Machine-Learning-with-Python -

This repository will contain both code and additional links to code / reading material refrences for Machine-Learning-with-Python - Machine-Learning-with-Python

Table of Contents

PyTorch

• 1 PyTorch-SimpleNet

• 1.1-PyTorch-Layers-Conv2d-Architecture

• 1.2-PyTorch-transforms.Compose

• 1.3-PyTorch-freezingLayers-torch.no_grad()

• 1.4-PyTorch-Initial-ObjectDetection-YouTube

• 1.4a-PyTorch-Initial-ObjectDetection-Git

• 1.5-PyTorch--SimpleNet-Airplane-Classifier

• [2] Diffusers - Text to Image

• 2.1-Create-own-pipeline

• [3] detectron2 from Facebook AI Research- for Object Detection

• 3.1-detectron2-FAIR-Panoptic-Segmentation

• 3.2-detectron2-faster_rcnn_R_50_FPN_3x

• 3.3-detectron2 from FAIR

• 3.4-kaggle_sartorius-cell-instance-segmentation-GIT-Repo 3.2-kaggle_sartorius-YOuTube-Explainer

• 4-OpenPCDet_Initial_Demo_MAYAVI_KITTI_LIDAR

• 4.1-OpenPCDet_Git-Experiments_KITTI_LIDAR

Active Learning

• [1] Active Learning - mostly Lightly
• testing Lightly
• 1.1-Lightly Active Learning -YouTube
• 1.2-Lightly Active Learning-SimSiam -YouTube
• 1.3-Lightly Active Learning- -YouTube
• 1.4-FeatureExtraction-Resnet50

Object Detection -- Yolov4

• [1] Yolov4
• 1.1-Initial-Experiments-Yolov4
• 1.2-Initial-Experiments-Yolov4

LLM Usage -- LangChain

• [1] Using Large Language Models - LangChain
• [TODO]
• [TODO]
• [TODO]

Classic Legacy NLP -- NLTK

• [FaceBook-WebHooks-ChatBot]
• [TODO]
• [TODO]

GEO-GIS-DeepLearning-for-Geography

• [1] raster-vision
• raster-vision
• 1.1-raster-vision
• 1.2-QGIS-SpaceNet
• 1.2a-QGIS-SpaceNet
• 1.3-QGIS-LAStools_LIDAR_1
• 1.3-QGIS-LAStools_LIDAR

OpenCV - OpenCV Projects

• [1] OpenCV Projects
• 1.1-Credit Card Digit Detection
• 1.1a-Credit Card Digit Detection
• 1.2-OpenCV_mask_blue - cv2.bitwise_and)
• 1.3-OpenCV_SIFT_ORB_KeyPoints_Detection)

Generic Core Python

• [1] Python-3 basics , data transforms etc.

• PySpark

• pandas

• [2] Download and Preprocess various kinds of Data

• data_aggregations

• [3] Visualizations of Data for EDA and others

• 3.1-EDA-Exploratory-Data-Analysis

• 3.2-Bokeh-plots-for-Tukeys-Five-Point-Summary

• 3.3-Bokeh-Box-plots-for-Tukeys-Five-Point-Summary

• [3.4-statsmodels] -- TODO

• [3.5-matplotlib-TimeSeries-Plots] -- TODO

• 3.6-Levenshtein-distance

• DataTables-DigitalCognition

• Code-walkthrough-datatables.net-datatables.js

Not Core Machine Learning [Full Stack Machine Learning]

• [1] Software Development - Data Focused App Development

• 1.1-ChatGPT-FlaskApp

• 1.1a-ChatGPT-FlaskApp-VariationAPI

• 1.2-Django-jQuery-Bokeh-Exploratory-Data-Analysis

• 1.2-uWSGI

• Django-wsgi - https://github.com/RohitDhankar/digitalCognition/blob/master/dc_dash_proj/wsgi.py

• 1.3-NGINX

• 1.3-Nginx_uWsgi_Django_Registration_Redux

• [] -- TODO

• [2] Tornado - async framework

• [2.1-Tornado] (https://github.com/RohitDhankar/Machine-Learning-with-Python_ML_Py/tree/master/dev_tornado)

Module -1 :-

Whats ML ? Why Python ? some bits of theory before the Code :)

Quick intro to - Numpy , Pandas , MatplotLib , Bokeh , Seaborn and SciKitLearn.

1. Introduction to Regression - Theory and Excel workbook examples

   Regression in Python - the very basics .

   Case Study -1 - Linear Regression within Python

   Choosing "the Best" Regression Model.

2. Classification Tasks - the k-Nearest Neighbour

   Related case study and examples .

Questions and Answers.

Module -2 :-

1. Decision Trees from Scratch - Source - Book - Programming Collective Intelligence.

Related case study and examples .

Questions and Answers.

Module -3 :-

1. Logistic Regression with Python. - from sklearn.linear_model import LogisticRegression

2. Gradient Boosting Classifier - Using sample code from Own - Titanic Dataset - Kaggle attempt.

3. Random Forest Classifer - Using sample code from Own - Titanic Dataset - Kaggle attempt.

Related case study and examples .

1. Using the Titanic - Kaggle Data Set -will build this Classification problem with using sample code from Own Kaggle attempt.

Questions and Answers.

Module -4 :-

1. k-Means clustering with Python.

Related case study and examples .

Questions and Answers.

Module -5 :-

1. Visualizing data with Python.

   Intermediate - MatPlotLib ,Bokeh Seaborn and JavaScript Lib - D3.js.

   Related case study and examples .

Hands on Exercises - Questions and Answers.

Module -6 :-

1. Intro to NLP [ Natural Language Processing ] - NLTK

   Web Scraping - Beautiful Soup - BS4 , stack

   Related case study and examples :-

   1. The internal workings of a Basic Chat Bot - ELISA Code and functionality.
   2. Creating your own Facebook Messenger (WebHook) ChatBot and hosting the same on Heroku - https://github.com/RohitDhankar/Heroku_Django_ChatBot_FacebookMessenger

Hands on Exercises - Questions and Answers.

Recap of earlier Modules and Important External Links :-

ANACONDA - Silent Install

ANACONDA - Official Page

ScikitLearn - Installation - After installing ANACONDA - pip install -U scikit-learn

Scikitlearn - Official Tutorials :-

Scikitlearn -Regression

Scikitlearn -Classification

Scikitlearn -Clustering

Scikitlearn -Model Selection etc

Numpy - Basics Official Tutorial

Installing -for LINUX and Mac - Numpy + Scipy Stack

Installing -for Windows - Numpy + Scipy Stack

Pandas - Basics Official Tutorial

MatPlotLib - PyPlot

Seaborn - Seaborn is a Python visualization library based on matplotlib

Installing Seaborn - Getting Started Official Guide