Random Forest

preprocessing

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import warnings

warnings.filterwarnings('ignore')

dataset = pd.read_csv('_data/08.csv')
x = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)

from sklearn.preprocessing import StandardScaler

sc = StandardScaler()

x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)

Modeling - linear

from sklearn.ensemble import RandomForestClassifier

classifier = RandomForestClassifier(n_estimators=10, criterion='entropy')
classifier.fit(x_train, y_train)

RandomForestClassifier(criterion='entropy', n_estimators=10)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

Predict

from sklearn.metrics import confusion_matrix, accuracy_score

y_pred = classifier.predict(x_test)
print(confusion_matrix(y_test, y_pred))
accuracy_score(y_test, y_pred)

[[54  4]
 [ 6 36]]

0.9

Predict

y_pred = classifier.predict(x_test)
print(confusion_matrix(y_test, y_pred))
accuracy_score(y_test, y_pred)

[[54  4]
 [ 6 36]]

0.9