|
--- |
|
license: mit |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
library_name: sklearn |
|
tags: |
|
- Traffic |
|
- ML |
|
- Random-forest |
|
- Classification |
|
- Scikit-learn |
|
--- |
|
# Traffic Prediction Model |
|
|
|
## Model Description |
|
This model is a **Random Forest Classifier** trained to predict **traffic conditions** based on various input features. |
|
It helps estimate traffic congestion levels using structured data such as **time of day, weather, and historical patterns**. |
|
|
|
## Training Details |
|
- **Algorithm**: Random Forest Classifier |
|
- **Dataset**: Custom traffic dataset |
|
- **Preprocessing**: Label encoding for categorical variables |
|
- **Framework**: scikit-learn |
|
|
|
## How to Use |
|
To use this model, install the required libraries and download the model from Hugging Face. |
|
|
|
To load and use the model: |
|
```python |
|
import joblib |
|
from huggingface_hub import hf_hub_download |
|
|
|
# Download model |
|
model_path = hf_hub_download(repo_id="AhaseesAI/traffic-prediction", filename="traffic_classifier.pkl") |
|
encoder_path = hf_hub_download(repo_id="AhaseesAI/traffic-prediction", filename="target_encoder.pkl") |
|
|
|
# Load model |
|
model = joblib.load(model_path) |
|
target_encoder = joblib.load(encoder_path) |
|
|
|
# Example prediction |
|
sample_data = [[value1, value2, value3, ...]] # Replace with actual feature values |
|
prediction = model.predict(sample_data) |
|
|
|
# Convert prediction to original label |
|
predicted_label = target_encoder.inverse_transform(prediction) |
|
print(f"Predicted Traffic Status: {predicted_label[0]}") |
|
|
