Genre: eLearning | MP4 | Video: h264, 1280x720 | Audio: aac, 48000 Hz
Language: English | VTT | Size: 3.64 GB | Duration: 8 section | 67 lectures | (4h 5m)
What you'll learn
Learn how to setup and use the Twitter API
Foundation of Machine Learning
Practical examples with Machine Learning: Linear Regression, K-Means, Sentiment Model
Deep dive study and usage of Sentiment Model on Twitter data: Compare the mood of Java vs Python
Visualize data on interactive map
Extract location data from tweets
Automate to lookup latitude and longitude of 40.000+ tweets (nice optimization to speed this step up)
Transform raw data to fit Machine Learning model (including cleaning, lemmatize, remove stop words)
Basic Python skills
Interest in Machine Learning
Interest to learn to use online API's (like Twitter and Geo-lookup)
How to start with Machine Learning?
Machine Learning seems to be a very complex subject - and yes, it is, but...
That does not mean you cannot make awesome projects using Machine Learning.
...but you need to understand the steps and basics behind it.
Theory with limited practice is not efficient learning.
Practice without theory gives questionable results.
Optimize your learning by the right balance of understanding and interesting projects.
Why Twitter API?
Twitter is the most amazing place to gather fresh data and make awesome analysis.
The data on Twitter is free and open to all and is a goldmine of opportunities.
Therefore developers and data scientist love Twitter.
In this course we are going to analyze over 40.000 tweets using Machine Learning to categorize them.
Also, you want to master how to program up against an online API.
But why Python?
Python is easy to master
It is easy to solve complex problems in an elegant manner
Used by data scientists and has various awesome libraries including to Machine Learning, Twitter API
...and it is a used by many professionals in most professions
The best way to learn is by getting involved.
Lectures are structured that we go through the setup and coding together in incremental steps.
Then you should do the coding to see if you fully master it.
If not, you can go through it again or ask for help in the QA or directly to me
Important steps in Data Science/Machine Learning.
Get a source of interesting data - here we use Twitter API
Create useful Machine Learning models - like the Sentiment model that can say whether a text/tweet is positive or negative - very useful for determine how people think of your brand.
Apply the model on lots of data - here se use it on 40.000+ unique tweets to test our model.
Visualize the data to present it in an easy digestible way - we will present it on interactive leaflet map in for your browser.
Result of this course?
After this course you will have the following.
How to use the Twitter API.
Create Machine Learning models - the full process in easy steps.
Using a Sentiment model to determine the mood of tweets - whether it is positive or negative.
Extracting locations from tweets and get GEO locations using an online API.
Visualize the data on an interactive map.
How will you benefit from this course?
Master how to get access to the Twitter API.
Creating Twitter bots.
Understand the Machine Learning types.
Creating Machine Learning models.
Train and test models.
Transform raw data into data a Machine Learning model can use.
Visualize data on an interactive leaflet map.
Lookup geo-locations using an online API - and optimize this process (as it is slow due to 40.000+ online lookups).
...and an awesome project on your portfolio.
What will we cover?
Setup your professional integrated development environment (IDE)
Setting up your Twitter Developer account.
Register to get your Twitter API key to get access to the Twitter API.
Creating your first Twitter Bot.
Machine Learn basics.
Play with data in simple examples with Machine Learning.
Create your first Linear Regression model
Make a K-Means model.
Understand Sentiment analysis.
The process of creating the Sentiment model
Gather the data
Clean the data: remove links etc, lemmatize, remove stop words
Transform the data to fit model
Create training and test sets
Train the model
Test the model
Save the model for later use
Use the model on big set of data 40.000+ unique tweets
Understand how the Sentiment model works.
Learn how CSV files can be used to store processed data
Visualize the data by reading the processed CSV data
Creating a map with color representation of countries by mood.
Descriptionting locations of all the tweets.
You code along - you only learn by trying yourself
At each small step you make the implementation along with me.
You implement it on all stages to increase your understanding of the data structures.
Basically, we learn along the way.
Who is this course for?
You have some Python experience.
Want to get started with Machine Learning.
Would love to try using online API's like Twitters.
Like to learn by doing projects.
The course has a 30 day money back guarantee that ensures if you are not satisfied, you will get your money back. Also, feel free to contact me directly if you have any questions.
Who this course is for:
Want to learn Machine Learning with practical examples
Learn basic Twitter API
Want to understand one of the cornerstones of Machine Learning - Sentiment Analysis
Master how to visualize data on interactive map
(If you need these, buy and download immediately before they are delete)
Nitroflare.com (Fast Speed):