+
+
+
+
+
+
+In [82]:
+
+
+
+
+
+
+# References model found by GridSearchCV
+logregbm = grid_search.best_estimator_
+# Loads in testing data
+lr_y_pred = logregbm.predict(X_test)
+# Assesses, prints accuracy of model's predictions to actual quartiles
+logregacc = accuracy_score(y_test, lr_y_pred)
+logregpre = precision_score(y_test, lr_y_pred, average='weighted')
+logregf1 = f1_score(y_test, lr_y_pred, average='weighted')
+logregrecall = recall_score(y_test, lr_y_pred, average='weighted')
+print(f"Accuracy: {logregacc:.4f}")
+print(f"Precision: {logregpre:.4f}")
+print(f"F1: {logregf1:.4f}")
+print(f"Recall: {logregrecall:.4f}")
+# Creates confusion matrixes and classification report detailing strengths and weaknesses of models' predictions
+ConfusionMatrixDisplay.from_estimator(logregbm, X_test, y_test, cmap = plt.cm.Reds, normalize = 'true')
+plt.show()
+print(confusion_matrix(y_test, lr_y_pred))
+print(classification_report(y_test, lr_y_pred))
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Accuracy: 0.6899 +Precision: 0.6907 +F1: 0.6903 +Recall: 0.6899 ++
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+[[203 56 10 1] + [ 56 154 50 7] + [ 12 51 170 39] + [ 1 9 42 216]] + precision recall f1-score support + + Q1 0.75 0.75 0.75 270 + Q2 0.57 0.58 0.57 267 + Q3 0.62 0.62 0.62 272 + Q4 0.82 0.81 0.81 268 + + accuracy 0.69 1077 + macro avg 0.69 0.69 0.69 1077 +weighted avg 0.69 0.69 0.69 1077 + ++
+
+
+
+
+
+
+
+