{"repo":"Sara12-2/Superised-Machine_learning_projects","free":true,"listed":false,"github":"https://github.com/Sara12-2/Superised-Machine_learning_projects","clone":"git clone https://github.com/Sara12-2/Superised-Machine_learning_projects.git","description":"This repository contains two machine learning projects: a Streamlit-based app for predicting household power consumption using a Random Forest model, and a Tkinter GUI application for predicting telecom customer churn using LightGBM with SMOTE handling.","language":"Python","stars":10,"topics":["data-visualization","joblib","model-evaluation","model-training","random-forest","smote","tkinter-gui"],"license":null,"category":"machine-learning","readme_excerpt":"⚡ Household Power Consumption & Telco Churn Prediction Projects This repository contains two end-to-end Machine Learning applications: 1. Household Power Consumption Prediction (Streamlit App) 2. Telco Customer Churn Prediction (Tkinter GUI App) Both projects demonstrate full ML pipelines including preprocessing, training, evaluation, and real-time prediction interfaces. --- 📊 1. Household Power Consumption — Streamlit ML App 📌 Overview This Streamlit application trains a Random Forest Regressor on the Household Power Consumption dataset and provides: Model training & evaluation Interactive visualizations Real-time prediction interface --- 🚀 Features 📂 Upload dataset ( .txt or .csv ) 🧹 Data preprocessing: Combines Date + Time Handles missing values 🌲 Model: RandomForestRegressor 📈 Model evaluation: Mean Squared Error (MSE) Mean Absolute Error (MAE) R² Score 📊 Visualizations: Distribution of Global active power Actual vs Predicted scatter plot 🔮 Real-time prediction form via Streamlit --- 🛠️ Installation --- ▶️ Run the App --- 📂 Dataset Requirements File: household power consumption.txt Separator: ; Missing values: ? Required Columns: Date Time Global active power (Target) Global reactive power Voltage Global intensity Sub metering 1 Sub metering 2 Sub metering 3 --- ⚙️ Model Details Train/Test Split: 80/20 Model: RandomForestRegressor n estimators: 30 max depth: 10 Scaling: StandardScaler --- 📌 Suggestions for Improvement Use SimpleImputer instead of dropping NaNs","default_branch":null,"files":null,"tree":[],"storefront":"/r/Sara12-2","claimed":false,"request_supported":{"post":"https://gitbuyer.com/r/Sara12-2/Superised-Machine_learning_projects/request-supported","requests":0},"note":"indexed from public GitHub; nothing is for sale on this page. Clone it from GitHub. Paid listings live at /search."}