--- UFC Fight Predictor: Best Model Analysis ---

--- Data Division ---
The dataset was split chronologically into two sets:
- Training Set: Used to train the models. Contains 727 events.
- Test Set: Used to evaluate model performance. Contains 10 events.

--- Feature Explanation ---
Each fight is converted into a feature vector representing the difference between the two fighters.
Features include base stat differentials (elo, height, reach) and historical performance metrics
(e.g., difference in wins, opponent ELO, and KO percentages from the last 5 fights).

--- Performance Metrics ---
The models listed below were trained on the Training Set and evaluated against the Test Set.
'Accuracy' represents the percentage of fights in the test set that the model predicted correctly.
Higher values for Accuracy, Balanced Accuracy, ROC AUC, and F1 Score are better.

--- Model Performance Ranking ---
                               Accuracy  Balanced Accuracy  ROC AUC  F1 Score  Time Taken
Model                                                                                    
ExtraTreesClassifier               0.92               0.92     0.92      0.92        3.50
XGBClassifier                      0.90               0.90     0.90      0.90        0.47
LGBMClassifier                     0.89               0.89     0.89      0.89        3.19
AdaBoostClassifier                 0.89               0.89     0.89      0.89        0.61
NuSVC                              0.89               0.89     0.89      0.89       21.76
RandomForestClassifier             0.89               0.89     0.89      0.89        3.60
RidgeClassifier                    0.88               0.88     0.88      0.88        0.05
CalibratedClassifierCV             0.88               0.88     0.88      0.88        0.18
LogisticRegression                 0.88               0.88     0.88      0.88        0.13
LinearDiscriminantAnalysis         0.88               0.88     0.88      0.88        0.19
BernoulliNB                        0.88               0.88     0.88      0.88        0.05
SVC                                0.88               0.88     0.88      0.88       10.24
RidgeClassifierCV                  0.88               0.88     0.88      0.88        0.04
LinearSVC                          0.88               0.88     0.88      0.88        0.12
SGDClassifier                      0.87               0.87     0.87      0.87        0.08
BaggingClassifier                  0.86               0.86     0.86      0.86        1.14
PassiveAggressiveClassifier        0.86               0.86     0.86      0.86        0.11
KNeighborsClassifier               0.86               0.86     0.86      0.86        0.11
GaussianNB                         0.86               0.86     0.86      0.86        0.04
NearestCentroid                    0.86               0.86     0.86      0.86        0.09
LabelSpreading                     0.82               0.82     0.82      0.82       51.25
ExtraTreeClassifier                0.81               0.81     0.81      0.81        0.06
DecisionTreeClassifier             0.80               0.80     0.80      0.80        0.25
LabelPropagation                   0.80               0.80     0.80      0.80       32.01
QuadraticDiscriminantAnalysis      0.64               0.64     0.64      0.64        0.04
Perceptron                         0.62               0.62     0.62      0.58        0.06
DummyClassifier                    0.50               0.50     0.50      0.33        0.04