Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

Programming in Python for Data Science

CS2PP22

ASSESSMENT CLASSIFICATIONS

This coursework assesses your ability to:

•    understand and use appropriate Python syntax and ecosystem;

•    implement common computer science algorithms and functional programming in Python;

•    understand statistical and machine learning methods for data analytics and mining in Python;

•    apply appropriate statistical and machine learning techniques for data science tasks .

In general, you will gain credit for:

•    preparing and submitting required files as requested;

•    successful implementation of the specified coding tasks;

•    writing efficient, functional code;

•    providing thoughtful, clear, well-structured written analysis.

Your assignment will be marked according to the marking scheme provided below. The scheme is designed so that  the  collectively  weighted  assignment  mark  will  correspond  to  the  following  qualitative  degree classification descriptions:

The table below shows what is typically expected of the work to obtain a given mark.

Classification Range

Typically, the work should meet these requirements:

First Class (>=70%)

Outstanding/excellent work with correct codes and results. An outstanding work should demonstrate coding proficiency with high efficiency and based on advanced techniques. Evidence of independent research into methods used and a thorough justification of applications of these methods.

Upper Second (60-69%)

Good work with few mistakes. Some minor tasks have not been carried out or are not completely correct. Coding with good efficiency. Evidence of good knowledge of the core concepts, with good explanations and justifications.

Lower Second (50-59%)

Demonstrates knowledge of core concepts but with some mistakes. Explanations and justifications of methods used are logical but limited in depth. Coding with average efficiency. Most tasks have been carried out with sufficient accuracy.

Third (40-49%)

Some parts of the assignment are missing and/or have partially correct results. Most tasks have not been carried out with sufficient accuracy. Results may not be correct or technically sound. Mistakes in application of knowledge and shows some misunderstandings. Explanations and justifications of methods used are not clear or logical. Coding might be inefficient.

Pass (35-39%)

Some significant part of the assignment is missing and/or has partially correct results. Gaps in knowledge and many mistakes, little evidence of understanding. Methods used are not well explained or justified. Coding is notably inefficient.

Fail (0-34%)

Many aspects of the assignment are missing, or there are large gaps in knowledge and significant mistakes, also showing limited understanding. Lack of logical explanations behind the methods used.

ASSIGNMENT DESCRIPTION

Major Coursework (100% of module assessment)

This assignment consists of two tasks.  Both of these will be used to assess your implementation of elements of the Data Science process, using Python as the main tool.

A detailed breakdown of theMarking Schemeis provided later in this document.

Task 1 – Data Preprocessing, Exploratory Data Analysis, and Python Classes

Using the cardata.csv file within the CS2PP22_Assessment_Task1.ipynb Jupyter notebook, you will execute several components of the data science process and design and implement a class structure that controls and compiles data about a fictional sporting event by writing Python code to perform the outlined sub-tasks detailed in the notebook. Working through this notebook, you will read, write, and manipulate data to extract specific features, design and implement functional routines, and design and implement an algorithm to select an optimal subset from a larger dataset.

Some sub-tasks will ask you to provide a written explanation of the justification behind it your coding choices. Code and written responses should be presented in a set of well-formatted code and Markdown cells at appropriate points in your Jupyter notebook. This work will require the production and submission of additional files; details about these files and how they should be submitted are provided in the notebook and the Assignment Submission Requirements.

Task 2 – Twitter Data Analysis

Using the CS2PP22_Assessment_Task2.ipynb Jupyter notebook, you will extract data from the social media platform, Twitter, and use the data as the basis for implementing components of the data science process to build and test a regression model. You will need to extract at least 300 tweets (perhaps, the 300 most recent tweets) from at least 3 Twitter accounts.

Visualise the results concisely and discuss the reasons why one might prefer the use of one of your tested methods over another. As in Task 1, written responses should be provided in a set of well-formatted Markdown cells at appropriate points in your Jupyter notebook.

Additional points of consideration and example extraction methods are provided in the notebook. Efficient extraction of the tweets will require installation of at least one new Python package. The most efficient of these, tweepy, requires that you obtain a developer account with Twitter. Instructions for gaining the appropriate access are found in the Additional Considerations section of this document.

 Project Directory and Data Description

The materials needed to complete this assessment are available in a single CS2PP22_Assessment.zip file on the CS2PP22 Blackboard space, under the Assessment heading, in the Coursework Description and Datasets item.  This is outlined below and contains a data directory with subdirectories for Task1 and Task2.

Additional Considerations

Task 2

To extract the tweets from the accounts you have selected with the tweepy package, you MUST:

•    Have or create a Twitter account.

•