|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
metrics: |
|
- accuracy |
|
base_model: |
|
- distilbert/distilbert-base-uncased-finetuned-sst-2-english |
|
library_name: sklearn |
|
--- |
|
# Potato Price Prediction Model |
|
|
|
This model predicts potato prices based on various features such as arrival quantity, temperature, humidity, and historical price data. |
|
|
|
## Input Features |
|
|
|
- Date: Date of prediction (format: YYYY-MM-DD) |
|
- ArrivalQuantity: Quantity of potatoes arriving at the market |
|
- Temperature: Temperature on the given date |
|
- Humidity: Humidity on the given date |
|
- Wind direction: Wind direction on the given date |
|
- Events: Any significant events on the given date |
|
- Impacts: Any significant impacts on the given date |
|
- PriceLag1: Previous day's price |
|
- PriceLag7: Price from 7 days ago |
|
- PriceRollingMean7: 7-day rolling mean price |
|
- PriceRollingStd7: 7-day rolling standard deviation of price |
|
- PrevWeekAvgPrice: Average price of the previous week |
|
|
|
## Output |
|
|
|
The model returns a predicted potato price for the given input features. |
|
|
|
## Usage |
|
|
|
```python |
|
from potato_price_model import predictor |
|
|
|
input_data = { |
|
'Date': '2024-09-14', |
|
'ArrivalQuantity': 1000, |
|
'Temperature': 25, |
|
'Humidity': 60, |
|
'Wind direction': 180, |
|
'Events': 'Normal day', |
|
'Impacts': 'No significant impacts', |
|
'PriceLag1': 50, |
|
'PriceLag7': 48, |
|
'PriceRollingMean7': 49, |
|
'PriceRollingStd7': 2, |
|
'PrevWeekAvgPrice': 49 |
|
} |
|
|
|
result = predictor.predict(input_data) |
|
print(f"Predicted potato price: {result['predicted_price']}") |
|
``` |
