Відео

Hello, I write your code And nothing happend, thank you for the video anyway

This should be titled Pandas ASMR

Every thing is amazing ! , More than very helpful. thank you

where vids mazafaka

this really helps me, thank you so much!

This video Really help me a lot for outliers. thankful to you and very clean and decent explanation, please do more videos on machine learning. Thanks a lot

You have really good channel. Im glad to watch new videos. You can raise the activity on the channel with G E T 4 V I E W S - no cheating, verified ads

Dear Eigen B, Instead of removing the outliers kindly help to code- how to replace them with mean value of respective column.

Define outliers error is coming

Great video! Thanks for making this

Great video! Keep up the good work.

Thanks a lot!

thank great video i have question if i have about 446 feature how can i deal with it like in your example i tried to store the features in a variable X then use your code but it did not work any help please

Wow. Watched entire video. So peaceful. good job!!!!

Instead of removing, how can we impute median values ?

Nice work. Liked the simplicity and the soothing voice + music.

excellent explanation and pace! so calm, will never forget these part #removing outliers

Thanks, can I get the test.csv file?

This is amazing thanks for sharing and such a lovely explanation

❤❤❤❤

I used the same technique for my dataset but outliers are still persistent any suggestions what to do? I tried rerunning the loop it removed some outliers but that reduced the original dataset i was working on. Anyone has any better suggestions?

Thanks for the help

Genia me ayudaste mucho

great coding but operation should be column wise not row wise, you are removing a possible valid adjacent value by using the index, imagine a large dataset with 500 columns...

Hi Eigen, I need help. I this is my code: def iqr_outlier(df,features): q1 = df[features].quantile(0.25) q3 = df[features].quantile(0.75) iqr = q3-q1 lower_fence = q1-(1.5*iqr) upper_fence = q1+(1.5*iqr) ls = df.index[(df['insulin'] < lower_fence) | (df['insulin'] > upper_fence)] return ls list1 = [] feature = ['insulin','bmi'] for i in feature: list1.extend(iqr_outlier(df,feature)) but i am getting error: ValueError Traceback (most recent call last) <ipython-input-178-5d03f5f1ff7a> in <module>() 2 feature = ['insulin','bmi'] 3 for i in feature: ----> 4 list1.extend(iqr_outlier(df,feature)) 3 frames /usr/local/lib/python3.7/dist-packages/pandas/core/series.py in _cmp_method(self, other, op) 5494 5495 if isinstance(other, Series) and not self._indexed_same(other): -> 5496 raise ValueError("Can only compare identically-labeled Series objects") 5497 5498 lvalues = self._values ValueError: Can only compare identically-labeled Series objects

Excelente video, estuve buscando bastante y tu lo explicaste super bien todo

I am really grateful for this video. I am doing research with my professor. And this is really an essential skill for me to conduct research with him. Thank you so much! I do appreciate your wisdom!

बहुत अच्छा सिखाया बहिनी

No entiendo ingles, pero entendi el video :D

Thanks!

How we can determine the value of the quantile?

Thank you! Your video was really helpful for me :)

Great tutorial

Error: TypeError: Cannot perform 'ror_' with a dtyped [float64] array and scalar of type [bool]

what is ft? here?

Thank you!!!! you are amazing

what will be the output of In[8].. can anyone explain?

great video! One question though: what if you only wanted to drop the outlier values and not the whole row in which the outlier is found?

I was doing something similar, with no results... Guess what: I used & instead of | when finding the lower and upper bounds. Thanks a lot for making this video!

This video is excellent, I tried the method on another data set , it worked a treat.

index_list = [] for feature in ['feature1', 'feature2']: index_list.extend(outliers(data, feature)) index_list = [] ----- > For this i am getting an error : Boolean array expected for the condition, not float64 , How can i fix it ?

Sweet voice....Nicely explained.... Thanks

Awesome....Thanks I love the method of teaching and background music

what if data has no outlier. In that case we will loose tiny data? how to know if not outlier removal is needed in big dataset?

Is there any way to replace those outliers rows with upper_bound or lower_bound please help

I loved to watch this video! it goes to the main point, your explanation was very clear and you've taken ur time to avoid letting any detail out. At the beginning I was considering if I should see ur video cause it lasted 13 minutes and I don't like to see videos longer than 5 minutes xd but I'll leave happy cause I've understood this topic and now I'll be able to apply this in futures data cleaning.

Your voice, the music and the explanation: everything is amazing! Thanks a lot ♥

i tried these codes and it doesn't work. it shows(an only compare identically-labeled Series objects)

Could you share your code? Thanks

Thank you so much!