example_rerfClassifier.py

"""
Example shows usage of rerfClassifier class.

Based on https://www.datacamp.com/community/tutorials/random-forests-classifier-python
with rerfClassifier swapped out instead of sklearn's RandomForestClassifier
"""

from rerf.rerfClassifier import rerfClassifier

# Import scikit-learn dataset library
from sklearn import datasets

# Load dataset
iris = datasets.load_iris()


# print the label species(setosa, versicolor,virginica)
print(iris.target_names)

# print the names of the four features
print(iris.feature_names)

# Creating a DataFrame of given iris dataset.
import pandas as pd

data = pd.DataFrame(
    {
        "sepal length": iris.data[:, 0],
        "sepal width": iris.data[:, 1],
        "petal length": iris.data[:, 2],
        "petal width": iris.data[:, 3],
        "species": iris.target,
    }
)
print(data.head())

# Import train_test_split function
from sklearn.model_selection import train_test_split

X = data[["sepal length", "sepal width", "petal length", "petal width"]]  # Features
y = data["species"]  # Labels

# Split dataset into training set and test set
X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.3
)  # 70% training and 30% test


# Create a Gaussian Classifier
clf = rerfClassifier(n_estimators=100)

print(clf)

# Train the model using the training sets y_pred=clf.predict(X_test)
clf.fit(X_train, y_train)

y_pred = clf.predict(X_test)

# Import scikit-learn metrics module for accuracy calculation
from sklearn import metrics

# Model Accuracy, how often is the classifier correct?
print("Accuracy:", metrics.accuracy_score(y_test, y_pred))