|
|
--- |
|
|
model_name: Crop Recommendation Model using Random Forest |
|
|
tags: |
|
|
- tabular-classification |
|
|
- sklearn |
|
|
- random-forest |
|
|
- crop-recommendation |
|
|
- agriculture |
|
|
library_name: sklearn |
|
|
inference: true |
|
|
model_description: > |
|
|
This crop recommendation model uses a Random Forest classifier to recommend |
|
|
the best crop |
|
|
|
|
|
based on environmental factors such as soil nutrients (N, P, K), pH, |
|
|
temperature, rainfall, |
|
|
|
|
|
and humidity. The model is trained to assist farmers in making optimal crop |
|
|
choices based on |
|
|
|
|
|
available agricultural data. |
|
|
|
|
|
|
|
|
**Features Used:** |
|
|
|
|
|
- Nitrogen (N) |
|
|
|
|
|
- Phosphorus (P) |
|
|
|
|
|
- Potassium (K) |
|
|
|
|
|
- pH |
|
|
|
|
|
- Temperature |
|
|
|
|
|
- Rainfall |
|
|
|
|
|
- Humidity |
|
|
|
|
|
|
|
|
**Example Usage:** |
|
|
|
|
|
```python |
|
|
|
|
|
import joblib |
|
|
|
|
|
model = joblib.load("crop.pkl") |
|
|
prediction = model.predict([[N, P, K, pH, temperature, rainfall, humidity]]) |
|
|
print("Recommended Crop:", prediction) |
|
|
metrics: |
|
|
- accuracy : 99.86(Random Forest), 99.88(adaboost) |
|
|
language: |
|
|
- en |
|
|
pipeline_tag: question-answering |
|
|
--- |
|
|
--- |
|
|
models: |
|
|
- model_name: "Crop Recommendation Model using Random Foresst classification" |
|
|
tags: |
|
|
- tabular-classification |
|
|
- sklearn |
|
|
- random-forest |
|
|
- crop-recommendation |
|
|
- agriculture |
|
|
library_name: "sklearn" |
|
|
inference: true |
|
|
model_description: | |
|
|
This crop recommendation model uses a Random Forest classifier to recommend the best crop |
|
|
based on environmental factors such as soil nutrients (N, P, K), pH, temperature, rainfall, |
|
|
and humidity. The model is trained to assist farmers in making optimal crop choices based on |
|
|
available agricultural data. |
|
|
|
|
|
**Features Used:** |
|
|
- Nitrogen (N) |
|
|
- Phosphorus (P) |
|
|
- Potassium (K) |
|
|
- pH |
|
|
- Temperature |
|
|
- Rainfall |
|
|
- Humidity |
|
|
|
|
|
**Example Usage:** |
|
|
```python |
|
|
import joblib |
|
|
model = joblib.load("crop.pkl") |
|
|
# Predict the crop for a given set of environmental features |
|
|
prediction = model.predict([[N, P, K, pH, temperature, rainfall, humidity]]) |
|
|
print("Recommended Crop:", prediction) |
|
|
``` |
|
|
|
|
|
- model_name: "Crop recommendation model using Adaboost ensemble method" |
|
|
tags: |
|
|
- tabular-classification |
|
|
- sklearn |
|
|
- adaboost |
|
|
- decision-tree |
|
|
- soil-analysis |
|
|
library_name: "sklearn" |
|
|
inference: true |
|
|
model_description: | |
|
|
This soil classification model is built using AdaBoost with a DecisionTreeClassifier as the base estimator. |
|
|
It classifies soil types based on various properties like pH, nutrient levels, and other soil characteristics. |
|
|
|
|
|
**Algorithm Details:** |
|
|
- Base Learner: DecisionTreeClassifier with max_depth=3 |
|
|
- Boosting Method: AdaBoostClassifier with SAMME.R |
|
|
- Number of Estimators: 500 |
|
|
- Learning Rate: 0.3 |
|
|
|
|
|
**Example Usage:** |
|
|
```python |
|
|
import joblib |
|
|
model = joblib.load("adaboost_model_soil.pkl") |
|
|
prediction = model.predict([[feature1, feature2, ..., featureN]]) |
|
|
print("Predicted Soil Type:", prediction) |
|
|
``` |
