Skip to content

ml tasks.md

Latest commit

 

History

History
168 lines (125 loc) · 5.51 KB

ml tasks.md

File metadata and controls

168 lines (125 loc) · 5.51 KB

🤖 Machine Learning Tasks

ML Difficulty Tasks

🌟 Overview

Welcome to the Machine Learning track! This task focuses on real-world data analysis, exploring patterns in teen smartphone usage and its impact on mental health and academic performance.

📱 Task: Teen Smartphone Usage Analysis

🎯 Objective

Analyze how smartphone addiction influences academic performance and well-being among teenagers through comprehensive EDA and insights generation.

📊 Dataset Information

Topic: Teen Smartphone Usage and Addiction Impact

Context: The rapid rise of smartphones has transformed the way teenagers connect, learn, and entertain themselves — but it has also raised concerns about excessive usage and its potential impact on mental health, academic performance, and daily routines.

Dataset URL: Download Here

🛠️ Tech Stack

  • Language: Python 3.7+
  • Environment: Jupyter Notebook / Google Colab
  • Libraries: pandas, numpy, matplotlib, seaborn, plotly, scikit-learn

✅ Required Analysis Components

📋 1. Data Understanding & Cleaning (40%)

  • Data Overview - Shape, columns, data types
  • Missing Values - Identification and handling strategy
  • Duplicates - Detection and removal
  • Outliers - Statistical identification and treatment
  • Data Types - Proper conversion and formatting
  • Clean Dataset - Export processed CSV

📈 2. Exploratory Data Analysis (50%)

Required Analysis Examples:

  • Top 5 Activities by average daily time spent
  • Usage vs Academic Performance - Correlation analysis
  • Sleep Patterns by addiction level
  • Bedtime Phone Usage Impact on sleep quality
  • Mental Health Indicators by addiction severity

Additional Analysis:

  • Demographics - Age, gender distribution
  • Screen Time Patterns - Daily, weekly trends
  • App Categories - Most used applications
  • Behavioral Patterns - Usage during different times

📊 3. Visualizations (Required)

  • Distribution Plots - Histograms, box plots
  • Correlation Heatmap - Feature relationships
  • Bar Charts - Categorical comparisons
  • Scatter Plots - Continuous variable relationships
  • Time Series - Usage patterns over time
  • Subplots - Multi-dimensional analysis

🧠 4. Insights & Conclusions (10%)

  • Key Findings - 5-7 major insights
  • Statistical Significance - Hypothesis testing results
  • Recommendations - Actionable suggestions
  • Future Work - Potential research directions

🎁 Bonus Points

  • Interactive Visualizations - Plotly/Dash
  • Machine Learning - Predictive models
  • Creative Analysis - Unique insights discovery
  • Professional Presentation - Clean notebook with markdown

📦 Deliverables

  • 📓 Jupyter Notebook (.ipynb) with complete analysis
  • 📄 Clean Dataset (.csv) after preprocessing
  • 📊 Visualizations - All plots saved as images

🗂️ Notebook Structure Template

# 📱 Teen Smartphone Usage Analysis

## 📋 Table of Contents
1. Introduction & Objectives
2. Data Loading & Overview
3. Data Cleaning & Preprocessing
4. Exploratory Data Analysis
5. Key Insights & Findings
6. Conclusions & Recommendations

## 🎯 Project Objectives
- Analyze smartphone usage patterns among teenagers
- Identify correlation between usage and academic performance
- Examine impact on sleep and mental health
- Generate actionable insights for stakeholders

## 📊 Data Overview
```python
# Your data loading and overview code here

🧹 Data Cleaning

# Your data cleaning code here

📈 Exploratory Data Analysis

Usage Patterns Analysis

Academic Performance Impact

Sleep & Mental Health Analysis

Additional Insights

📊 Dataset Access

Note: Dataset link is provided in this repository

📋 Submission Guidelines

📝 Issue Template

Create an issue in brl_akgec repository:

## 🤖 ML Task Submission

**👤 Name:** Your Full Name
**📧 Contact:** your.email@example.com
**🎯 Task:**  Teen Smartphone Usage Analysis

**🔗 Repository:** [Your GitHub Repo URL]
**📓 Notebook:** [Direct link to notebook file]

**🛠️ Tech Stack:**
- Python 3.x
- Libraries: [pandas, matplotlib, seaborn, etc.]
- Environment: [Jupyter/Colab]

**📊 Analysis Completed:**
- [x] Data cleaning and preprocessing
- [x] Usage patterns analysis
- [x] Academic performance correlation
- [x] Sleep impact analysis
- [x] Mental health indicators
- [x] [Additional analyses]

**🎁 Bonus Features:**
- [Any bonus features implemented]

💡 Analysis Tips

  • Ask meaningful questions before diving into data
  • Tell a story with your visualizations
  • Validate assumptions with statistical tests
  • Think like a researcher - what would be practically useful?

🚀 Ready to uncover insights? Let's dive into the data!