Fixing Incorrect Column Types in Pandas to Prepare Data for ML

Hello friends,

This is my course Hands-on Data Science which was released back in 2020 to help aspiring data scientists learn how the end-to-end process of a data science project works. It has been a paid course since it was published but now I believe it is time for it to be publicly accessible.

Here are the links you need for the course.👇

If you have any questions, feel free to leave comments. I will try to answer them as much as I can, but look through the comments and help others as much as you can! Let's make this a safe learning environment.

Sometimes, due to problems with data collection or during data importing the types if our Pandas DataFrame column can be read incorrectly. In this video, let's see how to correct this issue by updating all columns to the correct type.

👋 Keep in touch?
==========================

Courses & resources
============================
📙 Fundamentals of Deep Learning in 25 pages

📥 Streamlit template

🤖 Deep Learning 101 with Python and Keras (FREE)

🏃‍♀️ Data Science Kick-starter mini-course (FREE)

🐼 Pandas cheat sheet (FREE)

📝 NNs hyperparameters cheat sheet (FREE)

[MuhammadFaizanMumtaz]

"Great course I've ever followed. Thanks, Misra Sister."

[ajithdevadiga]

suppose if i Have missing values for 2 features when performing data cleaning,
and missing values count is around 100 thousand,
do I need to handle / impute missing data here or after splitting the data set into train and test sets ?, as it can avoid data leakages,
what approach would you follow ?

if anyone working on this, kindly share your thoughts
thanks 🙂

[darrenlefcoe]

all copies of a pandas dataframe are deep unless the keyword argument, deep=False. The it will be shallow.