Python script for automated reporting using AI with financial data on different reporting periods

automated_reporting_financial_periods.py

import pandas as pd
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
import seaborn as sns

# Example Monthly Balance Sheet and Income Statement Data
# Replace with your actual data

balance_sheet_data = {
    'Month': ['2020-01', '2020-02', '2020-03', '2020-04', '2020-05', '2020-06'],
    'Assets': [100000, 105000, 110000, 115000, 120000, 125000],
    'Liabilities': [50000, 52000, 54000, 56000, 58000, 60000],
    'Equity': [50000, 53000, 56000, 59000, 62000, 65000]
}

income_statement_data = {
    'Month': ['2020-01', '2020-02', '2020-03', '2020-04', '2020-05', '2020-06'],
    'Revenue': [20000, 21000, 22000, 23000, 24000, 25000],
    'Expenses': [15000, 15500, 16000, 16500, 17000, 17500],
    'Net Income': [5000, 5500, 6000, 6500, 7000, 7500]
}

# Convert to DataFrame
balance_sheet = pd.DataFrame(balance_sheet_data)
income_statement = pd.DataFrame(income_statement_data)

# Merge DataFrames on Month
financial_data = pd.merge(balance_sheet, income_statement, on='Month')

# Scale data
scaler = StandardScaler()
financial_data_scaled = scaler.fit_transform(financial_data.iloc[:, 1:])

# Train model to predict next month's Net Income based on previous financial data
model = LinearRegression()
model.fit(financial_data_scaled[:, :-1], financial_data_scaled[:, -1])

# Make predictions
predictions = model.predict(financial_data_scaled[:, :-1])

# Plot results
plt.figure(figsize=(10, 6))
plt.plot(financial_data['Month'], financial_data_scaled[:, -1], label='Actual')
plt.plot(financial_data['Month'], predictions, label='Predicted')
plt.title('Actual vs Predicted Net Income')
plt.legend()
plt.show()

# Save results to CSV
results = pd.DataFrame({'Month': financial_data['Month'], 'Actual': financial_data_scaled[:, -1], 'Predicted': predictions})
results.to_csv('results.csv', index=False)