Lalithachintha
commented
2 weeks ago I have exactly followed all the steps given
Open Lalithachintha opened 2 weeks ago
Lalithachintha
commented
2 weeks ago I have exactly followed all the steps given
When executing it, I encountered the following error :
Can someone help me pls?
**Code :** CROSS_VALIDATION_FOLDS = 10 POLYNOMIAL_FEATURES_DEGREE = 2
Create train and test Snowpark DataDrames
train_df, test_df = session.table("MARKETING_BUDGETS_FEATURES").random_split(weights=[0.8, 0.2], seed=0)
Preprocess the Numeric columns
We apply PolynomialFeatures and StandardScaler preprocessing steps to the numeric columns
NOTE: High degrees can cause overfitting.
numeric_features = ['SEARCH_ENGINE','SOCIAL_MEDIA','VIDEO','EMAIL'] numeric_transformer = Pipeline(steps=[('poly',PolynomialFeatures(degree = POLYNOMIAL_FEATURES_DEGREE)),('scaler', StandardScaler())])
Combine the preprocessed step together using the Column Transformer module
preprocessor = ColumnTransformer( transformers=[ ('num', numeric_transformer, numeric_features)])
The next step is the integrate the features we just preprocessed with our Machine Learning algorithm to enable us to build a model
pipeline = Pipeline(steps=[('preprocessor', preprocessor),('classifier', LinearRegression())]) parameteres = {}
Use GridSearch to find the best fitting model based on number_of_folds folds
model = GridSearchCV( estimator=pipeline, param_grid=parameteres, cv=CROSS_VALIDATION_FOLDS, label_cols=["REVENUE"], output_cols=["PREDICTED_REVENUE"], verbose=2 )
Fit and Score
model.fit(train_df) train_r2_score = model.score(train_df) test_r2_score = model.score(test_df)
R2 score on train and test datasets
print(f"R2 score on Train : {train_r2_score}") print(f"R2 score on Test : {test_r2_score}")
Error
SnowparkSQLException: (1304): 01b83a41-0004-21f5-0001-b2ff000694a6: 100357 (P0000): Python Interpreter Error: Traceback (most recent call last): File "/home/udf/7298028005/udf_py_1901916001.zip/udf_py_1901916001.py", line 429, in compute return func(session,arg1,arg2,arg3,arg4) File "/usr/lib/python_udf/15cd5df74ab7fd683d821c71e148956b28181c9e87413b0b6bffb8d2cd402e55/lib/python3.9/site-packages/snowflake/ml/modeling/_internal/snowpark_implementations/distributed_hpo_trainer.py", line 801, in _distributed_search from sklearn.utils.validation import _check_fit_params, indexable ImportError: cannot import name '_check_fit_params' from 'sklearn.utils.validation' (/usr/lib/python_udf/40aaaca3c394c0b2751774fb0239ba44f43487a3f73ef6f34480e87d2cf97f94/lib/python3.9/site-packages/sklearn/utils/validation.py) in function SNOWPARK_TEMP_PROCEDURE_12AC5SCX2R with handler udf_py_1901916001.compute Traceback: File "Cell [cell3]", line 33, in