EDA using Bivariate and Multivariate Analysis | Day 21 | 100 Days of Machine Learning

[@rose9024]

Best video seen on EDA till date...Great Work!

[@SKILLCRYSTAL]

Date : 27 July Status : Done ✅ Summary: Learn about bivariant and multivariate analysis , bivariant analysis means analysis two columns together , and multivariate means analysing two or more columns together. 1. Numerical Numerical ☘️ Scatterplot ☘️ Pair plot ☘️ Line plot 2. Numerical - Categorical ☘️Boxplot ☘️ Barplot ☘️ Distplot 3 Categorical Categorical ☘️Heatplot ☘️Clustermap

[@sid_x_18]

ab kya kar rahe ho ?

[@monikrayu2546]

@@sid_x_18 +1

[@fit_tubes_365]

Course Started : ML Lecture-01: 14/08/2024 Lecture-02: 14/08/2024 Lecture-03: 14/08/2024 Lecture-04: 14/08/2024 Lecture-05: 14/08/2024 Lecture-06: 15/08/2024 Lecture-07: 15/08/2024 Lecture-08: 15/08/2024 Lecture-09: 15/08/2024 Lecture-10: 15/08/2024 Lecture-11: 16/08/2024 Lecture-12: 16/08/2024 Lecture-13: 17/08/2024 Lecture-14: 17/08/2024 Lecture-15: 18/08/2024 Lecture-16: 19/08/2024 Lecture-17: 20/08/2024 Lecture-18: 20/08/2024 Lecture-19: 21/08/2024 Lecture-20: 21/08/2024 Lecture-21: 22/08/2024

[@tanmaygupta8288]

writing code in notebook alongside with you is a great way to learn things, thanks!

[@SunilVishwakarma-r1m]

slight modification in code at 33:17 is new = flights.groupby('year').sum('passengers').reset_index() and sns.lineplot(x=new['year'],y=new['passengers'])

[@VaishnaviShrivastava-z2b]

hey, 26:10 (titanic.groupby('Embarked').mean()['Survived']*100) TypeError: agg function failed [how->mean,dtype->object] please help

[@lethalgaming7087]

@@VaishnaviShrivastava-z2b (titanic.groupby('Embarked')['Survived'].mean()*100)

[@harshadpawar4234]

thank you

[@a1x45h]

Thoroughly enjoying this series. Thank you so much Nitish!

[@Engineer884]

5:00, scatterplot might have updated, correct way: sns.scatterplot(x=tips['total_bill'],y=tips['tip']) 6:26, sns.scatterplot(x=tips['total_bill'],y=tips['tip'],hue=tips['sex']) 10:30 sns.barplot(x=titanic['Pclass'],y=titanic['Age']) 16:10 sns.displot(x =titanic['Age'],kde=True,stat='density',linewidth=0) 18:45 sns.histplot(titanic[titanic['Survived']==0]['Age'],kde=True, stat="density", linewidth=0,fill=False) sns.histplot(titanic[titanic['Survived']==1]['Age'],kde=True, stat="density", linewidth=0,fill=False)

[@CatalystOfMisfortune]

groupby is not working for my case

[@Bhartiya766]

thank you bhai

[@SYETB076YashJadhav]

thanks bro

[@preetiyadav9891]

thankyou buddy

[@KRISHNAGupta-u1m]

@@CatalystOfMisfortune i am facing the same problem

[@ujefmalek77]

Yout videos are amazing 🔥🔥, You are most underrated KZbinr😶

[@introgaming7540]

BEST VIDEO IN ENTIRE UNIVERSE FOR EDA

[@Raj-v8j5u]

I really enjoy the way you go deep in analysis

[@zkhan2023]

Every time amazing information comes.Thanks, sir

[@harshkondkar3193]

Hello sir, amazing content. I had one request. Could you make a video on how to perform hypothesis testing in python while doing bivariate analysis? Would be really helpful to a lot of people. Thanks.

[@PM-ps5po]

Best Channel on the Earth to Learn Data Science from Scratch🔥🔥🔥🔥

[@priyanshugupta9192]

20:00 distplot() is depreciated by seaborn . For kdeplot, which gives probability density, it is giving slightly different graph, which is calculated in above video

[@VaishnaviShrivastava-z2b]

hey, 26:10 (titanic.groupby('Embarked').mean()['Survived']*100) TypeError: agg function failed [how->mean,dtype->object] please help

[@narvarstrange1920]

@@VaishnaviShrivastava-z2b simply add numeric_only=True inside mean bracket, like mean(numeric_only=True).

[@not_amanullah]

didn't find better playlist than this TYSM❤️

[@SamritiKhuranaCSE146]

Sir aap jo jo bhi dataset use krte ho please uski Excel file ka link description me de diya kro ese sahi se practice nhi ho pati and really your videos are so awesome😄

[@manishpingale6558]

EDA is really an art!

[@vKNemesis]

brother the way u explained i m loving it :)🙂

[@AmirJaved565]

CampusX unmatched...Love from Pakistan

[@alphaghost4330]

Internet chalta tumare, mehnga hoyga kafi?

[@Garrick645]

19:18 why aren't the probabilities of dying and surviving not adding up to 1 ? My mind can't understand this fallacy. Koi samjaho please 😢😢

[@sawankumar7628]

coz that probability of survial in class 1,2,3 . they have no relation. so if survival probability is 0.6 in pclass1 then p(died) = 0.4

[@darshanayenkar]

Best Video ever seen for ML

[@Raj-v8j5u]

I think finding great insights will take u long long way

[@beit2608]

great exxplanation very in sensitive

[@manujkumarjoshi9342]

Beautiful way of doing EDA

[@rajathpoojari7873]

Awesome content and explanation. Thank you!

[@arun5351]

Very informative lecture and great analysis

[@jahidmdhasan1021]

At 16:25 which extension you have used to check for hue feature in distplot

[@Engineer884]

shift+tab

[@ajaysinghrawat7157]

thank you sir ❤❤❤

[@GamerBoy-ii4jc]

Sir is your playlist of 100 days of Machine learning enough to Applying for internship in company? Or i need to do projects more upon these topics and practicals?Please suggest me. Thanks!

[@messiisthebest]

did you get the internship , i think you need to do more projects

[@SunilVishwakarma-r1m]

slight modification in code at 24:51 is---- (titanic.groupby('Pclass').mean('Survived')['Survived']*100).plot(kind='bar')

[@SunilVishwakarma-r1m]

(titanic.groupby('Sex').mean('Survived')['Survived']*100)

[@SunilVishwakarma-r1m]

(titanic.groupby('Embarked').mean('Survived')['Survived']*100)

[@shashankarora2945]

Thanks a lot man

[@allishere-study5206]

Salute hai sir aapko kya padhate aap

[@RahulSingh-t1k1r]

you are best sir

[@mdyounusahamed6668]

Awesome. Gave me a lot of insights.

[@saurabhbarasiya4721]

your videos are very helpfull

[@sameer9045]

Great explanation. I applied pair plot on a 17 column long dataset . And it showed me more than 100 plots. I don't know how to pick which one and understand.😵😵

[@NamrataGuru]

tx a lot ...made easy to my learning ...

[@yogendrajoshi7976]

you are the best sir.

[@shaktis6877]

26:14 not sherlock holmes its being ACP Pradyuman from CID

[@riyazsk7656]

how to know which pair/tuples should be selected for the analysis

[@itatul]

Amazing explanation .. thanks

[@mujeebrahman5282]

In scatter plot, where did you get df from? it should have been tips in hue, style and size.

[@Findritwik]

Right

[@lakshityagi684]

Pretty nice content. Thankyou!

[@vishnujatav6329]

Thank you very much sir. you are great

[@10arsh51]

25:17 The Boyz 😂

[@minalgupta7456]

I am a big fan of you

[@arshad1781]

Thanks

[@lavupadhyay]

awesome , 0 to HERO

[@SACHINKUMAR-px8kq]

Thankyou so much Sir

[@nrted3877]

Thankyou Sir

[@highflyer30]

load dataset not working tried everything updating python,notebook what to do

[@karanparashar6824]

Didn't know that it is possible to load data using the seaborn library.

[@001_chandrikasarkar7]

lol same

[@indra-zd9zu]

😂😂😂​@@001_chandrikasarkar7

[@indra-zd9zu]

You cant load all dataset.you can load only inbuit dataset

[@goyanii]

free me premium quailty lactures thank you sir

[@rivupangas2735]

At 17:46 we can use this code: sns.kdeplot(x='Age' ,data=titanic, hue='Survived')

[@JACKSPARROW-ch7jl]

thanxx nitish

[@heetbhatt4511]

thank you

[@amanshrivastava3613]

Sir, Can you please provide us these jupy notebooks.

[@akashmanojchoudhary3290]

how to plot too many categorical values in seaborn, for eg- I've 150 diseases in diagnosis column. How to plot it?

[@akashmanojchoudhary3290]

can anyone help me with this?

[@ajaykushwaha-je6mw]

@@akashmanojchoudhary3290 df[diagnosis].value_counts.plot(kind='"bar") or sns.countplot(df['diagnosis'],hue=df['label_column']) or sns.countplot(df['diagnosis'])

[@yogeshhajare8234]

thanks alot brother

[@Gurpreetkaur-oj7kb]

amazing video...

[@Zovi-kanu]

plz tell how to download csv file that use in this vedio

[@minalgupta7456]

I like ur videos

[@ClubLalpur]

barplot() takes from 0 to 1 positional arguments but 2 were given sir ye error a rha hai

[@ajaykuchhadiya5812]

this is bcz the seaborn libraby is updated now , you can check the seaborn documentation and understand that plotting function

[@Engineer884]

sns.barplot(x=titanic['Pclass'],y=titanic['Age'])

[@tusarmundhra5560]

awesome

[@ajaykushwaha-je6mw]

I have one doubt, Survive have two value 0 and 1. titanic.groupby['Pclass'].mean() how to know whether this give information survived passenger or dead passenger.

[@mukeshnayak7984]

same doubt

[@mukeshnayak7984]

have u found the ans ?

[@nikhiliyer8436]

Survived

[@aarindey]

0->Dead 1->Survived So, the mean will give Survived

[@ruhisharma2857]

titanic.groupby['Pclass'].mean()['Survived']

[@AbdurRahman-lv9ec]

great

[@acharjyaarijit]

bande uhape ultakgaye sare... nice sir..😀😀

[@123arskas]

8:11 You're using sex, smoker and size of someother dataset. It should be of tips but you've written df.

[@GamesKaMantralaya]

6:58 bro is speaking facts 🤣🤣🤣🤣

[@prithvigupta8215]

28:41

[@faizahmed007]

6:59 Now one thing I analyze girl are stingy because scatterplot proved...😅😂

[@Star-xk5jp]

Day2- date:10/1/24

[@sharangkulkarni1759]

guru

[@adnan8bb805]

25:17, "clearly dikh raha hai ki female ko bachaya gaya, aur bande ludhak gae saare "🤣🤣🤣🤣🤣🤣🤣

[@shahrukh3531]

Hindi sunkr, better feel hota h 😅

[@MRAgundli]

done

[@krishnakanthmacherla4431]

Done

[@anantsrivastava5567]

date 11 jan 2024 day 21

[@tempmail6469]

Bande bahot ludak gye was personal hahahaahaha

[@calvinfernandez1956]

Hey guys, an update on Seaborn. There is now a 'Future Warning' when ever you run the function 'distplot' saying that it will be discontinued in the future. So I did a little research and found a suitable replacement to it on stack overflow sns.histplot(x =titanic[titanic['Survived']==0]['Age'],kde=True,stat='density',bins = 50). You wont be able to turn off hist tho.

[@keshavkarki4635]

same I also come across this

[@mukteshsingh8370]

Day-22 Done

[@highflyer30]

not able to load dataset pls help tips=sns.load_dataset("tips") not working

[@prathamsaboo]

Have you got the solution?

[@Engineer884]

I was also facing issue with loading flights and iris, try loading it multiple times , you'll get it

[@prathamsaboo]

@@Engineer884 I have the solution, I was just asking if he needs it now.

[@AneeqMir]

slight modification in code 7:45 sns.scatterplot(x=tips['total_bill'], y=tips['tip'],hue=tips['sex'],style=tips['smoker'],size=tips['size']) plt.show()

[@adityakulkarni371]

sns.scatterplot(tips['total_bill'],tips['tip'],hue=df['sex'],style=df['smoker'],size=df['size']) sir shouldn't the smokers/size wala dataset be tips. you have written df. im confused here

[@vengeance9898]

I don't know but may be he used seaborn instead of pandas to load the data

[@Engineer884]

tips hi likhna chahiye tha

[@YashGaneriwal-je6rh]

done