College Data Analysis with Python
Budget: $30 – $250 AUD
I have a college assignment where I need to perform a data analysis task using Python. I have a specific dataset that I will provide.
Key requirements:
- Data Analysis: The task involves in-depth data analysis - not just basic statistical analysis but also some intermediate data processing and visualization.
- Python Proficiency: You must be skilled in Python for this project. Experience in using Python for data analysis is a definite plus.
- Dataset: I will provide the dataset which you will be working with, so you should be comfortable working with provided data.
this is the question :
In this question, you will use the dataset made available to the public by:
S. Moro, R. Laureano and P. Cortez. Using Data Mining for Bank Direct Marketing: An Application of the CRISP-DM Methodology. In P. Novais et al. (Eds.), Proceedings of the European Simulation and Modelling Conference - ESM'2011, pp. 117-121, Guimarães, Portugal, October, 2011. EUROSIS.
The data is related to a direct marketing campaign conducted by a Portuguese financial institution. The raw dataset has been modified for the purpose of this assignment. The attached “Bank_partB.csv” file contains the following columns:
Age : a continuous variable (respondent’s age)
Job : type of job ("admin.", "unknown","unemployed","management",
"housemaid", "entrepreneur", "student",
"blue-collar", "self-employed","retired","technician","services")
Marital status : single, married, divorced
Education : unknown, primary, secondary, tertiary
Balance : average yearly balance (in Euro) in the respondent’s bank account
(negative amount means bank overdraft)
Housing : whether the respondent has a housing loan (No vs Yes)
Loan : whether the respondent has a personal loan (No vs Yes)
Hint: You need to transform categorial data into numerical data. For example, re-express “Education” as 0 (unknown), 1 (primary), 2 (secondary) and 3 (tertiary). Also, the data does not have any missing entries; hence, you don’t have to ‘clean’ the data.
Required: The classification goal is to evaluate the accuracy of the (choosen) model in predicting if a respondent will subscribe to the term deposit (No vs Yes) offered by the bank.
Use all the knowledge that you have gained in class on KNN-classification to address this problem. You are free to choose (i) which independent variable(s) to use, (ii) whether you want to estimate the classification model using the entire sample observations, or splitting the full sample into training and testing sets, and (iii) the optimal k-neighbor value. But you must be prepared to justify your decision. For example, if you choose the optimal k-neighbor value = 3, then discuss the rationale behind it.
Key requirements:
- Data Analysis: The task involves in-depth data analysis - not just basic statistical analysis but also some intermediate data processing and visualization.
- Python Proficiency: You must be skilled in Python for this project. Experience in using Python for data analysis is a definite plus.
- Dataset: I will provide the dataset which you will be working with, so you should be comfortable working with provided data.
this is the question :
In this question, you will use the dataset made available to the public by:
S. Moro, R. Laureano and P. Cortez. Using Data Mining for Bank Direct Marketing: An Application of the CRISP-DM Methodology. In P. Novais et al. (Eds.), Proceedings of the European Simulation and Modelling Conference - ESM'2011, pp. 117-121, Guimarães, Portugal, October, 2011. EUROSIS.
The data is related to a direct marketing campaign conducted by a Portuguese financial institution. The raw dataset has been modified for the purpose of this assignment. The attached “Bank_partB.csv” file contains the following columns:
Age : a continuous variable (respondent’s age)
Job : type of job ("admin.", "unknown","unemployed","management",
"housemaid", "entrepreneur", "student",
"blue-collar", "self-employed","retired","technician","services")
Marital status : single, married, divorced
Education : unknown, primary, secondary, tertiary
Balance : average yearly balance (in Euro) in the respondent’s bank account
(negative amount means bank overdraft)
Housing : whether the respondent has a housing loan (No vs Yes)
Loan : whether the respondent has a personal loan (No vs Yes)
Hint: You need to transform categorial data into numerical data. For example, re-express “Education” as 0 (unknown), 1 (primary), 2 (secondary) and 3 (tertiary). Also, the data does not have any missing entries; hence, you don’t have to ‘clean’ the data.
Required: The classification goal is to evaluate the accuracy of the (choosen) model in predicting if a respondent will subscribe to the term deposit (No vs Yes) offered by the bank.
Use all the knowledge that you have gained in class on KNN-classification to address this problem. You are free to choose (i) which independent variable(s) to use, (ii) whether you want to estimate the classification model using the entire sample observations, or splitting the full sample into training and testing sets, and (iii) the optimal k-neighbor value. But you must be prepared to justify your decision. For example, if you choose the optimal k-neighbor value = 3, then discuss the rationale behind it.