Hands On with TensorFlow

2 / 31

Recap of End-to-end Machine Learning Project

Slides


No hints are availble for this assesment

Answer is not availble for this assesment

Please login to comment

29 Comments

This video seems to be very similar to Topic 5. Why are the topics duplicated? If they are duplicate, I can skip topic 20. Pl clarify.

  Upvote    Share

Hi,

Instead of skipping it altogether, I would suggest you to go through the video at 2x speed.

Thanks.

  Upvote    Share

I did not understand at 3:04:05

 

What is final data ??

 

What are things which we are doing in final dataset??

  Upvote    Share

Hi,

The final data was derived by applying all the changes mentioned above it, e.g. separating into train/test set, imputing missing values etc. This is a graphical representation of what we did in this video.

Thanks.

  Upvote    Share

why in this my name is not showing

  Upvote    Share

Hi,

Please try the following command:

PS1 [\u@\h \W]\$

Thanks.

  Upvote    Share

Is any cheat sheet prepared?

  Upvote    Share

Hi,

As of now we do not have any cheat sheet, but you can download the slides for your reference.

Thanks.

  Upvote    Share

In video it is mentioned that you are going to do that.

  Upvote    Share

Hi,

Yes,  understand. But considering the vastness of the subject, we thought it would be a best to focus on the slides. A cheat sheet would become too lengthy. However, we would take this as a feedback and would consider this when we are next udpating our courseware. Also, you can search in Google for cheat sheets related to Machine Learning and you would find a number of them available for free.

Thanks.

  Upvote    Share

Can you paste some good Google links here.

  Upvote    Share

Hi,

Please open www.google.com and search for "machine learning cheat sheets".

Thanks.

  Upvote    Share

If we are considering all the attributes in the model, then why did we carry out stratified sampling only on median income attribute earlier?

  Upvote    Share

Hi,

This is done to make the data inclusive of all categories since that is the target variable.

Thanks.

  Upvote    Share

Hello

In line 8, it is showing error while importing the data. Can you help me that where the mistake is? Where am I going wrong? Is the path ok?


  Upvote    Share

Hi,

Please check if you are providing the correct path for the data, and if the file is present on that path.

Thanks.

  Upvote    Share

Where is the housing file. I am unable to find it

  Upvote    Share

plz help

  Upvote    Share

Hi,

You need to clone our GitHub repository as shown in slide# 5 to access the housing.csv file.

Thanks.

  Upvote    Share

Thanks Sir. I got the file. Thanks for your help.

  Upvote    Share

The slides used in the video, and the slides attached here, have discrepancies again. Some individual sldies are missing. I am not making the effort myself to show you every difference.

Please find out yourself and help in getting the exact slides described in the video, else it becomes a problem with continuity

  Upvote    Share

Hi,

We have created these slides keeping in mind that there is no affect on continuity, so if we have ommitted some slides it must have been done purposely. Also, I checked these slides and could not find any missing content. Having said that, I maybe wrong, and so would request you to notify us of any missing slides and we would incorporate those if necessary.

Thanks.

  Upvote    Share

where is the housing.csv file ? I tried to find the path datasets/housing/ both in hadoop folder and also the linux shell, but couln'd find it

  Upvote    Share

I got it. Nevermind. Inore this question

  Upvote    Share

cbar.ax.set_yticklabels(["$%dk"%(round(v/1000)) for v in tick_values], fontsize=14)
pls sir explain the role of this line

  Upvote    Share

Hi,

This sets the tick values/labels for the charts.

Thanks.

-- Rajtilak Bhattacharjee

  Upvote    Share

hello sir , can you explain how random sampling works formula ..... i dont understand how the values comes for random sampling in compareprops

  Upvote    Share

Hi,

Say you want to select a subset of a population in which each member of the subset has an equal probability of being chosen, then you use Random Sampling. With compareprops, we are simply comparing the % error for overall, after random sampling, and after stratified sampling.

Thanks.

-- Rajtilak Bhattacharjee

  Upvote    Share

Hi, I am not seeing s and c parameters on pandas dataframe.plot. Can you please explain how to take it?

  Upvote    Share