import pandas as pd

# Specify the path to your CSV file
csv_file_path = 'your_data.csv'

# Read the CSV file into a Pandas DataFrame
try:
    df = pd.read_csv(csv_file_path)
except FileNotFoundError:
    print(f"File '{csv_file_path}' not found.")
    df = None

# Check if the DataFrame was successfully loaded
if df is not None:
    # Display the first few rows of the DataFrame to inspect the data
    print("Sample data from CSV:")
    print(df.head())

    # You can now manipulate and work with the 'df' DataFrame for further processing
else:
    print("Data extraction failed. Check the file path.")

import pandas as pd

# Sample data in a Pandas DataFrame
data = {
    'date': ['2023-01-01', '2023-01-05', '2023-01-10'],
    'description': ['Purchase', 'Withdrawal', 'Deposit'],
    'amount': [100.00, -50.00, 200.00]
}

df = pd.DataFrame(data)

# Transformations:
# 1. Convert the 'date' column to datetime format
df['date'] = pd.to_datetime(df['date'])

# 2. Convert negative amounts to positive (for consistency)
df['amount'] = df['amount'].abs()

# 3. Create a new 'transaction_type' column based on amount
df['transaction_type'] = df['amount'].apply(lambda x: 'Credit' if x > 0 else 'Debit')

# 4. Group by 'date' and calculate the daily balance
df['daily_balance'] = df.groupby('date')['amount'].cumsum()

# Display the transformed DataFrame
print("Transformed Data:")
print(df)

# Sample transactions lists
transactions1 = [
    {'date': '2023-01-01', 'description': 'Purchase', 'amount': 100.00},
    {'date': '2023-01-05', 'description': 'Withdrawal', 'amount': 50.00},
    {'date': '2023-01-10', 'description': 'Deposit', 'amount': 200.00},
]

transactions2 = [
    {'date': '2023-01-01', 'description': 'Purchase', 'amount': 100.00},
    {'date': '2023-01-06', 'description': 'Withdrawal', 'amount': 30.00},
    {'date': '2023-01-10', 'description': 'Deposit', 'amount': 200.00},
]

# Create sets of unique transaction identifiers (e.g., date and description)
set1 = {(t['date'], t['description']) for t in transactions1}
set2 = {(t['date'], t['description']) for t in transactions2}

# Find common transactions between the two lists
common_transactions = set1.intersection(set2)

# Find discrepancies by comparing transaction amounts
discrepancies = []
for date, description in common_transactions:
    amount1 = sum(t['amount'] for t in transactions1 if (t['date'], t['description']) == (date, description))
    amount2 = sum(t['amount'] for t in transactions2 if (t['date'], t['description']) == (date, description))
    if amount1 != amount2:
        discrepancies.append((date, description, amount1, amount2))

# Display the common transactions and discrepancies
print("Common Transactions:")
for date, description in common_transactions:
    print(f"{date} - {description}")

print("\nDiscrepancies:")
for date, description, amount1, amount2 in discrepancies:
    print(f"{date} - {description}: Amount in List 1 = {amount1}, Amount in List 2 = {amount2}")

import matplotlib.pyplot as plt

# ... (Previous code for matching and finding discrepancies) ...

# Display the common transactions and discrepancies
print("Common Transactions:")
for date, description in common_transactions:
    print(f"{date} - {description}")

print("\nDiscrepancies:")
for date, description, amount1, amount2 in discrepancies:
    print(f"{date} - {description}: Amount in List 1 = {amount1}, Amount in List 2 = {amount2}")

# Create a bar chart to visualize discrepancies
dates = [f"{date} - {description}" for date, description, _, _ in discrepancies]
amounts1 = [amount1 for _, _, amount1, _ in discrepancies]
amounts2 = [amount2 for _, _, _, amount2 in discrepancies]

plt.figure(figsize=(10, 6))
plt.barh(dates, amounts1, label='Amount in List 1', color='b', alpha=0.6)
plt.barh(dates, amounts2, label='Amount in List 2', color='r', alpha=0.6, left=amounts1)
plt.xlabel('Amount')
plt.title('Discrepancies in Transactions')
plt.legend(loc='upper right')
plt.tight_layout()

# Show the bar chart
plt.show()