import numpy as np
import pandas as pd
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score, classification_report
from sklearn.utils import resample
class CustomRandomForest:
def __init__(self, n_estimators=100, max_features='sqrt', random_state=None):
self.n_estimators = n_estimators
self.max_features = max_features
self.random_state = random_state
self.trees = []
np.random.seed(self.random_state)
def fit(self, X, y):
# Create multiple bootstrapped datasets and train decision trees
for _ in range(self.n_estimators):
# Create a bootstrapped sample
X_bootstrap, y_bootstrap = resample(X, y, random_state=self.random_state)
tree = DecisionTreeClassifier(max_features=self.max_features, random_state=self.random_state)
tree.fit(X_bootstrap, y_bootstrap)
self.trees.append(tree)
def predict(self, X):
# Aggregate predictions from all trees
predictions = np.array([tree.predict(X) for tree in self.trees])
# Take the majority vote
return np.array([np.bincount(pred).argmax() for pred in predictions.T])
# Load the iris dataset
iris = load_iris()
X = iris.data
y = iris.target
# Split the dataset into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
# Create a Custom Random Forest Classifier
custom_rf_model = CustomRandomForest(n_estimators=100, random_state=42)
# Train the model
custom_rf_model.fit(X_train, y_train)
# Make predictions
y_pred = custom_rf_model.predict(X_test)
# Calculate accuracy
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy:.2f}')
# Print classification report
print(classification_report(y_test, y_pred))
Comments