Notes

import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier

# Load the dataset
dataset = pd.read_csv("glass.csv")
X = dataset.iloc[:, :-1]
y = dataset.iloc[:, -1] # Assuming the last column is the target column

# Confirm the shape of X and y
print("Shape of X:", X.shape)
print("Shape of y:", y.shape) # Assuming the last column is the target column

# Split the data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=12)

# Scale the independent variables using StandardScaler
sc_x = StandardScaler()
X_train = sc_x.fit_transform(X_train)
X_test = sc_x.transform(X_test)

# Create and fit the Random Forest classifier
cls = RandomForestClassifier(criterion='entropy', n_estimators=300, random_state=42)
cls.fit(X_train, y_train)

# Make predictions on the test set
y_pred = cls.predict(X_test)

# Calculate and print the accuracy
accuracy = cls.score(X_test, y_test) * 100
print("ACCURACY is", accuracy, "%")