Data Analyst Bootcamp

Capstone Project
Guidebook

Introduction
Congratulations on successfully completing the data analyst program! Throughout
this journey, you have acquired a wide range of skills, including data analysis and
data visualization. Now, it's time to put all that learning into practice by working on
your data analyst capstone project.
The data analyst capstone project is a pivotal part of the program and serves as a
showcase of your abilities as a data scientist. This project is an opportunity for you
to demonstrate your problem-solving skills, analytical thinking, and creativity in
tackling real-world data challenges.
In this guide, we will provide you with essential points and guidelines for your data
analyst capstone project. While we offer some project outlines, you are also
encouraged to come up with your own unique project idea that aligns with your
interests and showcases your skills effectively.
Completing this capstone project is a mandatory requirement to successfully
graduate from the program, and it will be a gradable activity. So, make sure to
approach it with enthusiasm and dedication.
If you have any questions or need guidance during the project development, don't
hesitate to reach out to your buddy or learning advisor. We are here to support you
throughout this journey.
Happy coding and best of luck with your data analyst capstone project!
The upGrad KnowledgeHut Team

Key Points to Consider Before Submitting Your Data Analyst

Project:
When evaluating a data analyst project, we look for the following attributes. It is
essential for you to keep these in mind while building and submitting your data
analyst project:
 1. Data Exploration and Analysis:
 Conduct thorough data exploration and analysis to understand the
data's characteristics, patterns, and relationships.
 Use suitable visualizations and descriptive statistics to gain insights
from the data.
2. Data Preprocessing:
 Clean, preprocess, and transform the data to ensure it's suitable for
analysis.
 Handle missing values, outliers, and inconsistencies appropriately.
3. Feature Engineering:
 Create new features or transform existing ones to enhance analysis
and uncover meaningful insights.
 Use domain knowledge to generate features that could contribute to
understanding the NFT market trends.
4. Exploratory Data Analysis (EDA):
 Explore the distribution of NFT sales across different marketplaces and
time periods.
 Investigate characteristics of top-selling NFTs, such as artists, genres,
and price ranges.
 Identify correlations between NFT attributes and sales performance.
5. Trend Analysis and Insights:
 Utilize time series analysis techniques to identify trends and patterns
within the NFT market.
 Provide insights into the emergence of new trends, popular artists, and
genres.
6. Data Visualization:
 Present your findings using clear and informative data visualizations.
 Use tools like Plotly or Dash to create interactive dashboards for better
understanding.
7. Documentation and Reporting:
 Create a comprehensive report (PDF) detailing the project's
methodology, analysis process, and insights.
 Describe the significance of the findings and how they can be applied
in the NFT ecosystem.
8. Bonus Points:
 Enhance the user experience by creating interactive components or
visualizations within your project.
 Consider packaging your solution in a well-structured GitHub repository
with a detailed README.
 Demonstrate excellent documentation skills by providing clear
explanations of your findings and their potential benefits.

Instructions for Organizing Data Analyst Capstone Projects

Before you embark on your Data Analyst capstone project, it's crucial to organize
your project assets in a structured manner to ensure a smooth submission and
evaluation process. Here's a set of guidelines to help you organize your project files
during development and deployment:

During Development:
In this phase, follow this folder structure to organize your project files:
1. project-folder: Name this folder to reflect your project's name, using
lowercase letters and replacing spaces with underscores.
2. notebooks: Store your Jupyter notebooks or Python scripts here. These files
will cover data exploration, data cleaning, analysis, visualization, and any
other data-related tasks.
3. data: This folder should house the dataset(s) used in your project. Include
both the raw and processed data, and add a README file that explains the
attributes of the dataset.
4. visuals: Store any data visualizations, plots, or charts generated during your
analysis. Save them as image files (e.g., PNG or JPEG).
5. README.md: Write a Markdown file that provides a detailed project
description, problem statement, data sources, and explanations of your code
and analysis. Also, include instructions on how to run your code and replicate
the results.

Deployment:
When preparing your project for deployment, follow these steps:
1. Package Dependencies: Create a requirements.txt file that lists all the
Python dependencies required to run your project. This file is essential for
installing the necessary libraries on the deployment environment.
2. Documentation and Code Separation: Separate your code into logical
modules or scripts. Include comments that explain the purpose of each part
of your code.
3. Data Preprocessing: If any data preprocessing steps are involved, create
separate functions or modules to handle them. This ensures reproducibility
during deployment.
4. API (if applicable): If your Data Analyst project involves an API component,
create a separate folder (e.g., "api") to house the scripts and configurations
for the API.
5. Deployment Platform: Choose a suitable hosting service or cloud provider
(e.g., AWS, Heroku) to deploy your project. Ensure that your code is
accessible through a public URL.
6. User Instructions: Update your README.md with instructions on how to
access and interact with your deployed project. Make sure to provide clear
guidance on how users can utilize the insights generated from your analysis.
 7. Dockerization (Optional): Consider creating a Dockerfile to containerize
your project. This will simplify deployment across different environments and
ensure consistent behavior.

Success Metrics:
 Your project assets should be well-organized, making it easy for evaluators to
understand your work.
 The documentation should be clear and concise, enabling others to replicate
your analysis and understand your insights.

Bonus Points:
 Create an interactive visualization dashboard using tools like Plotly or Dash to
showcase your analysis.
 Demonstrate real-time data integration or updates if applicable to your
project.
 Package your project in a GitHub repository and provide a detailed README
with instructions for deployment and usage.

Submitting the Data Analyst Project

Congratulations on completing your Data Analyst capstone project! Before
submitting, make sure to follow these steps to ensure a successful submission:

1. Functionality Check:
 Ensure that all components of your data analysis project are functional
and achieve the defined objectives. This includes data preprocessing,
analysis, visualization, and any other relevant tasks.
2. Code Organization:
 Organize your project code according to the recommended folder
structure. Place files, notebooks, and scripts in appropriate directories
to maintain a clear and logical project structure.

3. Documentation and Explanation:

 Create a comprehensive README.md file in your GitHub repository.
This document should provide clear instructions for setting up and
running the data analysis project.
 Describe the purpose of the project, the problem statement, and the
objectives you aimed to achieve.
 Explain the sources of data used in the analysis and how it was
collected and preprocessed.
 Detail the steps of your data analysis process, including any statistical
techniques or algorithms applied.
 Describe the visualizations you created and their significance in
conveying insights.
 If you used any external libraries or dependencies, provide instructions
for installing them.

4. Exploration and Insights:

 In your README, share the key findings and insights you gained from
your analysis. Highlight any trends, patterns, or correlations you
discovered in the data.
 Explain how your insights can be beneficial to stakeholders or decision-
makers.

5. GitHub Repository:
 Store your well-organized project code in a GitHub repository. Make
sure to include all necessary files, including data, notebooks, scripts,
and visualizations.

6. Submission Details:
 Provide your learning advisor with the URL to your GitHub repository
containing the project code and documentation.
 If you created any interactive visualizations or dashboards, share the
appropriate URLs or access methods.

7. Timeline:
 Submit your project within the designated time frame specified in the
course guidelines.
What Should I Build?
Your data science capstone project is an opportunity to showcase your skills and
abilities as a data scientist. It should reflect your expertise and demonstrate your
problem-solving capabilities using data-driven approaches. Here are some
guidelines and ideas to help you decide what to build for your data science
capstone project:
1. Understand the Problem:
 Review the project's problem statement and objectives carefully.
 Ensure a clear understanding of the task and the insights you're
expected to deliver.

2. Leverage the Provided Dataset:

 The provided open-source dataset is the basis for your analysis.
 It's important to work with this dataset to solve the problem at hand.

3. Exploratory Data Analysis (EDA):

 Begin by exploring the dataset to understand its structure, variables,
and relationships.
 Visualize data distributions, correlations, and patterns using
appropriate charts and graphs.

4. Data Preprocessing:
 Clean the dataset by handling missing values, outliers, and
inconsistent data.
 Prepare the data for analysis by encoding categorical variables and
scaling numerical features if necessary.

5. In-depth Analysis:
 Dive deep into the dataset to extract insights that address the project
objectives.
 Apply relevant statistical techniques to uncover trends, relationships,
and patterns.

6. Data Visualization:
 Create visualizations that effectively communicate your findings.
 Utilize appropriate visualization tools to showcase insights and support
your conclusions.

7. Statistical Analysis:
 Apply statistical tests as needed to validate your observations and
draw meaningful conclusions.
  Clearly explain the statistical methods used and their relevance to the
project.

8. Documentation:
 Maintain thorough documentation throughout the project.
 Describe your data preprocessing steps, analysis methodologies, and
visualization choices.

9. Interpretation and Insights:

 Provide clear and concise explanations of the insights derived from
your analysis.
 Discuss the implications of your findings in the context of the problem
statement.

10.Presentation Skills:
 Create a professional presentation that effectively communicates your
analysis and findings.
 Structure your presentation logically, showcasing the key steps and
outcomes of your analysis.

11.Code and Reproducibility:

 Organize your analysis code in a structured manner for easy
readability.
 Include comments and explanations to guide readers through your
code.
 Ensure your analysis is reproducible by providing clear instructions to
replicate your work.

12.Time Management:
 Allocate sufficient time to each phase of the project, including EDA,
analysis, visualization, and reporting.
 Plan your time effectively to meet the project submission deadline.
Remember, the goal of the capstone project is not just completion but to
demonstrate your data analysis skills and the insights you can derive from real-
world data. Pay attention to detail, critically analyze your results, and effectively
communicate your findings. Your capstone project is your opportunity to showcase
your expertise and stand out as a capable Data Analyst. Good luck, and make the
most of this experience!

Project No. 1
Project Title: Boxify : Sales Analysis and Inventory Insights
Problem Statement:
Effective inventory management is essential for businesses to maintain optimal stock levels,
minimize carrying costs, and meet customer demand. As a data analyst, your task is to analyze a
sales dataset, extract valuable insights, and provide inventory-driven recommendations to
enhance inventory management practices.

Objectives:
1. Analyze the provided sales dataset to understand sales trends, stock levels, and product
performance.
2. Identify popular products, low-stock items, and sales patterns over time.
3. Generate actionable recommendations for improving inventory management efficiency.

Timeline:
The project is expected to be completed within two weeks.

Deliverables:
A report (PDF) containing:
 Description of the dataset analysis approach and methodology.
 Inventory-driven insights and recommendations.
 Source code used for data preprocessing, analysis, and visualization.

Tasks/Activities List:
1. Data Collection and Preprocessing:
 Obtain the sales dataset from the provided source: Sales Analysis Dataset.
 Clean and preprocess the data to handle missing values and inconsistencies.
2. Exploratory Data Analysis (EDA):
 Analyze sales trends and variations over time.
 Identify top-selling products and categories.
 Investigate stock levels and low-stock items.
3. Inventory Insights and Recommendations:
 Calculate key performance indicators (e.g., inventory turnover, stock-to-sales
ratio, reorder points).
 Provide actionable recommendations to optimize inventory management based
on sales patterns.
4. Data Visualization:
  Create interactive and informative visualizations (e.g., line charts, bar plots) to
present sales trends and inventory metrics.
 Highlight insights through well-designed graphs and charts.
5. Documentation and Reporting:
 Summarize the findings, inventory-driven insights, and recommendations from
the analysis.
 Explain how the inventory-focused insights can benefit businesses in enhancing
inventory management.

Success Metrics:
 The analysis should provide clear insights into sales trends, popular products, and
inventory performance.
 Recommendations should be actionable and focused on improving inventory
management efficiency.

Bonus Points:
 Utilize advanced visualization tools like Plotly or Tableau for interactive visualizations.
 Package your code, analysis, and visualizations in a GitHub repository with a clear
README.
 Provide insights on how businesses can implement the recommendations to optimize
their inventory management practices.

Project No. 2

Project Title : CheckMyFlight - Analyzing Flight Prices and Forecasting

Patterns
As a data analyst, your task is to analyze flight price data and identify patterns in flight prices.
By understanding these patterns, you will develop insights into the factors that influence flight
prices and create visualizations to help users forecast future flight patterns.

Objectives:
4. Extract meaningful insights from flight price data using Tableau.
 5. Identify trends and patterns in flight prices over time.
6. Develop visualizations to represent historical flight price patterns.
7. Forecast future flight price trends based on historical data.

Timeline:
The project is expected to be completed within two weeks.

Deliverables:
A report (PDF) containing:
1. Description of the data analysis approach and methodology.
2. Visualizations depicting flight price patterns and forecasting.
3. Insights into factors influencing flight prices.
4. Source code for creating Tableau visualizations.

Tasks/Activities List:
Data Collection: Download the flight price dataset from this link.
Data Exploration:
 Load the dataset into Tableau and explore its structure.
 Handle missing values, data cleaning, and transformation if necessary.
Flight Price Analysis:
 Create visualizations to analyze flight price trends over time.
 Identify seasonal variations, price spikes, and trends.
Forecasting Future Patterns:
 Develop visualizations to forecast future flight price patterns.
 Use techniques like time series forecasting to predict future prices.
Factors Influencing Flight Prices:
 Explore potential factors influencing flight prices (e.g., time of booking,
destination, airlines).
 Create visualizations to illustrate how these factors affect prices.
Documentation and Reporting:
 Summarize the findings and insights from the flight price analysis and
forecasting.
  Explain the significance of understanding flight price patterns for travelers.
2. Data Visualization:
 Create visualizations to represent suicide trends over time.
 Develop maps to visualize suicide clusters and hotspots.
3. Documentation and Reporting:
 Summarize the findings and insights from the suicide cluster analysis.
 Explain the importance of suicide prevention and the role of the user interface.

Success Metrics:
 Identification of significant flight price patterns and trends.
 Visualizations that effectively represent historical and forecasted flight price patterns.
 Insights into factors influencing flight prices and their impact.

Bonus Points:
 Provide interactive Tableau dashboards for users to explore flight price trends.
 Include dynamic filtering options to allow users to customize their analysis.
 Share the Tableau project on a public platform or website to showcase your work.

Project No. 3
Project Title : LifeSave - Analyzing Suicide Clusters and Providing
Helpline Numbers in India
Suicide prevention is a critical issue, and timely intervention can save lives. As a data analyst,
your task is to analyze suicide data in India to identify suicide clusters based on past trends.
Additionally, you will provide a user-friendly interface to access suicide helpline numbers for
those in need.

Objectives:
8. Extract meaningful insights from the suicide data in India.
 9. Identify suicide clusters and hotspots based on historical trends and geographic
locations.
10. Develop a user interface to provide suicide helpline numbers for different regions.
11. Raise awareness about suicide prevention and offer valuable resources to individuals in
crisis.

Timeline:
The project is expected to be completed within two weeks.

Deliverables:
A report (PDF) containing:
5. Description of data analysis approach and methodology.
6. Identification of suicide clusters and their characteristics.
7. User interface design for accessing suicide helpline numbers.
8. Source code for data analysis and the user interface.

Tasks/Activities List:
4. Data Collection: Download the suicide dataset for India from this link.
5. Data Preprocessing:
 Load and inspect the dataset.
 Handle missing values, data cleaning, and transformation if necessary.
6. Suicide Cluster Analysis:
 Analyze temporal and spatial patterns of suicides to identify clusters.
 Use techniques like kernel density estimation to visualize clusters.
 Determine factors that contribute to suicide clusters.
7. User Interface Development:
 Create a user-friendly interface using a web framework like Flask or Django.
 Display suicide helpline numbers based on user's region selection.
 Incorporate interactive maps or graphs to visualize suicide clusters.
8. Data Visualization:
 Create visualizations to represent suicide trends over time.
 Develop maps to visualize suicide clusters and hotspots.
 9. Documentation and Reporting:
 Summarize the findings and insights from the suicide cluster analysis.
 Explain the importance of suicide prevention and the role of the user interface.

Success Metrics:
 Identification of suicide clusters and their characteristics based on historical data.
 User interface providing access to suicide helpline numbers for different regions.
 Awareness raised about suicide prevention through data analysis and resources.

Bonus Points:
 Identification of suicide clusters and their characteristics based on historical data.
 User interface providing access to suicide helpline numbers for different regions.
 Awareness raised about suicide prevention through data analysis and resources.

Project No. 4
Project Title : NFTLyze - Real-time Analysis of NFT Market Trends
The Non-Fungible Token (NFT) ecosystem has gained significant attention for its role in digital
ownership and artistic expression. As a data analyst, your objective is to collect and analyze data
from various NFT marketplaces to uncover trends, patterns, and insights that can inform
strategic decisions within this dynamic and evolving landscape.

Objectives:
1. Collect and store real-time data from NFT marketplaces.
2. Perform exploratory data analysis to identify trends and patterns in NFT sales.
3. Develop forecasting models to predict future NFT market trends.
4. Provide actionable insights to stakeholders in the NFT ecosystem.
Timeline:
The project is expected to be completed within two weeks.

Deliverables:
A comprehensive report (PDF) including:
 Description of data collection methods and sources.
 Exploration of key trends and patterns in the NFT market.
 Detailed explanation of forecasting models and their performance.
 Source code for data collection, analysis, and forecasting.

Tasks/Activities List:
Data Collection:
 Gather data from various NFT marketplaces using the dataset available at this
link.
 Store the collected data in a suitable database or storage solution.
Exploratory Data Analysis (EDA):
 Explore the distribution of NFT sales across different marketplaces and time
periods.
 Analyze characteristics of top-selling NFTs, such as artists, genres, and price
ranges.
 Identify correlations between NFT attributes and sales performance.

Trend Analysis and Forecasting:

 Develop time series forecasting models (e.g., ARIMA, Prophet) to predict future NFT
sales trends.
 Evaluate the accuracy of the forecasting models using appropriate metrics.
Strategic Insights:
 Develop time series forecasting models (e.g., ARIMA, Prophet) to predict future
NFT sales trends.
 Evaluate the accuracy of the forecasting models using appropriate metrics.
Real-time Data Integration:
  Implement a data collection mechanism to update the dataset in real-time from
NFT marketplaces.
Documentation and Reporting:
 Document the data collection process, analysis methodology, and model
development.
 Explain the significance of the insights and how they can be used in the NFT
ecosystem

Success Metrics:
 The project should provide a comprehensive overview of NFT market trends.
 Forecasting models should demonstrate reasonable accuracy in predicting future trends.
 Insights should offer actionable guidance for stakeholders in the NFT ecosystem

Bonus Points:
 Create a Python-based dashboard using tools like Plotly or Dash to visualize NFT market
trends.
 Implement a real-time data collection and updating mechanism to ensure up-to-date
analysis.
 Package the project in a GitHub repository with a well-organized README.
 Highlight how the analysis and insights could benefit artists, collectors, and investors in
the NFT ecosystem.

Project No. 5
Project Title: NutriCal : McDonald's Menu Nutritional Analysis
Problem Statement:
McDonald's is a global fast-food chain known for its diverse menu offerings. As a data analyst,
your task is to analyze the nutritional content of the menu items available at McDonald's
outlets. This analysis will provide valuable insights into the calorie count and nutrition facts of
various menu items.

Objectives:
1. Extract meaningful information from the McDonald's menu nutritional dataset.
 2. Perform exploratory data analysis to understand the nutritional distribution and trends.
3. Create visualizations to present the calorie count and nutrition facts of different menu
items.
4. Identify healthy and less healthy menu options based on nutritional content.

Timeline:
The project is expected to be completed within two weeks.

Deliverables:
A report (PDF) containing:
 Description of data analysis approach and methodology.
 Exploratory data analysis findings and insights.
 Visualizations depicting nutritional information.
 Source code used for data preprocessing, analysis, and visualization.

Tasks/Activities List:
1. Data Collection: Download the McDonald's menu nutritional dataset from this link.
2. Data Preprocessing:
 Load and inspect the dataset.
 Handle missing values and data cleaning if necessary.
3. Exploratory Data Analysis (EDA):
 Analyze the distribution of calorie counts across menu items.
 Explore the nutritional content (e.g., fat, protein, carbohydrates) of different
items.
 Identify trends and patterns in the dataset.
4. Data Visualization:
 Create bar charts, histograms, and box plots to visualize calorie distribution and
nutritional content.
 Compare nutritional characteristics of different food categories (e.g., burgers,
salads, desserts).
5. Nutrition-Based Insights:
 Identify menu items with the highest and lowest calorie counts.
 Determine the average nutritional content of popular menu categories.
6. Documentation and Reporting:
 Summarize the findings and insights from the analysis.
 Explain how the nutritional analysis could benefit McDonald's customers and the
organization.
Success Metrics:
 The project should provide a comprehensive overview of the nutritional content of
McDonald's menu items.
  Visualizations should effectively convey calorie counts and nutritional information.
 Insights should highlight healthy and less healthy food options.

Bonus Points:
 Create a Jupyter Notebook or Python script detailing each step of the analysis.
 Package your code and findings in a GitHub repository with a clear README.
 Provide recommendations on how McDonald's could improve the nutritional profile of
their menu.