File size: 1,530 Bytes
7ef0172 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 |
import pandas as pd
from sklearn.preprocessing import LabelEncoder
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score, median_absolute_error
from joblib import dump
# Load the dataset
df = pd.read_csv('cleaned_housesTRAIN.csv')
# Apply label encoding to 'Area' and 'Suburb'
le_area = LabelEncoder()
df['Area'] = le_area.fit_transform(df['Area'])
le_suburb = LabelEncoder()
df['Suburb'] = le_suburb.fit_transform(df['Suburb'])
# Save the label encoders
dump(le_area, 'le_area.joblib')
dump(le_suburb, 'le_suburb.joblib')
# Shuffle the dataframe
df = df.sample(frac=1)
# Split the data into features (X) and target (y)
X = df.drop('Rent', axis=1)
y = df['Rent']
# Split the data into training and test sets (90/10 split)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)
# Create a Gradient Boosting regressor with specified hyperparameters
gb = GradientBoostingRegressor(n_estimators=850, learning_rate=0.195, max_depth=7, random_state=42)
# Train the model
gb.fit(X_train, y_train)
# Make predictions on the test set
y_pred = gb.predict(X_test)
# Calculate MAE, MSE, and R2
mae = mean_absolute_error(y_test, y_pred)
mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)
medae = median_absolute_error(y_test, y_pred)
print(f"MAE: {mae}, MSE: {mse}, R2: {r2}, MedAE: {medae}")
# Save the model
dump(gb, 'bestmodelyet.joblib')
|