This course consists of data wrangling, visualization, and decision and model evaluations.
As DataScience is one of the hottest jobs now adays. This course will cover many important tools that helps data scientists such as numpy, scipy and pandas. Before going through machine learning and deep learning, it is very important to gain the ability to work on data and makes it siutable and impact it as possible much as you can. Since data, most of the time is not in a good shape and impact so it is a crucial step.
I create the course in 5 seperate modules which are in order and complete each other.
In this module we read the csv file from a particular path and adding header to columns of the data set.
This module consists of cleaning data, identifying missing values and working on them. Binning and make data into one hot format. Getting the type of each column and change them if it is neccessary.
In this module i focuse on Exploratory,correlations and covariance. Visualization of correlations in suitable and tangible plots using different python libraries. This module actually help you to find the relations between columns.
- F_score.
- P_values.
- In this module i introduce linear regression models.
- Simple Linear Regression.
- Multiple Linear Regression.
- And which one is better according to situation.
In this section Model Evaluation and Refinement covered. I introduce important loss functions to evaluate our models.
- I wont go very deep because this course is INTRODUCTION !!!!
- I will cover complex models further.