I am newbie in Data Science, Machine Learning and any related to data science but I want to try it. Unfortunately, googling makes it tedious and complicated so I hope to be answered by anybody who's kindhearted to share and enlighten me with it. Thank you so much.
closed as primarily opinion-based by Siong Thye Goh, Ethan, Stephen Rauch♦ Jun 11 at 17:36
Many good questions generate some degree of opinion based on expert experience, but answers to this question will tend to be almost entirely based on opinions, rather than facts, references, or specific expertise. If this question can be reworded to fit the rules in the help center, please edit the question.
ML is a subset of artificial intelligence (AI) that creates systems to learn and predict outcomes without manually programming a computer and is also known as predictive analytics or statistical learning. It is a set of algorithms and techniques focused to learn from data. This algorithms can be implemented by:
- The scikit-learn (additional packages of SciPy) exposes a concise and consistent interface to the common machine learning algorithms.
- In case of Deep Learning, one of the most prominent and convenient libraries for Python in this field is Keras, which can function either on top of TensorFlow or Theano
- MATLAB especially using Deep Learning Toolbox
- JAVA or C++
The Data could be an organized collection of measures and/or classes; and learning means the ability to get information from data that would generalize to other sets of data. This last is what differences ML techniques from other statistical tools. They focus on the generalization aspect of the data analysis and not only in creating a model that works with the data at hand. A ML model is general, it is valid for new data points the model has never been exposed to.
Beside of that , there are another libraries and packages which pave the way to load, access, modify data, even plot them!
Data Science is a very broad expression, meaning: let's use a combination of statistics, math and computer science to make sense of data and produce predictive models that can generalize on data they have never seen. (Please refer to mainstream sources for a more thorough definintion).
Machine Learning is an approach to data analysis. It is based on splitting your data into (at least) train and test sets, training predictive models on the train set, and assessing their generalization capacity on the test set.
When it comes to choose the right language for DS / ML, please keep in mind that:
- R is the best language for econometrics and statistics
- Python is the best language for Deep Learning
- They are pretty much equivalent for non-deep ML
You can do anything you want with both of them, though. Choose based on your preferences and/or needs.