Separate names with a comma.
Recommended. Know people from your network.
Don't have an account?Sign up Now
To reset your password, enter the email address you registered with and we"ll send your instructions on their way.
Discussion in 'Big Data and Analytics' started by Prashant_Nair, Nov 2, 2019.
Dedicated Thread for Assignment Submission and Doubt Clearing !!!
I have done the below steps.
1. Loaded the data into Data Frame.
2. Replaced the missing values.
1. There are 21 columns in the datast ..How do we select the features which are important and neglect the rest?
2. There are columns e.g. Suburb,Address which are categorical in nature? How can we convert the values for them into numerical ones?
I am trying OHE for different columns in the dataset for Melbourne case study.
I am getting below warnings.
Could you please help on this?
Assignment - Lecture3 - NishithKumar
Please correct me if any steps seems to be incorrect. Thank you.
You forgot to perform Label Encoding
Assignment (preprocessing practice)
Just selected random columns and worked on them. with an assumption that we don't need to build working model in this. Let me know if I have to do it.
I have done the preprocessing using pandas and no issues with that. But when I used SK learn to handle missing values,I got an issue. Though I am replacing NAN, still the nd array shows NAN. Can you please check?
could you please share the drive link as some files are missing in it like the whiteboard sheet. In the day 3 folder also whiteboard sheet is missing.
Issue has been resolved. Please find the code based on stats analysis
for day 4 assignment : I have used feature selection technique ANNOVA. But after applying that I am not able to get which feature I should take as I have used after OHE for all object columns. Am I doing this wrongly? Can you please check?
If I reduce the feature and take only following
Index(['Rooms', 'Type', 'Method', 'Distance', 'Postcode', 'Bedroom2',
'Bathroom', 'Car', 'Landsize', 'BuildingArea', 'YearBuilt', 'Lattitude',
[ True False True False False False False False True True False True
True True False False True True True False]
then I am getting max test score as 66. How to get a better score
For the Assignment given on deleting rows based on a specific column (Label) in Salary Dataset,
we can achieve it using : "saldt.dropna(subset=['Salary'])"
Why is expected Price coming in the form of array.
How can we view PricePredictor model file.
In sci kit missing data for BuildingArea and Car are not being replaced, though there is no error.
While YearBuilt is giving IndexError: index 4 is out of bounds for axis1 with size 4
hello sir, when you will be starting the sessions of "Deep Learning with Tensor flow".
Here is the Model for melbourne dataset. thank you
Iris data set classification solution
uploaded two of the assignments.i.e. data pre-processing and classification one. working on other two
Iris Data set assignment Day 6
IRIS classification assignment submission (Nishith Kumar), Nov 10
Model for Melbourne data set
IRIS Dataset assignment submission
KNN Model for iris dataset, with accuracy of 0.95 in train and 1.0 in Test
Iris dataset assignment
Iris task submission
Assignment - Iris Dataset
Assignment Submitted, Archana
Sir assignment data of Melbourne data set and Iris data
Sir please find solution of Iris Dataset
Good day sir
trust you are well.
please see attached my assignment for Iris data set.
- how do i convert the data so that i can save to local drive (because if working offline then the github link would not be accessible)
- also after importing and writing to bytes (wb) - where would the object be stored in order to access?
Applied Linear Regression on Melbourne data. Logistic Regression and KNN Classification on Iris dataset.
Please find the irish dataset assignment.
Assignment : Linear Regression on Melbourne data
please find the assignment
For the melburne data, address has lot of unique values so can any one tell how to process that data? or for the assignment we need to use only the mentioned columns
Applied Linear Regression on Melbourne Domain approach
Mel Assignment submitted
The zip file contains 3 files:
a) Melbourne Housing Price Data set (csv)
b)Linear Regression Model - Using only the 4 features (Car,Landsize,BuildingArea,YearBuild) and Target(Price).
c) Linear Regression Model - Considering all features in the dataset
Kindly go through the attached Zip files for melbourne data and Iris
Please find attached my assignment 1 submission.
I am stuck with this error when trying to perform backward elimination on the Melb data.
Could you please advise?
Traceback (most recent call last) <ipython-input-201-166b072054ac> in <module>
2 #exog ---- feature columns in the form of numpy array 3 ----> 4 model1 = stat.OLS(endog=label , exog=featuresAllIn).fit()
5 model1.summary() AttributeError: module 'statsmodels.formula.api' has no attribute 'OLS'
import statsmodels.formula.api as stat
model1 = stat.OLS(endog=label , exog=featuresAllIn).fit()
I have question in Cancer case study on Binarise variables.
When we are doing label binarize as B and M
We are getting 1 D array
But in class we were getting values [1,0,0] as we were having 3 classes?
Am i getting correct results of binarize
2. If my binarize is working fine then how many PR curves i should plot 2 or 1
In the class we did plot 3 PR curves as we were having 3 classes.
So far I have plotted only one curve.
Sir Caner assignment using logistic regression
Day 7 - Assignment.
day 7 assignment
Submission for cancer case.
I faced an issue using "for loop" as an alternative to plot the graph:
TypeError: 'dict' object is not callable
May I know how to fix this?
please see attached assignment
still going through all the different algos that can be applied
To merge the data train and test data Append command can be applied or any other option in mercedes project