import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report, accuracy_score
# Assuming the dataset is in CSV format, replace 'data.csv' with your actual file path.
data = pd.read_csv('Soybean.csv')
# Display the first few rows of the dataset to understand its structure
print(data.head())
# Separate features and target variable
X = data.drop('Class', axis=1)  # Features
y = data['Class']                # Target variable
# Split the dataset into training and testing sets (80% train, 20% test)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a Random Forest classifier
rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)
# Fit the model on the training data
rf_classifier.fit(X_train, y_train)
# Predict the labels for the test set
y_pred = rf_classifier.predict(X_test)
# Print accuracy and classification report
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')
print(classification_report(y_test, y_pred))


# Display feature importances
importances = rf_classifier.feature_importances_
feature_importance = pd.DataFrame({'Feature': X.columns, 'Importance': importances})
print(feature_importance.sort_values(by='Importance', ascending=False))