July 10, 2019

645 words 4 mins read

mjbahmani/10-steps-to-become-a-data-scientist

mjbahmani/10-steps-to-become-a-data-scientist

Ready to learn or review your knowledge! You will learn 10 skills as data scientist: Python, Machine Learning, Deep Learning, Data Cleaning, EDA, python packages such as Numpy, Pandas, Seaborn, Matplotlib, Plotly, Tensorfolw, Theano…., Linear Algebra, Big Data, Analysis Tools and solve some real problems such as predict house prices.

repo name mjbahmani/10-steps-to-become-a-data-scientist
repo link https://github.com/mjbahmani/10-steps-to-become-a-data-scientist
homepage
language Jupyter Notebook
size (curr.) 47104 kB
stars (curr.) 1124
created 2018-10-10
license Apache License 2.0

📢 10 Steps to Become a Data Scientist

CLEAR DATA. MADE MODEL.

last update: 19/07/2019

💻💾📓✒📊

  1. Python
  2. Python Packages
  3. Mathematics and Linear Algebra
  4. Programming & Analysis Tools
  5. Big Data
  6. Data visualization
  7. Data Cleaning
  8. How to solve Problem?
  9. Machine Learning
  10. Deep Learning

Introduction

If you Read and Follow Job Ads to hire a machine learning expert or a data scientist, you find that some skills you should have to get the job. In this Repository, I want to review 10 skills that are essentials to get the job.

In fact, this Repository is a reference for 10 other Notebooks, which you can learn with them, all of the skills that you need.

1-Python

Python is a modern, robust, high level programming language. It is very easy to pick up even if you are completely new to programming.

You can read and learn following topic on this Notebook:

  1. web development (server-side)

  2. software development

  3. mathematics

  4. system scripting.

  5. Basics

  6. Functions

  7. Types and Sequences

  8. More on Strings

  9. Reading and Writing CSV files

  10. Dates and Times

  11. Objects and map()

  12. Lambda and List Comprehensions

  13. OOP

for Reading this section please fork this kernel:

numpy-pandas-matplotlib-seaborn-scikit-learn

2-Python Packages

  • Numpy

  • Pandas

  • Matplotlib

  • Seaborn

In this Step, we have a comprehensive tutorials for Five packages in python after that you can start reading my other kernels about machine learning and deep learning.

2-1. Numpy

  1. Creating Arrays

  2. Combining Arrays

  3. Operations

  4. Math Functions

  5. Indexing / Slicing

  6. Copying Data

  7. Iterating Over Arrays

  8. The Series Data Structure

  9. Querying a Series

2-2. Pandas

  1. The DataFrame Data Structure

  2. Dataframe Indexing and Loading

  3. Missing values

  4. Merging Dataframes

  5. Making Code Pandorable

  6. Group by

  7. Scales

  8. Pivot Tables

  9. Date Functionality

  10. Distributions in Pandas

  11. Hypothesis Testing

  12. Matplotlib

  13. Scatterplots

  14. Line Plots

  15. Bar Charts

  16. Histograms

  17. Box Plots

  18. Heatmaps

  19. Animations

  20. Interactivity

  21. DataFrame.plot

2-3. seaborn

  1. Seaborn Vs Matplotlib

  2. Useful Python Data Visualization Libraries

2-4. SKlearn

  1. Introduction

  2. Algorithms

  3. Framework

  4. Applications

  5. Data

  6. Supervised Learning: Classification

  7. Separate training and testing sets

  8. linear, binary classifier

  9. Prediction

  10. Back to the original three-class problem

  11. Evaluating the classifier

  12. Using the four flower attributes

  13. Unsupervised Learning: Clustering

  14. Supervised Learning: Regression

for Reading this section please fork this kernel:

numpy-pandas-matplotlib-seaborn-scikit-learn

3- Mathematics and Linear Algebra

for Reading this section please fork this kernel:

Linear Algebra in 60 Minutes

4- Programming & Analysis Tools

for Reading this section please fork and upvote this kernel:

Programming & Analysis Tools

5- Big Data

for Reading this section please fork this kernel:

A-Comprehensive-Deep-Learning-Workflow-with-Python

6- Data Visualization

for Reading this section please fork this kernel:

  1. Data visualization

7- Data Cleaning

for Reading this section please fork this kernel:

Data Cleaning

8- How to solve Problem?

The purpose of this section is to solve a few real problem. so, we have tried to solve some problems such as Quora, Elo, House price prediction. for Reading this section please fork this kernel:

A-Comprehensive-Deep-Learning-Workflow-with-Python

9- Machine learning

for Reading this section please fork this kernel:

A Comprehensive ML Workflow with Python


Do You Need Help?

I hope, you have enjoyed reading my python notebooks.

If you have any problem and question to run notebooks please open an issue here in GitHub.

for most of the my notebooks you need dataset as input.

To use the correct data, please download the data set from the Kaggle site and put it in your notebook folder.

Mj Bhamnai

Citation

If you use my code in your research, please cite this project.

@misc{10-steps-to-become-a-data-scientist,
  author =       {MJ Bahmani,
  title =        {10-steps-to-become-a-data-scientist},
  howpublished = {\url{https://github.com/mjbahmani/10-steps-to-become-a-data-scientist/}},
  year =         {2018}
}

Have Fun!

comments powered by Disqus