Notice: This page requires JavaScript to function properly.
Please enable JavaScript in your browser settings or update your browser.Challenge: Using DBSCAN Clustering to Detect Outliers | Machine Learning Techniques
course content

Course Content

Data Anomaly Detection

1. What is Anomaly Detection?

General InformationTypes of AnomaliesHow Outliers Influence On Prediction ResultsWhat Should We Do With Detected Outliers

2. Statistical Methods in Anomaly Detection

Rule-based ApproachChallenge: Rule-based Approach1.5 IQR Rule3-Sigma RuleMedian Absolute DeviationChallenge: Outlier Detection Using MAD Rule

3. Machine Learning Techniques

ClusteringChallenge: Using DBSCAN Clustering to Detect OutliersRegularisationChallenge: Solving Task Using RegularisationAutoencoders

Data Anomaly Detection

Challenge: Using DBSCAN Clustering to Detect OutliersChallenge: Using DBSCAN Clustering to Detect Outliers

Task

Now, you will apply the DBSCAN clustering algorithm to detect outliers on a simple Iris dataset.
You have to:

  1. Specify the parameters of the DBScan algorithm: set eps equal to 0.35 and min_samples equal to 6.
  2. Fit the algorithm and provide clustering.
  3. Get outlier indexes and indexes of normal data. Pay attention that outliers detected by the algorithm have a -1 label.

Everything was clear?

Section 3. Chapter 2
toggle bottom row
course content

Course Content

Data Anomaly Detection

1. What is Anomaly Detection?

General InformationTypes of AnomaliesHow Outliers Influence On Prediction ResultsWhat Should We Do With Detected Outliers

2. Statistical Methods in Anomaly Detection

Rule-based ApproachChallenge: Rule-based Approach1.5 IQR Rule3-Sigma RuleMedian Absolute DeviationChallenge: Outlier Detection Using MAD Rule

3. Machine Learning Techniques

ClusteringChallenge: Using DBSCAN Clustering to Detect OutliersRegularisationChallenge: Solving Task Using RegularisationAutoencoders

Data Anomaly Detection

Challenge: Using DBSCAN Clustering to Detect OutliersChallenge: Using DBSCAN Clustering to Detect Outliers

Task

Now, you will apply the DBSCAN clustering algorithm to detect outliers on a simple Iris dataset.
You have to:

  1. Specify the parameters of the DBScan algorithm: set eps equal to 0.35 and min_samples equal to 6.
  2. Fit the algorithm and provide clustering.
  3. Get outlier indexes and indexes of normal data. Pay attention that outliers detected by the algorithm have a -1 label.

Everything was clear?

Section 3. Chapter 2
toggle bottom row
some-alt