Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Data Science Mega-Course: #Build {120-Projects In 120-Days}

Name: Data Science Mega-Course: #Build {120-Projects In 120-Days}
Rating: 4.5 (422 reviews)

Build & Deploy Data Science, Machine Learning, Deep Learning (Python, Flask, Django, AWS, Azure, GCP, Heruko Cloud)

Created byPianalytix • 75,000+ Students Worldwide

Last updated 9/2025

English

What you'll learn

Make powerful analysis, Make robust Machine Learning models
Master Machine Learning on Python
Know which Machine Learning model to choose for each type of problem
Implement Machine Learning Algorithms
Explore how to deploy your machine learning models.
Understand the full product workflow for the machine learning lifecycle.
Present Data Science projects to management
Real life case studies and projects to understand how things are done in the real world
Build a portfolio of work to have on your resume

Course content

122 sections • 800 lectures • 133h 43m total length

Introduction To The Course0:42
Introduces the data science mega-course and its goal of completing 120 projects in 120 days, outlining what learners will explore in this journey.
Course Outline Video1:15
Explore the data science mega-course outline, featuring 120 projects in 120 days, in this course outline video.
Course Bonuses: Cheat Sheets, Downloads, Mind maps, Guides.0:47
Udemy Course Feedback Info0:14
Review Udemy course feedback to improve the data science mega-course and its 120 projects across 120 days, enhancing learner outcomes and course design.

Introduction to Pan Card Tempering Detector1:47
Explore bank card tampering detection using computer vision to verify PAN cards and Aadhaar IDs by uploading images, converting to grayscale, computing similarity indices, and contour-based thresholds to decide tampering.
Loading Libraries and Dataset4:00
Set up google colab with the required hardware accelerator and compare the original and tampered pan card images using structural similarity and basic image processing.
Creating the Pan Card Detector with Opencv12:28
Detect tampering in pan card images using OpenCV. Resize images, convert to grayscale, compute structural similarity, and analyze thresholds and contours.
Creating the Flask App3:50
Create a flask app by configuring settings, initializing the app and views, and wiring a model to handle file uploads and render templates, with development and debug configurations.
Creating Important Functions4:56
Build and run a web app that uploads images, resizes and grayscales them, analyzes with cv2 to detect contours and draw bounding rectangles, and render results on index.html.
Deploy the App in Heroku5:45
Deploy a python app to Heroku by preparing the environment, installing dependencies from requirements.txt, and running app.py. Connect GitHub to Heroku, deploy the main branch, and obtain the app URL.
Testing the Deployed Pan Card Detector1:56
Develop and test a deployed pan card detector using a computer vision app, with front-end file upload, tamper-detection results, and deployment on Heroku via GitHub integration.
Download The Project Files0:29

Introduction1:59
Build and train a convolutional neural network with Keras and TensorFlow to identify dog breeds from images, using Kaggle data, one-hot encoding, normalization, and evaluating model accuracy.
Importing the Data and Libraries6:15
Develop a dog breed classification model with Keras and TensorFlow in Google Colab, importing libraries, preparing data via Kaggle API, downloading datasets, and building a convolutional neural network with conv2d.
Data Preprocessing3:10
Load the data, select three dog breeds, one-hot encode labels, convert images to numpy arrays, and normalize pixels by 255 to prepare 357 images of 224 by 224 by 3.
Build and Train Model7:07
Develop a sequential CNN with conv 2D and max pooling 2D layers, flatten and dense layers, using 3-class softmax output and Adam optimization for 224 by 224 by three inputs.
Testing the Model2:28
Plot training and validation accuracy across epochs with matplotlib, save the model history, and evaluate predictions to reach 83.33% accuracy; explore hyperparameter tuning to improve results.
Creating the Flask App6:40
Build a Streamlit app that loads a saved dog breed model (dog breed dot h5), accepts uploaded images, and shows breed predictions with a live interface.
Running the App in System4:12
Learn to create a requirements file, install Streamlit, and run a dog breed prediction app locally with Streamlit run, accessing it at localhost:8501.
Download The Project Files0:27

Introduction2:08
Learn how to add image and text watermarks with OpenCV in Google Colab, loading and resizing assets, defining the region of interest, and applying text watermark to protect content.
Importing Libraries and Logo2:51
Use Google Colab and OpenCV to add logo and text watermarks to images, importing cv2, numpy, request, and PIL, and downloading logos and images from URLs for copyright.
Create Text and Image Watermark8:46
Learn to add image and text watermarks to images using OpenCV and numpy; compute center, define the region of interest, and apply logo or text watermark.
Creating the App13:16
Learn to build a Flask app for an image watermarking project, wiring config, app, and views, handle logo and text watermarks, uploads, and deploy with Heroku using requirements.txt and pipreqs.
Deploying the App in Heroku5:28
Create a new repository and upload the image watermarking project. Connect GitHub to Heroku, enable automatic deploys from the main branch, and deploy the Python app.
Download The Project Files0:23

Introduction3:25
Build a traffic sign classification model with a convolutional neural network using TensorFlow and Keras, covering Kaggle data, Colab setup, preprocessing, one-hot encoding, training, evaluation, and visualization for self-driving cars.
Importing the Data and Libraries5:56
Connect your Kaggle account to Google Colab, download and prepare the German traffic sign dataset, and build, train, and test a CNN using TensorFlow and Keras for traffic sign classification.
Image Processing4:23
Visualize the traffic sign dataset, resize images to 50 by 50 with RGB channels, and normalize pixel values. Split data 80/20 and one-hot encode labels across 43 balanced classes.
Creating and Testing the Model7:00
Create and train a convolutional neural network by configuring conv2d layers, pooling, dropout, flattening, and a dense softmax layer for 43-class classification; tune hyperparameters and monitor training to reduce overfitting.
Creating Model for Test Set5:17
Scale test images to 50 by 50 and normalize them, remove files, and prepare data for traffic sign recognition, then build a conv2d model achieving 95%+ accuracy across 43 classes.
Download The Project Files0:23

Introduction2:16
Learn to extract text from images using Tesseract and Pytesseract, then enhance results with OpenCV basics like noise removal, blur, thresholding, and erosion to automate OCR.
Importing Libraries and Data3:45
Use Google Colab to extract text from images with Tesseract, installing Pytesseract and OpenCV, downloading an image, and performing OCR.
Extracting the Test From Image4:27
Extract text from images using pytesseract with English language configuration. Remove symbols with a for loop, handle exceptions, and use OpenCV to grayscale, blur, and threshold.
Modifying the Extractor7:58
Modify the extractor by using erosion with a 5x5 kernel on the foreground, then apply morphological operations, canny edge detection, deskewing, and template matching with pytesseract to bound text.
Creating the Extractor App8:21
Create a flask based optical character recognition app by configuring settings, handling image uploads, processing images to extract text, and building a front end with upload and display.
Running the Extractor App2:19
Install all libraries from the requirements.txt with pip install -r requirements.txt, then run the app via python app.py and upload an image to the OCR app to extract text.
Download The Project Files0:21

Introduction3:56
Explore building a convolutional neural network with TensorFlow and Keras to detect plant diseases from images, using Colab and drive data, with preprocessing, training, evaluation, and visualization.
Importing Libraries and Data3:49
Connect google drive to colab, import libraries, and build a cnn classifier in tensorflow/keras to predict plant disease, training and testing with image data.
Understanding the Data and Data Preprocessing5:06
Visualize and convert plant disease images into a balanced 900-image dataset of 256 by 256 three-channel rgb arrays, then preprocess with normalization, train/test split, and one-hot encoding for multi-class classification.
Model Building7:34
Create a sequential cnn architecture with conv2d, max pooling, flatten, and dense layers for three classes using softmax. Compile with categorical cross-entropy and Adam, train, evaluate, and save the model.
Creating an App using Streamlit11:29
Create a Streamlit app that loads a plant disease model, uploads leaf images, and predicts diseases like tomato bacterial spot and common rust using OpenCV and Keras.
Download the project files0:22

Introduction to Detect and Count variables3:09
Detect and count vehicles in images and videos using OpenCV and Haar cascade classifiers, load XML models, convert to grayscale, draw contours, and label each detected vehicle.
Importing Libraries and Data3:10
Learn to detect and count vehicles in images and videos using Google Colab, OpenCV, and Haar cascade classifiers (cars.xml and bus front.xml), with image download and visualization.
Transforming Images and Creating Output10:54
Convert images to grayscale, apply Gaussian blur and dilation for morphological enhancements, then detect cars and buses with Haar cascades and output video with OpenCV's video writer.
Creating a Flask App17:28
Build a Flask app for vehicle detection using Python scripting and a modular structure (config, app.py, init.py, views.py). Perform image processing with OpenCV and deploy on Heroku via GitHub.
Download the project files0:23

Introduction to Face Swap App2:37
Apply OpenCV and Dlib to extract facial landmarks, swap a source face onto a destination image, use triangulation and masks, and perform seamless color adjustment to align the images.
Importing Libraries and Data4:32
Learn to build a face swapping app in Google Colab using OpenCV and dlib, download a pre-trained shape predictor 68 landmarks model, and extract faces and landmarks from images.
Data Preprocessing and Creating Output14:09
Convert images to numpy arrays and grayscale with cv2, detect faces with dlib, extract landmarks, triangulate, swap faces, and apply seamless clone for color adjustment.
Creating a Flask App14:49
Build and deploy a flask app for a faceswap project, wiring config, initialization, image uploads, dlib face landmarks and triangulation, plus a front end with templates and static assets.
Download The Project Files0:23

Introduction2:35
Build a convolutional neural network with Keras to predict bird species from images, covering data prep, one-hot encoding, model architecture, training, evaluation, and visualizing predictions.
Importing Libraries and Data6:14
Utilize Google Colab and drive to load a bird species dataset, build and train a CNN in Keras with hyperparameters, and perform multi-class classification.
Data Processing3:37
Learn to process bird image data by configuring a six-class dataset, inspecting 224×224 rgb images and 811 labels, and applying train-test split, normalization, reshaping, and one-hot encoding.
Creating ML Model10:16
Build and train a convolutional neural network using a sequential model with conv2d and max pooling for multi-class bird species classification, including flattening, dense layers, softmax output, and model saving.
Creating A Flask App13:27
Create a Flask app for a bird species classification model, wiring config, loading a pre-trained six-class model, and handling image uploads and predictions via get and post.
Download The Project Files0:22

Requirements

Basic knowledge of machine learning

Description

In This Course, Solve Business Problems Using Data Science Practically. Learn To Build & Deploy Machine Learning, Data Science, Artificial Intelligence, Auto Ml, Deep Learning, Natural Language Processing (Nlp) Web Applications Projects With Python (Flask, Django, Heroku, AWS, Azure, GCP, IBM Watson, Streamlit Cloud).

According to Glassdoor, the average salary for a Data Scientist is $117,345/yr. This is above the national average of $44,564. Therefore, a Data Scientist makes 163% more than the national average salary.

This makes Data Science a highly lucrative career choice. It is mainly due to the dearth of Data Scientists resulting in a huge income bubble.

Since Data Science requires a person to be proficient and knowledgeable in several fields like Statistics, Mathematics, and Computer Science, the learning curve is quite steep. Therefore, the value of a Data Scientist is very high in the market.

A Data Scientist enjoys a position of prestige in the company. The company relies on its expertise to make data-driven decisions and enable them to navigate in the right direction.

Furthermore, the role of a Data Scientist depends on the specialization of his employer company. For example – A commercial industry will require a data scientist to analyze their sales.

A healthcare company will require data scientists to help them analyze genomic sequences. The salary of a Data Scientist depends on his role and type of work he has to perform. It also depends on the size of the company which is based on the amount of data they utilize.

Still, the pay scale of Data scientists is way above other IT and management sectors. However, the salary observed by Data Scientists is proportional to the amount of work that they must put in. Data Science needs hard work and requires a person to be thorough with his/her skills.

Due to several lucrative perks, Data Science is an attractive field. This, combined with the number of vacancies in Data Science makes it an untouched gold mine. Therefore, you should learn Data Science in order to enjoy a fruitful career.

In This Course, We Are Going To Work On 120 Real World Projects Listed Below:

Project-1: Pan Card Tempering Detector App -Deploy On Heroku

Project-2: Dog breed prediction Flask App

Project-3: Image Watermarking App -Deploy On Heroku

Project-4: Traffic sign classification

Project-5: Text Extraction From Images Application

Project-6: Plant Disease Prediction Streamlit App

Project-7: Vehicle Detection And Counting Flask App

Project-8: Create A Face Swapping Flask App

Project-9: Bird Species Prediction Flask App

Project-10: Intel Image Classification Flask App

Project-11: Language Translator App Using IBM Cloud Service -Deploy On Heroku

Project-12: Predict Views On Advertisement Using IBM Watson -Deploy On Heroku

Project-13: Laptop Price Predictor -Deploy On Heroku

Project-14: WhatsApp Text Analyzer -Deploy On Heroku

Project-15: Course Recommendation System -Deploy On Heroku

Project-16: IPL Match Win Predictor -Deploy On Heroku

Project-17: Body Fat Estimator App -Deploy On Microsoft Azure

Project-18: Campus Placement Predictor App -Deploy On Microsoft Azure

Project-19: Car Acceptability Predictor -Deploy On Google Cloud

Project-20: Book Genre Classification App -Deploy On Amazon Web Services

Project 21 : DNA classification for finding E.Coli - Deploy On AWS

Project 22 : Predict the next word in a sentence. - AWS - Deploy On AWS

Project 23 : Predict Next Sequence of numbers using LSTM - Deploy On AWS

Project 24 : Keyword Extraction from text using NLP - Deploy On Azure

Project 25 : Correcting wrong spellings - Deploy On Azure

Project 26 : Music popularity classification - Deploy On Google App Engine

Project 27 : Advertisement Classification - Deploy On Google App Engine

Project 28 : Image Digit Classification - Deploy On AWS

Project 29 : Emotion Recognition using Neural Network - Deploy On AWS

Project 30 : Breast cancer Classification - Deploy On AWS

Project-31: Sentiment Analysis Django App -Deploy On Heroku

Project-32: Attrition Rate Django Application

Project-33: Find Legendary Pokemon Django App -Deploy On Heroku

Project-34: Face Detection Streamlit App

Project-35: Cats Vs Dogs Classification Flask App

Project-36: Customer Revenue Prediction App -Deploy On Heroku

Project-37: Gender From Voice Prediction App -Deploy On Heroku

Project-38: Restaurant Recommendation System

Project-39: Happiness Ranking Django App -Deploy On Heroku

Project-40: Forest Fire Prediction Django App -Deploy On Heroku

Project-41: Build Car Prices Prediction App -Deploy On Heroku

Project-42: Build Affair Count Django App -Deploy On Heroku

Project-43: Build Shrooming Predictions App -Deploy On Heroku

Project-44: Google Play App Rating prediction With Deployment On Heroku

Project-45: Build Bank Customers Predictions Django App -Deploy On Heroku

Project-46: Build Artist Sculpture Cost Prediction Django App -Deploy On Heroku

Project-47: Build Medical Cost Predictions Django App -Deploy On Heroku

Project-48: Phishing Webpages Classification Django App -Deploy On Heroku

Project-49: Clothing Fit-Size predictions Django App -Deploy On Heroku

Project-50: Build Similarity In-Text Django App -Deploy On Heroku

Project-51: Black Friday Sale Project

Project-52: Sentiment Analysis Project

Project-53: Parkinson’s Disease Prediction Project

Project-54: Fake News Classifier Project

Project-55: Toxic Comment Classifier Project

Project-56: IMDB Movie Ratings Prediction

Project-57: Indian Air Quality Prediction

Project-58: Covid-19 Case Analysis

Project-59: Customer Churning Prediction

Project-60: Create A ChatBot

Project-61: Video Game sales Analysis

Project-62: Zomato Restaurant Analysis

Project-63: Walmart Sales Forecasting

Project-64 : Sonic wave velocity prediction using Signal Processing Techniques

Project-65 : Estimation of Pore Pressure using Machine Learning

Project-66 : Audio processing using ML

Project-67 : Text characterisation using Speech recognition

Project-68 : Audio classification using Neural networks

Project-69 : Developing a voice assistant

Project-70 : Customer segmentation

Project-71 : FIFA 2019 Analysis

Project-72 : Sentiment analysis of web scrapped data

Project-73 : Determining Red Vine Quality

Project-74 : Customer Personality Analysis

Project-75 : Literacy Analysis in India

Project-76: Heart Attack Risk Prediction Using Eval ML (Auto ML)

Project-77: Credit Card Fraud Detection Using Pycaret (Auto ML)

Project-78: Flight Fare Prediction Using Auto SK Learn (Auto ML)

Project-79: Petrol Price Forecasting Using Auto Keras

Project-80: Bank Customer Churn Prediction Using H2O Auto ML

Project-81: Air Quality Index Predictor Using TPOT With End-To-End Deployment (Auto ML)

Project-82: Rain Prediction Using ML models & PyCaret With Deployment (Auto ML)

Project-83: Pizza Price Prediction Using ML And EVALML(Auto ML)

Project-84: IPL Cricket Score Prediction Using TPOT (Auto ML)

Project-85: Predicting Bike Rentals Count Using ML And H2O Auto ML

Project-86: Concrete Compressive Strength Prediction Using Auto Keras (Auto ML)

Project-87: Bangalore House Price Prediction Using Auto SK Learn (Auto ML)

Project-88: Hospital Mortality Prediction Using PyCaret (Auto ML)

Project-89: Employee Evaluation For Promotion Using ML And Eval Auto ML

Project-90: Drinking Water Potability Prediction Using ML And H2O Auto ML

Project-91: Image Editor Application With OpenCV And Tkinter

Project-92: Brand Identification Game With Tkinter And Sqlite3

Project-93: Transaction Application With Tkinter And Sqlite3

Project-94: Learning Management System With Django

Project-95: Create A News Portal With Django

Project-96: Create A Student Portal With Django

Project-97: Productivity Tracker With Django And Plotly

Project-98: Create A Study Group With Django

Project-99: Building Crop Guide Application with PyQt5, SQLite

Project-100: Building Password Manager Application With PyQt5, SQLite

Project-101: Create A News Application With Python

Project-102: Create A Guide Application With Python

Project-103: Building The Chef Web Application with Django, Python

Project-104: Syllogism-Rules of Inference Solver Web Application

Project-105: Building Vision Web Application with Django, Python

Project-106: Building Budget Planner Application With Python

Project-107: Build Tic Tac Toe Game

Project-108: Random Password Generator Website using Django

Project-109: Building Personal Portfolio Website Using Django

Project-110: Todo List Website For Multiple Users

Project-111: Crypto Coin Planner GUI Application

Project-112: Your Own Twitter Bot -python, request, API, deployment, tweepy

Project-113: Create A Python Dictionary Using python, Tkinter, JSON

Project-114: Egg-Catcher Game using python

Project-115: Personal Routine Tracker Application using python

Project-116: Building Screen -Pet using Tkinter & Canvas

Project-117: Building Caterpillar Game Using Turtle and Python

Project-118: Building Hangman Game Using Python

Project-119: Developing our own Smart Calculator Using Python and Tkinter

Project-120: Image-based steganography Using Python and pillows

Tip: Create A 60 Days Study Plan Or 120 Day Study Plan, Spend 1-3hrs Per Day, Build 120 Projects In 60 Days Or 120 Projects In 120 Days.

The Only Course You Need To Become A Data Scientist, Get Hired And Start A New Career

Note (Read This): This Course Is Worth Of Your Time And Money, Enroll Now Before Offer Expires.

Who this course is for:

Beginners in data science

Data Science Mega-Course: #Build {120-Projects In 120-Days}

What you'll learn

Explore related topics

Course content

Introduction To The Course4 lectures • 3min

Project-1: Pan Card Tempering Detector App -Deploy On Heroku8 lectures • 35min

Project-2: Dog breed prediction Flask App8 lectures • 32min

Project-3: Image Watermarking App -Deploy On Heroku6 lectures • 33min

Project-4: Traffic sign classification6 lectures • 26min

Project-5: Text Extraction From Images Application7 lectures • 29min

Project-6: Plant Disease Prediction6 lectures • 32min

Project-7: Detect and count vehicles5 lectures • 35min

Project-8: Create A Face Swapping Flask App5 lectures • 37min

Project-9: Bird Species Prediction Flask App6 lectures • 37min

Requirements

Description

Who this course is for: