https://github.com/shrish01/kaggle-competition-notebooks

Kaggle Competition Notebook
https://github.com/shrish01/kaggle-competition-notebooks

data-science kaggle

Last synced: 2 months ago
JSON representation

Kaggle Competition Notebook

• Host: GitHub
• URL: https://github.com/shrish01/kaggle-competition-notebooks
• Owner: SHRISH01
• License: apache-2.0
• Created: 2024-11-17T18:11:40.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-01-09T14:54:04.000Z (over 1 year ago)
• Last Synced: 2025-01-09T15:43:05.463Z (over 1 year ago)
• Topics: data-science, kaggle
• Language: Jupyter Notebook
• Homepage: https://www.kaggle.com/shrishh
• Size: 2.96 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Kaggle Competition Notebooks 

Welcome to my collection of Kaggle competition notebooks! In this repository, I share my solutions, insights, and techniques for tackling various real-world data science challenges through Kaggle competitions.

## Overview 

This repository contains notebooks for several Kaggle competitions I've participated in. The notebooks include detailed explanations, step-by-step approaches, and code implementations that showcase different machine learning techniques, data wrangling methods, and model optimization strategies.

### Key Areas of Focus:

- **Predictive Modeling**: Building models to predict outcomes based on historical data.

- **Data Preprocessing**: Cleaning and transforming data for optimal model performance.

- **Feature Engineering**: Creating new features to improve model accuracy.

- **Model Optimization**: Tuning models to achieve competitive results.

- **Visualization**: Using data visualizations to uncover patterns and insights.

## Notebooks 

You can explore the following notebooks within this repository:

1. **Dog Vs Cat Classification - `Dog_Vs_Cat.ipynb`**

   - Description: A basic deep learning model using TensorFlow-Keras to classify images of dogs and cats.

   - Techniques used: Convolutional Neural Networks (CNN), data augmentation, and transfer learning.

2. **Mental Health Prediction using H2O.ai - `mental-health-data-using-h2o-ai.ipynb`**

   - Description: Predicting mental health outcomes using a dataset and H2O.ai's machine learning capabilities.

   - Techniques used: H2O.ai AutoML, data preprocessing, and model evaluation.

3. **Child Mind Institute Data - `child-mind-institute-l-gbm-h2o-ai.ipynb`**

   - Description: A model for predicting outcomes related to child mental health using LightGBM and H2O.ai.

   - Techniques used: Gradient Boosting Machine (GBM), feature selection, and hyperparameter tuning.

4. **CatBoost for Classification - `cibmtr-catboost.ipynb`**

   - Description: A classification model using CatBoost for predicting outcomes based on categorical features.

   - Techniques used: CatBoost, feature engineering, and model interpretation.

5. **Deep Learning for Classification - `classification-using-dl-basic.ipynb`**

   - Description: A simple deep learning model to classify data with a basic architecture.

   - Techniques used: Deep Learning (DL), activation functions, and backpropagation.

6. **Prediction with H2O.ai - `prediction-using-h2o-ai (1).ipynb`**

   - Description: A predictive modeling approach using H2O.ai, focusing on automating the machine learning pipeline.

   - Techniques used: H2O.ai AutoML, model stacking, and model evaluation.

## Installation

To run these notebooks, you'll need to set up the required Python environment. You can use the following steps:

1. Clone this repository:

   ```bash

   git clone https://github.com/SHRISH01/Kaggle-Competition-Notebooks.git

   cd Kaggle-Competition-Notebooks