6. Project - 4 (Case Study - 4) Part 1 | Data Analysis With Python Pandas | Kaggle Dataset

[@abhishekanand5898]

Sirji please add questions here also in description... I'm solving one dataset a day and it is helping me a lot bcoz just theory padhne se smjh ni aata... you're doing best job...

[@DataThinkers]

Thanks for your comment. just added. Keep Watching.Thanks

[@magicmedia7950]

Best you tube pandas explaination

[@shakilahammed1887]

I Love this Playlist.

[@RakeshKumar-hv5hn]

Thanks for To the point explanation

[@DataThinkers]

Thanks for all your comments. Glad you liked these videos. Keep watching

[@satyamjha9783]

Thank You very much Sir for these wonderful sessions. Grateful. I have one question, kindly answer if possible- Let’s say there is a variable Marks which is supposed to have numerical values but has some char values also (error). How can I convert this into numerical and replace all char values with 0 or remove the char value rows entirely. Regards

[@KakashiHatake-tm4pq]

Thank you so muchh💫

[@DataThinkers]

Thanks for your comment. Glad you like this video. Keep watching. Thanks

[@kartikeyasingh1694]

sir please upload such videos of sql as well please.your method is realy great

[@DataThinkers]

Thanks for your comment. Will upload soon

[@learnwithyeme]

please how did you display the docstring

[@akshrags-mindmaze3407]

Pls provide correct link of dataset that you are using

[@unploughed]

hello, first of all thank you to these videos. i just go stuck, can you explain the logic of / len(data) please. what does mean divided by len(data) ?

[@DataThinkers]

First of all thanks for your comment. len(data) is used to find number of data sample available in the dataframe (as simple as find the number of rows available in the dataframe) that i have used to find percentage of missing values. per_missing = data.isnull().sum() * 100 / len(data) per_missing here len(data) gives 891 (total number of rows available in the dataframe) Thanks

[@unploughed]

@@DataThinkers hmm, but how these formul gives us percentage? isn't it should be divided by 100? why divided by len(data)? and also does len fonc calcuate vacancy or just data?

[@DataThinkers]

Percentage, % = (Value × 100) / Total Value . As we know this is the normal calculation for percentage. In our case value means missing value * 100 / len(data) . len(data) means total value.

[@diyajaber2936]

Good day , thanks for your effort , I have problem on downloading the csv file , May you assist

[@DataThinkers]

Hello, you can download this dataset from my GitHub account. github.com/PRIYANG-BHATT/Datasets-KZbin-Pandas/tree/main/DS

[@bharatapar3937]

The created column "Gender" is chnaged to Float . I am getting 1.0 instead of 1 . any suggestion ?

[@devilsworld7299]

Use astype(int)

[@ridoychandraray2413]

Bro is there any project using sikit learn?

[@DataThinkers]

First of all thanks for your comment. I have created an entire playlist for that. Link :kzbin.info/www/bejne/rIWWg6Fqfblkg8k

[@ridoychandraray2413]

Bro, per_missing=data.isnull().sum()*100/len(data) What is mean that?

[@hamzamohammad7138]

missing vals ka percentage find krna hai