model run

model-v1.joblib

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41dcd60d356e52288c1c14eab8a25ea684958f04a9000770ed71153e49ad38af
-size 4721680
+oid sha256:9d42378540751e7b97f6d4502eca01baef7afe937fc526b2657339b895aa0158
+size 4721568

train.py

@@ -0,0 +1,36 @@
+import joblib
+
+from sklearn.datasets import fetch_openml
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.compose import make_column_transformer
+from sklearn.pipeline import make_pipeline
+from sklearn.model_selection import train_test_split
+from sklearn.tree import DecisionTreeRegressor
+
+dataset = fetch_openml(data_id=43355, as_frame=True, parser='auto')
+
+diamond_prices = dataset.data
+
+target = ['price']
+numeric_features = ['carat']
+categorical_features = ['shape', 'cut', 'color', 'clarity', 'report', 'type']
+
+X = diamond_prices.drop(columns=target)
+y = diamond_prices[target]
+
+Xtrain, Xtest, ytrain, ytest = train_test_split(
+    X, y,
+    test_size=0.2,
+    random_state=42
+)
+
+preprocessor = make_column_transformer(
+    (StandardScaler(), numeric_features),
+    (OneHotEncoder(handle_unknown='ignore'), categorical_features)
+)
+
+model_pipeline = make_pipeline(preprocessor, DecisionTreeRegressor())
+
+model_pipeline.fit(Xtrain, ytrain)
+
+joblib.dump(model_pipeline, 'model-v1.joblib')