I have a excel file with some calculated columns.
for example, I have some data in columns 'a' and column 'b' is calculated using values in column 'a'.
i need to append new data to column 'a' and calculate column 'b' and save the file.
import pandas as pd
df = pd.DataFrame({'a':[1,2,3],'b':["=a2","=a3","=a4"]})
df.to_excel('test.xlsx',index=False)
when i try to read the file using pandas read excel it reads the column 'b' as NaN.
df = pd.read_excel(r'test.xlsx')
how do i achieve this. may be if i can read the file as string and append the formulas as string. when i open the file in excel the excel will do the calculations?
Use OpenPyXL to load the excel worksheet instead of directly with pandas
from openpyxl import load_workbook
import pandas as pd
wb = load_workbook(filename = 'test.xlsx')
sheet_name = wb.get_sheet_names()[0]
ws = wb[sheet_name]
df = pd.DataFrame(ws.values)
import pandas as pd
import xlsxwriter
name = '123.xlsx'
writer = pd.ExcelWriter(name,engine='xlsxwriter')
pd.DataFrame({}).to_excel(writer,sheet_name='Sheet1')
workbook = writer.book
worksheet = writer.sheets['Sheet1']
worksheet.write('A1',1)
worksheet.write('A2','=A1')
writer.save()
Related
Need help please.
I have a dataframe that reads rows from Excel and appends to Dataframe if certain columns exist.
I need to add an additional Dataframe if the columns don't exist in a sheet and append filename and sheetname and write all the file names and sheet names for those sheets to an excel file. Also I want the values to be unique.
I tried adding to dfErrorList but it only showed the last sheetname and filename and repeated itself many times in the output excel file
from xlsxwriter import Workbook
import pandas as pd
import openpyxl
import glob
import os
path = 'filestoimport/*.xlsx'
list_of_dfs = []
list_of_dferror = []
dfErrorList = pd.DataFrame() #create empty df
for filepath in glob.glob(path):
xl = pd.ExcelFile(filepath)
# Define an empty list to store individual DataFrames
for sheet_name in xl.sheet_names:
df = pd.read_excel(filepath, sheet_name=sheet_name)
df['sheetname'] = sheet_name
file_name = os.path.basename(filepath)
df['sourcefilename'] = file_name
if "Project ID" in df.columns and "Status" in df.columns:
print('')
*else:
dfErrorList['sheetname'] = df['sheetname'] # adds `sheet_name` into the column
dfErrorList['sourcefilename'] = df['sourcefilename']
continue
list_of_dferror.append((dfErrorList))
df['Status'].fillna('', inplace=True)
df['Added by'].fillna('', inplace=True)
list_of_dfs.append(df)
# # Combine all DataFrames into one
data = pd.concat(list_of_dfs, ignore_index=True)
dataErrors = pd.concat(list_of_dferror, ignore_index=True)
dataErrors.to_excel(r'error.xlsx', index=False)
# data.to_excel("total_countries.xlsx", index=None)
import pandas as pd
import os
import pandas as pd
from pandas import ExcelWriter
from pandas import ExcelFile
path=os.getcwd()
files=os.listdir(path)
for i in range(len(files)):
filename = files[i]
filepath=os.path.join(path,filename)
print(filepath)
df=pd.ExcelFile(filepath) # read sheet name
sheet = df.sheet_names
print(sheet)
df=pd.read_excel(filepath, sheet_name=sheet,skiprows = 5, nrows=15, usecols = 'E:L')
print(df)
when I click on the number it show 6 digits in the header but I want to change it into the excel also
import openpyxl
wb = openpyxl.load_workbook('ds.xlsx')
ws = wb.active
for row in ws.iter_rows():
for cell in row:
# only relevant column and without header
if cell.column_letter == 'A' and cell.row > 1: # put the cell number from where to where you want to check
ws[cell.coordinate].number_format = '0.0000000' # it will change the number format
wb.save('ds2.xlsx')
If the ninth column doesn't contains the name of city ISTANBUL, then I need to be able to delete
the entire row. i wrote the code it works but it doesn't delete row.
from openpyxl import Workbook, load_workbook
from openpyxl.utils import get_column_letter
wb = load_workbook('deneme.xlsx')
ws = wb.active
for row in range(1, 3313):
for col in [9]:
char = get_column_letter(col)
if ws[char + str(row)].value is not 'İSTANBUL':
ws.delete_rows(row)
wb.save('deneme.xlsx')
Here it is solution i just found.
import pandas as pd
df = pd.read_excel('staji.xlsx') #here you can put your file path
filt = (df['ŞEHİR'] == 'İSTANBUL') # put your condition ŞEHİR=column name.
df[filt].to_excel('den1.xlsx')
I am trying to query based on different criteria, and then create individual tabs in Excel to store the query results.
For example, I want to query all the results that match criteria A, and write the result to an Excel tab named "A". The query result is stored in the panda data frame format.
My problem is, when I want to perform 4 different queries based on criteria "A", "B", "C", "D", the final Excel file only contains one tab, which corresponds to the last criteria in the list. It seems that all the previous tabs are over-written.
Here is sample code where I replace the SQL query part with a pre-set dataframe and the tab name is set to 0, 1, 2, 3 ... instead of the default Sheet1, Sheet2... in Excel.
import pandas as pd
import xlsxwriter
import datetime
def GCF_Refresh(fileCreatePath, inputName):
currentDT = str(datetime.datetime.now())
currentDT = currentDT[0:10]
loadExcelName = currentDT + '_' + inputName + '_Load_File'
fileCreatePath = fileCreatePath +'\\' + loadExcelName+'.xlsx'
wb = xlsxwriter.Workbook(fileCreatePath)
data = [['tom'], ['nick'], ['juli']]
# Create the pandas DataFrame
df = pd.DataFrame(data, columns=['Name'])
writer = pd.ExcelWriter(fileCreatePath, engine='xlsxwriter')
for iCount in range(5):
#worksheet = writer.sheets[str(iCount)]
#worksheet.write(0, 0, 'Name')
df['Name'].to_excel(fileCreatePath, sheet_name=str(iCount), startcol=0, startrow=1, header=None, index=False)
writer.save()
writer.close()
# Change the file path here to store on your local computer
GCF_Refresh("H:\\", "Bulk_Load")
My goal for this sample code is to have 5 tabs named, 0, 1, 2, 3, 4 and each tab has 'tom', 'nick' and 'juli' printed to it. Right now, I just have one tab (named 4), which is the last tab among all the tabs I expected.
There are a number of errors in the code:
The xlsx file is created using XlsxWriter directly and then overwritten by creating it Again in Pandas.
The to_excel() method takes a reference to the writer object not the file path.
The save() and close() are the same thing and shouldn't be in the
loop.
Here is a simplified version of your code with these issues fixes:
import pandas as pd
import xlsxwriter
fileCreatePath = 'test.xlsx'
data = [['tom'], ['nick'], ['juli']]
# Create the pandas DataFrame
df = pd.DataFrame(data, columns=['Name'])
writer = pd.ExcelWriter(fileCreatePath, engine='xlsxwriter')
for iCount in range(5):
df['Name'].to_excel(writer,
sheet_name=str(iCount),
startcol=0,
startrow=1,
header=None,
index=False)
writer.save()
Output:
See Working with Python Pandas and XlsxWriter in the XlsxWriter docs for some details about getting Pandas and XlsxWriter working together.
I am trying to import certain columns of data from several different sheets inside of a workbook. However, while appending it only seems to append 'q2 survey' to a new workbook. How do I get this to append properly?
import sys, os
import pandas as pd
import xlrd
import xlwt
b = ['q1 survey', 'q2 survey','q3 survey'] #Sheet Names
df_t = pd.DataFrame(columns=["Month","Date", "Year"]) #column Name
xls = "path_to_file/R.xls"
sheet=[]
df_b=pd.DataFrame()
pd.read_excel(xls,sheet)
for sheet in b:
df=pd.read_excel(xls,sheet)
df.rename(columns=lambda x: x.strip().upper(), inplace=True)
bill=df_b.append(df[df_t])
bill.to_excel('Survey.xlsx', index=False)
I think if you do:
b = ['q1 survey', 'q2 survey','q3 survey'] #Sheet Names
list_col = ["Month","Date", "Year"] #column Name
xls = "path_to_file/R.xls"
#create the empty df named bill to append after
bill= pd.DataFrame(columns = list_col)
for sheet in b:
# read the sheet
df=pd.read_excel(xls,sheet)
df.rename(columns=lambda x: x.strip().upper(), inplace=True)
# need to assign bill again
bill=bill.append(df[list_col])
# to excel
bill.to_excel('Survey.xlsx', index=False)
it should work and correct the errors in your code, but you can do a bit differently using pd.concat:
list_sheet = ['q1 survey', 'q2 survey','q3 survey'] #Sheet Names
list_col = ["Month","Date", "Year"] #column Name
# read once the xls file and then access the sheet in the loop, should be faster
xls_file = pd.ExcelFile("path_to_file/R.xls")
#create a list to append the df
list_df_to_concat = []
for sheet in list_sheet :
# read the sheet
df= pd.read_excel(xls_file, sheet)
df.rename(columns=lambda x: x.strip().upper(), inplace=True)
# append the df to the list
list_df_to_concat.append(df[list_col])
# to excel
pd.concat(list_df_to_concat).to_excel('Survey.xlsx', index=False)