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 Bundle: 180 Hands-On Projects - Course 2 of 3

Name: Data Science Bundle: 180 Hands-On Projects - Course 2 of 3
Rating: 4.4 (43 reviews)

Build & Deploy 180 Projects - Data Science, Machine Learning, Deep Learning (Python, Flask, Django, AWS, Azure Cloud)

Created byPianalytix • 75,000+ Students Worldwide

Last updated 10/2025

English

What you'll learn

Master the essentials of Machine Learning using Python, the go-to language for Data Science.
Learn to build robust Machine Learning models that can withstand real-world uncertainties.
Gain insights into the end-to-end product workflow of the Machine Learning lifecycle, ensuring you understand each phase deeply.
Acquire the skills needed to deploy Machine Learning models, making them functional in a live environment.
Develop a strong intuition for choosing the right Machine Learning models for different tasks.
Empower yourself to conduct powerful data analyses that can drive decision-making processes.
Learn data-cleaning techniques to handle and remove outliers, ensuring data quality.
Equip yourself with skills that are in high demand, increasing your chances of getting hired as a Data Scientist.

Course content

61 sections • 339 lectures • 42h 14m total length

Introduction to the course0:29
Kick off the data science bundle by outlining the course goals and structure, and introducing the hands-on projects focus for course 2 of 3.
Outline of the course0:40
Outline the course structure for data science bundle course 2 of 3, highlighting the 180 hands-on projects as a practical path to build analytics skills.
Course Bonuses: Cheat Sheets, Downloads, Mind maps, Guides.0:47

Introduction - Developing an AI Chatbot using GPT-3.56:22
Develop an AI chatbot web app using natural language processing, tokenization, vector embeddings, and transformers with GPT-3.5, then deploy via a Flask app and OpenAI API key.
create app7:01
Learn to create a Flask web app with a structured project directory, including static and templates folders, an index.html front end, and a GPT-3.5 turbo chat integration.
Download the project files0:29

Introduction - American Sign Language Detection with CNN2:24
Develop American Sign Language detection via image classification with convolutional neural networks, learn image cleaning and processing, and deploy model as a Flask web app using Lex set 27,000-image dataset.
Data Reading and Processing2:38
Read and pre-process image data with TensorFlow Keras image data generator, set train and validation splits, and configure 128x128 RGB inputs across 27 classes and about 24,300 images.
Model - American Sign Language Detection with CNN7:39
Design a convolutional neural network in TensorFlow and Keras to detect American Sign Language with 27 classes, using conv, pooling, ReLU, and dense layers, and evaluate with accuracy.
Flask app5:15
Create a Flask app with static and templates folders, upload png or jpg images, process them with image pre and predict functions, and display predicted class from a Keras model.
Download the project files0:27

Introduction2:29
Classify urban built-up areas from land data using neural networks trained on k-means generated ground-truth maps from multispectral Landsat imagery, and deploy the model as a flask web app.
Ground Truth4:30
Read six-channel multispectral rasters using gdal. Reshape the data for model input and apply k-means to identify land-cover classes like water, vegetation, and built-up areas.
Model6:31
Explore artificial neural networks, including neuron structure and activation functions, and build a binary classifier with two dense layers of 50 and 20 neurons trained on multispectral images.
Flask6:06
Create a Flask web app with a structured layout, handle image uploads, load a Keras model, preprocess input, predict, and save the output image in static for display.
Download the project files0:27

Introduction7:01
Explore clustering Covid papers using Tf-Idf and K-means, learning vector embeddings, text cleaning, and dimensionality reduction with PCA, t-SNE, and Diezani to visualize results.
Model5:15
Import numpy and pandas to load a csv, build a dataframe, vectorize title and journal with tf-idf. Reduce with PCA, cluster with 25 k-means, visualize with matplotlib and seaborn.
Download the project files0:23

Introduction4:09
Develop a crop recommendation and yield prediction system using classification with artificial neural networks and regression with XGBoost, including data cleaning and deploying a Flask web app.
Model9:08
Build machine learning models for crops grown in India using a Jupyter notebook workflow, TensorFlow and Keras, with data prep, train-test split, model architecture, training, evaluation, and prediction pipelines.
Flask8:44
Learn to build a flask web app with a model pipeline that takes n, p, k, temperature, humidity, pH, rainfall, and predicts crop recommendations and yield via /recommend and /yield.
Download the project files0:23

Introduction - Generating Images with DCGAN Architecture4:28
Generate paintings with deep convolutional generative adversarial networks (dcgan) by training a generator and discriminator on a paintings dataset, then deploy the model as a Flask web app.
Model - Generating Images with DCGAN Architecture11:39
Build and train a dcgan to generate rgb images from a 100-d latent vector with a 16-sample batch and adam optimizer, covering data loading, generator and discriminator architectures, flask export.
Flask6:11
Learn to build a Flask web app with a static and templates structure, an index.html form, and a generate function that outputs images from a Keras model.
Download the project files0:21

Introduction2:40
Explore seizure detection with EEG signals through a classification project using SVM, data cleaning, feature exploration, and deploying the model as a Flask web app.
Data Processing3:29
Import NumPy, pandas, TensorFlow, Keras, matplotlib, and seaborn to read EEG data and visualize brainwaves; convert seizure labels to binary, split data into train and test, and apply scaling.
Model3:05
Learn how support vector machines find an optimal hyperplane that maximizes margin between two classes, using support vectors and scikit-learn's svc to build, evaluate, and deploy a classification model.
Flask app5:09
Create a Flask web app with a structured directory (static and templates), input a brain signal snippet, plot and display result using a saved model loaded in model.py via App.py.
Download the project files0:22

Introduction2:37
Explore music genre classification with mel spectrograms and CNNs, using a five-class dataset, and deploy the model as a Flask web app.
Data Processing2:30
Import modules, define dataset root, batch size, and image size for pre-processing. Read images from directory, split 80/20 for training and validation, and list blues, classical, hip hop, pop, rock.
Model7:23
Create a convolutional neural network with TensorFlow and Keras, including convolutional, pooling, ReLU, and dense layers. Train, evaluate, and save the model for multi-class image classification.
Flask App6:00
Build a Flask web app with a static and templates structure to upload images or spectrograms and display predictions via a Jinja expression.
Download the project files0:22

Introduction3:58
Predict diseases from symptoms using natural language processing, tokenize text, create vector embeddings with spaCy, train a support vector machine, and deploy a Flask web app.
Model5:03
Import pandas and numpy, preprocess text with spaCy, vectorize, and train a support vector classifier achieving 94-95% accuracy on an 80/20 split. Build a Flask pipeline for live classification.
Flask5:37
Create a Flask web app to deploy a trained disease prediction model, organizing static and templates folders, wiring app.py to a model.py predict function, and rendering results through index.html.
Download the project files0:23

Requirements

Basic knowledge of machine learning

Description

Unleash your data science mastery in this dynamic course! Learn to build and deploy machine learning, AI, NLP models, and more using Python and web frameworks like Flask and Django. Elevate your projects to the cloud with Heroku, AWS, Azure, GCP, IBM Watson, and Streamlit. Get ready to turn data into powerful solutions!

Enrolling in this course is a transformative decision for several compelling reasons. This dynamic program is meticulously designed to take you on a journey from theory to practical, hands-on mastery.

Firstly, you'll delve into the exciting world of real-world machine learning and data-driven projects, offering you invaluable skills to solve complex problems. Secondly, this course empowers you to unleash your data science prowess. You'll not only learn to build and deploy machine learning, AI, and NLP models but also gain proficiency in using Python and web frameworks like Flask and Django. Elevate your projects to the cloud with Heroku, AWS, Azure, GCP, IBM Watson, and Streamlit, making your creations accessible to the world.

Moreover, you'll navigate the entire project lifecycle, from ideation to deployment, gaining practical experience at every step. By working on real industry-inspired projects, you'll develop the confidence and skills needed to excel in the real world

In This Course, We Are Going To Work On 60 Real World Projects Listed Below:

Data Science Projects:

Project-1: Developing an AI Chatbot using GPT-3.5

Project-2: American Sign Language Detection with CNN

Project-3: Builtup Area Classification using K-Means and DNN

Project-4: Clustering COVID-19 Research Articles using Vector Embeddings

Project-5: Crop Recommendation and Yield Prediction Model

Project-6: Generating Images with DCGAN Architecture

Project-7: Seizure Prediction using EEG Signals and SVM

Project-8: Music Genre Classification using Spectrometers

Project-9: Disease Detection from Symptoms using Transformers and Tokenizer

Project-10: Text Summarization with Advanced Techniques

Project-11: SentimentSense: Deciphering Sentiments - Sentiment Analysis Django App on Heroku

Project-12: AttritionMaster: Navigating the Path of Employee Attrition - Django Application

Project-13: PokeSearch: Legendary Pokemon Quest - Django App Adventure on Heroku

Project-14: FaceFinder: Unmasking Hidden Faces - Face Detection with Streamlit Magic

Project-15: FelineCanine: Pawsitively Classy - Cats Vs Dogs Classification Flask App

Project-16: RevGenius: Predicting Revenue Gems - Customer Revenue Prediction on Heroku

Project-17: VoiceGender: Vocal Clues Unveiled - Gender Prediction from Voice on Heroku

Project-18: EatSuggest: A Culinary Companion - Restaurant Recommendation System

Project-19: JoyRank: Spreading Happiness - Happiness Ranking Django App on Heroku

Project-20: WildFireWarn: Taming the Inferno - Forest Fire Prediction Django App on Heroku

Project-21: SonicWaveWhisper: Echoes of Prediction - Sonic Wave Velocity Prediction using Signal Processing Techniques

Project-22: PressureQuest: Delving into Pore Pressure - Estimation of Pore Pressure using Machine Learning

Project-23: SoundSorcerer: Enchanting Audio Processing - Audio Processing using ML

Project-24: TextTalker: Unveiling Textual Secrets - Text Characterization using Speech Recognition

Project-25: AudioMaestro: Harmonizing Audio Classifications - Audio Classification using Neural Networks

Project-26: VoiceCompanion: Your AI Voice Assistant - Developing a Voice Assistant

Project-27: SegmentSense: Uncovering Customer Segments - Customer Segmentation

Project-28: FIFAPhenom: Scoring Goals with FIFA 2019 Analysis

Project-29: SentimentWeb: Surfing the Waves of Web Scraped Sentiments - Sentiment Analysis of Web Scraped Data

Project-30: VinoVirtuoso: Unveiling the Essence of Red Wine - Determining Red Vine Quality

Project-31: PersonaProbe: Decoding Customer Personalities - Customer Personality Analysis

Project-32: LiterateNation: A Journey into India's Literacy Landscape - Literacy Analysis in India

Project-33: CropGuide: Cultivating Crop Knowledge with PyQt5 and SQLite - Building Crop Guide Application

Project-34: PassKeeper: Safeguarding Secrets with PyQt5 and SQLite - Building Password Manager Application

Project-35: NewsNow: Unveiling the News with Python - Create A News Application

Project-36: GuideMe: Guiding You Along the Way - Create A Guide Application with Python

Project-37: ChefWeb: Savoring Culinary Delights - Building The Chef Web Application with Django, Python

Project-38: SyllogismSolver: Unlocking the Logic of Inference - Syllogism-Rules of Inference Solver Web Application

Project-39: VisionCraft: Crafting Visual Experiences - Building Vision Web Application with Django, Python

Project-40: BudgetPal: Navigating Financial Paths - Building Budget Planner Application with Python

Power BI Projects:

Project-41: Road Accident Analysis: Relations and Time Intelligence

Project-42: Generic Sales Analysis for Practice: Data Transformation

Project-43: Maven Toy Sales Analysis: Transformations and DAX

Project-44: Maven Pizza Sales Analysis: Transformations and DAX

Project-45: IT Spend Analysis: Variance of Global IT Firm

Project-46: Sales Data Analysis: Generic Super Market Sales

Project-47: Foods and Beverages Sales Analysis Dashboard

Project-48: Budget vs. Actual Spending Analysis Dashboard

Project-49: HR Analytics Dashboard: Attrition Analysis

Project-50: E-commerce Super Store Sales Analysis

Tableau Projects:

Project-51: Video Game Sales Dashboard: Gaming Market

Project-52: IMDB Movie Review Dataset Dashboard: Film Insights

Project-53: Goodreads Dataset Dashboard: Book Analysis

Project-54: Friends Sitcom Dashboard: TV Series Data Analysis

Project-55: Amazon Sales Dashboard: Online Retail Insights

Project-56: Hollywood's Most Profitable Stories Dashboard: Film Analysis

Project-57: Netflix Dashboard: Streaming Service Performance

Project-58: TripAdvisor Hotel Review Dataset: Travel Analysis

Project-59: Breaking Bad Dashboard: TV Series Insights

Project-60: Customer Personality Analysis: Marketing and Sales Strategies

Tips: Create A 60 Days Study Plan , Spend 1-2hrs Per Day, Build 60 Projects In 60 Days.

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

Note: 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 Bundle: 180 Hands-On Projects - Course 2 of 3

What you'll learn

Explore related topics

Course content

Introduction to the course3 lectures • 2min

Project-1: Developing an AI Chatbot using GPT-3.53 lectures • 14min

Project-2: American Sign Language Detection with CNN5 lectures • 18min

Project-3: Builtup Area Classification using K-Means and DNN5 lectures • 20min

Project-4: Clustering COVID-19 Research Articles using Vector Embeddings3 lectures • 13min

Project-5: Crop Recommendation and Yield Prediction Model4 lectures • 22min

Project-6: Generating Images with DCGAN Architecture4 lectures • 23min

Project-7: Seizure Prediction using EEG Signals and SVM5 lectures • 15min

Project-8: Music Genre Classification using Spectrometers5 lectures • 19min

Project-9: Disease Detection from Symptoms using Transformers and Tokenizer4 lectures • 15min

Requirements

Description

Who this course is for: