BDS4440 Advanced Programming for AI and Big Data
Course number/section: BDS4440 Instructor Name: Joe Ganser
Course name: Advanced Programming for AI Big Data and Cloud Computing
Prerequisite: BDS 2240 Instructor Email:
Credit Hours: 3 Credits Office Hours:
Classroom Number:
Syllabus Author: Joe Ganser
COURSE DESCRIPTION
This course is designed to provide students with advanced machine learning and Python programming skills to learn today’s most compelling leading-edge computing technologies including AI, big data and cloud case studies on natural language processing, machine learning, deep learning, computer vision, Hadoop, Spark and the internet of things.
COURSE LEARNING OBJECTIVES
At the successful conclusion of this course, students will be able to:
REQUIRED RESOURCES
To improve student learning and provide students with a more enjoyable academic experience, a customized eText and/or digital learning resources are provided for this course. These customized learning resources are preloaded into this course and are accessible through the course Canvas site.
For assistance with issues related to customized eText access, contact: helpdesk@BerkeleyCollege.edu or call 973-278-5400 ext. 1540.
Texts
GRADING POLICY
All assignments are submitted on Canvas by the due date/time required. All grading is done by the rubrics. Please check your Canvas grade book regularly and review grading feedback. Feel free to contact me during my office hours if you have any question or concern about your grades.
Grades in this course are based on a weighted average, as follows:
% | Component | Learning Objectives |
10 | Class Discussion | #1, #2, #7 |
50 | Homeworks | #1-#7 |
40 | Final Project |
Class Discussion
Each week there will be discussion questions. Students should answer the question and participate in feedback of other student’s responses.
40% Final Project
No tests - just homeworks and projects! Use any resources needed, just don’t plagiarize. Always cite sources properly.
FINAL PROJECT
Final Project will be the presentation of a data science project in a web based format.
It must include a presentation of analysis on data. I will give reference links to data sources.
It will include two major components:
Main objectives of the project:
Project Criteria:
Options of the project
See my own blog for reference example: https://JoeGanser.github.io. To pass the course, you must pass & complete the final project.
Final Project Grading Rubric | |||
Proficient (90-100 %) | Competent 70-80% | Novice 60-70% | Below expectations Below 60% |
Contextual information was relevant and clearly explained. Clear evidence of a thoughtful approach to the project. Every analytical technique is given an accurate justifiable reasoning for its use. Sources cited, code well written | Contextual information was relevant and sufficiently explained. Some evidence of a thoughtful approach to the project, but not all techniques are justified using the scientific method. Sources cited, and code is decent but not at professional level. | Contextual information was brief and/or vague. Limited evidence of a thoughtful project approach | Contextual information lacks relevance and quality No evidence of a thoughtful approach to the project. |
GRADING SCALE
100-90% | A |
| 79-75% | C+ |
89-85% | B+ |
| 74-70% | C |
84-80% | B |
| 69-60% | D |
|
| Below 60 = F |
| |
Syllabus
Week | Topic | Text Source | Assessments |
1 | Files and Exception Text files, JSONs, pickle files, try except finally clauses, raising errors, CSV files | Ch 9 | Ch9 Problems 1-6 |
2 | Object Oriented Programming Simulating private attributes, Case studies, Inheritance, inheritance hierarchy, polymorphisms, docstrings, namespaces, scope, simple regression | Ch 10-10.17 | Ch10 Problems 2,3,4,6,9 Ch9 Problem 7 |
3 | Recursion, Searching, Sorting and Big O Factorials, recursion, iteration, searching, sorting, linear search, algorithm efficiency | Ch 11-11.8 | Ch11 Problems 1-6 Ch10 problem 12 Ch9 problem 16 |
4 | Recursion, Searching, Sorting and Big O Binary Search, sorting, selection, insertion, merging, visualizing Natural Language Processing (NLP) Text blob, Visualizing Word frequencies with bar charts and word clouds | Ch 11.9-11.16 Ch 12-12.3 | Ch11 Problem 8,13,14 Ch12 Problems 1,2,3 Ch9 Problem 16 |
5 | Natural Language Processing (NLP) Text blob, Visualizing Word frequencies with bar charts and word clouds | Ch 12.3-12.14 | Ch12 Problems 4-12 Ch 10 Problem 18 |
6 | Data Mining Twitter Twitter API, Creating an App, Tweepy, Getting twitter data, Searching tweets | Ch 13-13.10 | Ch 13 Problems Ch 11 Problem 18 |
7 | Data Mining Twitter Spotting twitter trends, cleaning tweet data, streaming twitter APIs, sentiment analysis, geocoding and mapping, storing tweets, time series | Ch 13.11-13.18 | Ch 13 Problems Ch 12 Problem 17 |
8 | Machine Learning: Classification, Regression and Clustering Types of ML, Classification case studies, Time series and regression | Ch 15.1-15.4 | Ch 15 Problems 3,4,6,7,8,11,12 Ch10 Problem 11 |
9 | Machine Learning: Classification, Regression and Clustering Multiple Regression, Dimensionality Reduction, Kmeans | Ch15.5-15.8 | Ch 15 Problems 1,2,5,15,17,18 Ch 11 Problem 19 |
10 | Deep Learning Keras, Neural Networks, Tensors, CNNs | Ch16.1-16.6 | Ch16 Problems 1-6 Ch15 Problem 19 |
11 | Deep Learning Visualizing Neural Networks, RNNs, Tuning Neural Networks, Pretrained Models and Reinforcement Learning | Ch16.7-16.13 | Ch16 Problems 7-13 Ch15 Problem 20 |
12 | Big Data SQL, NoSQL and MongoDB | Ch 17.1-17.4 | Ch17 Problems 1-7 Ch13 Problem 18 |
13 | Big Data Hadoop, Spark, IoT | Ch 17.5-17.9 | Ch17 Problems 8-14 Ch 16 Problem 15,16 |
14 | Association Rules: Frequent Itemset Generation, Rule Generation, Compact Representation of frequent itemsets, FP-Growth Algorithm, Evaluation of Association Patterns | Second Text Ch 6 | Ch6 Second Text Problems 1-6 ==== Ch15 (first text) Problem 29 Ch11 Problem 20 |
15 | Unsupervised Learning: K means,Agglomerative Clustering and DB Scan | Second Text: Ch 8 | |
Final Project Presentation |
BIBLIOGRAPHY OF REFERENCE TEXTS
Berkeley College complies with Section 504 of the Rehabilitation Act of 1973 and the Americans with Disabilities Act of 1990, as amended by the ADA Amendments Act of 2008. Any student who seeks a reasonable accommodation of a disability with respect to an academic matter should obtain a Berkeley College Request for Accommodation of Disability Form, as soon as the need becomes apparent, from one of the following ADA Coordinators: 1) NJ Campuses and OL Campus: Sandra Coppola – (973) 278-5400, ext. 1320, sec@BerkeleyCollege.edu; 2) NY Campuses: Diane Georges - (212) 986-4343, ext. 4216 diane-georges@berkeleycollege.edu or Disability Services directly at DisabilityServices@berkeleycollege.edu. The student should specify on this form the accommodation sought, as well as the reason for and duration of the need, and attach appropriate supporting documentation when submitting this signed form to one of the ADA Coordinators. The eligibility for an academic accommodation will be determined based upon the level of disability, its impact on learning, and the College’s ability to provide the accommodation without incurring undue burden or fundamentally altering its programs, facilities, policies, or activities. Specific details of the disability will remain confidential between the student and the ADA Coordinator/Director of Disability Services, unless the student chooses to disclose, or there is a legitimate academic need for disclosure, on a case-by-case basis."
CREDIT HOUR ASSIGNMENT POLICY
Course work performed outside of the classroom (such as reading, studying, writing papers, doing projects or receiving tutoring) is critical to academic success. While the time requirements for individual students may vary somewhat, a general rule of thumb is that students should spend two hours outside the classroom for every hour required in it. For more information about this policy, review the full credit hour assignment policy in the Berkeley College Undergraduate Catalog.
ACADEMIC INTEGRITY
Berkeley College is committed to providing an educational experience designed to develop professional competencies, including habits of personal and professional integrity. The College expects all members of its community – students, faculty, and staff – to act honestly in all situations. Actions of Academic Dishonesty will not be tolerated. "Academic dishonesty (is any) form of cheating and plagiarism which result in students giving or receiving unauthorized assistance in an academic exercise or receiving credit for work which is not their own." (Kibler et. al.,1988, Academic integrity and student development: Legal issues and policy perspectives, Ashville, NC: College Administration Publications, Inc., p. 1.) All students are expected to agree to a pledge of honesty concerning their academic work, and faculty are expected to maintain the standards of that pledge.
TURNITIN AS A LEARNING TOOL
Turnitin helps prevent plagiarism by providing both the student and the professor a feedback report that compares any student work submitted through the software with a comprehensive database of books, journals, websites and papers written by other students. Some of the writing assignments in this course will use Turnitin software to help students improve their skill at paraphrasing statements contained in research on a topic and to help increase awareness of the proper use of citation when a student writes a paper using ideas or statements taken from a research source. For any essay-based assignment submissions, including but not limited to homework, papers, and projects, students will be expected to submit that assignment through Turnitin in Canvas, following the submission guidelines given with the assignment instructions. Prior to submitting a final draft of an assignment, students will have the opportunity to submit several drafts of that assignment to Canvas in order to get sufficient feedback from Canvas reports to help minimize the risk of plagiarism. If the assignment continues to have evidence of plagiarism in the final draft of the assignment, the professor will file a report to the Department Chair documenting the use of the paper as an action of academic dishonesty. If a student fails to submit an assignment to Turnitin, the professor will assign a grade of zero for that assignment. By submitting a paper to Turnitin, that paper will become source material included in the Turnitin database.
PROGRESS REPORTS
At the end of Weeks 4, 7 and 11, students whose course performance needs improvement will be notified through their Berkeley email. These progress reports may include specific strategies for course improvement and your options if you are at risk for course failure.
CENTER FOR ACADEMIC SUCCESS
The Center for Academic Success offers academic assistance to all students through the use of services including tutoring, workshops, and access to computer based programs. For further information, please visit the Center for Academic Success online or in-person.
INFORMATION LITERACY
Information Literacy is a valuable set of skills that empowers students to become agile information seekers who adapt to changing modes of information delivery and are selective, critical, ethical users of information in all formats. These skills are embedded within course work throughout academic programs. "
Student Participation
Students are expected to actively participate in all their courses throughout each term. Those who fail to do so may be administratively withdrawn from individual courses or the College. Faculty members will include their course-specific policies and procedures in each course syllabus. Students impacted by illnesses, accidents, or other circumstances that will significantly limit their participation in their courses must notify their faculty members as soon as possible. Students who are withdrawn for a failure to participate will receive a grade of W, WP or WF for the course(s), depending on whether the student was passing or failing at the time of withdrawal. This may affect the student's financial aid eligibility."
