description
scikit-learn is one of the most popular and user-friendly machine learning libraries for Python

Supervised Learning with scikit-learn

Supervised Learning vs Unsupervised Learning

Supervised learning uses labeled data and when there are no labeled data, we call it unsupervised learning.

Supervised learning

In supervised learning we have Predictor variables / features and a target variable.

Goal:

• Make future predictions (Predict the target variable, given the predictor variables., say will a customer click on an add or not?)
• Automate time-consuming task (doctor's diagnosis)

Task type	Target variable
Classification	is categorical (spam or legit)
Regression	is continuous (like price of houses)

Supervised learning Requirements

For supervised learning you need labeled data

• Historical data with labels
• Experiments to get labeled data (see how many click a page gets)

There are many ways to do supervised learning in python. One of the powerful libraries is scikit learn or sklearn.

Other libraries are: TensorFlow and Keras

Unsupervised learning

Uncovering hidden patterns from unlabeled data.

• Grouping customers into distinct categories (clustering) based on their purchasing behavior without knowing in advance what these categories maybe. This is known as clustering (just of the branches of unsupervised learning)

Reinforcement learning

This is where machines interact with an environment. These reinforcement learning agents can optimize their behavior based on a given system of rewards and punishments. Similar to what google GO project was able to achieve playing GO.

• Grouping customers into distinct categories (clustering) based on their purchasing behavior without knowing in advance what these categories maybe. This is known as clustering (just of the branches of unsupervised learning)