AJAY KUMAR GARG ENGINEERING COLLEGE GHAZIABAD
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
27th KM Milestone, Delhi - Meerut Expy, Ghaziabad, Uttar Pradesh 201015
INTERNSHIP / MINI PROJECT REPORT
ON
NourishNet: FOOD AND NUTRIENT MAPPER
AT
COMPANY NAME - GUVI(GOOGLE FOR EDUCATION PARTNER), KARTEXA
Submitted by
NAME- Divyanshu Pathak
YEAR- 3rd
SEMESTER- 5th (V)
SECTION- CSE 1
BRANCH- CSE
ROLL NUMBER - 2100270100059
1
DECLARATION
I hereby declare that this submission is my own work and that, to the best of my knowledge
and belief, it contains no material previously published or written by another person nor
material which to a substantial extent has been accepted for the award of any other degree or
diploma of the university or other institute of higher learning, except where due
acknowledgment has been made in the text.
Signature:
Name : Divyanshu Pathak
Roll No: 2100270100059
Date : 13th December 2023
2
COMPANY CERTIFICATE
Img 1: GUVI (GOOGLE FOR EDUCATION PARTNER) IN PYTHON
PROGRAMMING LANGUAGE
3
COMPANY CERTIFICATE (cont…)
Img 2: KARTEXA INTERNSHIP IN DATA SCIENCE
4
CERTIFICATE
This is to certify that Mini Project/Internship Assessment Report entitled “NourishNet: Food
& Nutrient Mapper” which is submitted by Divyanshu Pathak in partial fulfillment of the
requirement for the award of degree B. Tech. in Department of Computer Science and
Engineering of Ajay Kumar Garg Engineering College Ghaziabad affiliated to Dr. APJ Abdul
Kalam Technical University, Uttar Pradesh, Lucknow is a record of the candidate’s own work
carried out by him/her under my supervision. The matter embodied in this report is original
and has not been submitted for the award of any other degree.
Supervisor Signature:
Supervisor Name:
Mrs. Harnit Saini
Assistant Professor,
Department of CSE,
AKGEC, Ghaziabad
Date: 11th December 2023
5
ACKNOWLEDGEMENT
We would like to express our deepest thanks to Mrs. Harnit Saini, our Mini Project/Internship Lab Faculty,
for his cooperative attitude and consistent guidance, due to which we were able to complete our project
successfully.
We would like to express our sincere gratitude to Dr. Anu Chaudhary (H.O.D. CSE Department), Ajay
Kumar Garg Engineering College, Ghaziabad and Dr R. K. Aggarwal (Director General), Ajay Kumar Garg
Engineering College for allowing us to pursue our choice of project. They gave us their valuable guidance
and support.
We wish to thank various people in our college, Ajay Kumar Garg Engineering College, for their valuable
guidance. We received practical as well as theoretical knowledge and experience in this project. Finally, last
but by no means least, a paper is not enough for us to express the support and guidance we received from
them.
- Divyanshu Pathak
2100270100059
CSE 1
6
ABSTRACT
NourishNet: Food & Nutrient Mapper is an innovative web-based solution seamlessly integrating
machine learning (ML) to empower users with comprehensive insights into the nutritional composition
of various food items. By simply inputting a food item, users can effortlessly access detailed
information on the percentage of essential vitamins and nutrients it contains. Moreover, the system
offers a unique feature where users input a nutrient's name, and the platform intelligently displays the
top five food items with the highest average nutrient values.
Additionally, NourishNet: Food & Nutrient Mapper caters to users querying about specific ingredients
by providing the precise nutrient content available in 100 grams of the entered ingredient. For those
seeking a more granular analysis, the system accommodates inputs of ingredient names along with
their respective quantities. In response, NutriNourish: Food & Nutrient Mapper promptly calculates
and presents the accurate amounts of nutrients present in the specified proportions.
This user-friendly platform not only promotes informed dietary choices but also assists
health-conscious individuals, nutritionists, and researchers in effortlessly accessing and interpreting
nutritional data. NourishNet: Food & Nutrient Mapper stands at the intersection of technology and
nutrition, simplifying the journey towards a healthier lifestyle.
Leveraging the power of Python, Streamlit, Pandas, NumPy, and VS Code, this project seamlessly
blends advanced machine learning capabilities with user-friendly interfaces.
The backbone of NourishNet: Food & Nutrient Mapper lies in Python, a versatile and powerful
programming language known for its readability and extensive library support. The interactive and
intuitive user interface is crafted using Streamlit, a Python library specifically designed for creating
data applications with minimal effort. Streamlit's simplicity ensures a smooth user experience,
allowing individuals to effortlessly input food items, nutrients, or ingredients.
Pandas, a data manipulation library, and NumPy, a numerical computing library, work in tandem to
process and analyze nutritional data efficiently. This dynamic duo enables NourishNet: Food &
Nutrient Mapper to handle diverse datasets with ease, providing accurate and rapid calculations of
nutrient percentages and values.
The development process is streamlined using VS Code, a feature-rich integrated development
environment (IDE). Its debugging capabilities and extensions support the creation of a scalable and
maintainable codebase, ensuring the project remains flexible for future enhancements and updates.
7
TABLE OF CONTENTS
Contents Page No.
Declaration 2
Company Certificate 3
Supervisor Certificate 5
Acknowledgment 6
Abstract 7
Chapter 1 : Introduction 9
Chapter 2 : Project Scope and Features 11
Chapter 3 : System Architecture 12
Chapter 4 : Implementation 14
Chapter 5 : Datasets 17
Chapter 6 : Code Screenshots 19
Chapter 7 : Project testing and system overview 21
Chapter 8 : Result and Discussion 23
Conclusion 25
References 26
8
CHAPTER 1: INTRODUCTION
In a world where well-being is paramount, the quest for optimal health has become a universal aspiration.
Recognizing the significance of nutrition in this pursuit, we present our innovative solution—NourishNet:
Food & Nutrient Mapper. This project is born out of the fundamental belief that individuals should have the
means to meticulously monitor their dietary intake, allowing them to make informed choices and proactively
safeguard their health.
The cornerstone of NourishNet: Food & Nutrient Mapper is our Food Recommendation System, a dynamic
platform designed to empower users in comprehending the nutritional essence of their daily meals. This
system revolutionizes health tracking by offering a detailed breakdown of vitamin and nutrient percentages in
the foods individuals consume. Our approach is driven by a commitment to facilitating users in curating diets
that align with their health objectives and mitigate the risk of diseases.
To fuel this groundbreaking initiative, we meticulously curated two comprehensive datasets. The first, FOOD
DATA, comprises 1181 rows and 20 columns, encapsulating an extensive array of food items and their
respective nutrient profiles. Simultaneously, the INGREDIENT DATA dataset, with 176 rows and 20
columns, delves into the nutrient content of 100 grams of various ingredients.
Data Preprocessing forms a critical phase in our methodology, where we ensure the cleanliness and
consistency of our datasets. By subjecting the information to rigorous cleaning and preprocessing procedures,
we guarantee the integrity of the data, laying a robust foundation for accurate and insightful nutritional
analyses.
NourishNet: Food & Nutrient Mapper stands as a testament to our dedication to merging technological
innovation with health-conscious living. Through meticulous data curation and rigorous preprocessing, we
aim to provide users with a seamless, reliable, and personalized tool to embark on their journey towards
holistic well-being.
Significance of the Project:
NourishNet: Food & Nutrient Mapper, a food recommendation system suggests food items based on
their nutrient content. It can have several significant implications and benefits. Here are some key
points highlighting the significance of such a project:
● Personalized Nutrition:
The system can provide personalized recommendations, taking into account the
individual's dietary preferences, restrictions, and nutritional needs. This can be
particularly useful for people with specific health conditions or dietary requirements.
9
● Health and Wellness:
Promoting healthier food choices by recommending items with optimal nutrient content
can contribute to overall health and wellness. Users can be guided towards a balanced
diet that meets their nutritional goals.
● Dietary Planning:
Users can plan their meals more effectively by receiving recommendations that help
them achieve their desired nutrient intake. This is especially valuable for those who are
conscious about their calorie intake, macronutrient distribution, or specific nutrient
goals.
● Preventing Nutrient Deficiencies:
The system can help users avoid nutrient deficiencies by suggesting foods rich in
specific vitamins, minerals, and other essential nutrients that might be lacking in their
current diet.
● Weight Management:
For individuals aiming to manage their weight, the system can recommend foods that
align with their dietary goals, whether it be weight loss, maintenance, or muscle
building.
Structure of the report:
This report unfolds in a structured manner, delving into the various facets of the project. Following this
introductory section, subsequent sections will explore the project's development process, the
underlying technology stack, features and functionality, system architecture, challenges encountered,
testing methodologies, and the user interface design. The report will conclude with reflections on the
project's success, potential future enhancements, and acknowledgments to the contributors and
resources instrumental in bringing this Food recommendation system to fruition.
10
CHAPTER 2: PROJECT SCOPE AND FEATURES
The development of the Machine Learning-based Food Recommendation System encompasses a
comprehensive set of features carefully designed to address the specific needs and challenges
associated with food and its related nutrient content suggestions. The project scope outlines the
boundaries and objectives of the system, while the features represent the core functionalities that users
can leverage to enhance their diet planning(according to the nutrient content) experience.
Project scope:
● Target Audience:
1. Health-conscious individuals, fitness enthusiasts, and those with specific dietary goals
or restrictions.
● Testing and Quality Assurance:
a. Conduct thorough testing, including unit testing, integration testing, and user
acceptance testing, to ensure the reliability and accuracy of the recommendation system.
● Intuitive User Interface::
A user-friendly interface is paramount to the success of the application. The design prioritizes
simplicity without compromising functionality, ensuring that users of varying technical proficiencies
can navigate the application seamlessly.
● Responsive Design:
Considering the diverse devices and screen sizes used by individuals, the application is
developed
with a responsive design. This ensures a consistent and optimal user experience across desktops,
laptops, tablets, and smartphones
Features and Functionalities:
a. User Registration and Profile Creation
b. Input of User Preferences, Dietary Restrictions, and Health Goals
c. Integration with a Nutrient Database for Accurate Food Nutrient Information
d. Machine Learning Algorithms for Personalized Food Recommendations
e. User Feedback Mechanism for Continuous Improvement
f. Integration with External APIs for Real-Time Data (e.g., fitness trackers, health apps)
g. Social Features: Recipe Sharing and Community Engagement
11
CHAPTER 3: SYSTEM ARCHITECTURE
Hardware Requirement:
1. Quad-core processor: A processor equipped with at least 4 independent cores for high efficiency and
faster executions of instructions.
2.
500MB free disk space: The disk on which you would like to install the game should at least have
500MB of free space to ensure proper installation and working of the game.
3.
4GB RAM: The system must have at least 4GB of main memory (RAM) to ensure the playability of
the game.
Software Requirement:
1. Windows Operating System 7/8/10/11, 32/64-bit Architecture: A windows 7/8/10/11 stable release
with no restrictions for any user and proper resources and instructions set. Windows 10 is a major
release of Microsoft's Windows NT operating system. It is the direct successor to Windows 8.1, which
was released nearly two years earlier. It was released to manufacturing on July 15, 2015, and later to
retail on July 29, 2015. Windows 10 was made available for download via MSDN and TechNet, as a
free upgrade for retail copies of Windows 8 and Windows 8.1 users via the Windows Store, and to
Windows 7 users via Windows Updates
Work-flow:
Figure 1: Flowchart
12
Technologies used:
1. Python: Python, revered for its simplicity and readability, stands as a versatile, high-level
programming language. Its extensive standard library and vibrant community support have positioned
it as a go-to choice for developers across various domains. Python's ease of use and flexibility make it
well-suited for tasks ranging from web development to artificial intelligence, and its syntax promotes
efficient coding practices.
2. Visual Studio Code (VS Code): Visual Studio Code, a lightweight and feature-rich integrated
development environment (IDE), has gained immense popularity, particularly in the Python
community. Developed by Microsoft, VS Code provides a seamless coding experience with a
user-friendly interface, robust debugging tools, and an extensive library of extensions. Its adaptability
and cross-platform compatibility make it an invaluable tool for developers working on diverse
projects.
3. NumPy: NumPy, short for Numerical Python, is a fundamental library for numerical computations in
Python. It introduces support for large, multi-dimensional arrays and matrices, along with an
assortment of high-level mathematical functions to operate on these arrays. Numpy's efficiency and
speed are crucial for scientific and data-related computations, making it an essential building block
for various data science and machine learning applications.
4. Pandas: Pandas, a data manipulation library, excels in providing data structures for efficient data
analysis in Python. It introduces two key data structures, Series and DataFrame, which simplify tasks
like data cleaning, aggregation, and transformation. Pandas' versatility makes it an indispensable tool
for handling and analyzing structured data, streamlining the data preprocessing phase in data science
workflows.
5. Streamlit: Streamlit is a Python library designed to simplify the process of creating web applications
for data science and machine learning. It allows developers to transform data scripts into shareable
web apps with minimal effort. Streamlit's user-friendly API and interactive widgets make it easy to
build visually appealing and functional applications, making data exploration and analysis accessible
to a broader audience.
6. Google Colaboratory (Colab): Google Colaboratory, or Colab, is a cloud-based platform that
provides a free, interactive environment for running Python code in a Jupyter notebook format.
Hosted by Google, Colab offers collaborative coding features and seamless integration with Google
Drive. It provides access to GPU and TPU resources, making it an attractive choice for machine
learning experiments and data analysis tasks that require substantial computational power. Colab's
collaborative nature enables real-time collaboration, making it a convenient option for team projects
and educational purposes.
13
CHAPTER 4: IMPLEMENTATION
Implementing the Food Recommendation system involves a detailed examination of various aspects,
including the development process, coding practices, database integration, user authentication, and
testing methodologies. This section will comprehensively explore the implementation of the project,
providing insights into the decision-making processes, challenges faced, and the iterative evolution of
the application.
DEVELOPMENT PROCESS:
Dataset Analysis:
The journey of NourishNet commences with the initiation of the platform. As the system starts, it
progresses to loading the meticulously curated datasets: FOOD DATA with 1181 rows and 20 columns
and INGREDIENT DATA with 176 rows and 20 columns. This foundational step sets the stage for the
subsequent data-driven operations.
Data cleaning, the next pivotal phase, ensures the integrity and quality of the datasets. This process
involves identifying and rectifying inconsistencies or anomalies, fortifying the foundation for accurate
analyses. Following data cleaning, the platform transitions seamlessly into data preprocessing, where
the information undergoes transformations to enhance its suitability for analysis, setting the stage for
insightful computations.
NourishNet incorporates a series of functions that cater to diverse user queries. The system boasts a
function to print details of a specific food item, providing users with a comprehensive breakdown of
nutrient percentages. Additionally, users can utilize functions designed to search for food items based
on nutrient input, print the top 5 food items based on the average of specified nutrients, or extract
nutrient content in 100 grams of a particular ingredient.
Moreover, NourishNet accommodates user flexibility. If users seek information on a specific item, the
platform caters to their request. Alternatively, users can input a list of ingredients along with their
respective quantities, invoking a function that calculates and prints the cumulative nutrient content—a
feature designed to facilitate detailed dietary planning.
As NourishNet advances, it deploys a machine learning model that underpins its recommendation
system. The model, having learned from the datasets, enhances the platform's ability to provide
accurate and personalized nutritional insights. The streamlining of these complex operations is
facilitated through VS Code, a versatile IDE that ensures efficient code management and execution.
The pinnacle of NourishNet's user interface lies in the deployment of a Streamlit app. This
user-friendly app is designed to accommodate seamless interactions, enabling users to input queries
and receive instant, comprehensible results. The functions responsible for deploying the model within
the Streamlit app transform NourishNet into an accessible and user-centric solution.
In the final stride, NourishNet runs in its entirety. Users interact with the platform, leveraging its
14
capabilities to make informed dietary decisions and embark on a path toward healthier living. This
comprehensive data flow encapsulates the intricate yet user-friendly journey of NourishNet,
positioning it as an indispensable tool in the realm of nutritional awareness and well-being.
In summation, NourishNet: Food & Nutrient Mapper is not merely a platform; it is a dynamic
testament to the evolving narrative of health-conscious living in a technologically driven society.
Through its innovative features, comprehensive datasets, and unwavering commitment to accessibility,
NourishNet: Food & Nutrient Mapper metamorphoses into a catalyst for transformative change—a
catalyst that propels individuals toward a future where health is not just a goal but an integral and
empowering facet of the daily journey towards a more vibrant, nourished, and fulfilling life.
CHALLENGES FACED DURING MAKING OF THIS PROJECT AND THEIR SOLUTIONS:
1. Data Quality and Availability:
● Challenge: Obtaining a reliable and comprehensive nutrient database with up-to-date
information on a wide range of food items.
● Solution: Conduct thorough research to identify and integrate a reputable nutrient database
API. Implement data validation processes to ensure data accuracy.
2. User Engagement:
● Challenge: Encouraging users to actively input preferences and provide feedback.
● Solution: Implement a user-friendly interface, incentivize user participation through
gamification or rewards, and regularly communicate the benefits of user engagement.
3. Machine Learning Model Training:
● Challenge: Training machine learning algorithms to accurately predict personalized food
recommendations.
● Solution: Use a diverse and representative dataset for training, fine-tune model
hyperparameters, and implement continuous learning mechanisms to adapt to changing user
preferences.
15
4. Real-Time Data Integration:
● Challenge: Integrating real-time data from external sources, such as fitness trackers and health
apps.
● Solution: Collaborate with relevant API providers, implement secure and efficient data transfer
protocols, and ensure compatibility with a variety of devices and platforms.
5. Privacy and Security:
● Challenge: Ensuring the privacy and security of user data, especially when dealing with
health-related information.
● Solution: Implement robust encryption measures, comply with data protection regulations, and
clearly communicate the privacy policy to users. Regularly conduct security audits.
6. Scalability:
● Challenge: Designing the system to handle a growing user base without compromising
performance.
● Solution: Implement scalable architecture, utilize cloud services, and optimize database
queries for efficient data retrieval. Regularly monitor system performance and scale resources
accordingly.
16
CHAPTER 5: DATASETS
Table 1: Dataset for Food Items
17
Table 2: Dataset for Ingredients
18
CHAPTER 6: CODE SCREENSHOTS (VS CODE)
Figure 2: Float List of Nutrients
19
Figure 3: Importing Streamlit
20
CHAPTER 7: PROJECT TESTING & SYSTEM
OVERVIEW
Figure 4: Entering Food Item for Description
21
Figure 5: Entering Food Item for Nutrients
22
CHAPTER 8: RESULT AND DISCUSSION
RUNNING PROJECT SCREENSHOTS:
Figure 6: Recommendation on basis of Nutrient Input
Figure 7: Recommendation on basis of Ingredient Input
23
Results:
● User Engagement:
A significant level of user engagement was observed, with users regularly inputting
preferences and providing feedback on recommended food items.
● Personalization Accuracy:
The machine learning algorithms demonstrated a high level of accuracy in providing
personalized recommendations, aligning with user dietary goals and preferences.
● Nutrient Database Accuracy:
The nutrient database integration proved effective, offering reliable information on the
nutritional content of various food items.
Discussion:
● User Satisfaction:
User feedback indicated a high level of satisfaction with the system's ability to offer
tailored recommendations, contributing to positive user experiences.
● Health Impact:
The project positively impacted users' health and dietary habits by encouraging the
consumption of nutritionally balanced foods in line with their goals.
● Community Interaction:
Social features, such as recipe sharing and community engagement, fostered a sense of
community among users, enhancing the overall project experience.
Future Enhancements:
● Continuous Learning:
Implement mechanisms for continuous learning to further enhance the accuracy of
personalized recommendations over time.
● Expand External Integrations:
Explore additional partnerships with health-related platforms to broaden the scope of
real-time data integration.
24
CONCLUSION
In conclusion, NourishNet stands as a testament to the intersection of health-conscious living and
cutting-edge technology, aiming to empower individuals in their journey toward optimal well-being.
The foundations of this innovative platform are rooted in extensive datasets meticulously curated for
both food items and ingredients, creating a robust infrastructure for precise nutritional analyses.
Leveraging a tech stack comprising Python, Streamlit, Pandas, NumPy, and VS Code, NourishNet
seamlessly integrates machine learning capabilities to offer users a comprehensive Food
Recommendation System.
The mysobol.com study underscores the widespread commitment to healthy living, with 93 percent of
consumers expressing a desire to incorporate healthier eating habits into their lifestyles. NourishNet not
only addresses this societal inclination but also embraces the digital age by providing an accessible
web-based solution. The platform's user-friendly interface, coupled with functions catering to various
queries—ranging from nutrient details of specific food items to personalized dietary planning—ensures
inclusivity across diverse user backgrounds.
The data flow within NourishNet navigates through crucial stages, including data loading, cleaning, and
preprocessing, setting the stage for informed analyses. The deployment of a machine learning model
enhances the recommendation system, while the utilization of VS Code ensures efficient code
management. The culmination of these intricate processes results in the creation of a Streamlit app,
providing users with a seamless and interactive experience.
As NourishNet runs its course, it becomes a dynamic ally for individuals striving to make informed
dietary decisions. The platform not only meets the aspirations of the health-conscious majority but also
bridges the gap between traditional well-being practices and the digital age. NourishNet envisions a
future where health is not merely a goal but an intrinsic part of everyday life, promoting a holistic and
fulfilling lifestyle for individuals from all walks of life. In essence, NourishNet is more than a platform;
it is a catalyst for transformative change in the way we approach nutrition and well-being.
25
REFERENCES
Text books:
[1] The Hundred-Page Machine Learning Book by Andriy Burkov
[2] Learn Web Development with Python: Get hands-on with Python Programming and Django web
development : Romano, Fabrizio, C. Hillar, Gaston, Ravindran, Arun
[3] Ben Shneiderman and Catherine Plaisant Designing the User Interface: Strategies for Effective
Human-Computer Interaction (5th Edition, pp. 672, ISBN 0- 321-53735-1, March 2019), Reading, MA:
Addison-Wesley Publishing Co.
[4] Machine Learning For Absolute Beginners by Oliver Theobald.
Journals:
[5] EFFICIENT WAY OF WEB DEVELOPMENT USING PYTHON AND FLASK (link: Efficient
Way Of Web Development Using Python And Flask | Aslam | International Journal of Advanced
Research in Computer Science (ijarcs.info)
[6] Hilde Weerts, Miroslav Dudík, Richard Edgar, Adrin Jalali, Roman Lutz, Michael Madaio, 2023.
[7] Consumer recommendation prediction in online reviews using Cuckoo optimized machine learning
models: https://www.sciencedirect.com/science/article/pii/S0045790621003633
Websites:
[8] Learn Python - Free Interactive Python Tutorial
[9] Python Tutorials – Real Python
[10] Python Tutorial (w3schools.com)
[11] Kaggle – Datasets, Kernels & Competitions
[12] OpenML – Datasets, Tools & Tutorials
26
