Wine Data Set

Classify wine grown in Italy

Data Set Information:

These data are the results of a chemical analysis of wines grown in the same region in Italy but derived from three different cultivars. The analysis determined the quantities of 13 constituents found in each of the three types of wines. 

We think that the initial data set had around 30 variables, but for some reason I only have the 13 dimensional version. We had a list of what the 30 or so variables were, but a.) we lost it, and b.), we would not know which 13 variables are included in the set. 

The attributes are (dontated by Riccardo Leardi, riclea '@' anchem.unige.it ) 

Source:

Original Owners: 

Forina, M. et al, PARVUS - 
An Extendible Package for Data Exploration, Classification and Correlation. 
Institute of Pharmaceutical and Food Analysis and Technologies, Via Brigata Salerno, 
16147 Genoa, Italy. 

Donor: 

Stefan Aeberhard, email: stefan '@' coral.cs.jcu.edu.au


Evaluation

The evaluation of this dataset is done using Area Under the ROC curve (AUC).

An example of its application are ROC curves. Here, the true positive rates are plotted against false positive rates. An example is below. The closer AUC for a model comes to 1, the better it is. So models with higher AUCs are preferred over those with lower AUCs.

Please note, there are also other methods than ROC curves but they are also related to the true positive and false positive rates, e. g. precision-recall, F1-Score or Lorenz curves.

                                            Example of a ROC curve

AUC is used most of the time to mean AUROC,  AUC is ambiguous (could be any curve) while AUROC is not.


Interpreting the AUROC

The AUROC has several equivalent interpretations:

  • The expectation that a uniformly drawn random positive is ranked before a uniformly drawn random negative.
  • The expected proportion of positives ranked before a uniformly drawn random negative.
  • The expected true positive rate if the ranking is split just before a uniformly drawn random negative.
  • The expected proportion of negatives ranked after a uniformly drawn random positive.
  • The expected false positive rate if the ranking is split just after a uniformly drawn random positive.

Computing the AUROC

Assume we have a probabilistic, binary classifier such as logistic regression.

Before presenting the ROC curve (= Receiver Operating Characteristic curve), the concept ofconfusion matrix must be understood. When we make a binary prediction, there can be 4 types of outcomes:

  • We predict 0 while we should have the class is actually 0: this is called a True Negative, i.e. we correctly predict that the class is negative (0). For example, an antivirus did not detect a harmless file as a virus .
  • We predict 0 while we should have the class is actually 1: this is called a False Negative, i.e. we incorrectly predict that the class is negative (0). For example, an antivirus failed to detect a virus.
  • We predict 1 while we should have the class is actually 0: this is called a False Positive, i.e. we incorrectly predict that the class is positive (1). For example, an antivirus considered a harmless file to be a virus.
  • We predict 1 while we should have the class is actually 1: this is called a True Positive, i.e. we correctly predict that the class is positive (1). For example, an antivirus rightfully detected a virus.

To get the confusion matrix, we go over all the predictions made by the model, and count how many times each of those 4 types of outcomes occur:

enter image description here

In this example of a confusion matrix, among the 50 data points that are classified, 45 are correctly classified and the 5 are misclassified.

Since to compare two different models it is often more convenient to have a single metric rather than several ones, we compute two metrics from the confusion matrix, which we will later combine into one:

  • True positive rate (TPR), aka. sensitivity, hit rate, and recall, which is defined as TPTP+FN. Intuitively this metric corresponds to the proportion of positive data points that are correctly considered as positive, with respect to all positive data points. In other words, the higher TPR, the fewer positive data points we will miss.
  • False positive rate (FPR), aka. fall-out, which is defined as FPFP+TN. Intuitively this metric corresponds to the proportion of negative data points that are mistakenly considered as positive, with respect to all negative data points. In other words, the higher FPR, the more negative data points we will missclassified.

To combine the FPR and the TPR into one single metric, we first compute the two former metrics with many different threshold (for example 0.00;0.01,0.02,,1.00) for the logistic regression, then plot them on a single graph, with the FPR values on the abscissa and the TPR values on the ordinate. The resulting curve is called ROC curve, and the metric we consider is the AUC of this curve, which we call AUROC.

The following figure shows the AUROC graphically:

enter image description here

In this figure, the blue area corresponds to the Area Under the curve of the Receiver Operating Characteristic (AUROC). The dashed line in the diagonal we present the ROC curve of a random predictor: it has an AUROC of 0.5. The random predictor is commonly used as a baseline to see whether the model is useful.

If you want to get some first-hand experience:

Source : http://stats.stackexchange.com/questions/132777/what-does-auc-stand-for-and-what-is-it

Rules

  • One account per participant

    You cannot sign up from multiple accounts and therefore you cannot submit from multiple accounts.

  • No private sharing outside teams

    Privately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.

  • Submission Limits

    You may submit a maximum of 5 entries per day.

    You may select up to 2 final submissions for judging.

Specific Understanding

  • Use of external data is not permitted. This includes use of pre-trained models.
  • Hand-labeling is allowed on the training dataset only. Hand-labeling is not permitted on test data and will be grounds for disqualification.