Midterm
docx
keyboard_arrow_up
School
Humber College *
*We aren’t endorsed by this school
Course
DIGI4001
Subject
Aerospace Engineering
Date
Dec 6, 2023
Type
docx
Pages
3
Uploaded by DrHornet2794
Q1. Generate a box plot to visualize the spread of Y
Figure 1: Boxplot to represent the spread of Y
The box plot shows the general outlay of the data provided in the Y column. The data shaded in
is majority. The horizontal lines indicate the maximum and minimum values (except outliers).
The dots show the outliers. As you can see, there are a lot of them in this box plot. The “X” is
the mean value. The Line in the shaded area is a median.
Q2. What is the correlation between x5 and X2
The correlation between x5 and X2 is .019145.
As this is a low value, this shows that x2 and x5 are not strongly correlated. The closer the value
is to 1, the more correlated they are. Further, as the number is positive, the correlation is
positive. So, this is a weak positive correlation between x2 and x5.
Q3. Use Table01 to:
1. Divide the data by 60% for training and 40% for validation.
2. Calculate the error matrices (e.g., MAE, MPE, RMSC) for both (validation and training data)
Training Error Matrices:
Avg. MAPE
1.66264128
MAE
101.733668
RMCS
251.27459
Validation Error Matrices
Avg. MAPE
2.33632175
MAE
98.6290727
RMSC
252.758411
3. Compare the results using bar plot
Avg. MAPE -
Training
Avg.
MAPE -
Val
idation
MA
E -
Trainin
g
MA
E -
Validation
RMCS -
Training
RMSC -
Validatio
n
0
50
100
150
200
250
300
Comparison of Training and Validation Results
Figure 2: Bar Graph comparison of training and validation results
The average MAPE of each training and validation results are very similar. As such, the data did
not vary much between the training and validation datasets. The average MAPE being low for
both of these datasets indicates that the predictions observed do not deviate much, on average,
from the actual results.
The MAE for both training and validation are very similar as well. The results showed an MAE of
about 100 for each dataset. With a smaller value of 100, the MAE indicates that the predicted
values did not deviate much from the actual results on average (an average deviation of about
100 for both datasets).
The RMSC is consistent between both datasets which is also consistent with the results of MAPE
and MAE indicated above. The RMSC for both training and validation was about 250.
Your preview ends here
Eager to read complete document? Join bartleby learn and gain access to the full version
- Access to all documents
- Unlimited textbook solutions
- 24/7 expert homework help