Spaces:
Sleeping
Sleeping
| import os | |
| import hopsworks | |
| import numpy as np | |
| from catboost import CatBoostRegressor | |
| class Predict: | |
| def __init__(self): | |
| """ Initialization code goes here: | |
| - Download the model artifact | |
| - Load the model | |
| """ | |
| # Add seed for reproducibility | |
| np.random.seed(42) | |
| project = hopsworks.login() | |
| mr = project.get_model_registry() | |
| dataset_api = project.get_dataset_api() | |
| # Download model | |
| my_model = mr.get_best_model("grailed_prediction_catboost_model", "RMSLE", 'max') | |
| model_dir = my_model.download() | |
| # Download feature engineering file | |
| current_dir = os.getcwd() | |
| feature_engineering_file = dataset_api.download( | |
| "Resources/feature_engineering.py", overwrite=True | |
| ) | |
| # Load the feature engineering file into the current path | |
| import sys | |
| sys.path.append(current_dir) | |
| # Load the feature engineering file | |
| from feature_engineering import engineering_all_features | |
| self.engineering_all_features = engineering_all_features | |
| # Print the feature engineering parameters | |
| print(self.engineering_all_features) | |
| # Load the saved model | |
| self.model = CatBoostRegressor() | |
| self.model.load_model(f"{model_dir}/model.json") | |
| # Define the embedding features (same as in training) | |
| self.embedding_features = ['designer_names', 'hashtags', 'description', 'title'] | |
| def predict(self, inputs): | |
| """ Serve predictions using the trained model""" | |
| """ | |
| Expects inputs as a dictionary with the same features used in training: | |
| - designer_names (list of strings, in original API it's just a string) | |
| - category_path (string) | |
| - color (string) | |
| - condition (string) | |
| - followerno (int) | |
| - hashtags (list of strings) | |
| - description (string) | |
| - title (string) | |
| """ | |
| labels = ["designer_names", "category_path", "color", "condition", "followerno", "hashtags", "description", "title", "size"] | |
| transformed_features = self.engineering_all_features([inputs], labels) | |
| polars_df = transformed_features[0] | |
| pandas_df = polars_df.to_pandas() | |
| print(f"{pandas_df}=") | |
| # Drop size column | |
| pandas_df = pandas_df.drop(columns=["size"]) | |
| # Make prediction | |
| prediction = self.model.predict(pandas_df) | |
| return float(prediction[0]) # Return single prediction value |