File size: 4,209 Bytes
f10ec56 2c359f1 c7d0bb8 f10ec56 c7d0bb8 2c359f1 a6ee9ca c7d0bb8 a6ee9ca 6ca4f9e 11d5829 a6ee9ca 11d5829 a6ee9ca 11d5829 a6ee9ca 11d5829 a6ee9ca 11d5829 a6ee9ca 11d5829 631a831 77dc4ed 631a831 77dc4ed 631a831 |
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 93 94 95 96 97 98 99 |
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
import streamlit as st
from transformers import pipeline
# Upload CSV file containing transaction data
uploaded_file = st.file_uploader("Upload Expense CSV", type="csv")
if uploaded_file is not None:
# Load the file into a DataFrame
df = pd.read_csv(uploaded_file)
# Debug: Display the column names to check if 'Description' exists
st.write("Columns in the uploaded file:", df.columns)
# Check if the 'Description' column exists
if 'Description' not in df.columns:
st.error("Error: The CSV file does not contain a 'Description' column.")
else:
# Initialize Hugging Face's zero-shot text classification model
model_name = 'distilbert-base-uncased'
classifier = pipeline('zero-shot-classification', model=model_name)
# List of possible expense categories
categories = ["Groceries", "Rent", "Utilities", "Entertainment", "Dining", "Transportation", "Salary"]
# Function to classify transaction descriptions into categories
def categorize_expense(description):
result = classifier(description, candidate_labels=categories)
return result['labels'][0] # Choose the most probable category
# Apply the categorization function to the 'Description' column in the dataset
df['Category'] = df['Description'].apply(categorize_expense)
# Show the categorized data
st.write("Categorized Data:", df.head())
# Visualization 1: Pie Chart of Spending by Category
category_expenses = df.groupby('Category')['Amount'].sum()
# Plot pie chart for expense distribution by category
fig1, ax1 = plt.subplots(figsize=(8, 8))
category_expenses.plot(kind='pie', autopct='%1.1f%%', startangle=90, colors=plt.cm.Paired.colors, ax=ax1)
ax1.set_title('Expense Distribution by Category')
ax1.set_ylabel('') # Hide the y-axis label
st.pyplot(fig1)
# Visualization 2: Monthly Spending Trends (Line Chart)
# Convert 'Date' to datetime and remove time part
df['Date'] = pd.to_datetime(df['Date']).dt.date # Keep only the date, no time
# Extract month-year for grouping and convert the Period to string to avoid JSON serialization issues
df['Month'] = df['Date'].apply(lambda x: x.strftime('%Y-%m')) # Extract Year-Month as string
# Group by month and calculate the total amount spent per month
monthly_expenses = df.groupby('Month')['Amount'].sum()
# Plot monthly spending trends as a line chart
fig2 = px.line(
monthly_expenses,
x=monthly_expenses.index,
y=monthly_expenses.values,
title="Monthly Expenses",
labels={"x": "Month", "y": "Amount ($)"}
)
st.plotly_chart(fig2)
# Budget and Alerts Example (Tracking if any category exceeds its budget)
budgets = {
"Groceries": 300,
"Rent": 1000,
"Utilities": 150,
"Entertainment": 100,
"Dining": 150,
"Transportation": 120,
}
# Track if any category exceeds its budget
df['Budget_Exceeded'] = df.apply(lambda row: row['Amount'] > budgets.get(row['Category'], 0), axis=1)
# Show which categories exceeded their budgets
exceeded_budget = df[df['Budget_Exceeded'] == True]
st.write("Categories that exceeded the budget:", exceeded_budget[['Date', 'Category', 'Amount']])
# Visualization 3: Monthly Spending vs Budget (Bar Chart)
# Create a figure explicitly for the bar chart
fig3, ax3 = plt.subplots(figsize=(10, 6)) # Create figure and axes
monthly_expenses_df = pd.DataFrame({
'Actual': monthly_expenses,
'Budget': [sum(budgets.values())] * len(monthly_expenses) # Same budget for simplicity
})
monthly_expenses_df.plot(kind='bar', ax=ax3) # Pass the axes to the plot
ax3.set_title('Monthly Spending vs Budget')
ax3.set_ylabel('Amount ($)')
# Display the plot with Streamlit
st.pyplot(fig3)
|