ollama serve
ollama pull mistral
ollama pull llava
ollama run mistral
ollama run llava

Generate a realistic dataset of 1,000 financial transactions for a young professional working in finance, residing in Europe, covering the period from January 2022 to December 2023. Ensure a balanced representation of income and expenses across various categories typical for this demographic. Include the following four columns:

Date: Transaction date (format: YYYY-MM-DD)
Name/Description: A unique and detailed description of each transaction (e.g., "Salary deposit," "Monthly rent payment," "Restaurant dinner with friends")
Expense/Income: Clearly indicate whether the transaction is an expense (e.g., "Expense") or income (e.g., "Income")
Amount(EUR): Transaction amount in Euros

pip install langchain-community
pip install streamlit

import streamlit as st
import pandas as pd
from langchain_community.llms import Ollama

llm = Ollama(model="mistral")
categories = [
    "Salary/Wages", "Investment Income", "Freelance Income", "Business Revenue","Rental Income","Housing", "Utilities","Groceries","Transportation","Insurance","Healthcare","Entertainment","Personal Care","Education","Savings/Investments","Loans/Debt","Taxes","Childcare","Gifts/Donations","Dining Out","Travel","Shopping","Subscriptions","Pet Care", "Home Improvement","Clothing","Tech/Gadgets", "Fitness/Sports",
]
categories_string = ",".join(categories)

def categorize_transactions(transaction_names, llm):
    prompt = f"""Add an appropriate category to the following expenses.
        Remember The category should only be one of the following and  choose only one category from the list that is most relevant based on their primary purpose or nature:   {categories_string}.\n  
        The output format should always be : transaction name - category. For example For example: Spotify #2 - Entertainment, Basic Fit Amsterdam Nld #3 - Fitness/Sports \n 
        Here are the Transactions to be categorized: {transaction_names} \n"""

    print(prompt)
    filtered_response = []
    # retry is the LLM output is not consistent
    while len(filtered_response) < 2:
        response = llm.invoke(prompt).split("\n")
        print(response)
        # Remove items that do not contain "transaction: category" pairs
        filtered_response = [item for item in response if '-' in item]
    print(filtered_response)
    # Put in dataframe
    categories_df = pd.DataFrame({"Transaction vs category": filtered_response})

    size_dif = len(categories_df) - len(transaction_names.split(","))
    if size_dif >= 0:
        categories_df["Transaction"] = transaction_names.split(",") + [None] * size_dif
    else:
        categories_df["Transaction"] = transaction_names.split(",")[:len(categories_df)]
    categories_df["Category"] = categories_df["Transaction vs category"].str.split("-", expand=True)[1]
    return categories_df

def hop(start, stop, step):
    for i in range(start, stop, step):
        yield i
    yield stop

def process_data(df: pd.DataFrame):
    unique_transactions = df["Name/Description"].unique()
    index_list = list(hop(0, len(unique_transactions), 30))

    # Intialise the categories_df_all dataframe
    categories_df_all = pd.DataFrame()

    # Loop through the index_list
    for i in range(0, len(index_list) - 1):
        print(f"Looping: {i}")
        transaction_names = unique_transactions[index_list[i] : index_list[i + 1]]
        transaction_names = ",".join(transaction_names)

        categories_df = categorize_transactions(transaction_names, llm)
        categories_df_all = pd.concat(
            [categories_df_all, categories_df], ignore_index=True
        )

    # futher clean data:
    # Drop NA values
    categories_df_all = categories_df_all.dropna()
    # Remove the numbering eg "1. " from Transaction column
    categories_df_all["Transaction"] = categories_df_all["Transaction"].str.replace(
        r"\d+\.\s?", "", regex=True
    ).str.strip()

    new_df = pd.merge(
        df,
        categories_df_all,
        left_on="Name/Description",
        right_on="Transaction",
        how="left",
    )
    new_df.to_csv(f"data/{uploaded_file.name}_categorized.csv", index=False)
    return new_df

st.title("📝 Load your financial data here")
uploaded_file = st.file_uploader("Upload your financial data", type=("txt", "csv", "pdf"))

if uploaded_file:
    with st.spinner("Processing data..."):
        file_details = {"FileName": uploaded_file.name, "FileType": uploaded_file.type}
        df = pd.read_csv(uploaded_file)
        df = process_data(df)
        st.markdown("Data processed : OK")

import os
import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
from langchain_community.llms import Ollama

llm_llava = Ollama(model="llava")
llm = Ollama(model="mistral")

def financial_analysis(data:pd.DataFrame):
    key_figures = {}
    # Calculate yearly total income and total expenses
    yearly_income = data.loc[data['Expense/Income'] == 'Income'].groupby('Year')['Amount(EUR)'].sum().mean()
    yearly_expenses = data.loc[data['Expense/Income'] == 'Expense'].groupby('Year')['Amount(EUR)'].sum().mean()

    # Identify the top expense categories
    top_expenses = data.loc[data['Expense/Income'] == 'Expense'].groupby('Category')['Amount(EUR)'].sum().sort_values(
        ascending=False)

    # Calculate average monthly income and expenses
    monthly_income = data.loc[data['Expense/Income'] == 'Income'].groupby(data['Date'].dt.to_period('M'))[
        'Amount(EUR)'].sum().mean()
    monthly_expenses = data.loc[data['Expense/Income'] == 'Expense'].groupby(data['Date'].dt.to_period('M'))[
        'Amount(EUR)'].sum().mean()

    # Determine the savings rate
    savings = yearly_income - yearly_expenses
    savings_rate = (savings / yearly_income) * 100 if yearly_income > 0 else 0

    key_figures['Average Annual Income'] = f"€{yearly_income:,.2f}"
    key_figures['Average Annual Expenses'] = f"€{yearly_expenses:,.2f}"
    key_figures['Annual Savings Rate'] = f" {savings_rate:.2f}%"
    key_figures['Top Expense Categories'] = {category: f"€{amount:,.2f}" for category, amount in
                                             top_expenses.head().items()}
    key_figures['Average Monthly Income'] = f"€{monthly_income:,.2f}"
    key_figures['Average Monthly Expenses'] = f"€{monthly_expenses:,.2f}"
    return key_figures

def plot_income_vs_expense_over_time(df):
    # Income vs Expense Over time
    st.markdown("1. Income vs Expense Over time")
    income_expense_summary = (
        df.groupby(["YearMonth", "Expense/Income"])["Amount(EUR)"]
        .sum()
        .unstack()
        .fillna(0)
    )
    income_expense_summary.plot(kind="bar", figsize=(10, 8))
    plt.title("Income vs Expenses Over Time")
    plt.ylabel("Amount (EUR)")
    plt.xlabel("Month")
    plt.savefig("data/income_vs_expense_over_time.png", bbox_inches="tight")
    st.pyplot(plt)


def plot_saving_rate_trend(data: pd.DataFrame):
    st.markdown("2. Monthly Saving Rate Trend")
    monthly_data = data.groupby(['YearMonth', 'Expense/Income'])['Amount(EUR)'].sum().unstack().fillna(0)
    monthly_data['Savings Rate'] = (monthly_data['Income'] - monthly_data['Expense']) / monthly_data['Income'] * 100
    fig, ax = plt.subplots()
    monthly_data['Savings Rate'].plot(ax=ax)
    ax.set_xlabel('Month')
    ax.set_ylabel('Savings Rate (%)')
    plt.savefig("data/saving_rate_over_time.png", bbox_inches="tight")
    st.pyplot(fig)

def plot_income_source_analysis(data: pd.DataFrame):
    st.markdown("3. Income Sources Analysis")

    income_sources = data[data['Expense/Income'] == 'Income'].groupby('Category')['Amount(EUR)'].sum()
    income_sources.plot(kind="pie", figsize=(10, 8), autopct="%1.1f%%", startangle=140)
    plt.title("Income Sources Analysis")
    plt.ylabel("")  # Hide the y-label as it's unnecessary for pie charts
    plt.savefig("data/income_source_analysis.png", bbox_inches="tight")
    st.pyplot(plt)


def plot_category_wise_spending_analysis(data: pd.DataFrame):
    st.markdown("4. Category-wise Spending Analysis")
    expenses_by_category = data[data['Expense/Income'] == 'Expense'].groupby('Category')['Amount(EUR)'].sum()
    expenses_by_category.plot(kind="pie", figsize=(10, 8), autopct="%1.1f%%", startangle=140)
    plt.title("Expenses Analysis")
    plt.ylabel("")  # Hide the y-label as it's unnecessary for pie charts
    plt.savefig("data/expense_category_analysis.png", bbox_inches="tight")
    st.pyplot(plt)

total_df = pd.DataFrame()
for root, dirs, files in os.walk("data"):
    for file in files:
        if file.endswith(".csv"):
            df = pd.read_csv(os.path.join(root, file))
            total_df = pd.concat([total_df, df], ignore_index=True)

total_df["Date"] = pd.to_datetime(total_df["Date"])
total_df["YearMonth"] = total_df["Date"].dt.to_period("M")
total_df["Year"] = total_df["Date"].dt.year

st.title("My Local AI Finance Insighter")
st.markdown(
    "**A personalized and secure approach to analyzing financial data, providing insights and recommendations tailored to individual needs.**"
)

analysis_results = financial_analysis(total_df)
results_str = ""
# Loop through the dictionary
for key, value in analysis_results.items():
    if isinstance(value, dict):
        # If the value is another dictionary, further iterate to get sub-keys and values
        sub_results = ', '.join([f"{sub_key}: {sub_value}" for sub_key, sub_value in value.items()])
        results_str += f"{key}: {sub_results}\n"
    else:
        # For direct key-value pairs, simply concatenate
        results_str += f"{key}: {value}\n"

st.subheader("Yearly Figures")
col1, col2, col3 = st.columns(3)
col1.metric(label="Average Annual Income", value=analysis_results['Average Annual Income'])
col2.metric(label="Average Annual Expenses", value=analysis_results['Average Annual Expenses'])
col3.metric(label="Savings Rate", value=analysis_results['Annual Savings Rate'])

# Display average monthly figures
st.subheader("Average Monthly Figures")
col1, col2 = st.columns(2)
col1.metric(label="Average Monthly Income", value=analysis_results['Average Monthly Income'])
col2.metric(label="Average Monthly Expenses", value=analysis_results['Average Monthly Expenses'])

# Display top expense categories in a table
st.subheader("Top Expense Categories")
expenses_df = pd.DataFrame(list(analysis_results['Top Expense Categories'].items()), columns=['Category', 'Amount'])
st.table(expenses_df)

with st.container():
    col1, col2 = st.columns(2)
    with col1:
        plot_income_vs_expense_over_time(total_df)
    with col2:
        plot_saving_rate_trend(total_df)

with st.container():
    col3, col4 = st.columns(2)
    with col3:
        plot_income_source_analysis(total_df)
    with col4:
        plot_category_wise_spending_analysis(total_df)

with st.container():
    col3, col4 = st.columns(2)
    with col3:
        plot_income_source_analysis(total_df)
    with col4:
        plot_category_wise_spending_analysis(total_df)


with st.spinner("Generating reports ..."):
    total_response = ""
    for root, dirs, files in os.walk("data"):
        for file in files:
            if file.endswith(".png"):
                response = llm_llava.invoke(
                    f"Act as an expert finance planner and analyse the image : {os.path.join(root, file)}. You should give your insights extracted from the image and key figures you see from the image "
                )
                total_response += response
    total_response += f"\nHere are the user key financial figures : {results_str}"

    st.write("---------------")
    st.markdown("**Finance analysis and budget planner**")

    summary = llm.invoke(
        f"You are a helpful and expert finance planner. Base on the following analysis: {total_response}, make a summary of the financial status of the user and suggest tips on savings. Highlight categories where the user can potentially reduce expenses and suggest an ideal savings rate based on their income and goals. Tailor these suggestions to fit the user’s lifestyle and financial objectives. Use a friendly tone. "
    )
    st.write(summary)
    st.write("---------------")
    st.markdown("**Investment tips**")
    if "user_answers_str" in st.session_state:
        user_investment_answer = st.session_state.user_answers_str
    else:
        user_investment_answer = ""
    investment_tips = llm.invoke(
        f"You are a helpful and expert finance planner. Based on the user's risk tolerance and investment goals, provide an overview of suitable investment options. Discuss the basics of stocks, bonds, mutual funds, ETFs, and other investment vehicles that align with their profile. Explain the importance of diversification and the role of risk management in investing. Offer to guide them through setting up a diversified investment portfolio, suggesting steps to get started based on their current financial situation. Use a friendly tone. Below are the user´s investment objective and risk tolerance : {user_investment_answer}"
    )
    st.write(investment_tips)