Real Data Science Problems With Python

Posted By: ELK1nG

Real Data Science Problems With Python
Last updated 1/2018
MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.22 GB | Duration: 7h 43m

Practice machine learning and data science with real problems

What you'll learn
Work with many ML techniques in real problems such as classification, image processing, regression
Build neural networks for classification and regression
Apply machine learning and data science to Audio Processing, Image detection, real time video, sentiment analysis and many more things
Requirements
Some experience with Python
General knowledge on Machine Learning, Statistics
Description
This course explores a variety of machine learning and data science techniques using real life datasets/images/audio collected from several sources. These realistic situations are much better than dummy examples, because they force the student to better think the problem, pre-process the data in a better way, and evaluate the performance of the prediction in different ways.
The datasets used here are from different sources such as Kaggle, US Data.gov, CrowdFlower, etc. And each lecture shows how to preprocess the data, model it using an appropriate technique, and compute how well each technique is working on that specific problem. Certain lectures contain also multiple techniques, and we discuss which technique is outperforming the other. Naturally, all the code is shared here, and you can contact me if you have any questions. Every lecture can also be downloaded, so you can enjoy them while travelling.
The student should already be familiar with Python and some data science techniques. In each lecture, we do discuss some technical details on each method, but we do not invest much time in explaining the underlying mathematical principles behind each method
Some of the techniques presented here are: 
Pure image processing using OpencCVConvolutional neural networks using Keras-TheanoLogistic and naive bayes classifiersAdaboost, Support Vector Machines for regression and classification, Random ForestsReal time video processing, Multilayer Perceptrons, Deep Neural Networks,etc.Linear regressionPenalized estimatorsClusteringPrincipal components
The modules/libraries used here are:
Scikit-learnKeras-theanoPandasOpenCV
Some of the real examples used here:
Predicting the GDP based on socio-economic variablesDetecting human parts and gestures in imagesTracking objects in real time videoMachine learning on speech recognitionDetecting spam in SMS messagesSentiment analysis using Twitter dataCounting objects in pictures and retrieving their positionForecasting London property pricesPredicting whether people earn more than a 50K threshold based on US Census dataPredicting the nuclear output of US based reactorsPredicting the house prices for some US countiesAnd much more…
The motivation for this course is that many students willing to learn data science/machine learning are usually suck with dummy datasets that are not challenging enough. This course aims to ease that transition between knowing machine learning, and doing real machine learning on real situations.

Overview

Section 1: Introduction

Lecture 1 Introduction

Section 2: Wines

Lecture 2 Predicting Wine characteristics - Using GridsearchCV

Section 3: Doing Machine learning with Audio - Classifying sounds

Lecture 3 Reading WAV files and extracting features

Lecture 4 Classifying words using Adaboost and SVM

Lecture 5 Classifying words using Multilayer Perceptron Deep Neural networks

Section 4: Nuclear reactors in the US

Lecture 6 Predicting nuclear output in the US via MLP and SVR

Lecture 7 Multi-output neural networks

Section 5: Clustering

Lecture 8 K-Means and PCA on a real dataset containing data for 168 countries

Section 6: Used car prices for German Ebay

Lecture 9 Incremental training in Keras

Section 7: Identifying poisonous mushrooms

Lecture 10 Poisonous mushrooms detection using Kaggle Data

Lecture 11 Classifying mushrooms using a super GPU on AWS

Section 8: Plotting

Lecture 12 Heatmaps: plotting traffic camera revenues in Chicago and Homicides in the US

Section 9: Useful image classes

Lecture 13 A class that maps Black&White images to Python objects

Lecture 14 A class that maps RGB Images to Python objects

Section 10: Image classification

Lecture 15 Detecting hands in pictures via Convolutional Neural Networks

Lecture 16 Identifying bolts and nuts in images

Lecture 17 Identifying bolts and nuts by calculating polygons

Section 11: Working with Video

Lecture 18 Processing video in real time using OpenCV

Lecture 19 Machine learning on real time video

Lecture 20 Following a marker on the screen

Section 12: Sentiment analysis and social media

Lecture 21 Sentiment analysis

Lecture 22 Sentiment analysis on self driving cars

Section 13: Forecasting

Lecture 23 Intro to time series

Lecture 24 Forecasting the US GDP:Part1

Lecture 25 Forecasting the US GDP: Part2

Lecture 26 Forecasting London property prices

Section 14: House Prices in the US

Lecture 27 Predicting real house prices using ExtraTrees

Lecture 28 Estimating contributions in US house prices via regression

Section 15: SPAM

Lecture 29 Detecting spam in real SMS data

Section 16: Economics

Lecture 30 Predicting whether income exceeds 50K using logistic regression

Lecture 31 Predicting the GDP based on socio-economic variables

Intermediate Python users with some knowledge on data science,Students wanting to practice with real datasets,Students who know some machine learning, but want to evaluate scikit-learn and Keras(Theano/Tensorflow) to real problems they will encounter in the analytics industry