File size: 4,016 Bytes
f10ec56 2c359f1 c7d0bb8 53977a7 118b9d7 9189033 a6ee9ca 6ca4f9e 01e575d 9189033 53977a7 01e575d 9189033 53977a7 9189033 e57fb31 9189033 53977a7 9189033 53977a7 9189033 53977a7 9189033 53977a7 9189033 53977a7 9189033 53977a7 9189033 e6dd97e 53977a7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 |
import pandas as pd
import plotly.express as px
import streamlit as st
from transformers import pipeline
import datetime
# File upload
uploaded_file = st.file_uploader("Upload your expense CSV file", type=["csv"])
if uploaded_file:
df = pd.read_csv(uploaded_file)
# Display Dataframe
st.write(df.head())
# Initialize Hugging Face model for zero-shot classification
classifier = pipeline('zero-shot-classification', model='distilbert-base-uncased')
categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation"]
# Function to categorize
def categorize_expense(description):
result = classifier(description, candidate_labels=categories)
return result['labels'][0] # Most probable category
# Apply categorization
df['Category'] = df['Description'].apply(categorize_expense)
# Sidebar for setting the monthly budget using sliders
st.sidebar.header("Set Your Monthly Budget")
groceries_budget = st.sidebar.slider("Groceries Budget", 0, 1000, 300)
rent_budget = st.sidebar.slider("Rent Budget", 0, 5000, 1000)
utilities_budget = st.sidebar.slider("Utilities Budget", 0, 500, 150)
entertainment_budget = st.sidebar.slider("Entertainment Budget", 0, 1000, 100)
dining_budget = st.sidebar.slider("Dining Budget", 0, 1000, 150)
transportation_budget = st.sidebar.slider("Transportation Budget", 0, 500, 120)
# Store the updated budget values
budgets = {
"Groceries": groceries_budget,
"Rent": rent_budget,
"Utilities": utilities_budget,
"Entertainment": entertainment_budget,
"Dining": dining_budget,
"Transportation": transportation_budget
}
# Add a date slider for start and end date (default is the last month)
today = datetime.date.today()
last_month = today - pd.DateOffset(months=1)
start_date = st.sidebar.date_input("Start Date", last_month)
end_date = st.sidebar.date_input("End Date", today)
# Filter data by date range
df['Date'] = pd.to_datetime(df['Date'])
df_filtered = df[(df['Date'] >= pd.to_datetime(start_date)) & (df['Date'] <= pd.to_datetime(end_date))]
# Track if any category exceeds its budget
df_filtered['Budget_Exceeded'] = df_filtered.apply(lambda row: row['Amount'] > budgets.get(row['Category'], 0), axis=1)
# Show categories that exceeded their budget
exceeded_budget = df_filtered[df_filtered['Budget_Exceeded'] == True]
st.write("Categories that exceeded the budget:", exceeded_budget[['Date', 'Category', 'Amount']])
# Visualizations
# 1. Pie Chart for expense distribution by category
category_expenses = df_filtered.groupby('Category')['Amount'].sum()
fig1 = px.pie(category_expenses, values=category_expenses.values, names=category_expenses.index, title="Expense Distribution by Category")
st.plotly_chart(fig1)
# 2. Monthly Spending Trends (Line Chart)
df_filtered['Month'] = df_filtered['Date'].dt.to_period('M').astype(str) # Convert Period to string for Plotly compatibility
monthly_expenses = df_filtered.groupby('Month')['Amount'].sum()
# Convert monthly_expenses into DataFrame for correct plotting
monthly_expenses_df = monthly_expenses.reset_index()
if not monthly_expenses_df.empty:
fig2 = px.line(monthly_expenses_df, x='Month', y='Amount', title="Monthly Expenses", labels={"Month": "Month", "Amount": "Amount ($)"})
st.plotly_chart(fig2)
else:
st.write("No data to display for the selected date range.")
# 3. Monthly Spending vs Budget (Bar Chart)
if not monthly_expenses_df.empty:
monthly_expenses_df = pd.DataFrame({
'Actual': monthly_expenses,
'Budget': [sum(budgets.values())] * len(monthly_expenses) # Same budget for simplicity
})
fig3 = monthly_expenses_df.plot(kind='bar', figsize=(10, 6))
st.pyplot(fig3)
else:
st.write("No data to display for the selected date range.")
|