This is a group project, and I am assigned these items. I am a single mother and I do not have time to do this assignment. please help! thank you! I do not need everything done just what I have added below I did attach the whole project just to reference. Also, I have added screen shots of the assignment that are split up. EVERYTHING IS RED is my portion. please if you have any questions, please let me know.
3.1 Identify Highly-correlated attributes (6 points).
3.1.1 Like Week 10 lab, please generate a correlation coefficient matrix in RM and take a screenshot of it
with date and time (Screenshot 1). Make sure that your screenshot shows all the attributes and
correlation coefficients clearly.
3.1.2 Discuss your correlation coefficient matrix briefly and indicate whether or not the dataset has highly correlated attributes (the absolute value of correlation coefficient greater than or equal to 0.9).
3.1.3 Based on your finding above, please discuss your decision: do you need to remove any highlycorrelated attributes? If so, how?
3.2 Data Transformation (6 points).
3.2.1 Take a look at the Statistics view of your dataset in RM and then take a screenshot of it with date
and time (Screenshot 2).
3.2.2 Attributes with very different scales and ranges may generate a misleading result when using
distance-based classifiers such as K-NN (not a problem for other methods). Observe all the attributes
to check whether there are attributes with very different scales and ranges.
3.2.3 Based on your observation above, please discuss your decision: do you need to handle it? If so, How?
3.3 Attribute Weight (5 points).
3.3.1 Follow Week 9 Lab to generate the weight of each attribute (Hint: you may need to use the operator,
Weight by Information Gain).
3.3.2 Take a screenshot of your weight table with date and time (Screenshot 3).
3.3.3 Discuss what this table means and what conclusions can you make based on the weight table.
4.3 Logistic Regression (5 points)
4.3.1 Please follow Week 9 lab to build a logistic regression model with the same parameters there. Note:
It may take a while to get the results.
4.3.2 Take a screenshot of your logistic regression model with date
and time (Screenshot 7) and briefly interpret it.
4.3.3 Use the logistic regression model to make predictions for the 100 new customers in the prediction
dataset.
4.3.4 Briefly discuss the prediction results (You may refer to Exam 1 Step 5).
4.3.5 Export your prediction results in an Excel File.
Now, we are going to assess the quality of the data and explore the data.