About Toolkit Projects ML Projects Personal Experience Certificates Contact
Open to opportunities

Nadir
Khan

Data Analyst

Diploma in Computer Engineering. I turn raw, messy data into clear business insight — through EDA, SQL, interactive dashboards and Python-based machine learning apps — and I build practical tools with Python and AI.

View Projects Contact Me Resume ↓
Portfolio Projects
15+
Analytics · SQL · ML · Python · Django
Largest Dataset Analyzed
150K
Records — Ride Booking Analysis
Core Stack
Python SQL Power BI Pandas PostgreSQL Excel EDA DAX Scikit-learn Streamlit
scroll
about

Who I Am

NK
Education Diploma — Computer Engineering
Focus Data Analysis, EDA & Applied ML
Experience Data Analytics & Python with AI Intern (2026)
Tools Python · SQL · Power BI · Excel
Status Open to Opportunities
GitHub LinkedIn Email Me

I'm Nadir Khan, a data analyst with a Diploma in Computer Engineering and a year of hands-on, project-based practice in data analytics — a genuine obsession with understanding what data is trying to say. I don't just run scripts — I ask the right questions first, then let the data answer them.

My analytical journey started with building desktop applications in Python and gradually evolved into a full-stack data practice — from writing complex SQL queries and designing relational databases to building interactive Power BI dashboards that stakeholders can actually use.

My strongest discipline is Exploratory Data Analysis (EDA) — I dig into raw datasets, clean them rigorously, and surface patterns, outliers, and trends that drive real decisions. From 150K ride bookings to e-commerce purchase behavior, every dataset has a story — and I know how to find it.

As a fresher, I have worked through a Data Analytics internship at Thiranex and completed a 1-month Python with AI internship at EWB Courses. I'm now extending my analytics foundation into Machine Learning and AI-powered applications — deploying Scikit-learn models with Streamlit so analysis can move from insight to prediction.

Python Ecosystem
Pandas NumPy Matplotlib Seaborn ydata-profiling OpenPyXL Missingno Streamlit SQLAlchemy
Database & SQL
SQL PostgreSQL MySQL SQLite Database Design Subqueries Window Functions CTEs
BI & Visualization
Power BI DAX Power Query Looker Studio Excel Figma
Machine Learning & NLP
Scikit-learn Logistic Regression NLTK TF-IDF ML Fundamentals Data Preprocessing Web Scraping BeautifulSoup LLM / Ollama
Backend & Web
Django Bootstrap 5 ReportLab FastAPI
Development & Tools
Git HTML / CSS Tkinter CustomTkinter Google Colab
skills

My Toolkit

🐍
Python
Pandas, NumPy, Matplotlib, Seaborn, ydata-profiling, and Streamlit for data wrangling, EDA, and reporting.
🗄️
SQL
Complex queries, joins, aggregations, subqueries, and window functions across PostgreSQL, MySQL, and SQLite.
📊
Power BI
DAX measures, data modeling, Power Query transformations, and interactive dashboards for business reporting.
🤖
Machine Learning
Scikit-learn, Logistic Regression, and NLP (NLTK, TF-IDF) — from EDA and leak-free preprocessing to deployed, interactive prediction apps.
🏗️
Django
Models, migrations, signals, class-based views, and admin customization — building full-stack apps like StockFlow and a billing system.
📈
Excel
Pivot tables, VLOOKUP, advanced formulas, and data cleaning for rapid exploratory analysis.
🎨
Figma
Designing clean dashboard layouts and visualization mockups before building them out in Power BI, ensuring a polished, presentation-ready end product.
🕸️
Web Scraping
Collecting structured data from public web sources using Python-based scraping tools to build custom analysis-ready datasets.
data analytics

Analytics Projects

01 / analytics
Sales Performance Dashboard
Interactive Power BI dashboard tracking KPIs across regions, products, and time periods. Includes drill-through reports and dynamic slicers for executive decision-making.
Power BI SQL Excel
02 / analytics
E-Commerce Customer Purchase Behavior — EDA
EDA Heavy
In-depth EDA on ~3,900 customer records across 18 features — analyzing demographics, product categories, seasonal trends, payment preferences, and discount impact. Full pipeline: automated YData Profiling report → data cleaning (median imputation) → univariate, bivariate & multivariate analysis → actionable business insights.
Python Pandas Matplotlib Seaborn EDA ydata-profiling Data Cleaning Google Colab
Key Insights
→ 25–45 age group is the largest customer segment
→ Clothing leads all categories by purchase volume
→ Fall & Winter drive higher average spend
→ Credit Card & PayPal are top payment methods
GitHub → Notebook →
03 / analytics
Customer Segmentation — SQL Analysis
Segmented customers into behavioral cohorts using pure SQL on transactional data. Applied RFM logic (Recency, Frequency, Monetary), window functions, CTEs, and GROUP BY aggregations to identify high-value, at-risk, and dormant customer groups — enabling targeted retention strategy.
PostgreSQL CTEs Window Functions RFM Analysis Segmentation
GitHub →
04 / analytics
Starbucks Beverage Analytics — Power BI
Brand-aligned Power BI dashboard analyzing Starbucks beverage nutrition data across 33 products. KPI cards for Avg Calories (193.78), Avg Caffeine (82), Avg Sugar (32.9), Top 5 caffeine beverages with product images, category distribution donut chart, and interactive filters for Protein Range and Beverage Prep method.
Power BI DAX Power Query Data Visualization Brand Design
GitHub →
05 / analytics
Online Book Store — SQL Database Project
Designed a relational database for an online book store with Books, Customers, and Orders tables. Wrote SQL queries covering table creation, JOINs, GROUP BY, and aggregate functions to solve real-world business questions.
PostgreSQL Database Design JOINs
GitHub →
06 / analytics
Wave Shoes Store — Sales Dashboard
Interactive Looker Studio dashboard analyzing ₹113.33M in sales across 7.8K+ transactions and 24K units sold. SQL queries for data prep, with category, geographic, and state-wise profit breakdowns plus dynamic filters.
SQL Looker Studio Data Viz EDA
GitHub → Live Dashboard →
07 / analytics
Ride Booking Analytics Dashboard
EDA Heavy
End-to-end analysis of 1,50,000 ride bookings across 21 variables — covering booking status, vehicle demand, revenue, cancellations, and peak-hour trends. EDA & data cleaning in Python, full Power BI dashboard with DAX measures and dynamic slicers.
Power BI DAX Python EDA Pandas Seaborn
GitHub →
08 / analytics
Hospital Data Analysis — SQL
Analyzed hospital records covering patients, doctors, departments, and medical expenses. Used aggregate functions, GROUP BY, subqueries, and date arithmetic to find top departments, longest stays, and monthly expense trends.
PostgreSQL Subqueries Aggregation
GitHub →
machine learning

ML Projects

01 / ml
Customer Churn Prediction System
End-to-end ML project predicting whether a bank customer will churn — the full pipeline from raw data through EDA, leak-free preprocessing, and Logistic Regression training to a deployed, interactive Streamlit app. Reports honest, class-wise metrics rather than a single headline accuracy figure, given the imbalance in the underlying data.
10K Customers 80.8% Accuracy Streamlit App Logistic Regression
  • Full ML workflow — EDA, preprocessing, model training & evaluation, deployment
  • Leak-free preprocessing — One-Hot Encoding + StandardScaler fit only on the train split
  • Class-wise evaluation — precision, recall, F1 & ROC-AUC reported by class on an imbalanced churn dataset
  • Live predictions with churn probability through an interactive Streamlit interface
Python Scikit-learn Pandas Streamlit
GitHub → Live Demo →
02 / ml
Fake News Detection AI
Machine learning web app that classifies news articles as Real or Fake using an NLP text-cleaning pipeline, TF-IDF vectorization, and a Logistic Regression classifier — wrapped in an interactive Streamlit UI with live confidence scoring.
97% Accuracy 45.7K Articles Streamlit App Logistic Regression
  • NLP pipeline — lowercasing, punctuation removal, tokenization, stopword removal & Porter stemming
  • TF-IDF + Logistic Regression trained on the WELFake dataset (~45.7K labeled articles)
  • Live predictions with confidence score and full probability breakdown
  • Cached inference via st.cache_resource for fast repeat predictions
Python Scikit-learn NLTK Streamlit TF-IDF
GitHub → Live Demo →
personal

Personal Builds

01 / personal
Student Result Management System
Full-featured desktop app for the complete student academic lifecycle — course registration, enrollment, result entry, and grade reports — backed by SQLite and a polished Tkinter GUI.
5 Screens SQLite / rms.db Real-time Clock Desktop App
  • Secure admin login with session management & logout flow
  • Full CRUD for courses, students, and results via ttk Treeview
  • Auto-calculate pass/fail, percentage, and grade per subject
  • Report viewer — search by roll number, print formatted result card
Python Tkinter SQLite3 ttk OOP
GitHub →
02 / personal
Library Management System — LMS
Production-quality desktop LMS handling the complete book-lending lifecycle. Modern CustomTkinter UI, live-updating admin dashboard, modular OOP architecture, and automatic DB initialisation.
CustomTkinter SQLite / lib.db 6 Classes Auto-refresh 2s
  • Live KPI dashboard — Total Books, Students, Issued Books updating every 2s
  • Secure login with show/hide password toggle & account registration
  • Book & Student CRUD — add, edit, delete, search with ttk Treeview
  • Centralised data layer with path-safe DB init, isolated .venv, and Pillow UI
Python CustomTkinter SQLite3 Pandas OOP
GitHub →
03 / personal
StockFlow — Inventory & Order Management
Full-stack Django inventory and order management system built the way a small retail shop or warehouse would actually use one day-to-day — not another tutorial to-do app. Stock adjusts itself the moment an order is placed, and a dashboard flags what needs reordering before it runs out.
Django 5.2 PostgreSQL Role-Based Access PDF Invoices
  • Auto stock adjustment via Django signals on Purchase & Sales orders, with overselling protection
  • Low-stock dashboard and a sales report — 30-day revenue & top products via ORM aggregation
  • PDF invoices generated on demand for every sale (ReportLab)
  • Role-based access — Owner and Staff see and can do different things
Python Django PostgreSQL Bootstrap 5 ReportLab
GitHub →
04 / personal
Billing System — Invoice Management App
Lightweight Django invoicing app built to practice core backend fundamentals — a custom user model, class-based CRUD views, form validation, and Django admin customization, wrapped in a clean, card-based UI.
Django 6.0 Custom Auth Invoice CRUD Admin Integration
  • Custom user model (CustomUser) built before the first migration, not bolted on after
  • Full invoice CRUD via Django's class-based generic views (List/Detail/Create/Update/Delete)
  • Custom validation — clean_amount() ensures invoice amounts are always greater than zero
  • Django admin integration — invoices searchable and filterable by payment status and date
Python Django SQLite CSS
GitHub →
05 / personal
Dashboard Automation Tool
A multipage Streamlit application that automates the repetitive first half of every analytics engagement — loading a messy file, cleaning it, understanding it, visualising it, and handing back a documented deliverable. Built for analysts who get the same broken exports every week and spend an hour fixing them by hand before the real work starts.
5-Stage Pipeline 73 Tests 6 File Formats Streamlit App
  • Auto Clean pipeline — one-click fixes for whitespace, placeholders, and duplicates, with conservative type inference and identifier protection for values like PIN codes
  • Data quality scoring — every dataset graded out of 100 across completeness, uniqueness, and type consistency
  • Interactive dashboard — global filters, KPI tiles, and nine chart types with Top-N ranking, built on Plotly
  • Full export suite — CSV, Excel, Parquet, and JSON, including a multi-sheet formatted workbook and a full cleaning audit trail
Python Streamlit Pandas Plotly
GitHub → Live Demo →
experience

Internship Experience

01 / internship · Sept – Oct 2026
Data Analytics Intern
Thiranex · Remote · Project-Based
Project-based remote internship in data analytics, applying Python, SQL and Power BI skills to practical datasets — from data cleaning and EDA to reporting and insight communication.
Data Analytics Python SQL EDA
02 / internship · October 2026
Python with AI Intern
EWB Courses (EWB Edu Tech Pvt. Ltd.) · 1 Month · Certificate ID EWB/INT/2026/0343
Completed a one-month Python with AI internship and delivered an assigned real-world project, applying Python and AI techniques to a practical problem.
Python AI Real-world Project
certifications

Certificates & Courses

01 / certificate
Microsoft Power BI (Self Learning)
Issued by Skill Course · ISO 9001:2015 Certified · March 2026
Completed a self-paced course covering Power BI fundamentals — data modeling, DAX basics, report design, and building interactive dashboards for business reporting.
Power BI Data Modeling DAX
02 / certificate
C & C++ Programming Certification
Issued by iTronix Solutions · ISO 9001:2015 Certified · July 2025
Completed certification in C and C++ programming languages, covering core programming concepts, data structures, and problem-solving fundamentals — the foundation for analytical and logical thinking in data work.
C C++ Programming Fundamentals
03 / certificate
30-Days SQL Micro Course
Issued by Skill Course / CoursePe · ISO 9001:2015 Certified · January 2026
Completed an intensive 30-day SQL program covering querying, joins, aggregations, subqueries, and database fundamentals — directly applied across multiple analytics and SQL-based portfolio projects.
SQL PostgreSQL Database Querying
04 / certificate
Resume Writing & Job Interviewing
Issued by HP LIFE / HP Foundation · July 2025
Completed HP LIFE's career-readiness course on building a tailored resume and cover letter, preparing for interviews, and using self-assessment as a tool for career growth and job search strategy.
Resume Writing Interview Prep Career Skills
05 / certificate
Prompt Engineering
Issued by Vedam School of Technology · CodeSprint
Completed a dedicated Prompt Engineering course covering effective prompt design and structuring for working productively with AI language models — applied directly to building AI-assisted analytics workflows.
Prompt Engineering AI Tools CodeSprint
06 / certificate
Basics of Data Science
Issued by UniAthena · In Partnership with Cambridge International Qualifications, UK · August 2026
Completed a foundational course in data science — covering core concepts, terminology, and the analytical mindset that underpins the EDA and machine learning work across other portfolio projects.
Data Science Fundamentals Analytics
07 / certificate
Full-Stack Mobile App Development using Flutter & REST APIs
Issued by C-DAC, Mohali · FutureSkills PRIME — MeitY & NASSCOM · July 2026
Completed a hands-on bootcamp on building full-stack mobile apps with Flutter, covering REST API integration and cross-platform UI development, conducted under the Ministry of Electronics & IT's FutureSkills PRIME digital skilling initiative.
Flutter REST APIs Mobile Development
Certificate preview
contact

Let's Talk

I'm open to internships, freelance data projects, and collaborations. Whether you have a dataset to analyze, a dashboard to build, or just want to connect — drop me a message.

Something went wrong. Please try again or email me directly at nadirkhan5864@gmail.com.
✓

Thanks for reaching out!

Your message has been sent successfully. I'll get back to you as soon as possible — usually within a day or two.