Students are required to submit a Mini Project in the field of data science. The mini project will essentially

involve working with a dataset to be imported from from either a CSV or Excel file. Students should find

a suitable dataset and define their problem statement clearly. The dataset should have a minimum of $1000$

rows and some missing data, ouliers, noise, etc. It is recommended to use Pandas library$/$package in Python

to work on the project.

The project will be divided into four main stages:

$1.$ Data Cleaning: Students will be required to clean the dataset by handling missing data

appropriately, removing duplicates and outliers, and ensuring consistency in data format. Based on

the data sets, students can implement some more cleaning if required.

$2.$ Exploratory Data Analysis $($EDA$)$: After cleaning the data, students are expected to display the

basic statistics about dataset. Students will perform EDA to understand the dataset's distribution,

correlation, and relationship between variables. Students are expected to visualize their findings in

at least five ways, including but not limited to scatter plots, bar charts, histograms, and heat$-$maps

or any other format they prefer.

$3.$ Feature Selection: Based on their EDA findings, students will select the relevant features for

analysis. Any suitable method of feature selection can be used so that students can explain why

they have selected the features and justify why other features were excluded.

$4.$ Predictive Modeling: Students will use linear or multiple regression to predict the values for the

output variable for new inputs. For this, students should divide the dataset into training and test

sets, train their model on the training set, and validate the results on the test set. They should also

provide the accuracy of their model. Students should explain the rationale behind selecting the

regression method and interpret the results obtained.

The final project report should include a detailed explanation of the project's problem statement, the data

cleaning process, the EDA findings, the feature selection process, and the regression model. Students should

also include the visualizations they used to communicate their findings.

Students will be evaluated on the quality of project report, the quality of the code, and their ability to

communicate their findings effectively.

Student$-$Centered Learning Assignment $/$ Mini Project Statement

Rubric for Evaluating Assignment $($Total Marks: $15)$

Criteria Marks Comments

Data Cleaning $43$ marks for appropriately handling missing data and removing

duplicates and outliers.

$1$ mark for ensuring consistency in data format.

Exploratory Data

Analysis

$41$ mark for accurately summarizing the dataset distribution.

$1$ mark for identifying correlations and relationships between

variables.

$2$ marks for using at least five visualizations to effectively

communicate findings.

Feature Selection $21$ mark for justifying the selection of relevant features.

$1$ mark for explaining why other features were excluded.

Regression Modeling $31$ mark for appropriately dividing the dataset into training and test

sets.

$1$ mark for selecting the appropriate regression method and

justifying the selection.

$1$ mark for interpreting the results obtained from the regression

model.

Presentation & Clarity $22$ marks for clear and concise writing, effective organization, and

appropriate formatting.