You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
# IPL Score Prediction Project
यह प्रोजेक्ट मशीन लर्निंग का उपयोग करके IPL मैचों में टीम के फाइनल स्कोर की भविष्यवाणी करता है।
## आवश्यकताएं
सभी आवश्यक पैकेज इंस्टॉल करने के लिए:
```bash
pip install -r requirements.txt
```
## प्रोजेक्ट स्ट्रक्चर
```
IPL-Score-prediction-ML-Project/
├── data/
│ └── ipl_data.csv
├── models/
│ ├── random_forest_model.pkl
│ └── linear_regression_model.pkl
├── requirements.txt
├── train_models.py
└── IPL_score_pred.py
```
## उपयोग
1. मॉडल्स को ट्रेन करने के लिए:
```bash
python train_models.py
```
2. स्कोर की भविष्यवाणी करने के लिए:
```python
from IPL_score_pred import load_models, predict_score
# मॉडल्स लोड करें
models = load_models()
# भविष्यवाणी करें
prediction = predict_score(
models,
batting_team="Mumbai Indians",
bowling_team="Chennai Super Kings",
current_score=100,
overs=15.0,
wickets=3,
last_five_runs=50,
last_five_wickets=2
)
print(f"Predicted final score: {prediction}")
```
## फीचर्स
- बैटिंग टीम
- बॉलिंग टीम
- वर्तमान स्कोर
- खेले गए ओवर्स
- गिरे विकेट
- पिछले 5 ओवर्स में बने रन
- पिछले 5 ओवर्स में गिरे विकेट
## मॉडल्स
1. रैंडम फॉरेस्ट रिग्रेसर
2. लीनियर रिग्रेशन
दोनों मॉडल्स का औसत लिया जाता है जिससे अधिक सटीक भविष्यवाणी मिलती है।
## Features
- Interactive web interface built with Streamlit
- Multiple machine learning models (Linear Regression, Random Forest, SVM)
- Real-time score predictions
- Team performance statistics and visualizations
- Beautiful and responsive UI
## Setup Instructions
1. Clone this repository
2. Install the required dependencies:
```bash
pip install -r requirements.txt
```
3. Make sure you have the `ipl.csv` dataset in the project directory
4. Run the application:
```bash
streamlit run app.py
```
## Usage
1. Select the batting and bowling teams from the dropdown menus
2. Enter the current match statistics:
- Current runs
- Wickets fallen
- Overs completed
- Runs in last 5 overs
- Wickets in last 5 overs
3. Click the "Predict Score" button to get predictions from all three models
4. View the average predicted score and visualizations
## Technologies Used
- Python
- Streamlit
- Pandas
- NumPy
- Scikit-learn
- Plotly
## Data Source
The application uses historical IPL match data from the `ipl.csv` dataset. Make sure to place this file in the project directory before running the application.
# IPL-Victory-Predictor
About
"IPL Cricket Victory Predictor" is a Streamlit-based web app that predicts match winners using team, player, and stadium data from 2010–2023. Built in Python, the model achieves 90% accuracy.