app.py

import gradio as gr
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.preprocessing import PolynomialFeatures
from sklearn.pipeline import make_pipeline
import plotly.express as px

# Simulate data
np.random.seed(42)
n_samples = 100
income = np.random.randint(30000, 200000, n_samples)
investment = 0.000001 * (income ** 2) - 0.05 * income + 10000 + np.random.normal(0, 5000, n_samples)

df = pd.DataFrame({'Monthly_Income': income, 'MF_Investment': investment})

# Train polynomial model
X = df[['Monthly_Income']]
y = df['MF_Investment']
model = make_pipeline(PolynomialFeatures(degree=2), LinearRegression())
model.fit(X, y)

# Predict and round
df['Predicted_Investment'] = model.predict(X).round(0).astype(int)

# Sort by Monthly Income
df = df.sort_values(by='Monthly_Income')

# Prediction function using min/max income
def investment_predictor(min_income, max_income):
    filtered_df = df[(df['Monthly_Income'] >= min_income) & 
                     (df['Monthly_Income'] <= max_income)]

    table = filtered_df[['Monthly_Income', 'Predicted_Investment']].head(20)

    fig = px.scatter(filtered_df, x='Monthly_Income', y='MF_Investment',
                     title="📉 Actual vs Predicted Investment",
                     labels={'MF_Investment': 'Actual Investment'},
                     color_discrete_sequence=["blue"])
    fig.add_traces(px.line(filtered_df, x='Monthly_Income', y='Predicted_Investment').data)
    fig.update_traces(name='Predicted Investment', selector=dict(mode='lines'))

    return table, fig

# UI components
min_income_slider = gr.Slider(minimum=int(df['Monthly_Income'].min()),
                              maximum=int(df['Monthly_Income'].max()),
                              step=1000,
                              value=int(df['Monthly_Income'].min()),
                              label="Minimum Monthly Income (₹)")

max_income_slider = gr.Slider(minimum=int(df['Monthly_Income'].min()),
                              maximum=int(df['Monthly_Income'].max()),
                              step=1000,
                              value=int(df['Monthly_Income'].max()),
                              label="Maximum Monthly Income (₹)")

# Interface
demo = gr.Interface(
    fn=investment_predictor,
    inputs=[min_income_slider, max_income_slider],
    outputs=[
        gr.Dataframe(label="📊 Prediction Table (Top 20)"),
        gr.Plot(label="📉 Actual vs Predicted Investment")
    ],
    title="📈 Mutual Fund Investment Predictor ",
    description="This dashboard uses Polynomial Regression to predict mutual fund investments based on monthly income."
)

demo.launch()