In [2]: import pandas as pd
import os
# Define the file path
file_path = 'C:/Users/mawul/OneDrive/Documents/financial statements.csv'
# Check if the file exists
if os.path.exists(file_path):
# Load the CSV file into a DataFrame
df = pd.read_csv(file_path)
# Display the first few rows of the DataFrame to verify
display(df.head())
else:
print(f"File not found: {file_path}. Please check the file path and try again.")
COMPANY (ALL AMMOUNT ARE IN MILLIONS) YEAR 3 YEAR 2 YEAR1
0 MICROSOFT 2023.0 2022.0 2021.0
1 TOTAL REVENUE 211915.0 198270.0 168088.0
2 NET INCOME 72361.0 72738.0 61271.0
3 TOTAL ASSET 411976.0 364840.0 333799.0
4 TOTAL LIABILITIES 205753.0 198298.0 191791.0
In [4]: # Define the financial data
data = {
'Microsoft': {
'2023': {'Total Revenue': 211915, 'Net Income': 72361, 'Total Asset': 411976, 'Total Liabilities': 205753, 'Cash Flow from Operating Activities': 87585},
'2022': {'Total Revenue': 198270, 'Net Income': 72738, 'Total Asset': 364840, 'Total Liabilities': 198298, 'Cash Flow from Operating Activities': 89035},
'2021': {'Total Revenue': 168088, 'Net Income': 61271, 'Total Asset': 333799, 'Total Liabilities': 191791, 'Cash Flow from Operating Activities': 76740}
},
'Tesla': {
'2023': {'Total Revenue': 96773, 'Net Income': 14974, 'Total Asset': 106618, 'Total Liabilities': 43009, 'Cash Flow from Operating Activities': 13256},
'2022': {'Total Revenue': 81462, 'Net Income': 12587, 'Total Asset': 82338, 'Total Liabilities': 36440, 'Cash Flow from Operating Activities': 14724},
'2021': {'Total Revenue': 53823, 'Net Income': 5644, 'Total Asset': 62131, 'Total Liabilities': 30548, 'Cash Flow from Operating Activities': 11497}
},
'Apple': {
'2023': {'Total Revenue': 383285, 'Net Income': 96995, 'Total Asset': 352583, 'Total Liabilities': 290437, 'Cash Flow from Operating Activities': 110543},
'2022': {'Total Revenue': 394328, 'Net Income': 99803, 'Total Asset': 352755, 'Total Liabilities': 302083, 'Cash Flow from Operating Activities': 122151},
'2021': {'Total Revenue': 365817, 'Net Income': 94680, 'Total Asset': 351002, 'Total Liabilities': 287912, 'Cash Flow from Operating Activities': 104038}
}
}
# Define the responses
responses = {
"What is the total revenue for Microsoft in 2023?": f"The total revenue for Microsoft in 2023 is {data['Microsoft']['2023']['Total Revenue']} million.",
"How has net income changed for Tesla over the last year?": f"The net income for Tesla in 2023 is {data['Tesla']['2023']['Net Income']} million, compared to {data['Tesla']['2022']['Net Income']} million in 2022.",
"What are the current assets for Apple in 2022?": f"The current assets for Apple in 2022 are {data['Apple']['2022']['Total Asset']} million.",
"What is the debt-to-equity ratio for Microsoft in 2021?": f"The debt-to-equity ratio for Microsoft in 2021 is {data['Microsoft']['2021']['Total Liabilities'] / (data['Microsoft']['2021']['Total Asset'] - data['Microsoft']['2021']['To
"How much is the net profit margin for Tesla in 2023?": f"The net profit margin for Tesla in 2023 is {(data['Tesla']['2023']['Net Income'] / data['Tesla']['2023']['Total Revenue']) * 100:.2f}%."
}
In [10]: # Function to get response based on user query
def get_response(query):
return responses.get(query, "Sorry, I don't understand that question.")
# Function to simulate chatbot interaction in Jupyter Notebook
def chatbot(query):
return get_response(query)
# Example queries to test the chatbot
queries = [
"What is the total revenue for Microsoft in 2023?",
"How has net income changed for Tesla over the last year?",
"What are the current assets for Apple in 2022?",
"What is the debt-to-equity ratio for Microsoft in 2021?",
"How much is the net profit margin for Tesla in 2023?"
]
# Test the chatbot with example queries
for query in queries:
print(f"Query: {query}")
print(f"Response: {chatbot(query)}\n")
Query: What is the total revenue for Microsoft in 2023?
Response: The total revenue for Microsoft in 2023 is 211915 million.
Query: How has net income changed for Tesla over the last year?
Response: The net income for Tesla in 2023 is 14974 million, compared to 12587 million in 2022.
Query: What are the current assets for Apple in 2022?
Response: The current assets for Apple in 2022 are 352755 million.
Query: What is the debt-to-equity ratio for Microsoft in 2021?
Response: The debt-to-equity ratio for Microsoft in 2021 is 1.35.
Query: How much is the net profit margin for Tesla in 2023?
Response: The net profit margin for Tesla in 2023 is 15.47%.
Financial Chatbot Documentation
Overview
This chatbot is designed to answer predefined financial queries based on the financial statements of Microsoft, Tesla, and Apple for the years 2021, 2022, and 2023. The chatbot uses a simple if-else logic to match user queries with
predefined responses.
How It Works
Data Loading: The financial data is loaded from a CSV file into a pandas DataFrame.
Predefined Queries: The chatbot can respond to specific financial queries related to total revenue, net income changes, current assets, debt-to-equity ratio, and net profit margin.
User Interaction: Users can type their queries, and the chatbot will provide the corresponding response. If the query is not recognized, the chatbot will inform the user.
Predefined Queries
"What is the total revenue for Microsoft in 2023?"
"How has net income changed for Tesla over the last year?"
"What are the current assets for Apple in 2022?"
"What is the debt-to-equity ratio for Microsoft in 2021?"
"How much is the net profit margin for Tesla in 2023?"
Limitations
Limited Query Set: The chatbot can only respond to the predefined queries listed above. It does not handle other types of financial questions.
Static Data: The responses are based on static data from the provided financial statements. Any updates to the financial data will require manual updates to the chatbot’s responses.
Simple Logic: The chatbot uses basic if-else logic, which may not be suitable for more complex interactions or dynamic data analysis.
In [ ]:
