Skip to main content
techtonic-lab-logoTechtonic-Lab

Syllabus

Data Science Course in Nagpur — full syllabus

Every module, every topic, every tool and the hours behind each. Published in full so you can compare it against any other institute in Nagpur before you pay anyone.

Modules
8
Topics
40
Tools
22
Projects
4
Duration
9 months
Prerequisites
Comfort with school-level mathematics helps. Python is taught from scratch.

Tool stack

Everything you will touch

Named in full, because a syllabus that says “BI tools” is hiding something.

  • Python
  • NumPy
  • pandas
  • Git
  • MySQL
  • Excel
  • Matplotlib
  • Seaborn
  • Plotly
  • SciPy
  • scikit-learn
  • XGBoost
  • TensorFlow
  • Keras
  • OpenCV
  • Transformers
  • OpenAI API
  • LangChain
  • Flask
  • FastAPI
  • Streamlit
  • Docker

Module by module

The whole thing, in order

Modules run in this sequence deliberately. Each one assumes the last, which is why the Excel or foundations block comes before anything harder.

01

Python, NumPy and Pandas

Months 1–2

Topics

  • Python fundamentals, data structures, OOP and file handling
  • Exception handling, modules and packages
  • NumPy arrays, broadcasting and linear algebra
  • pandas — DataFrames, cleaning, GroupBy, merge and join
  • Version control with Git and GitHub

Tools

  • Python
  • NumPy
  • pandas
  • Git

You finish with

A reusable data-loading and cleaning module of your own

02

SQL, Advanced Excel and visualisation

Month 3

Topics

  • SQL — joins, subqueries, CTEs, window functions, stored procedures
  • Data modelling and normalisation
  • Advanced Excel — Power Query, Power Pivot, VBA and macros
  • Matplotlib, Seaborn and Plotly
  • Statistical and interactive visualisations

Tools

  • MySQL
  • Excel
  • Matplotlib
  • Seaborn
  • Plotly

You finish with

An interactive dashboard combining SQL-sourced data and Python plots

03

Statistics and mathematics

Month 4 (first half)

Topics

  • Descriptive and inferential statistics, probability and sampling
  • Hypothesis testing — T-test, ANOVA, Chi-square
  • Correlation and covariance
  • Linear algebra, matrices and vectors
  • Calculus basics, gradient descent and optimisation

Tools

  • Python
  • SciPy

You finish with

A written statistical analysis with stated assumptions and limits

04

EDA and machine learning

Months 4–5

Topics

  • Data profiling, outlier detection and feature engineering
  • Supervised learning — regression, decision trees, random forest, SVM, XGBoost
  • Unsupervised learning — K-Means, hierarchical, DBSCAN, PCA
  • Model evaluation — precision, recall, F1, ROC-AUC
  • Cross-validation and hyperparameter tuning

Tools

  • scikit-learn
  • XGBoost
  • Python

You finish with

A tuned, cross-validated classifier with an honest error analysis

05

Deep learning

Month 6

Topics

  • Neural networks and the perceptron
  • ANN, CNN, RNN and LSTM
  • TensorFlow and Keras
  • Transfer learning
  • Image classification

Tools

  • TensorFlow
  • Keras
  • Python

You finish with

An image classifier trained and evaluated end to end

06

NLP and computer vision

Month 7

Topics

  • Text processing, tokenisation, stemming and lemmatisation
  • Sentiment analysis and text classification
  • Word embeddings, transformers and BERT basics
  • Image processing with OpenCV
  • Object detection and face recognition

Tools

  • OpenCV
  • Transformers
  • Python

You finish with

A sentiment-analysis model and an OpenCV vision task

07

Generative AI and LLMs

Month 8

Topics

  • Introduction to AI, GenAI and prompt engineering
  • Large Language Models and the OpenAI APIs
  • LangChain and Retrieval-Augmented Generation (RAG)
  • AI agents and AI automation
  • Building a GenAI application

Tools

  • OpenAI API
  • LangChain
  • Python

You finish with

A RAG-based application over your own document set

08

Deployment, capstone and corporate grooming

Month 9

Topics

  • Model deployment — Flask, FastAPI, Streamlit and REST APIs
  • Docker basics and an introduction to MLOps
  • Cloud fundamentals (AWS / Azure)
  • End-to-end industry capstone project
  • Resume, LinkedIn, GitHub portfolio, mock interviews and grooming

Tools

  • Flask
  • FastAPI
  • Streamlit
  • Docker

You finish with

A deployed model behind a working endpoint, defended in review

Portfolio

The four projects you leave with

Documented, reviewed and defended out loud. This is the part of the syllabus that gets you interviews.

Demand forecasting model

Forecast weekly demand for a retail category, then explain honestly where the model breaks and what it would cost the business.

Tools
Python, scikit-learn, pandas
Dataset
Public retail sales history

Credit-risk classifier

Build and tune a classifier, then work through the class-imbalance and fairness problems that make this a hard problem rather than a tutorial.

Tools
scikit-learn, XGBoost
Dataset
Public lending dataset

Sentiment analysis and NLP

Process real text, build a classifier and interpret it, using embeddings and transformer basics rather than a bag-of-words toy.

Tools
Transformers, Python
Dataset
Public review corpus

Deployed GenAI capstone

Take a model or a RAG application all the way to a running endpoint with a simple interface, so you can demonstrate it live in an interview.

Tools
LangChain, FastAPI, Docker
Dataset
Your own choice from earlier projects

Compare this syllabus against anyone

Take it to another institute and ask for theirs in the same detail. That comparison is the whole reason we publish it.