berikut contoh penggunaan dataset employee dengan beberapa fitur
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler, LabelEncoder
from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.impute import SimpleImputer
# Load dataset
df_em = pd.read_csv('employee_train.csv')
# Load the dataset
# Define features and target
X = df_em[['Age','NumCompaniesWorked','TrainingTimesLastYear','StandardHours']] #numerical
y = df_em['MonthlyIncome'] ##numerical
# 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)
# Apply KNN regression
knn_regressor = KNeighborsRegressor(n_neighbors=3)
knn_regressor.fit(X_train, y_train)
predictions = knn_regressor.predict(X_test)
# Evaluate the model
print('R2 Score:', knn_regressor.score(X_test, y_test))
