app.py

# Import necessary libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import r2_score, mean_absolute_error
from transformers import pipeline
import streamlit as st

# Step 1: Data Collection
def load_data(file_path):
    data = pd.read_csv(file_path)
    return data

# Step 2: Data Cleaning
def clean_data(data):
    data.dropna(inplace=True)
    return data

# Step 3: Exploratory Data Analysis (EDA)
def perform_eda(data):
    st.write(data.describe())
    st.write(data.info())

# Step 4: Data Visualization
def visualize_data(data):
    plt.figure(figsize=(10, 6))
    sns.histplot(data['price'], kde=True)
    plt.title('Price Distribution')
    plt.show()

    plt.figure(figsize=(10, 6))
    sns.boxplot(x='brand', y='price', data=data)
    plt.title('Price by Brand')
    plt.show()

# Step 5: Feature Engineering
def encode_features(data):
    le = LabelEncoder()
    categorical_columns = ['brand', 'processor', 'Ram_type', 'ROM_type', 'GPU', 'OS']
    for col in categorical_columns:
        data[col] = le.fit_transform(data[col])
    return data

# Step 6: Machine Learning Modeling
def build_model(data):
    X = data.drop(['price'], axis=1)
    y = data['price']
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
    
    model = RandomForestRegressor(n_estimators=100, random_state=42)
    model.fit(X_train, y_train)
    y_pred = model.predict(X_test)
    
    # Model Evaluation
    st.write(f'R² Score: {r2_score(y_test, y_pred)}')
    st.write(f'Mean Absolute Error: {mean_absolute_error(y_test, y_pred)}')
    
    return model

# Step 7: NLP Analysis using Hugging Face (if any text data)
def analyze_text(feedback_data):
    sentiment_analysis = pipeline('sentiment-analysis')
    feedback_data['sentiment'] = feedback_data['feedback'].apply(lambda x: sentiment_analysis(x)[0]['label'])
    return feedback_data

# Step 8: User Interaction with Streamlit
def main():
    st.title("Laptop Price Predictor")
    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
    
    if uploaded_file is not None:
        data = load_data(uploaded_file)
        data = clean_data(data)
        
        st.subheader("Exploratory Data Analysis")
        perform_eda(data)
        
        st.subheader("Data Visualization")
        visualize_data(data)
        
        st.subheader("Feature Engineering")
        data = encode_features(data)
        
        st.subheader("Machine Learning Model")
        model = build_model(data)
        
        st.subheader("Make Predictions")
        if st.button('Predict'):
            predictions = model.predict(data.drop(['price'], axis=1))
            st.write(predictions)
            plt.figure(figsize=(10, 6))
            sns.histplot(predictions, kde=True)
            plt.title('Predicted Price Distribution')
            plt.show()

        # NLP Analysis (if applicable)
        # st.subheader("NLP Analysis")
        # feedback_data = load_feedback_data()  # Assuming a function to load text data
        # feedback_data = analyze_text(feedback_data)
        # st.write(feedback_data)

if __name__ == "__main__":
    main()