KNN regressor dengan Python

contoh KNN regressor dengan dataset employee.csv

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

mengembalikan data ke tipedata object kemudian dirubah menjadi numerical

# Load dataset
data = pd.read_csv('employee_train.csv')
########################################################################################
# Data preprocessing
# Handle missing values
imputer = SimpleImputer(strategy='most_frequent')
data_imputed = pd.DataFrame(imputer.fit_transform(data), columns=data.columns)

# Convert back to original data types
for col in data.columns:
    if data[col].dtype == 'object':
        data_imputed[col] = data_imputed[col].astype('object')
    else:
        data_imputed[col] = pd.to_numeric(data_imputed[col])
############################################################################################

label encoder dengan pengecualian target variable

# Encode categorical variables
label_encoders = {}
categorical_cols = data.select_dtypes(include=['object']).columns
for col in categorical_cols:
    if col != 'Attrition':  # We'll keep Attrition as is for potential classification later
        le = LabelEncoder()
        data_imputed[col] = le.fit_transform(data_imputed[col].astype(str))
        label_encoders[col] = le

split data dan standardisasi

# Define features and target
X = data_imputed.drop(['MonthlyIncome', 'ID', 'Attrition'], axis=1)  # Exclude ID and Attrition
y = data_imputed['MonthlyIncome']

# Split data
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Standardize features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

mengecek data hasil convert tipe data

data_imputed.info()

memuat model KNN regressor

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
   

# Create and train KNN Regressor
knn_reg = KNeighborsRegressor(n_neighbors=5)  # You can tune this parameter
knn_reg.fit(X_train_scaled, y_train)

prediksi dan evaluasi

# Predictions
y_pred = knn_reg.predict(X_test_scaled)

# Evaluation
mse = mean_squared_error(y_test, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(y_test, y_pred)


print(f"Model Evaluation:")
print(f"RMSE: {rmse:.2f}")
print(f"R-squared: {r2:.2f}")