PRACTICAL 4

Practical 4

AIM : 

Visual programming with Orange tool.

THEORY:

What is Visual Programming ?

Visual programming is a form of programming language that uses illustration to allow humans to represent processes. A visual programming language helps the programmer to explain the process in terms that make sense to humans, while a traditional text-based programming language lets the programmer think like a machine.

Now we will train and test our model using visual programming with orange tool.

Let's start digging!!

1. Load the dataset by adding file widget.

2. Now we will add data sampler widget and we will split the data into two parts, 85% of data for training and 15% for testing. We will send the first 85% onwards to build a model.

3. Add kNN Model widget to train the model.

4. Add a test and score widget.

Now exploring the results:

Accuracy of at 85% sampling.

Now changing the value of Number of folds in cross validation:

Number folds = 10

Number folds = 5

Number folds = 20

Question and Answers:

1. Does this visual programing is enough for data analytics?

No, Visual programming may provide easy to implement environment, but it doesn't give developer the full control over the program.

2. How to get much more deeper insights of data?

There can be 3 simple steps to get much more deeper insights of data:

• Use As Much Data As You Can
• Automate Your Discovery of Insights
• Leverage Machine Learning for the Masses

References:

    https://orange.biolab.si/blog/2017/11/29/how-to-properly-test-models/