import numpy as np import pandas as pd from sklearn.model_selection import train_test_split from sklearn.metrics import roc_auc_score from tpot import TPOTClassifier # Load your dataset data = pd.read_csv('bitcoin_data.csv') # Split your dataset into training and testing sets X_train, X_test, y_train, y_test = train_test_split(data.drop('price', axis=1), data['price'], test_size=0.2, random_state=42) # Initialize the TPOT classifier tpot = TPOTClassifier(generations=5, population_size=20, verbosity=2, scoring='roc_auc') # Fit the classifier to the training data tpot.fit(X_train, y_train) # Get the best model from the TPOT classifier best_model = tpot.fitted_pipeline_ # Get the AUC score for the model on the test set auc_score = roc_auc_score(y_test, best_model.predict(X_test)) print(f'AUC score for the best model: {auc_score}')