The following repository contains source code for various machine learning and deep learning projects or frameworks I tried my hands on.
Day 1 : Contains code for Wine Quality Dataset
Day 2 : FashionMNIST dataset using DNN
Day 3 : Object Detection using OpenCV
Day 4 : LinearClassifier Model for Titanic Dataset using TF
Day 5 : NER on Annotated NER dataset from Kaggle using LSTM.
Day 6 : Neural Network Visualiser Web App
Day 7 : Fashion MNIST using Convolution Neural Networks
Day 8 : Sentiment Analysis with Deep Learning using BERT
Day 9 : Hyper Parameter Tuning using Optuna, Titanic Dataset using RandomForestClassifier and Pima Indian Diabetes Classification
Day 10 : Face recognition of Mark Zuckerberg, Bill Gates and Mukesh Ambani using face_recogniton and openCV
Day 11 : Charity Donation Prediction and Sentiment Analysis using VADER
Day 12 : Document Retrieval System using Naive TF-IDF
Day 13 : Pika Pika : Pokemon Classification using VGG16
Day 14 : Pima Indian Diabetes Classification using Deep Learning
Day 15 : Movie Box-Office Collection prediction using DecisionTreeRegressor and Movie Start-Tech Oscar prediction using DecisionTreeClassifier
Day 16 : Movie Start-Tech Oscar prediction using Bagging, RandomForestClassifier,GradientBoostingClassifier,AdaBoost and XGBoost and GridSearchCV
Day 17 : Basic (Beginner Model) Image to Sketch Converter using cv2, imageio and plain python.
Day 18 : Titanic Survival (Cleaned Dataset) Prediction using Decision Trees
Day 19 : Web Scraping using BeautifulSoup - Created a dataset of Premiere League Scores from 2000-2019.
Day 20 : Created a dataset of GOT episodes using BeautifulSoup
Day 21 : Fake news classifier using transformers (MHW20) using 2 different methods.
Day 22 : Hyperparameter Optimization Templates for Tree Classifier on Mobile Price Classification dataset namely GridSearchCV,RandomSearchCV,gp_minimize,hyperopt and optuna
Day 23 : Detecting whether a mail is spam or ham using Bert and Pytorch
Day 24 : Regular Expressions Basics
Pending : Bag of Words meet Bag of Popcorns