Spaces:
Sleeping
Sleeping
File size: 2,424 Bytes
9252403 |
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 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 |
import joblib
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.impute import SimpleImputer
from sklearn.pipeline import Pipeline
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error
# Load the dataset
df = pd.read_csv("insurance.csv")
# Define features and target
target = 'charges'
numerical_features = ['age', 'bmi', 'children']
categorical_features = ['sex', 'smoker', 'region']
print("Creating data subsets")
X = df[numerical_features + categorical_features]
y = df[target]
Xtrain, Xtest, ytrain, ytest = train_test_split(
X, y,
test_size=0.2,
random_state=42
)
# Define the numerical and categorical pipelines
numerical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='median')),
('scaler', StandardScaler())
])
categorical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='most_frequent')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
preprocessor = make_column_transformer(
(numerical_pipeline, numerical_features),
(categorical_pipeline, categorical_features)
)
# Define the Random Forest model with the best parameters
model_random_forest = RandomForestRegressor(
n_estimators=125,
min_samples_split=3,
min_samples_leaf=4,
max_depth=25,
random_state=42,
n_jobs=-1
)
print("Estimating Best Model Pipeline")
model_pipeline = Pipeline([
('preprocessor', preprocessor),
('regressor', model_random_forest)
])
# Train the model
model_pipeline.fit(Xtrain, ytrain)
# Predict on the test set
y_pred = model_pipeline.predict(Xtest)
# Calculate evaluation metrics
mae = mean_absolute_error(ytest, y_pred)
mse = mean_squared_error(ytest, y_pred)
rmse = np.sqrt(mse)
r2 = r2_score(ytest, y_pred)
print("Logging Metrics")
print(f"Mean Absolute Error (MAE): {mae}")
print(f"Mean Squared Error (MSE): {mse}")
print(f"Root Mean Squared Error (RMSE): {rmse}")
print(f"R-squared (R²): {r2}")
print("Serializing Model")
# Save the model to a file
saved_model_path = "random_forest_pipeline.pkl"
joblib.dump(model_pipeline, saved_model_path)
print(f"Model saved as {saved_model_path}")
|