Spaces:
Sleeping
Sleeping
File size: 1,750 Bytes
dd5531a |
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 |
import joblib
import pandas as pd
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import make_column_transformer
from sklearn.pipeline import make_pipeline, Pipeline
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error, r2_score
data_df = pd.read_csv("insurance.csv")
#dataset = fetch_openml(name='insurance')
#data_df = dataset.data
target = 'charges'
numeric_features = ['age', 'bmi', 'children']
categorical_features = ['sex', 'smoker', 'region']
print("Creating data subsets")
X = data_df[numeric_features + categorical_features]
y = data_df[target]
Xtrain, Xtest, ytrain, ytest = train_test_split(
X, y,
test_size=0.2,
random_state=42
)
numerical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='median')), # No missing!
('scaler', StandardScaler())
])
categorical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy='most_frequent')),
('onehot', OneHotEncoder(handle_unknown='ignore'))
])
preprocessor = make_column_transformer(
(numerical_pipeline, numeric_features),
(categorical_pipeline, categorical_features)
)
model_logistic_regression = LinearRegression(n_jobs=-1)
print("Estimating Model Pipeline")
model_pipeline = make_pipeline(
preprocessor, # Applying preprocessing steps
model_logistic_regression # Training logistic regression model
)
model_pipeline.fit(Xtrain, ytrain)
print("Logging Metrics")
print(f"R-squared: {r2_score(ytest, model_pipeline.predict(Xtest))}")
print("Serializing Model")
saved_model_path = "model.joblib"
joblib.dump(model_pipeline, saved_model_path)
|