File size: 2,285 Bytes
2c359f1
f10ec56
 
 
 
2c359f1
f10ec56
4a7d41a
2c359f1
f10ec56
4a7d41a
2c359f1
 
 
f10ec56
2c359f1
 
4a7d41a
2c359f1
4a7d41a
 
f10ec56
2c359f1
 
4a7d41a
2c359f1
 
4a7d41a
 
2c359f1
 
 
4a7d41a
2c359f1
 
 
 
 
4a7d41a
2c359f1
4a7d41a
2c359f1
 
4a7d41a
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
import gradio as gr
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from transformers import pipeline
import plotly.express as px

# Initialize the Hugging Face model for expense categorization (use zero-shot classification)
expense_classifier = pipeline("zero-shot-classification", model="facebook/bart-large-mnli")

# Batch categorization function for efficiency
def categorize_transaction_batch(descriptions):
    candidate_labels = ["Groceries", "Entertainment", "Rent", "Utilities", "Dining", "Transportation", "Shopping", "Others"]
    return [expense_classifier(description, candidate_labels)["labels"][0] for description in descriptions]

# Function to process the uploaded CSV and generate visualizations
def process_expenses(file):
    # Read CSV data
    df = pd.read_csv(file.name)
    
    # Check if required columns are present
    if 'Date' not in df.columns or 'Description' not in df.columns or 'Amount' not in df.columns:
        return "CSV file should contain 'Date', 'Description', and 'Amount' columns."

    # Categorize the expenses (using batch processing to minimize model calls)
    df['Category'] = categorize_transaction_batch(df['Description'].tolist())

    # Create visualizations:
    # 1. Pie chart for Category-wise spending
    category_spending = df.groupby("Category")['Amount'].sum()
    fig1 = px.pie(category_spending, names=category_spending.index, values=category_spending.values, title="Category-wise Spending")
    
    # 2. Monthly spending trends (Line plot)
    df['Date'] = pd.to_datetime(df['Date'])
    df['Month'] = df['Date'].dt.to_period('M')
    monthly_spending = df.groupby('Month')['Amount'].sum()
    fig2 = px.line(monthly_spending, x=monthly_spending.index, y=monthly_spending.values, title="Monthly Spending Trends")
    
    # 3. Budget vs Actual Spending (Bar chart)
    category_list = df['Category'].unique()
    budget_dict = {category: 500 for category in category_list}  # Default budget is 500 for each category
    budget_spending = {category: [budget_dict[category], category_spending.get(category, 0)] for category in category_list}
    budget_df = pd.DataFrame(budget_spending, index=["Budget", "Actual"]).T
    fig3 = px.bar(budget_df, x=budget_df.index, y=["Budget", "Actual"], title=