Machine Learning Tutorial Python - 8: Logistic Regression (Binary Classification)

[@codebasics]

Check out our premium machine learning course with 2 Industry projects: codebasics.io/courses/machine-learning-for-data-science-beginners-to-advanced

[@interesting_vdos]

I have never seen any other video explaining the concepts of machine learning so clearly. Keep up the great work..!!

[@sidduhedaginal]

Finally i got perfect trainer for ML, your skills are excellence sir, we are very proud of you sir.

[@codebasics]

Glad you liked it :)

[@matinpathan5186]

Yes is good but if you like his tutorials then tell your friend to subscribe his channel and hit the like button... that we can do from our side

[@manusingh9007]

On first attempt, i considered 'left' as dependent variable and everything else including salary and department as independent variable, got 77% score of accuracy. Thanks for the wonderful video.

[@codebasics]

Great job manu. its a good score. Video description has a solution link, you can verify your code with mine.

[@riyamitra8901]

For the first time after so many courses, videos, whitepapers, github, kaggle, exercises, wiki pages I am genuinely enjoying Machine Learning and I am doing all the coding and exercises by myself obviously after learning and understanding it all. Thanks a lot!!!

[@codebasics]

Glad you like them Riya and I wish you all the best! I have many playlists and recently left my job to focus on online teaching. My goal is to produce even a better quality tutorials then this.

[@riyamitra8901]

@@codebasics I am trying to follow all of your videos to improve in my career. I am trying to get a job with a clear concept.

[@riyamitra8901]

@@codebasics One question here. Why we did not remove one of the dummy variable after dropping salary column in Logistic regression like we did for Linear?

[@09_samarpanbasu7]

@@riyamitra8901 I think ...as logistic regression can handle multicollinearity between the dummy variables so it's not necessary to drop the last col.

[@ansh6848]

Best course you can get for learning ML is this only. Explanation is super awesome. Actually most of the books and courses shows you complex looking mathematical equations but this guy made all that easy for us.

[@PollyMwangi-cp3jn]

Actually, I fine tuned my model and was able to achieve an accuracy of 1.0. Thankyou so much sir. This might just be the best channel I have seen.🥳

[@kibs_neville]

Hi, I have some slight problem. How can I plot the prediction curve after training my model? Would be glad if you reply. Thanks

[@anishagarwal71]

Could you pls tell me what exactly did you do to fine tune it?

[@bhawin101283]

Perfect explanation with proper examples. Great job.

[@anand.prasad502]

medium.com/trainyourbrain/would-you-read-this-article-or-not-b757d0e26cf8

[@zerostudy7508]

i'm Not afraid to learn things with complicated term anymore! this teacher is the best at explanation.

[@zerostudy7508]

@@codebasics You are good at it. I thank you.

[@MoreBalaji]

Perfectly balanced video. It forces anyone to continue to watch other videos of this series. Very well explained in simple language. 👌

[@Sarah-st7jp]

Sir, I know so surely that I can bank on your data science and python videos when I need to gain an in-depth understanding. Your content gives me the hope and clarity that I needed. God bless you and your undying passion to make such useful content for us. Thank you so much for all your hard-work sir!!! :)

[@codebasics]

Step by step roadmap to learn data science in 6 months: kzbin.info/www/bejne/fmW8lKSLgb5kY7M How to learn coding for beginners | Learn coding for free: kzbin.info/www/bejne/eaHXo5-veZV_gJo 5 FREE data science projects for your resume with code: kzbin.info/www/bejne/b2aal4R5opqUetE

[@hanselsamuel]

I really appreciate your tutorial videos, thank you. But how to find the "bought_insurance" values ?

[@piyushjha8888]

78 percent accuracy. I do all your exercises but in this I learned a lot. Thank you sir for such a great series @codebasics

[@kalaipradeep2753]

Hi bro....

[@kalaipradeep2753]

Now I learn machine learning.... Now What are you doing. I mean study or work

[@piyushjha8888]

I work in a bank as a software engineer. This channel is a gem as this explains the ML concept in laymen terms. I was able to give most of the answers related to ML because of codebasics and deep learning Andrew Ng course

[@icyjump1684]

I only could get 77 with logisitic, but then i used lazypredict to find a higher accuracy and then used desicion tree classifier to get a 98, ty!

[@ObianujuFlorenceOhawuchi]

You make people feel so welcomed to data field with your teaching skills. You are always the best.

[@sunnyveerpratapsingh1102]

bro you are best .. tried to swirl thru other online videos and then I end up watching your videos and I understand better .

[@codebasics]

Sunnny Singh, I am happy this was helpful to you

[@rutvikkumbhar6736]

Any update you can give how's your data science journey is going as I am aspiring to be a data scientist..

[@mageshs5726]

I got 78.833 accuracy value. In this exercise i had known lot of things thank you bro.

[@pranavnigam11]

I also got around ~78.5% using the average monthly hours and satisfaction level. Did you use the same features??

[@codebasics]

That’s the way to go Magesh, good job working on that exercise

[@nilupulperera]

Dear Sir What a beautiful datasheet you have provided for practice with this video. Spent more than two days to play with it. Playing with the datasheet opened another dimension of the learning curve. Thank you very much for providing relevant exercises like this as a challenge!

[@codebasics]

Happy that this is helping you Nilupul.

[@siddhantkaushik4606]

amazing. astounding. bewildering. breathtaking. extraordinary. impressive. marvelous. miraculous. even all these adjectives are less to tell the quality of the video. Thanks a million.

[@codebasics]

ha ha .. nice. you made my day with this shower of praise Siddhant. Thank you for your kind words :)

[@adityabikramarandhara9477]

Thanks a lot for the lucid explanation. In the exercise, I got an accuracy of 77.2% in my model prediction.

[@kalaipradeep2753]

Hi bro... Now I learn machine learning... What are you doing.... I mean study or work

[@nguyentuanhung3858]

Started learning machine learning on your youtube. Absolute Masterclass , you are my real teacher sir!!!

[@pamp3657]

One of the few videos that clearly shows the training data that the model is attempting to fit to. Thank you.

[@michaelpeel3716]

Many thanks this is the first explanation that provides context and examples making its so simple to understand.

[@codebasics]

Glad you liked it Michael

[@engihabit]

@@codebasics 15:35 I can’t execute it?? model.predict(57) and any number like 25, 60 got the following ValueError: Expected 2D array, got 1D array instead: array=[57].

[@shivangitomar5557]

You are the best teacher! I love the exercises at the end of each topic, which strengthens our understanding of what we learnt!!! Thank you so much! :)

[@codebasics]

I am glad it was helpful. :)

[@businnovate]

Why didn't you plot the sigmoid curve but only showed the scatter plot?

[@khalidhasan1793]

I paused the video and commented, it's an excellent series that begins with ML.

[@shreyasb.s3819]

I never seen anyone explaining simple as like this. Others making complicated like maths intuition. Thanks code basics

[@pratikghute2343]

I have no other words to say, the comments done by others have already conveyed my message to you!, Lots of love and thank you !

[@mario1ua]

Great explanation, I've understood everything, thanks!

[@codebasics]

Glad you found it helpful!

[@GeorgeTrialonis]

Thank you very much for the videos on ML, AI, Python, etc. They help me learn a lot. Your explanations are clear and well understood. Thanks.

[@codebasics]

George I am glad 😊

[@MohamedAshraf-zs6nv]

at 14:00 , why you used model.score(x_test, y_test), as you have to replace x_test with the prediction from the model to be like this: prediction = model.predict(x_test) model.score(prediction, y_test) then you can compare the prediction with the real value and so you can get the actual score

[@codebasics]

Score function will internally calculate y predicted from x test. After that it will compare y predicted with y test.

[@suleimanachimugu9048]

0.84 accuracy score and 0.83 mean cross validation score. Thanks, Your tutorials have been helpful.

[@antimuggle_ridhi2565]

how?

[@SandeepYadav-pm8yc]

Finally got the Python version of Andrew Ag's machine learning course. With a better explanation. thanks.

[@codebasics]

😊👍

[@zestful14]

This video is fantastic. I'm teaching myself machine learning and this was one of the most helpful resources I've found online. Excited to watch/work-through the rest of the videos! Thank you so much

[@anand.prasad502]

medium.com/trainyourbrain/would-you-read-this-article-or-not-b757d0e26cf8

[@codebasics]

Solution link for the exercise: github.com/codebasics/py/blob/master/ML/7_logistic_reg/Exercise/7_logistic_regression_exercise.ipynb Step by step guide on how to learn data science for free: kzbin.info/www/bejne/jJ_CnqCFqraeiaM Machine learning tutorials with exercises: kzbin.info/www/bejne/nZ7Zp5Sll9Jqm7M

[@shreyaasthana7313]

Sir I tried this method, it is very easy to understand and use.. thank you sir

[@guneyfatma]

Thnaks a lot for theese amazing contents. I have just discovered your videos!

[@abhishekdobliyal7178]

Thank You Sir, I have learned a lot from your vids :). I was really perplexed by Logistic Regression and I am glad KZbin recommended this to me :)

[@tariqahassan5692]

it is one of the fantastic videos about Logistic Regression .. Many thanks

[@Malayalam_learner]

Daily 2 videos of your ml playlist completes my day❤

[@mehmetkaya4330]

Thank you again! Great explanation! Always great tutorials!

[@shuaibalghazali3405]

Thanks a lot for this i was able to implement logistic regression after so many tutorials

[@vinitasharma5025]

very useful video.... you explain everything in a very simple manner. Thank you

[@codebasics]

Glad it was helpful!

[@flyingsalmon]

I love your tutorials. They're perfectly paced, with right amount of context and explanation, great examples, and patient but efficient delivery. I hope you continue to produce more. Subscribed here and also Liked all of the videos I've found so far from you. Best.

[@codebasics]

👍🤗

[@leooel4650]

Awesome as always, thanks for everything! i got a 77% model accuracy based on the satisfaction_level

[@jsbean8415]

How did you get the prediction model accuracy by depedent variable? And 77% meaning is the probability that they will leave the company?

[@nxbil2397]

@@jsbean8415 model.score()

[@jsbean8415]

@@nxbil2397 that will show you the overal accuracy of your model. My question is , how you will get the probablity % that the employee will leave given the dependent variables? Like the one you have mentioned "satisfaction level".

[@asamadawais]

Dhavel you are excellent in explaining difficult concepts in very simple language!

[@codebasics]

I am happy this was helpful to you.

[@sundayagu2078]

God bless you and may He provide angles to solve all your problems. Thank you

[@userhandle-u7b]

Thank you so much, sir. I've got the score in the exercise 0.797. 🙂

[@fahadreda3060]

Another Great Tutorial, Thank you sir, Waiting for the next tutorial, keep up the good work

[@boughrood]

Very interesting and useful - well presented too

[@mapa5000]

Thank you very much ! Your videos are always my best choice to learn ML

[@flyingsalmon]

I have an interesting problem for you that I think you'll really enjoy sharing in a video. We would like to know your approach to solving the following problem: We have a soccer (euro football) game where there are penalty picks. We have data on who's the shooter/kicker and who's the goalie, and how many historically have been saved or not saved by the goalie as follows: (Assume the Shooter and Goalie letters are names of players and Saved is 0 (goal not saved, saved) Shooter Goalie Saved A Z 1 B Z 0 A Z 0 B Y 0 A Y 1 .... and so on for various rows Challenge: What we want to know is if shooter B is facing goalie Z, will the goal be saved or not? We want to leverage machine language (not just probability calculation, which can be done manually based on data). How should we solve this? Many thanks in advance! If you make a video on such, I'll even donate :) Promise!

[@0xN1nja]

one of the best explanation I've ever seen

[@devanshgoel9070]

Thank you sir for this amazing explanation of Logistic Regression.

[@codebasics]

Glad you liked it

[@mponcardas94]

I love your series of videos as you are concerned with the student's learning! Thanks!

[@harshvardhanpardeshi3584]

for anyone facing problem in using the df.groupby().mean() function, just drop the non numeric columns. It'll work :)

[@JunaidAnsari-my2cx]

Tysm It worked

[@jugabrat6797]

Your way of teaching is very good. Thanks for the video ❤❤❤

[@pablu_7]

Reasons behind the employee retentions are: 1.Satisfaction Level 2.Average Monthly Hours 3.Promotion Last 5 Years

[@nxbil2397]

Noted that

[@MrPrudhvisai]

why not work accident?

[@arshdeepsingh8289]

@@MrPrudhvisai work accident should be there

[@VyNguyen-xy3il]

Sir, I extremely appreciate your videos and efforts in teaching these things. Very helpful and great explanation!!

[@codinghighlightswithsadra7343]

Thanks a bunch, Subscribed here and also Liked all of the videos I've found so far from you. Best.

[@bestineouya5716]

Actually you are the best explainer

[@RiefvanAchmadMasrury]

Really nice and clear explanation, will be very useful for my students

[@codebasics]

Sure riefvan, feel free to use this content in your classroom. May I know which country, university and school are you from?

[@RiefvanAchmadMasrury]

@@codebasics It's in Indonesia, Telkom University :)

[@anuk9846]

thank u for the video as i m a teacher it helped me a lot

[@codebasics]

👍🙏🙏

[@noorameera26]

This video is really really good. Love the way you teach, your pacing and all the things you mentioned are really useful. Thank u and may god bless u!

[@codebasics]

Glad it was helpful!

[@study_with_thor]

Perfect explanation!

[@codebasics]

Glad it was helpful!

[@namitakala393]

thankyou for making videos, your content is great

[@1bitmultiverse]

I got 80% accuracy in my model of HR analytics! I used satisfaction_level,number_project,average_montly_hours,promotion_last_5years,salary as my independent variables

[@codebasics]

Good job Banzer, that’s a pretty good score. good job working on that exercise

[@1bitmultiverse]

@@codebasics Thank you soo much I am working on it and following all of your playlists ♥😍 Thanks for this playlist ♥

[@mridulahmed7186]

wow so nice. Thanx to explain in a very nice way.

[@codebasics]

Mridul I am happy it helped you 😊

[@mridulahmed7186]

@@codebasics make this kind of tutorial more and more. Your teaching methods are very nice. All the good wishes for you.☺️☺️

[@codebasics]

Sure mridul, I am trying my best and I am actively working on adding many more tutorials 👍

[@prakritreeeeeee]

Thank you so much for the graphical explanation...the concepts are crystal clear in my mind now.

[@phaniauce]

Awesome explanation. I like this practical math and algorithmic explanation.

[@bhavyanaik74]

Thank you so much....very good explanation

[@codebasics]

Glad it was helpful!

[@abdulmuzakir]

Thanks, sir .. your explanation is really clear and so easy to understand 👍🏼

[@SohelRana-eq4ib]

You are the best teacher

[@MultiSpiros123]

Thanks one of the best tutorials !

[@codebasics]

Glad you liked it

[@PolkadOfficial]

Very well explained, thanks!

[@codebasics]

Glad you enjoyed it.

[@sameer-verma]

tried on three different set of features and the accuracy scores are: 0.799 (keeping all the features), 0.763 (keeping five features selected by chi square) and 0.785 (keeping variables based on correlation test/filter). below is my entire script: import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.linear_model import LogisticRegression from sklearn.feature_selection import SelectKBest from sklearn.feature_selection import chi2 from matplotlib import pyplot as plt import seaborn as sns %matplotlib inline pd.set_option('display.max_columns',15) hrd = pd.read_csv("D:/SelfLearning/python/data/HR_comma_sep.csv") hrd.head() hrd.describe() hrd.pivot_table(values='salary',index=['satisfaction_level'],columns=['left'],aggfunc="count") hrd.pivot_table(index='time_spend_company',columns='left',values='salary',aggfunc="count") hrd.groupby('number_project').count()[['left']] hrd.groupby('time_spend_company').count()[['left']] hrd.groupby('salary').count()[['left']] hrd.groupby('Department').count()[['left']] sts_conditions = [(hrd['satisfaction_level']0.2) & (hrd['satisfaction_level']0.4) & (hrd['satisfaction_level']0.6) & (hrd['satisfaction_level']0.8)] sts_values = [0.2,0.4,0.6,0.8,1] last_evl_conditions = [(hrd['last_evaluation']0.2) & (hrd['last_evaluation']0.4) & (hrd['last_evaluation']0.6) & (hrd['last_evaluation']0.8)] last_evl_values = [0.2,0.4,0.6,0.8,1] hrs_condition = [(hrd['average_montly_hours']100) & (hrd['average_montly_hours']200) & (hrd['average_montly_hours']300)] hrs_values = [100,200,300,400] tm_spent_conditions = [(hrd['time_spend_company']2) & (hrd['time_spend_company']4) & (hrd['time_spend_company']6) & (hrd['time_spend_company']8)] tm_spent_values = [2,4,6,8,10] no_prjct_conditions = [(hrd['number_project']2) & (hrd['number_project']4) & (hrd['number_project']6) & (hrd['number_project']8)] no_prjct_values = [2,4,6,8,10] hrd['satisfaction_lvl'] = np.select(sts_conditions,sts_values,default=0) hrd['last_eval']=np.select(last_evl_conditions,last_evl_values,default=0) hrd['avg_monthly_hrs'] = np.select(hrs_condition,hrs_values,default=0) hrd['tm_spent_company'] = np.select(tm_spent_conditions,tm_spent_values,default=0) hrd['no_projects_done'] = np.select(no_prjct_conditions,no_prjct_values,default=0) hrd['departments_group'] = ["sales" if i == "sales" else "technical" if i=="technical" else "others" for i in hrd.Department] hrd.pivot_table(index='last_eval',columns='left',values='salary',aggfunc="count") hrd.pivot_table(index='avg_monthly_hrs',columns='left',values='salary',aggfunc="count") hrd.pivot_table(index='tm_spent_company',columns='left',values='salary',aggfunc="count") hrd.groupby('departments_group').count()[['left']] sal_dummies = pd.get_dummies(hrd['salary'],prefix='sal') dept_grps = pd.get_dummies(hrd['departments_group'],prefix='dpt') sal_dummies.head() dept_grps.head() hrd_new = pd.concat([hrd,sal_dummies,dept_grps],axis=1) hrd_new.shape hrd_new.info() hr_data = hrd_new.drop(['satisfaction_level','last_evaluation','number_project', 'average_montly_hours','time_spend_company','Department', 'departments_group','salary','sal_high','dpt_others'] ,axis='columns') #hrd2=hrd[['satisfaction_bins','left']] #hrd2.head() #hrd2.plot(kind='bar', stacked=True) #plt.show() #sns.pairplot(hrd) hr_data.info() hr_data.shape hr_data.pivot_table() sns.pairplot(hr_data) hr_data[['satisfaction_lvl','left']].plot(kind='bar',stacked=True) eda=sns.barplot(x="promotion_last_5years",y="satisfaction_lvl",hue='left',data=hr_data).title('testing') plt.show() x = hr_data.drop(['left'],axis=1) y = hr_data.left y.head() x_new = SelectKBest(chi2, k=5).fit_transform(x,y) x_new hr_data.var() plt.figure(figsize=(10,10)) sns.heatmap(hr_data.corr(),annot=True,fmt='.1g',vmin=-1, vmax=1, center=0,cmap='coolwarm' ,square=True) plt.show() cor = abs(hr_data.corr()) cor plt.figure(figsize=(10,10)) sns.heatmap(cor,annot=True,fmt='.1g',vmax=1,vmin=-1,center=0) a=cor['left'] features=a[a>0.5] features x = hr_data.drop(['left'],axis=1) y = hr_data.left x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=10) model=LogisticRegression() model.fit(x_train,y_train) model.score(x_test,y_test) #features selection based on chi square x_new = SelectKBest(chi2, k=5).fit_transform(x,y) y = hr_data.left x_train,x_test,y_train,y_test = train_test_split(x_new,y,test_size=0.2,random_state=10) model=LogisticRegression() model.fit(x_train,y_train) model.score(x_test,y_test) #features select based on correalation x = hr_data[['Work_accident','satisfaction_lvl','tm_spent_company' ,'last_eval','avg_monthly_hrs','sal_low','sal_medium' ,'dpt_sales','dpt_technical']] y = hr_data.left x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.2,random_state=10) model=LogisticRegression() model.fit(x_train,y_train) model.score(x_test,y_test)

[@gusinthecloud]

The best explanation as always

[@codebasics]

Glad you liked it

[@shylashreedev2685]

Thank u so much..it really helped to clear my concepts

[@ravisrivastava2909]

Hello Sir! Great work by you. there is a problem in your code may be due to version of python .... If we use X_train, X_test, y_train, y_test = train_test_split(df[['age']],df[['bought_insurance']],train_size=0.9) then only we get score of 1 otherwise with your code it is 0.66.

[@Myanmartaeyang]

OMG. I was trying to run the code and did not know why mine was 66%. Thank you for this !!!

[@paramjeetgill1558]

Very nice and you present easiest way to understand. Thank you

[@micro_Dots]

clearly understandable explanation. Thank you so much.

[@shreyjoshi18]

How to plot the sigmoid function over the scatter plot in the graph in a single visualisation ?

[@mrstudent1957]

delightfuldata.blogspot.com/2020/10/sigmoid-function-simplified.html

[@sukumarroychowdhury4122]

import numpy as np import pandas as pd import math import matplotlib.pyplot as plt %matplotlib inline x = np.arange(-10,11,1) df1 = pd.DataFrame(data = x, columns=["X"]) list = [] def sigmoid(x): sigmoid = 1/(1+ pow(math.e,-x)) return sigmoid for i in x: list.append(sigmoid(i)) df2 = pd.DataFrame(list, columns=["Y"]) df = pd.concat([df1, df2], axis = 1) X = df.X Sigmoid_X = df.Y plt.figure(figsize=(10,10)) plt.xlabel("X") plt.ylabel("Sigmoid_X") plt.title("Sigmoid_X versus X") plt.scatter(X,Sigmoid_X) plt.plot(X,Sigmoid_X) plt.show()

[@laxpanwar11]

Thanks. It is really informative.

[@guneyfatma]

Why do we write x and y arguments in split method? Is it because of syntax?

[@ChiTamNguyen-d9d]

At 8:00, when converting the linear regression line to the logistic regression line, I think the point where y = m*x + b = 0 (left corner) is also the point where the y = 1 / 1 + e^-(m*x + b) = 0.5 (inflection point). Why are the two graphs are different? Or am I missing something?

[@dongliu7739]

Great! by the time of 5:17, I understand sth I did not figure out by hours

[@khalidfahim100]

I was doing the exercise and noticed something in the solution you provided. I think you need to drop one of the salary columns to avoid dummy variable trap. This was not done in the solution python notebook provided. Btw, excellent tutorial!!!

[@aashishshrestha8180]

Very Clear Explanation

[@codebasics]

Glad it was helpful!

[@pagnonig]

Your videos are awesome. I'm learning so much!

[@PlayingCode]

Hey plz tell me what to do when I have multiple Columns like age ,weight , bmi that i need to consider for prediction

[@danielnderitu5886]

I like your tutorials very much, the explanation therein is superb and makes one understand even very hard to grasp concepts.

[@Sparshchokra]

Hi, i found your course is truly enhancing the path towards Machine Learning concepts, kindly continue this and sir achieve a complete set of this machine learning course including all the kick start algorithms. Thanks Sparsh

[@codebasics]

Thanks for appreciation Sparsh. I am continuing the series, it is just that due to my schedule I am not finding lot of time to work on it but I will try my best to speed up new tutorial additions.

[@Hari983]

Very well done and explained even for beginners - thank you so much!

[@REPATHATHYALA]

Hi, thank you for the video, how do we plot the output into a graph as you have shown in the initial part of the video... can you please help

[@lakshmanans3760]

I am also having the same doubt. I am getting a very wierd graph with multiple lines if i try. can you please help @codebasics

[@REPATHATHYALA]

@@lakshmanans3760 Hi Lakshmanan, I am learning, sorry, at this stage I may not help you, but I will keep this problem in my mind... thank you.

[@ayushpant6190]

I have a question, how is the slope value updated for logistic regression when finding the best fit plane or line to seperate the 2 classes? At first I thought gradient descent but that doesn't work because it is used to find the global minima

[@ojassaxena2891]

Maaeri aapahi hans di Maaeri aapahi rondi Maaeri yaad yaad wo aaeri

[@shashikantpandit663]

awesome explanation....really

[@codebasics]

😊👍

[@anselmtuachi3298]

class example: 2+2 = 4 homework: if 3+3 = 6, calculate the mass of the sun😂😂 i'm really grateful for this tutorial though its been really great till this point

[@Christian-mn8dh]

just subscribed, your very good at explaining. thank you!

[@codebasics]

I am glad you liked it Pablo

[@vikramjitsingh6769]

The instructor is doing fabulous work in teaching these concepts. But aspiring Data Scientists don't just learn how to use libraries, and know whats the maths behind ... u should know what derivative is, gradient is, what log functions sigmoid etc as in later stages you would need these. Avoiding maths can not make u good with this.

[@codebasics]

Vikram, in this playlist I have a math video related to gradient descent. Also I have a separate playlist called "math and statistics for data science" where I covered few of those topics.

[@bandhammanikanta1664]

Perfect explanation on logistic regression. Loved it. Thanks a lot.

[@anand.prasad502]

medium.com/trainyourbrain/would-you-read-this-article-or-not-b757d0e26cf8