TDS2101 Introduction to Data Science Assignment

Assignment Help Python Programming

Reference no: EM132458264

TDS2101 - Introduction to Data Science - Multimedia University, Malaysia

Topic - Air Pollution in the US.

Section A. Understanding how a problem can be solved with the Data Science process

Question 1. You may formulate more than one Question. Aim for a variety of types (Descriptive, Predictive, etc.). More complex Questions are more challenging, but they can also more insightful and can give you a better problem to solve.

Question 2. Try to tie your problem to a Sectionicular industry sector, business, and/or society. It will give you a lot more foundation on why the problem you are tackling is meaningful or beneficial.

Question 3. To provide you with some idea, among the sectors that typically leverage data science are: Finance, Telecommunications, Retail/Commerce, Government, Society, Healthcare, Lifestyle/Fitness, Sports, Manufacturing, Travel, and more.

Question 4. The art of "pitching" an idea or problem requires the ability to communicate clearly and convincingly to the target audience that your problem is worth pursuing or investigating.

Section B. Data Science pipeline in-action

Picking up from the problem proposed in Section A, you need to put the ideas and plans into action. Here are some points to guide you along:

Question 1. Set the context that you would like to examine i.e. the Question(s) you would like to answer.

What is/are your questions? Typically, you can have several questions which are descriptive in nature and at least ONE predictive question. The question(s) may be formulated based on the problem that you have identified, with good context from a Sectionicular industry sector, business or society. Although this has been presented in Section A, you can still refine it in Section B.

Question 2. Identify the dataset(s) that you have used and describe the contents.
• What is your dataset about? Where did you get it? What kind of information is in the data?
• Feel free to make alterations if your earlier proposed data was found to be infeasible. For certain cases, you may even have to refine the question formulated previously if you are unable to identify directly relevant or appropriate datasets.

Question 3. Examine the quality of the data and perform the necessary data cleaning.
• What are the data cleaning activities/tasks that you have performed? How were they done and why do it?

Question 4. Explore the data to understand its descriptive statistics.
• What are some graphical plots that can help illustrate the current state of the data and are there any interesting correlations in the data?
• Construct scripts that can help reveal answers to the descriptive questions that you have asked (if relevant).

Question 5. Employ ONE of the data mining or predictive modelling techniques (e.g. Decision Tree, Naïve Bayes, Linear Regression, K-means Clustering, Logistic Regression etc.) that may be suitable for making some simple predictions.
• Are you able to mine some interesting patterns, or build a model to predict future behaviour based on the data you have obtained?
• Note: It is not necessary to use machine learning techniques here if you do not know how. However, there is no restriction if you wish to do so.

Question 6. Use compelling visualizations to support a consistent narrative.
• Show with visuals how your Question(s) can be answered.
• With visuals, it is also easier to discuss and analyse further, making observations that are useful to the target sector.

Question 7. Mention and discuss some of the challenges or restrictions you had faced in this project.
• What are some actionable insights that can be done based on your data analysis?
• What is the way forward for further insights to be generated?

Attachment:- Introduction to Data Science.rar

Reference no: EM132458264

Questions Cloud

What factors led to ronald reagan election in 1980 : What difficulties did the United States face in fighting a war against North Vietnam and the Vietcong in South Vietnam?

Prepare the journal entry when the bonds mature : The market rate of interest on the date of the bond issue was 8%. On what date do the bonds mature? Prepare the journal entry when the bonds mature

Explain the foundations and development of atlantic slave : Explain the foundations and development of the Atlantic slave trade. Why did Europeans enslave Africans and not, for the most part, American Indians?

Prepare the amortization table for the first two years : The issue price of the bonds based on a 4% market rate of interest is $1,493,755. Prepare the amortization table for the first 2 years

TDS2101 Introduction to Data Science Assignment : TDS2101 Introduction to Data Science Assignment Help and Solution, Multimedia University, Malaysia - Assessment Writing Service.

Discuss the machiavellis concept of a strong ruler : Machiavelli's concept of a strong ruler, who was driven by pragmatism instead of morality, was a direct challenge to the political thought of his time

Discuss how society has transitioned : Discuss how society has transitioned from such type of behavior being considered as being deviant to acceptable in today's society.

What changed after martin luther : What changed after Martin Luther? How did Protestant Reformation change Europe and impact world history?

Develop the statement ideas have consequences : Develop the statement "ideas have consequences" by applying the Cultural Epoch Theory to a culture. You could use America as an example.

User Account

All Pages