DHRUV BHATIA's repositories
Iris-Flower-Classification---ANN
Classify the Iris Flower is Setosa or Not using ANN - single perceptron
End-to-End-lifecycle-Text-Analysis
Data story of the online/social media response of a movie (text data)
Python-Request-Hands-On
Pagination Method of Data Scraping
Maven-Fuzzy-Factory---Case-Study
As e-Commerce Database Analyst for Maven Fuzzy Factory, to optimize marketing channels and test website conversion performance
Jupyter-Notebook-Basic-Intro
Introduction to Jupyter Notebook and its Components: Hands on Experience
Linear-Regression---CloudyML-Assignment
Linear Regression is a statistical technique which is used to find the linear relationship between dependent and one or more independent variables. This technique is applicable for Supervised learning Regression problems where we try to predict a continuous variable.
Maven-Movies---MySQL
Maven Analytics Assignment Case Study Competition:
Face-Mask-Detection---CNN
The Dataset contains images of people wearing masks and people not wearing masks. The database contains 10000 colored images in the training folder, 800 images in the validation folder, and 992 images in the test folder. To create a CNN model for identifying whether a person in the image is wearing a mask or not.
Classify-Coloured-Images-of-Cats-and-Dogs---Image-Recognition---CNN
To build a model to classify 1000 images of cats and dogs. Dataset containing 4000 pictures of cats and dogs (2000 cats, 2000 dogs). We will use 2000 pictures for training, 1000 for validation, and finally 1000 for testing
Handwritten-Digit-Classification---CNN-
The MNIST data is a database of handwritten digits from 0 to 9. The database contains 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images. Your task is to create a CNN model for identifying the digit from the handwritten images.
California-Housing-Prediction---ANN
Building Neural Network on regression problem of predicting house price based on 8 predictor variables. Using both Sequential API and Functional API to check the performance of the model plus also using Callback checkpoint and early stopping checkpoint to save the best model to be used anytime.
Movie-Collection-Prediction---ANN
Dataset contains data of movies, where our task is to predict the collection (revenue) the movie is going to make using variables such as expense, rating genre, etc.
Fashion-MNIST---ANN
working on the MNIST database. The MNIST data is a database of handwritten digits from 0 to 9. The database contains 60,000 28x28 grayscale images of the 10 digits, along with a test set of 10,000 images. Your task is to create an ANN model for identifying the digit from the handwritten images.
Technocolabs-Internship-Majpr-Project-Bitcoin-API-Price-Prediction-Based-on-Twitter-Sentiments
Project shows that real-time Twitter data can be used to predict market movement of Bitcoin Price. The goal of this project is to prove whether Twitter data relating to cryptocurrencies can be utilized to develop advantageous crypto coin trading strategies. By way of supervised machine learning techniques, have outlined several machine learning pipelines with the objective of identifying cryptocurrency market movement. The prominent alternative currency ex- amined in this paper is Bitcoin (BTC). Our approach to cleaning data and applying supervised learning algorithms such as logistic regression, Decision Tree Classifier, and LDA leads to a final prediction accuracy exceeding 70%. In order to achieve this result, rigorous error analysis is employed in order to ensure that accurate inputs are utilized at each step of the model.
The-Spark-Foundation-Internship
The Spark Foundation Data Science and Analytics internship tasks repository.
Technocolab---Internship---Mini-Project---Predict-Blood-Donation
Predict Blood Donation for Future Expectancy
Technocolabs-Internship
Data Science intern role for one month at Technocolabs
KPMG-Virtual-Internship
KPMG’s Analytics, Information & Modelling group helps organizations take the mystery out of big data and show them how to leverage their data resources to produce better business outcomes. Our approach is based on the proposition that business success depends on what you actually do with your business information, not how much of it you control and collate. With our information-driven approach, we can give your organisation a holistic view of your data, enabling you to learn from and use it to make better business decisions, grow revenue, enhance operational capabilities, and manage enterprise risks and compliance mandates.