python

I'm new to pandas/python and Ive come up with the following code to extract data from a specific part of a worksheet.
import openpyxl as xl
import pandas as pd
rows_with_data = [34,37,38,39,44,45,46,47,48,49, 50,54,55,57,58,59,60,62,63,64,65,66,70,71,72,76,77, 78,79,80,81,82,83,84,88,89,90,91,92]
path = r'XXX'
xpath = input('XXX')
file = r'**.xlsm'
xfile = input('Change file name, current is ' + file + ' :')
sheetname = r'Summary'
wb = xl.load_workbook(filename = xpath + '\\' +file, data_only = True)
sheet = wb.get_sheet_by_name(sheetname)
rows = len(rows_with_data)
line_items = []
for i in range(rows) :
line_items.append(sheet.cell(row = rows_with_data[i], column = 13).value)
period = []
for col in range(17,35):
period.append(sheet.cell(row = 20, column = col).value)
print(line_items)
vals = []
x = []
for i in range(rows):
if i != 0:
vals.append(x)
x = []
for col in range(17,35):
x.append(sheet.cell(row = rows_with_data[i], column = col).value)
vals.append(x)
all_values = {}
all_values['Period'] = period
for i in range(rows):
print(line_items[i])
all_values[line_items[i]] = vals[i]
print(all_values)
period_review = input('Enter a period (i.e. 2002): ')
item = input('Enter a period (i.e. XXX): ')
time = period.index(period_review)
display_item = str(all_values[item][time])
print(item + ' for ' + period_review + " is " + display_item)
Summary_Dataframe = pd.DataFrame(all_values)
writer = pd.ExcelWriter(xpath + '\\' + 'values.xlsx')
Summary_Dataframe.to_excel(writer,'Sheet1')
writer.save()
writer.close()
I have the same worksheet (summary results) across a library of 60 xlsm files and I'm having a hard time figuring out how to iterate this across the entire folder of files. I also want change this from extracting specific rows to taking the entire "Summary" worksheet, pasting it to the new file and naming the worksheet by its filename ("Experiment_A") when pasted to the new excel file. Any advice?

I was having hard time to read your code to understand that what you want to do finally. So it is just an advice not a solution. You can iterate through all files in the folder using os then read the files in to one dataframe then save the single big data frame in to csv. I usually avoid excel but I guess you need the excel conversion. In the example below I have read all txt file from a directory put them in to dataframe list then store the big data frame as json. You can also store it as excel/csv.
import os
import pandas as pd
def process_data():
# input file path in 2 part in case it is very long
input_path_1 = r'\\path\to\the\folder'
input_path_2 = r'\second\part\of\the\path'
# adding the all file path
file_path = input_path_1 + input_path_2
# listing all file in the file folder
file_list = os.listdir(os.path.join(file_path))
# selecting only the .txt files in to a list object
file_list = [file_name for file_name in file_list if '.txt' in file_name]
# selecting the fields we need
field_names = ['country', 'ticket_id']
# defining a list to put all the datafremes in one list
pd_list = []
inserted_files = []
# looping over txt files and storing in to database
for file_name in file_list:
# creating the file path to read the file
file_path_ = file_path + '\\' + file_name
df_ = pd.read_csv(os.path.join(file_path_), sep='\t', usecols=field_names)
# converting the datetime to date
# few internal data transformation example before writting
df_['sent_date'] = pd.to_datetime(df_['sent_date'])
df_['sent_date'] = df_['sent_date'].values.astype('datetime64[M]')
# adding each dataframe to the list
pd_list.append(df_)
# adding file name to the inserted list to print later
inserted_files.append(file_name)
print(inserted_files)
# sql like union all dataframes and create a single data source
df_ = pd.concat(pd_list)
output_path_1 = r'\\path\to\output'
output_path_2 = r'\path\to\output'
output_path = output_path_1 + output_path_2
# put the file name
file_name = 'xyz.json'
# adding the day the file processed
df_['etl_run_time'] = pd.to_datetime('today').strftime('%Y-%m-%d')
# write file to json
df_.to_json(os.path.join(output_path, file_name), orient='records')
return print('Data Stored as json successfully')
process_data()

Python , get duplicates in 1st column of all csv files in a directory

import pandas as pd
import glob
dataset = pd.read_csv('masterfeedproduction-EURNA_2016-06-27.csv',sep =
',',delimiter = None) # select 1 file in the directory
datasets_cols = ['transactionID','gvkey','companyName']
df= dataset.transactionID
df.shape
df.loc[df.duplicated()]
returns the duplicates in the selected file. displays row number and transactionID. so this is correct.
target_directory = r'C:\Users\nikol\Downloads\fullDailyDeltas\fullDailyDeltas'
file_list = glob.glob(target_directory + "/*.csv")
df_result = df.loc[df.duplicated()]
for file in file_list:
return(df_result)
here I am stuck.
target_directory = r'C:\Users\nikol\Downloads\fullDailyDeltas\fullDailyDeltas'
file_list = glob.glob(target_directory + "/*.csv")
for file in file_list:
dataset = pd.read_csv(file)
df = dataset.transactionID
duplicated = df.loc[df.duplicated()]
if duplicated.empty == False:
print(file)
print(duplicated)

Have a look at the glob module.
import pandas as pd
import glob
def your_function(file):
# put your df processing logic here
return df_result
Step 1 - Create list of files in directory
target_directory = r'Path/to/your/dir'
file_list = glob.glob(target_directory + "/*.csv")
# Include slash or it will search in the wrong directory!!
Step 2 - Loop through files in list
for file in file_list: # Loop files
df_result = your_function(file) # Put your logic into a separate function
new_filename = file.replace('.csv', '_processed.csv')
df_result.to_csv(new_filename, index = False)
Comment
In case you would have included your code showing your attempts to do this yourself, your question was answered within seconds.