Hello-world

Learning Github I am learning about branches and commit import pandas as pd

tax_keywords = ['HST', 'GST', 'QST']

def replace_tax_descriptions(group): # Sort transactions by amount in descending order sorted_group = group.sort_values(by='Amount', ascending=False)

# Filter for non-tax transactions
non_tax_rows = sorted_group[~sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
non_tax_descriptions = non_tax_rows['Description'].tolist()

# Only proceed if there are non-tax descriptions
if non_tax_descriptions:
    # Identify tax rows
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        # Replace tax description with the first available non-tax description and mark as updated
        transactions_df.at[idx, 'Updated Description'] = non_tax_descriptions.pop(0)
        transactions_df.at[idx, 'Update Flag'] = 1
else:
    # If no non-tax descriptions are available, leave as is and do not update
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        transactions_df.at[idx, 'Updated Description'] = transactions_df.at[idx, 'Description']
        transactions_df.at[idx, 'Update Flag'] = 0

Group by Date and Employee Name, then apply the replacement function

grouped = transactions_df.groupby(['Date', 'Employee Name']) grouped.apply(replace_tax_descriptions)

def replace_tax_descriptions(group): print("Processing group:", group) # Debug: print the group being processed sorted_group = group.sort_values(by='Amount', ascending=False) non_tax_rows = sorted_group[~sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)] non_tax_descriptions = non_tax_rows['Description'].tolist()

if non_tax_descriptions:
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        transactions_df.at[idx, 'Updated Description'] = non_tax_descriptions.pop(0)
        transactions_df.at[idx, 'Update Flag'] = 1
else:
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        transactions_df.at[idx, 'Updated Description'] = transactions_df.at[idx, 'Description']
        transactions_df.at[idx, 'Update Flag'] = 0

grouped = transactions_df.groupby(['Date', 'Employee Name']) grouped.apply(replace_tax_descriptions)

..(.??;&@@"""@

import pandas as pd

tax_keywords = ['HST', 'GST', 'QST']

def replace_tax_descriptions(group): # Sort transactions by amount in descending order sorted_group = group.sort_values(by='Amount', ascending=False)

# Filter for non-tax transactions and get their descriptions
non_tax_rows = sorted_group[~sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
non_tax_descriptions = non_tax_rows['Description'].tolist()

# Process each row to replace tax descriptions
tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
for idx, tax_row in tax_rows.iterrows():
    if non_tax_descriptions:
        # Replace tax description with the first available non-tax description and update the flag
        transactions_df.at[idx, 'Updated Description'] = non_tax_descriptions.pop(0)
        transactions_df.at[idx, 'Update Flag'] = 1
    else:
        # If no more non-tax descriptions are available, leave the tax descriptions as is
        transactions_df.at[idx, 'Updated Description'] = transactions_df.at[idx, 'Description']
        transactions_df.at[idx, 'Update Flag'] = 0

Apply the function to each group

grouped = transactions_df.groupby(['Date', 'Employee Name']) grouped.apply(replace_tax_descriptions)

Code

import pandas as pd

tax_keywords = ['HST', 'GST', 'QST']

def replace_tax_descriptions(group):
# Sort transactions by amount in descending order
sorted_group = group.sort_values(by='Amount', ascending=False)

# Filter for non-tax transactions
non_tax_rows = sorted_group[~sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
non_tax_descriptions = non_tax_rows['Description'].tolist()

# Only proceed if there are non-tax descriptions
if non_tax_descriptions:
    # Identify tax rows
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        # Replace tax description with the first available non-tax description and mark as updated
        transactions_df.at[idx, 'Updated Description'] = non_tax_descriptions.pop(0)
        transactions_df.at[idx, 'Update Flag'] = 1
else:
    # If no non-tax descriptions are available, leave as is and do not update
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        transactions_df.at[idx, 'Updated Description'] = transactions_df.at[idx, 'Description']
        transactions_df.at[idx, 'Update Flag'] = 0

Group by Date and Employee Name, then apply the replacement function

grouped = transactions_df.groupby(['Date', 'Employee Name'])
grouped.apply(replace_tax_descriptions)

-//new

import pandas as pd

tax_keywords = ['HST', 'GST', 'QST']

def replace_tax_descriptions(group):
# Sort transactions by amount in descending order
sorted_group = group.sort_values(by='Amount', ascending=False)

# Filter for non-tax transactions and get their descriptions
non_tax_rows = sorted_group[~sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
non_tax_descriptions = non_tax_rows['Description'].tolist()

# Check if there are non-tax descriptions available
if not non_tax_descriptions:
    # If no non-tax descriptions, leave all descriptions as is and set flag to 0
    sorted_group['Updated Description'] = sorted_group['Description']
    sorted_group['Update Flag'] = 0
else:
    # Process each row to replace tax descriptions
    tax_rows = sorted_group[sorted_group['Description'].str.contains('|'.join(tax_keywords), case=False, na=False)]
    for idx, tax_row in tax_rows.iterrows():
        if non_tax_descriptions:
            # Replace tax description with the first available non-tax description and update the flag
            transactions_df.at[idx, 'Updated Description'] = non_tax_descriptions.pop(0)
            transactions_df.at[idx, 'Update Flag'] = 1
        else:
            # If no more non-tax descriptions are available, leave the tax descriptions as is
            transactions_df

leena-verma / hello-world Goto Github PK

hello-world's Introduction

Hello-world

Group by Date and Employee Name, then apply the replacement function

Apply the function to each group

hello-world's People

Contributors

Watchers

hello-world's Issues

Leena

Code

Group by Date and Employee Name, then apply the replacement function

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent