Skip to content

ledian-selimaj/data_processing_python

Repository files navigation

Data processing with python: pandas, numpy, sklearn

This material was prepared by the author in conjuction with the "Python - Data Processing" at Tirana Center of Technology in 2022: https://tct.edu.al/python-programming/

Day 1: Introduction Installing Anaconda Running jupyter notebooks Basic operations in python

Day 2: Basic operations in python cont’ Python data types Python loops and conditional statements

Day 3: Introduction to pandas Loading csv, xlsx, txt file Basic operation in pandas

Day 4: Pandas cont’ (row & column operations, filtering, group by) Inplace Apply

Day 5: Pandas cont’ (working with dates) Combining pandas dataframes Storing a pandas dataframe

Day 6: Homework 3 walk-through Pandas cont’ (profiling, pivoting)

Day 7: Hands-on in-class exercises

Day 8: Homework 4 walk-through Additional pandas tricks & best practises Cumulative values Rolling average Creating categorical values using cut Scaling numerical columns One-hot-coding Fillna Map

Day 9: Cont’ on pandas additional functions of interest select_dtypes Duplicates Append Sample np.where() Reading and parsing json Intro to Numpy

Day 10: Class-work hands-on exercise

Day 11: Iterating through df rows and columns Chaining and pipe function

Day 12: Numpy Cont’ vstack and hstack Random number generation Intro to visualization using seaborn

Day 13: Intro to machine learning, lecture Intro to google colab
Intro to linear regression

Day 14: Intro to machine learning, lecture con’t Connect SQL Database through python and return query results Visualization using matplotlib Intro to polynomial regression

Day 15: Intro to regular expressions Reading & writing from multiple files pandas Introduction to NLP Intro to github

Day 16: Intro to clustering Intro to classification Visualization using plotly

About

A introduction to data processing with python (pandas, numpy, sklearn)

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published