https://github.com/baghettigh/f1-podium-prediction

A Streamlit web application that predicts if a driver will finish on the podium (1st,2nd, or 3rd Place) in a Formula 1 Grand Prix Race using their qualifying times and initial position. This application performs EDA, Data Preprocessing, and Supervised Machine Learning to predict instances using Logistic Regression.
https://github.com/baghettigh/f1-podium-prediction

data-science formula1 logistic-regression prediction streamlit

Last synced: about 1 month ago
JSON representation

A Streamlit web application that predicts if a driver will finish on the podium (1st,2nd, or 3rd Place) in a Formula 1 Grand Prix Race using their qualifying times and initial position. This application performs EDA, Data Preprocessing, and Supervised Machine Learning to predict instances using Logistic Regression.

• Host: GitHub
• URL: https://github.com/baghettigh/f1-podium-prediction
• Owner: BaghettiGH
• Created: 2024-11-01T03:27:48.000Z (about 2 months ago)
• Default Branch: main
• Last Pushed: 2024-11-11T04:41:44.000Z (about 1 month ago)
• Last Synced: 2024-11-11T05:30:38.363Z (about 1 month ago)
• Topics: data-science, formula1, logistic-regression, prediction, streamlit
• Language: Python
• Homepage:
• Size: 1.48 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# F1 Podium Prediction

A Streamlit web application that predicts if a driver will finish on the podium (1st,2nd, or 3rd Place) in a Formula 1 Grand Prix Race using their qualifying times and initial position. This application performs **EDA**, **Data Preprocessing**, and **Supervised Machine Learning** to predict instances using **Logistic Regression**.

![Main Page Screenshot](screenshots/main_page_screenshot.png)

### 🔗 Links:  

-  [Streamlit Link]()

-  [Google Colab Notebook](https://colab.research.google.com/drive/1AxRBCJX24u00DtShTovHU3tbSkpzfIt7?usp=sharing)

### 📊 Dataset:

- [Formula 1 World Championship (1950 - 2024)(Kaggle)](https://www.kaggle.com/datasets/rohanrao/formula-1-world-championship-1950-2020)

This repository serves as a project guide template for my students in **Introduction to Data Science** course for their final project. It contains a Python file `dashboard_template.py` which contains a boilerplate for a Streamlit dashboard.

### 📖 Pages:

1. `Dataset` - Brief description of the Formula 1 Dataset used in this dashboard.

2. `EDA` - Exploratory Data Analysis of the F1 Dataset. Highlights relationship of initial positionl, qualifying times and finishing on the podium. Includes bar graphs,histogram, scatter graph, etc.

3. `Data Cleaning / Pre-processing` - Data cleaning and pre-processing steps such as encoding the species column and splitting the dataset into training and testing sets.

4. `Machine Learning` - Training Logistic Regression model. This page also includes the model evaluation, feature importance and classification report.

5. `Prediction` - Prediction page where users can input values to predict if the driver will finish on the podium.

6. `Conclusion` - Summary of the insights and observations from the EDA and model training.

### 💡 Findings / Insights

Through exploratory data analysis and training of two classification models (`Decision Tree Classifier` and `Random Forest Regressor`) on the **Iris Flower dataset**, the key insights and observations are:

#### 1. 📊 **Dataset Characteristics**:

- 

- 

#### 2. 📝 **Feature Distributions and Separability**:

- 

- 

#### 3. 📈 **Model Performance (Decision Tree Classifier)**:

- 

- 

#### 4. 📈 **Model Performance (Random Forest Regressor)**:

- 

- 

##### **Conclusion:**

(Text here)