DidaWiki

Strumenti Utente

Strumenti Sito

Ti trovi qui: DidaWiki » Data Mining A.A. 2023/24
dm:start

Differenze

Queste sono le differenze tra la revisione selezionata e la versione attuale della pagina.

Link a questa pagina di confronto

Entrambe le parti precedenti la revisione Revisione precedente
Prossima revisione 		Revisione precedente
Prossima revisione Entrambe le parti successive la revisione
dm:start [14/10/2021 alle 12:55 (3 anni fa)]
Mirco Nanni [News] 		dm:start [21/03/2023 alle 07:55 (13 mesi fa)]
Riccardo Guidotti [Second Semester (DM2 - Data Mining: Advanced Topics and Applications)]
Linea 9: Linea 9:
 ga('create', 'UA-34685760-1', 'auto', 'personalTracker', {'allowLinker': true}); ga('create', 'UA-34685760-1', 'auto', 'personalTracker', {'allowLinker': true});
 ga('personalTracker.require', 'linker'); ga('personalTracker.require', 'linker');
-ga('personalTracker.linker:autoLink', ['pages.di.unipi.it', 'enforce.di.unipi.it', 'didawiki.di.unipi.it'] ); +ga('personalTracker.linker:autoLink', ['pages.di.unipi.it', 'enforce.di.unipi.it', 'didawiki.di.unipi.it', 'luciacpassaro.github.io'] );    
-  +
 ga('personalTracker.require', 'displayfeatures'); ga('personalTracker.require', 'displayfeatures');
-ga('personalTracker.send', 'pageview', 'ruggieri/teaching/dm/');+ga('personalTracker.send', 'pageview', 'courses/dm/');
 setTimeout("ga('send','event','adjusted bounce rate','30 seconds')",30000);  setTimeout("ga('send','event','adjusted bounce rate','30 seconds')",30000); 
 </script> </script>
Linea 51: Linea 50:
 </script> </script>
 </html> </html>
-====== Data Mining A.A. 2021/22 ======+====== Data Mining A.A. 2022/23 ======
  
 ===== DM1 - Data Mining: Foundations (6 CFU) ===== ===== DM1 - Data Mining: Foundations (6 CFU) =====
Linea 61: Linea 60:
     * [[dino.pedreschi@unipi.it]]       * [[dino.pedreschi@unipi.it]]  
  
-  * **Mirco Nanni** +  * **Riccardo Guidotti** 
-    * KDDLab, ISTI - CNR, Pisa +    * KDDLab, Università di Pisa 
-    * [[http://www-kdd.isti.cnr.it]] +    * [[https://kdd.isti.cnr.it/people/guidotti-riccardo]]    
-    * [[mirco.nanni@isti.cnr.it]]  +    * [[riccardo.guidotti@di.unipi.it]]
  
 Teaching Assistant Teaching Assistant
-  * **Salvatore Citraro** +  * **Francesco Spinnato** 
-    * KDDLab, Università di Pisa +    * KDDLab, Scuola Normale Superiore 
-    * [[http://www-kdd.isti.cnr.it]] +    * [[https://kdd.isti.cnr.it/people/spinnato-francesco]] 
-    * [[salvatore.citraro@phd.unipi.it]]  +    * [[francesco.spinnato@sns.it]]  
 ===== DM2 - Data Mining: Advanced Topics and Applications (6 CFU) ===== ===== DM2 - Data Mining: Advanced Topics and Applications (6 CFU) =====
  
Linea 79: Linea 78:
     * [[riccardo.guidotti@di.unipi.it]]     * [[riccardo.guidotti@di.unipi.it]]
  
 +Teaching Assistant 
 +  * **Francesco Spinnato** 
 +    * KDDLab, Scuola Normale Superiore 
 +    * [[https://kdd.isti.cnr.it/people/spinnato-francesco]] 
 +    * [[francesco.spinnato@sns.it]]  
 ====== News ====== ====== News ======
-     * **[14.10.2021] The class planned for Monday 18.10.2021 is cancelled for public ceremony.** +     * **[23.02.2023]** Spinnato Booking Agenda: [[https://calendly.com/fspinna/dm|here]] 
-     * [06.09.2021] The first lesson will be held on 16/09/2021.+     * **[20.02.2023]** Project Groups [[https://docs.google.com/spreadsheets/d/1j5A6JPurO6o3ycjb4qc1lKZ4K2HqpdQhb_eyII_37dc/edit?usp=sharing|link]] 
 +     * [23.11.2022] In order to recover from skipped and suspended lectures we signal the presence of two new dates in unusual slots for our lectures, i.e., Wed 7th Dec 14.00-16.00 Room A1 and Wed 14th Dec 14.00-16.00 Room A1. 
 +     * [15.09.2022] Project Groups [[https://docs.google.com/spreadsheets/d/1j5A6JPurO6o3ycjb4qc1lKZ4K2HqpdQhb_eyII_37dc/edit?usp=sharing|link]] 
 +     * [15.09.2022] MS Teams [[https://teams.microsoft.com/l/team/19%3a-E-BCEQRJk-qyKrkyNoos6n4h6neLOfJM4zI5GxY9Us1%40thread.tacv2/conversations?groupId=dfb4c6f2-9430-4eda-8bb4-69bdebd5e01b&tenantId=c7456b31-a220-47f5-be52-473828670aa1|link]]  
 +     * [15.09.2022] Lectures will be in presence only. Registrations of the lectures of past years can be found at the bottom of this web page. 
 +     
 ====== Learning Goals ====== ====== Learning Goals ======
   * DM1   * DM1
Linea 91: Linea 99:
      * Classification      * Classification
      * Pattern Mining and Association Rules      * Pattern Mining and Association Rules
-     * Clustering+     * Sequential Pattern Mining
  
   * DM2   * DM2
      * Outlier Detection      * Outlier Detection
-     * Regression and Forecasting +     * Dimensionality Reduction 
-     * Advanced Classification+     * Regression  
 +     * Advanced Classification and Regression
      * Time Series Analysis      * Time Series Analysis
-     * Sequential Pattern Mining 
-     * Advanced Clustering 
      * Transactional Clustering      * Transactional Clustering
-     * Ethical Issues+     * Explainability
  
 ====== Hours and Rooms ====== ====== Hours and Rooms ======
Linea 110: Linea 117:
  
 ^  Day of Week  ^  Hour  ^  Room  ^  ^  Day of Week  ^  Hour  ^  Room  ^ 
-|  Monday  |  11:00 - 13:00  |  Aula C / [[https://teams.microsoft.com/l/team/19%3aRQK4eHK7Z7ogIuZu84k30riyA7YW6fCTF7f54PblHzc1%40thread.tacv2/conversations?groupId=c101108b-7634-4982-9d61-b38deee14681&tenantId=c7456b31-a220-47f5-be52-473828670aa1|MS Teams]]  |  +|  Monday  |  11:00 - 13:00  |  Aula A1   |  
-|  Thursday  |  11:00 - 13:00  |  Aula A1 / [[https://teams.microsoft.com/l/team/19%3aRQK4eHK7Z7ogIuZu84k30riyA7YW6fCTF7f54PblHzc1%40thread.tacv2/conversations?groupId=c101108b-7634-4982-9d61-b38deee14681&tenantId=c7456b31-a220-47f5-be52-473828670aa1|MS Teams]]  | +|  Thursday  |  11:00 - 13:00  |  Aula A1  | 
  
 **Office hours - Ricevimento:** **Office hours - Ricevimento:**
  
-  * Prof. Pedreschi: Monday 16:00 - 18:00, Online +  * Prof. Pedreschi 
-  * Prof. Nanni: appointment by email, Online+      * Monday 16:00 - 18:00 
 +      * Online 
 +  * Prof. Guidotti 
 +      * Wednesday 15-17 or Appointment by email 
 +      * Room 363 Dept. of Computer Science or MS Teams
  
      
Linea 125: Linea 136:
  
 ^  Day of Week  ^  Hour  ^  Room  ^  ^  Day of Week  ^  Hour  ^  Room  ^ 
-|  Monday  |  14:00 - 16:00  |  [[https://teams.microsoft.com/l/team/19%3aRQK4eHK7Z7ogIuZu84k30riyA7YW6fCTF7f54PblHzc1%40thread.tacv2/conversations?groupId=c101108b-7634-4982-9d61-b38deee14681&tenantId=c7456b31-a220-47f5-be52-473828670aa1|MS Teams]]  |  +|  Monday   |  09:00 - 11:00  |  C1  |  
-|  Wednesday  |  16:00 - 18:00  |  [[https://teams.microsoft.com/l/team/19%3aRQK4eHK7Z7ogIuZu84k30riyA7YW6fCTF7f54PblHzc1%40thread.tacv2/conversations?groupId=c101108b-7634-4982-9d61-b38deee14681&tenantId=c7456b31-a220-47f5-be52-473828670aa1|MS Teams]]  |  +|  Tuesday  |  09:00 - 11:00  |  C1  |  
  
 **Office Hours - Ricevimento:** **Office Hours - Ricevimento:**
  
-  * Room 268 Dept. of Computer Science +  * Wednesday 16.30-18.00 or Appointment by email 
-  * Tuesday: 15-17, Room: MS Teams +  * Room 363 Dept. of Computer Science or MS Teams
-  * Appointment by email+
  
 ====== Learning Material -- Materiale didattico ====== ====== Learning Material -- Materiale didattico ======
Linea 140: Linea 150:
   * Pang-Ning Tan, Michael Steinbach, Vipin Kumar. **Introduction to Data Mining**. Addison Wesley, ISBN 0-321-32136-7, 2006   * Pang-Ning Tan, Michael Steinbach, Vipin Kumar. **Introduction to Data Mining**. Addison Wesley, ISBN 0-321-32136-7, 2006
     * [[http://www-users.cs.umn.edu/~kumar/dmbook/index.php]]     * [[http://www-users.cs.umn.edu/~kumar/dmbook/index.php]]
-    * I capitoli 4, 6, 8 sono disponibili sul sito del publisher. -- Chapters 4,6 and 8 are also available at the publisher's Web site.+    * I capitoli 3, 5, 7 sono disponibili sul sito del publisher. -- Chapters 3,5 and 7 are also available at the publisher's Web site.
   * Berthold, M.R., Borgelt, C., Höppner, F., Klawonn, F. **GUIDE TO INTELLIGENT DATA ANALYSIS.** Springer Verlag, 1st Edition., 2010. ISBN 978-1-84882-259-7   * Berthold, M.R., Borgelt, C., Höppner, F., Klawonn, F. **GUIDE TO INTELLIGENT DATA ANALYSIS.** Springer Verlag, 1st Edition., 2010. ISBN 978-1-84882-259-7
   * Laura Igual et al.** Introduction to Data Science: A Python Approach to Concepts, Techniques and Applications**. 1st ed. 2017 Edition.   * Laura Igual et al.** Introduction to Data Science: A Python Approach to Concepts, Techniques and Applications**. 1st ed. 2017 Edition.
Linea 154: Linea 164:
 ===== Software===== ===== Software=====
  
-  * Python - Anaconda (3.7 version!!!): Anaconda is the leading open data science platform powered by Python. [[https://www.anaconda.com/distribution/| Download page]] (the following libraries are already included)+  * Python - Anaconda (>3.7): Anaconda is the leading open data science platform powered by Python. [[https://www.anaconda.com/distribution/| Download page]] (the following libraries are already included)
   * Scikit-learn: python library with tools for data mining and data analysis [[http://scikit-learn.org/stable/ | Documentation page]]   * Scikit-learn: python library with tools for data mining and data analysis [[http://scikit-learn.org/stable/ | Documentation page]]
   * Pandas: pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. [[http://pandas.pydata.org/ | Documentation page]]   * Pandas: pandas is an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language. [[http://pandas.pydata.org/ | Documentation page]]
 +
 +Other softwares for Data Mining
   * [[http://www.knime.org | KNIME ]] The Konstanz Information Miner. [[http://www.knime.org/download-desktop| Download page ]]   * [[http://www.knime.org | KNIME ]] The Konstanz Information Miner. [[http://www.knime.org/download-desktop| Download page ]]
   * [[http://www.cs.waikato.ac.nz/ml/weka/ | WEKA ]] Data Mining Software in JAVA. University of Waikato, New Zealand [[http://www.cs.waikato.ac.nz/ml/weka/ | Download page ]]   * [[http://www.cs.waikato.ac.nz/ml/weka/ | WEKA ]] Data Mining Software in JAVA. University of Waikato, New Zealand [[http://www.cs.waikato.ac.nz/ml/weka/ | Download page ]]
Linea 165: Linea 177:
 ===== First Semester (DM1 - Data Mining: Foundations) ===== ===== First Semester (DM1 - Data Mining: Foundations) =====
  
-^ ^ Day ^ Room ^ Topic ^ Learning material ^ Recording ^ Instructor ^ +^ ^ Day ^ Time ^ Room ^ Topic ^ Learning Material ^ Lecturer ^ 
-|1.|  16.09.2021  11:00-12:45 | Aula Fib A1 | Introduction. | {{ :dm:1.dm_2021-22.overview-corso.pptx_1_.pdf | Introducing DM1 }} {{ :dm:dm1_project_guidelines.pptx_1_.pdf | Project-work guidelines }} | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/Meeting%20in%20_General_-20210916_111002-Meeting%20Recording.mp4?web=1|Lecture 1]] | Pedreschi | +|01.| 15.09.2022 | 11-13 |A1| Overview, Intro, KDD and CRIPS. | {{ :dm:00_dm1_introduction_2022_23.pdf | Intro}} | Pedreschi/Guidotti | 
-|2.|  20.09.2021  11:00-12:45 | Aula Fib C | Course overview | {{ :dm:2.introduction-short.pdf | Overview of contents }} |[[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/Meeting%20in%20_General_-20210920_111429-Meeting%20Recording.mp4?web=1|Lecture 2]] | Pedreschi | +|   | 19.09.2022 | 11-13 |  | No Lecture |  |  | 
-|3.|  23.09.2021  11:00-12:45 | Aula Fib A1 | Data Understanding | {{ :dm:3.dataunderstanding-2019.pdf | Slides }} | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/Data%20Mining%20Lecture%203-20210923_111708-Meeting%20Recording.mp4?web=1|Lecture 3]] | Pedreschi | +|02.| 22.09.2022 | 11-13 |A1| Project Guideliens & Intro to Python | {{ :dm:dm1_project_guidelines_22_23.pdf | Project Guidelines}}, {{ :dm:dm1_lab01_python_basics.zip | Intro Python}} | Spinnato | 
-|4.|  27.09.2021  11:00-12:45 | Aula Fib C | Data  Preparation  | {{ :dm:3.dm_ml_data_preparation.pdf | Slides }} | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/General-20210927_111919-Meeting%20Recording.mp4?web=1|Lecture 4]] |Pedreschi | +|   | 26.09.2022 | 11-13 |  | No Lecture |  |  | 
-|5.|  30.09.2021  11:00-12:45 | Aula Fib A1 | Lab: Data Understanding & Preparation -- Python  | {{ :dm:python_basics.ipynb.zip |Python Introduction}} Dataset: {{ :dm:iris.csv.zip | Iris}} {{ :dm:hands_on_dm1_pt1.zip |Hands-On Python (Iris)}} | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/General-20210930_110913-Registrazione%20della%20riunione.mp4?web=1|Lecture 5]] |Citraro | +|03.| 29.09.2022 | 11-13 |A1| Data Understanding | {{ :dm:01_dm1_data_understanding_2022_23.pdf | Data Understanding}}  | Pedreschi | 
-|6.|  04.10.2021  11:00-12:45 | Aula Fib C | Lab: Data Understanding & Preparation -- Python (cont.) & KNIME  | Dataset: {{ :dm:titanic.csv.zip | Titanic}} {{ :dm:hands_on_dm1_pt2.zip |Hands-On Python (Titanic)}}, {{ :dm:titanic_data_understanding2.ipynb.zip | Titanic DU+DP (complete)}}  KMIME: {{ :dm:00_start_with_knime.zip | Intro}}, {{ :dm:01_data_understanding.zip | KNIME DU+DP}}  | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/Lecture%206%20-%20Lab_%20Data%20Understanding%20%26%20Preparation%20(cont.)-20211004_110939-Registrazione%20della%20riunione.mp4?web=1|Lecture 6]] | Citraro | +|04.| 03.10.2022 | 11-13 |A1| Data Understanding & Data Preparation  | {{ :dm:02_dm1_data_preparation_2022_23.pdf | Data Preparation}}| Pedreschi | 
-|7. |  07.10.2021  11:00-12:45 | Aula Fib A1 | Clustering: Intro & K-means | {{ :dm:clustering_1_intro-kmeans_v2.pdf |Clustering intro and k-means}} [revised version] | [[https://unipiit.sharepoint.com/sites/a__td_52415/Shared%20Documents/General/Recordings/General-20211007_110727-Meeting%20Recording.mp4?web=1|Lecture 7]] | Nanni | +|05.| 06.10.2022 | 11-13 |A1| Lab. Data Understanding | {{ :dm:data_understanding.zip | Data Und Python}} | Spinnato/Guidotti | 
-| |  <del>11.10.2021  11:00-12:45</del> | <del>Aula Fib C</del> |   | | |  | +|   | 10.10.2022 | 11-13 |  | No Lecture |  |  | 
-|8. |  14.10.2021  11:00-12:45 | Aula Fib A1 | Clustering: k-means | | | Nanni | +|06.| 13.10.2022 | 11-13 |A1| Data Preparation, Similarity | {{ :dm:03_dm1_data_similarity_2022_23.pdf | Data Similarity}}, {{ :dm:data_understanding.zip | Data Und Python}} | Pedreschi | 
-| |  <del>18.10.2021  11:00-12:45</del> | <del>Aula Fib C</del> |  | | |  | +|07.| 17.10.2022 | 11-13 |A1| Intro Clustering, K-Means | {{ :dm:04_dm1_clustering_intro_2022_23.pdf | Intro Clustering}}, {{ :dm:05_dm1_kmeans_2022_23.pdf | K-Means}} | Pedreschi | 
-|9. |  21.10.2021  11:00-12:45 | Aula Fib A1 | Clustering: Hierarchical methods | | | Nanni | +|08.| 20.10.2022 | 11-13 |A1| K-Means | {{ :dm:05_dm1_kmeans_2022_23.pdf | K-Means}} | Pedreschi | 
-|10. |  25.10.2021  11:00-12:45 | Aula Fib C | Clustering: density-base methods & exercises| | | Nanni | +|09.| 24.10.2022 | 11-13 |A1| Hierarchical & Density-based | {{ :dm:06_dm1_hierarchical_clustering_2022_23.pdf | Hierarchical}}, {{ :dm:07_dm1_density_based_2022_23.pdf | Density}} | Pedreschi | 
-|11. |  28.10.2021  11:00-12:45 | Aula Fib A1 | Lab: Clustering | | | Citraro |+|10.| 27.10.2022 | 11-13 |A1| Lab. Clustering | {{ :dm:clustering.zip | Clustering Python}} | Spinnato/Guidotti | 
 +|   | 30.10.2022 | 11-13 |  | No Lecture |  |  | 
 +|11.| 03.11.2022 | 11-13 |A1| Exercises Clustering | {{ :dm:ex1_dm1_clustering_2022_23.pdf | Exercises Clustering}} | Guidotti | 
 +|12.| 07.11.2022 | 11-13 |A1| Intro Classification | {{ :dm:08_dm1_classification_intro_2022_23.pdf | Intro Classification}}, {{ :dm:09_dm1_knn_2022_23.pdf | kNN}} | Guidotti | 
 +|13.| 10.11.2022 | 11-13 |A1| Eval Measures, Exercises kNN | {{ :dm:08_dm1_classification_intro_2022_23.pdf | Intro Classification}}, {{ :dm:09_dm1_knn_2022_23.pdf | kNN}} | Guidotti | 
 +|14.| 14.11.2022 | 11-13 |A1| Decision Tree | {{ :dm:10_dm1_decision_trees_2022_23.pdf | Decision Trees}} | Guidotti | 
 +|15.| 17.11.2022 | 11-13 |A1| Decision Tree, Exercises DT | {{ :dm:10_dm1_decision_trees_2022_23.pdf | Decision Trees}}, {{ :dm:tree_exercise.xlsx | Ex DT}} | Guidotti | 
 +|16.| 22.11.2022 | 11-13 |A1| Decision Tree | {{ :dm:10_dm1_decision_trees_2022_23.pdf | Decision Trees}} | Guidotti | 
 +|17.| 24.11.2022 | 11-13 |A1| Naive Bayes Classifier | {{ :dm:11_dm1_naive_bayes_2022_23.pdf | NBC}} | Guidotti | 
 +|18.| 28.11.2022 | 11-13 |A1| Lab. Classification | {{ :dm:classifcazion.zip | Classification Python}} | Spinnato/Guidotti | 
 +|19.| 01.12.2022 | 11-13 |A1| Intro Regression | {{ :dm:12_dm1_linear_regression_2022_23.pdf | Intro Regression}} | Guidotti | 
 +|20.| 05.12.2022 | 11-13 |A1| Pattern Mining | {{ :dm:13_dm1_pattern_mining_2022_23.pdf | Pattern Mining}} | Pedreschi | 
 +|21.| 07.12.2022 | 14-16 |A1| Pattern Mining | {{ :dm:13_dm1_pattern_mining_2022_23.pdf | Pattern Mining}} | Pedreschi | 
 +|   | 08.12.2022 | 11-13 |  | No Lecture |  |  | 
 +|22.| 12.12.2022 | 11-13 |A1| Exercises Apriori | {{ :dm:ex_apriori.pdf | Exercises Apriori}}, {{ :dm:ex_apriori_sol.pdf | Solutions}}| Guidotti | 
 +|23.| 14.12.2022 | 14-16 |A1| Pattern Mining (FP-Growth) | {{ :dm:13_dm1_pattern_mining_2022_23.pdf | Pattern Mining}} | Guidotti | 
 +|24.| 15.12.2022 | 11-13 |A1| Lab. Pattern Mining | {{ :dm:pattern_mining.zip | Pattern Mining Python}} | Spinnato/Guidotti |
 ===== Second Semester (DM2 - Data Mining: Advanced Topics and Applications) ===== ===== Second Semester (DM2 - Data Mining: Advanced Topics and Applications) =====
  
-^ ^ Day ^ Room ^ Topic ^ Learning material ^ Instructor ^ Recordings ^ +^ ^ Day ^ Room  ^ Topic ^ Learning Material ^ Lecturer ^ 
-|1.| ??.02.2022 ??:00-??:00 | link teams | Introduction, CRIPS, KNN | {{ :dm:00_dm2_intro_2021.pdf | Intro}}, {{ :dm:01_dm2_crispdm_2021.pdf | CRISP}}, {{ :dm:02_dm2_knn_2021.pdf | KNN}} | Guidotti |link registrazione | +| 01.| 20.02.2023 09:00--11:00 |  C1  | Course Overview, Imbalanced Learning | {{ :dm:14_dm2_intro_2022_23.pdf | Intro}}, {{ :dm:15_dm2_imbalanced_learning_2022_23.pdf | ImbLearn}}, {{ :dm:01_dm2_imbalance23.ipynb.zip | LabImbLearn}} | Guidotti |  
 +| 02.| 21.02.2023 09:00--11:00 |  C1  | Dimensionality Reduction | {{ :dm:16_dm2_dimred_2022_23.pdf | DimRed}}, {{ :dm:02_dm2_23_dimensionality_reduction.ipynb.zip | LabDimRed}} | Guidotti |  
 +| 03.| 27.02.2023 09:00--11:00 |  C1  | Outlier Detection: Taxonomy, Stat. & Depth-based | {{ :dm:17_dm2_anomaly_detection_2022_23.pdf |OutDet}} | Guidotti |  
 +| 04.| 28.02.2023 09:00--11:00 |  C1  | Outlier Detection: Distance & Density-based | {{ :dm:17_dm2_anomaly_detection_2022_23.pdf |OutDet}} | Guidotti |  
 +| 05.| 06.03.2023 09:00--11:00 |  C1  | Outlier Detection: Ensemble & Model-based | {{ :dm:17_dm2_anomaly_detection_2022_23.pdf |OutDet}}, {{ :dm:03_dm2_23_outlier_detection.ipynb.zip | LabOutDet}} | Guidotti |  
 +| 06.| 07.03.2023 09:00--11:00 |  C1  | Gradient Descent, Maximum-Likelihood Estimation | {{ :dm:18_dm2_gradient_descent_2022_23.pdf | GD}}, {{ :dm:19_dm2_maximum_likelihood_estimation_2022_23.pdf | MLE}} | Guidotti |  
 +| 07.| 13.03.2023 09:00--11:00 |  C1  | Odds, Odds Ratio, Logistic Regression | {{ :dm:20_dm2_odds_2022_23.pdf | Odds}}, {{ :dm:21_dm2_logistic_regression_2022_23.pdf | LogReg}}, {{ :dm:04_dm2_23_logistic_regression.ipynb.zip | LabLogReg}} | Guidotti |  
 +| 08.| 14.03.2023 09:00--11:00 |  C1  | SVM | {{ :dm:22_dm2_svm_2022_23.pdf | SVM}}, {{ :dm:22_dm2_svm_2022_23.pdf | LabSVM}} | Guidotti |  
 +| 09.| 20.03.2023 09:00--11:00 |  C1  | Neural Networks (Perceptron) | {{ :dm:23_dm2_perceptron_2022_23.pdf | Perceptron}} | Guidotti |  
 +| 10.| 21.03.2023 09:00--11:00 |  C1  | (Deep) Neural Networks | {{ :dm:24_dm2_neural_network_2022_23.pdf | NeuralNetwork}} | Guidotti |  
 +|   | 27.03.2023 09:00--11:00 |  C1  | No Lecture |  | |  
 +|   | 28.03.2023 09:00--11:00 |  C1  | Office Hours (in class) |  | Spinnato | 
 ====== Exams ====== ====== Exams ======
  
-===== Exam DM1 ======+** How and Where: ** 
 +The exam will take place in oral mode only at the teacher's office or classroom previously designated. 
 +The exam will be held online on the 420AA Data Mining course channel only at the request of the 
 +student in accordance with current legislation.
  
-The exam is composed of two parts: +** When: ** 
- +The dates relating to the start of the three exams are/will be published on the online platform 
-  * An **oral exam **, that includes: (1) discussing the project report; (2) discussing topics presented during the classes, including the theory and practical exercises.  +https://esami.unipi.it/. Within each session, we will identify dates and slots in order to distribute the 
- +various orals. The dates and slots to take the exam will be published on the course page by the end of 
-  * A **project**, that consists in exercises requiring the use of data mining tools for analysis of data. Exercises include: data understanding, clustering analysis, frequent pattern mining, and classification (guidelines will be provided for more details). The project has to be performed by min 3, max 4 people. It has to be performed by using Knime, Python or a combination of them. The results of the different tasks must be reported in a unique paper. The total length of this paper must be max 20 pages of text including figures. The paper must be emailed to [[datamining.unipi@gmail.com]]. Please, use “[DM1 2021-2022] Project” in the subject.  +May. Each student must also register on https://esami.unipi.it/. The examination can only be carried out after the delivery of the project. The project must be delivered one week before when you want to take the exam. Group oral discussions will be preferred in respect of the project groups in order to parallelize any discussion on the project. It is not mandatory to take the oral exam together with the other members of the group.  
-=== Project 1 === +In the event that the oral exam is not passed, it will not be possible to take it for 20 days. If the project is not considered sufficient, it must be carried out again on a new dataset or a very updated version of the current one.
-  - Assigned: 30/09/2021 +
-  - MidTerm Deadline: **21/11/2021** (half project required, i.e., Data understanding & Preparation and at least 2 clustering algorithms) +
-  - Final Deadline: **TBD** (complete project required) +
-  - Data: choose between {{ :dm:glasgow_norms.zip | Glasgow Norms}}, {{ :dm:Seismic_Bumps.zip | Seismic Bumps}}+
  
 +** What: ** 
 +The oral test will evaluate the practical understanding of the algorithms. The exam will evaluate three aspects.
 +  - Understanding of the theoretical aspects of the topics addressed during the course. The student may be required to write on formulas or pseudocode. During the explanations, the student can use pen and paper (if online, the student can use the Miro graphic system https://miro.com/ during the explanations)
 +  - Understanding of the algorithms illustrated during the course and their practical implementation. You will be asked to perform one or more simple exercises. The text will be shown on the teacher's screen and / or copied to Miro. The student will have to use pen and paper (if online by Miro https://miro.com/ to show how the exercise is solved.
 +  - Discussion of the project with questions from the teacher regarding unclear aspects,
 +questionable steps or choices.
  
 +** Final Mark: ** for 12-credit exam, the final mark will be obtained as the
 +average mark of DM1 and DM2.
  
 +**Exam Booking Periods**
 +  * Exam portal link: [[https://esami.unipi.it/|here]]
 +  * 1st Appello: 11/12/2022 00:00 - 05/01/2023 23:59
 +  * 2nd Appello: 01/01/2023 00:00 - 26/01/2023 23:59
    
-===== Exam DM part II (DMA) ====== 
- 
-** Exam Rules** 
-  * Rules for DM2 exam available {{ :dm:dm2_exam_rules.pdf | here}}. 
- 
-**Exam Booking Periods** 
-  * 3rd Appello: ??/??/2022 00:00 - ??/??/2022 23:59 
-  * 4th Appello: ??/??/2022 00:00 - ??/??/2022 23:59 
-  * 5th Appello: ??/??/2022 00:00 - ??/??/2022 23:59 
- 
 **Exam Booking Agenda** **Exam Booking Agenda**
-  * Agenda Link: ??? +  * Agenda Link: [[https://agende.unipi.it/nfj-juo-qms|here]] 
-  * 3rd Appello: starts ??/??/2022 +  * 1st Appello: starts 10/01/2023 
-  * 4th Appello: starts ??/??/2022 +  * 2nd Appello: starts 31/01/2023 
-  * 5th Appello: starts ??/??/2022 +===== Exam DM1 ======
-  * Important! if you book in the agenda in data in days between ??/??/2022 and ??/??/2022 you MUST be registered for the 3rd appello, if you book in the agenda in data in days between ??/??/2022 and ??/??/2022 you must be registered for the 4th appello, if you book in the agenda in data in days after ??/??/2022 you must be registered for the 5th appello. +
- +
-The link to the agenda for booking a slot for the exam is displayed at the end of the registration. +
-During the exam the camera must remain open and you must be able to share your screen. For the exam could be required the usage of the Miro platform (https://miro.com/app/dashboard/).+
  
 The exam is composed of two parts: The exam is composed of two parts:
  
-  * A **project**, that consists in employing the methods and algorithms presented during the classes for solving exercises on a given dataset. The project has to be realized by max 3 people. The results of the different tasks must be reported in a unique paper. The total length of this paper must be max 30 pages (suggested 25) of text including figures + 1 cover page (minimum font 11, minimum interline 1). The project must be delivered at least 7 days before the oral exam. The project must be delivered to [[riccardo.guidotti@unipi.it]] AND [[francesco.spinnato@sns.it]] with subject "[DM2 Project]"+  * An **oral exam**, that includes: (1) discussing the project report; (2) discussing topics presented during the classes, including the theory and practical exercises. 
  
-  * An **oral exam**, that includes: (1) discussing topics presented during the classes, including the theory of the parts already covered by the written exam; (2) resolving simple exercises using the Miro platform; (3) discussing the project report with a group presentation;  +  * A **project**, that consists in exercises requiring the use of data mining tools for analysis of data. Exercises include: data understanding, clustering analysis, pattern mining, and classification (guidelines will be provided for more details). The project has to be performed by min 2, max 3 people. It has to be performed by using Python or any other data mining software. The results of the different tasks must be reported in a unique paper. The total length of this paper must be max 20 pages of text including figures. The paper must be emailed to [[francesco.spinnato@sns.it]] and [[riccardo.guidotti@unipi.it]]. Please, use “[DM1 2022-2023] Project” in the subject. 
 +  
 +  * **Dataset** 
 +    - Assigned: 15/09/2021 
 +    - MidTerm Submission: **28/11/2022 (extended)** (half project required, i.e., Data Understanding & Preparation and Clustering) 
 +    - Final Submission: **31/12/2022** or one week before the oral exam (complete project required). 
 +    - Dataset: {{:dm:ravdess_dm1_2223.zip | RAVDESS}} 
 +    - Link original pages: [[https://zenodo.org/record/1188976#.YyLSI-xBz0o| zenodo]], [[https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-speech-audio| kaggle1]], [[https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-song-audio| kaggle2]]
  
-  * **Dataset**: the data is about ??? and can be downloaded here: ??? +** DM1 Project Guidelines ** 
-     * Data can be downloaded here ??? +See {{ :dm:dm1_project_guidelines_22_23.pdf | Project Guidelines}}.
-     * Submission Draft 1: ??/??/2022 23:59 Italian Time (we expect Module 1 and Module 2) +
-     * Submission Draft 2: ??/??/2022 23:59 Italian Time (we expect Module 3) +
-     * Final Submission: one week before the oral exam.+
  
-** Project Guidelines ** 
  
-  * **Module 1 - Introduction, Imbalanced Learning and Anomaly Detection** 
-      - Explore and prepare the dataset. You are allowed to take inspiration from the associated GitHub repository and figure out your personal research perspective (from choosing a subset of variables to the class to predict…). You are welcome in creating new variables and performing all the pre-processing steps the dataset needs. 
-      - Define one or more (simple) classification tasks and solve it with Decision Tree and KNN. You decide the target variable. 
-      - Identify the top 1% outliers: adopt at least three different methods from different families (e.g., density-based, angle-based... ) and compare the results. Deal with the outliers by removing them from the dataset or by treating the anomalous variables as missing values and employing replacement techniques. In this second case, you should check that the outliers are not outliers anymore. Justify your choices in every step. 
-      - Analyze the value distribution of the class to predict with respect to point 2; if it is unbalanced leave it as it is, otherwise turn the dataset into an imbalanced version (e.g., 96% - 4%, for binary classification). Then solve the classification task using the Decision Tree or the KNN by adopting various techniques of imbalanced learning. 
-      - Draw your conclusions about the techniques adopted in this analysis. 
  
-  * **Module 2 - Advanced Classification Methods** 
-      - Solve the classification task defined in Module 1 (or define new ones) with the other classification methods analyzed during the course: Naive Bayes Classifier, Logistic Regression, Rule-based Classifiers, Support Vector Machines, Neural Networks, Ensemble Methods and evaluate each classifier with the techniques presented in Module 1 (accuracy, precision, recall, F1-score, ROC curve). Perform hyper-parameter tuning phases and justify your choices. 
-      - Besides the numerical evaluation draw your conclusions about the various classifiers, e.g. for Neural Networks: what are the parameter sets or the convergence criteria which avoid overfitting? For Ensemble classifiers how the number of base models impacts the classification performance? For any classifier which is the minimum amount of data required to guarantee an acceptable level of performance? Is this level the same for any classifier? What is revealing the feature importance of Random Forests? 
-      - Select two continuous attributes, define a regression problem and try to solve it using different techniques reporting various evaluation measures. Plot the two-dimensional dataset. Then generalize to multiple linear regression and observe how the performance varies. 
  
-  * **Module 3 - Time Series Analysis** +  
-      - Select the feature(s) you prefer and use it (them) as a time series. You can use the temporal information provided by the authors’ datasets, but you are also welcome in exploring the .mp3 files to build your own dataset of time series according to your purposes. You should prepare a dataset on which you can run time series clustering; motif/anomaly discovery and classification.  +===== Exam DM2 ======
-      - On the dataset created, compute clustering based on Euclidean/Manhattan and DTW distances and compare the results. To perform the clustering you can choose among different distance functions and clustering algorithms. Remember that you can reduce the dimensionality through approximation. Analyze the clusters and highlight similarities and differences. +
-      - Analyze the dataset for finding motifs and/or anomalies. Visualize and discuss them and their relationship with other features. +
-      - Solve the classification task on the time series dataset(s) and evaluate each result. In particular, you should use shapelet-based classifiers. Analyze the shapelets retrieved and discuss if there are any similarities/differences with motifs and/or shapelets. +
  
-  * **Module 4 - Sequential Patterns and Advanced Clustering**  +The exam is composed of two parts:
-      - Sequential Pattern Mining: Convert the time series into a discrete format (e.g., by using SAX) and extract the most frequent sequential patterns (of at least length 3/4) using different values of support, then discuss the most interesting sequences. +
-      - Advanced Clustering: On a dataset already prepared for one of the previous tasks in Module 1 or Module 2, run at least one clustering algorithm presented in the advanced clustering lectures (e.g. X-Means, Bisecting K-Means, OPTICS). Discuss the results that you find analyzing the clusters and reporting external validation measures (e.g SSE, silhouette). +
-      - Transactional Clustering: By using categorical features, or by turning a dataset with continuous variables into a dataset with categorical variables (e.g. by using binning), run at least one clustering algorithm presented in the transactional clustering lectures (e.g. K-Modes, ROCK). Discuss the results that you find analyzing the clusters and reporting external validation measures (e.g SSE, silhouette).+
  
-  * **Module 5 - Explainability (optional)**  +  * An **oral exam**, that includes: (1) discussing the project report; (2) discussing topics presented during the classes, including the theory and practical exercises. 
-      - Try to use one or more explanation methods (e.g., LIME, LORE, SHAP, etc.) to illustrate the reasons for the classification in one of the steps of the previous tasks.+
  
 +  * A **project**, that consists in exercises requiring the use of data mining tools for analysis of data. Exercises include: imbalanced learning, dimensionality reduction, outlier detection, advanced classification/regression methods, time series analysis/clustering/classification (guidelines will be provided for more details). The project has to be performed by min 1, max 3 people. It has to be performed by using Python or any other data mining software. The results of the different tasks must be reported in a unique paper. The total length of this paper must be max 30 pages of text including figures. The paper must be emailed to [[francesco.spinnato@sns.it]] and [[riccardo.guidotti@unipi.it]]. Please, use “[DM2 2022-2023] Project” in the subject.
 + 
 +  * **Dataset**
 +    - Assigned: 20/02/2023
 +    - MidTerm Submission: **20/04/2023** (Modules 1 and 2)
 +    - Final Submission: **31/05/2023** or one week before the oral exam (complete project required).
 +    - Dataset: {{ :dm:ravdess_dm2_2223.zip | RAVDESS2}}
 +    - Link original pages: [[https://zenodo.org/record/1188976#.YyLSI-xBz0o| zenodo]], [[https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-speech-audio| kaggle1]], [[https://www.kaggle.com/datasets/uwrfkaggler/ravdess-emotional-song-audio| kaggle2]]
  
- +** DM2 Project Guidelines ** 
- +See {{ :dm:dm2_project_guidelines_22_23.pdf |Project Guidelines}}.
-N.B. When "solving the classification task", remember, (i) to test, when needed, different criteria for the parameter estimation of the algorithms, and (ii) to evaluate the classifiers (e.g., Accuracy, F1, Lift Chart) in order to compare the results obtained with an imbalanced technique against those obtained from using the "original" dataset. +
  
  
Linea 272: Linea 300:
  
 ===== Exam Sessions ===== ===== Exam Sessions =====
-^ Session ^ Date            ^ Time        ^ Room   ^ Notes ^ Marks ^ +^ Session ^ Date  ^ Room   ^ Notes ^ Marks ^ 
-|1.|16.01.2019| 14:00 - 18:00| [[https://teams.microsoft.com/l/team/19%3aeebd8a88148d433582ca36bc54d6e441%40thread.tacv2/conversations?groupId=adba5ac4-f242-40be-b8aa-e375da1d4f2c&tenantId=c7456b31-a220-47f5-be52-473828670aa1|MS Teams]] | Please, use the system for registration: https://esami.unipi.it/ | | +|1.|10.01.2023| | Please, use the system for registration: https://esami.unipi.it/ | | 
 +|2.|31.01.2023| | Please, use the system for registration: https://esami.unipi.it/ | | 
 +|3.|??.??.2023| | Please, use the system for registration: https://esami.unipi.it/ | | 
 +|4.|??.??.2023| | Please, use the system for registration: https://esami.unipi.it/ | | 
 +|5.|??.??.2023| | Please, use the system for registration: https://esami.unipi.it/ | | 
 +|6.|??.??.2023| | Please, use the system for registration: https://esami.unipi.it/ | |
 ===== Past Exams ===== ===== Past Exams =====
   * Past exams texts can be found in old pages of the course. Please do not consider these exercises as a unique way of testing your knowledge. Exercises can be changed and updated every year and will be published together with the slides of the lectures.   * Past exams texts can be found in old pages of the course. Please do not consider these exercises as a unique way of testing your knowledge. Exercises can be changed and updated every year and will be published together with the slides of the lectures.
Linea 291: Linea 323:
   * Special issue of Crossroads - The ACM Magazine for Students - on Big Data Analytics {{:dm:crossroadsxrds2012fall-dl.pdf|download}}   * Special issue of Crossroads - The ACM Magazine for Students - on Big Data Analytics {{:dm:crossroadsxrds2012fall-dl.pdf|download}}
   * Peter Sondergaard, Gartner, Says Big Data Creates Big Jobs. Oct 22, 2012: [[https://www.youtube.com/watch?v=mXLy3nkXQVM|YouTube video]]   * Peter Sondergaard, Gartner, Says Big Data Creates Big Jobs. Oct 22, 2012: [[https://www.youtube.com/watch?v=mXLy3nkXQVM|YouTube video]]
- 
   * Towards Effective Decision-Making Through Data Visualization: Six World-Class Enterprises Show The Way. White paper at FusionCharts.com. [[http://www.fusioncharts.com/whitepapers/downloads/Towards-Effective-Decision-Making-Through-Data-Visualization-Six-World-Class-Enterprises-Show-The-Way.pdf|download]]   * Towards Effective Decision-Making Through Data Visualization: Six World-Class Enterprises Show The Way. White paper at FusionCharts.com. [[http://www.fusioncharts.com/whitepapers/downloads/Towards-Effective-Decision-Making-Through-Data-Visualization-Six-World-Class-Enterprises-Show-The-Way.pdf|download]]
  
 ====== Previous years ===== ====== Previous years =====
 +  * [[dm.2021-22ds]]
   * [[dm.2020-21]]   * [[dm.2020-21]]
-   * [[dm.2019-20]] +  * [[dm.2019-20]] 
-   * [[dm.2018-19]] +  * [[dm.2018-19]] 
-   * [[dm.2017-18]]+  * [[dm.2017-18]]
   * [[dm.2016-17]]   * [[dm.2016-17]]
   * [[dm.2015-16]]   * [[dm.2015-16]]
Linea 305: Linea 337:
   * [[dm.2012-13]]   * [[dm.2012-13]]
   * [[dm.2011-12]]   * [[dm.2011-12]]
-  * [[dm.2010-11]] 
-  * [[dm.2009-10]] 
-  * [[dm.2008-09]] 
-  * [[dm.2007-08]] 
-  * [[dm.2006-07]] 
-  * [[PhDWorkshop2011]] 
-  * [[SNA.Ingegneria2011]] 
-  * [[SNA.IMT.2011]] 
-  * [[MAINS.SANTANNA.2011-12]] 
-  * [[MAINS.SANTANNA.DM4CRM.2012]] 
-  * [[MAINS.SANTANNA.DM4CRM.2016]] 
-  * [[MAINS.SANTANNA.DM4CRM.2017 | Data Mining for Customer Relationship Management 2017]] 
-  * [[MAINS.SANTANNA.DM4CRM.2018]] 
-  * [[MAINS.SANTANNA.DM4CRM.2019]] 
-  * [[SDM2018 | Instructions for camera ready and copyright transfer]] 
-  * [[DM-SAM | Storie dell'Altro Mondo]] 
-  * [[DM-I40 | Master Industry 4.0]] 
  
dm/start.txt · Ultima modifica: 16/04/2024 alle 16:21 (30 minuti fa) da Riccardo Guidotti

Strumenti Pagina

Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki