Linear Regression study on the 3D printing dataset

# Importing the libraries

import pandas as pd
import numpy as np
import [Link] as plt
import seaborn as sns

#To enable matplot visualization

%matplotlib inline

#Importing the Dataset using .read csv)function of pandas

#We will call the dataset as 'printer'

printer = pd.read_csv(./input/3 dprinter/[Link])

#Let's check few rows of the dataset using the .head() function of pandas
[Link]()

layerheight wallthickness infill density infil pattern n0zzle_temperature bed temperature prin
0 0.02 90 grid 220 60 40

1 0.02 7 90 honeycomb 225 65 40

2 0.02 1 80 grid 230 70 40

3 002 4 70 honeycomb 240 75 40

4 0.02 6 90 gnd 250 80 40

 1. Layer Height in mm
2, Wall Thícknoss in mm
3. Infill Density in %
4 Infill Pattern in either Grid or Honeycomb
5. Nozzle Temperature in Degree C
6. Bed Temperature in degree C
7. Print speed in mm/s
8. Material in either abs or pla
9. Fan Speed in %

# Basic information of the dataset using .info() function of pandas

[Link]()

<class '[Link]. DataFrame'>

RangeIndex: 50 entries, 0 to 49
Data columns (total 12 col umns) :
Column Non-Null Count Dtype

layer height 50 non-null float64

wall thickness 50 non-nul int64
infill density 50 non-null int64
3 infill pattern 50 non-null object
nozzle temperature 50 non-null int64
bed temperature 50 non-null int 64
print speed 50 non-null int64
7 material 50 non-null object
8 fan speed 50 non-null int64
9 roughness 50 non-null int64
tensi on strenght 50 non-null int64
11 elongation 50 non-null float64
dtypes: fioat64 (2), int64 (8), object (2)
memory usage: 4.8+ KB

printer['infill pattern'].replace(['grid', honeycomb'], [0,1], inplace = True)

printer('material'].replacc(['abs,pla'), [0,1], inplace True)
In [7):
linkcode
Met's view the first 10 observations
[Link](10)
 layer height wall thickness infill_density infit pattern nozzie_ temperature bed temperature prin
0.02 8 90 220 60 40

1 002 7 225 65 40

2 0.02 1 80 0 230 70 40
3 002 70 1 240 40

4 0.02 90 250 40
5 0 02 10 40 1 200 60 40
6 0.02 10 205 6 40
7 0.02 10 10 1 210 70 40
0.02 9 70 0 215 75 40
9 0 02 8 40 1 220 80 40

# Creating the heatmap

# Firsttcreatea
e space for the heatmap und then draw the heatmap inside the space

fig, ax = [Link](figsize = (20,7))

#Title for the heatmap
title 'Correlation Heatmap of the 3D printing Dataset'
[Link](title, fontsize = 20)
tl [Link]

# Correlation heatmap using heatmap() function of sns library

[Link]([Link](), cbar - True, cmap 'cool', annot = True, linewidths = 1, ax = ax)

#enable visualization using .show)function of matplot

[Link](0
 Correlation Heatmap of the 30 printing Dataset

441

# Defining features and labels

X = printer. drop(['roughness!, tension_strenght, elongation']. axis = I)
y = printer['roughness']
In (10l:
linkcode
[Link]()

layer_height wal_thickness infil_ density infill patern nozzle termperature bed temperature prin
0 0.02 90 0 220 60 40
0 02 7 90 1 225 65 40
0 02 30 0 230 70 40
D.02 4 70 1 240 75 40
4 002 90 250 80 40

#importing statsmodels library

import [Link] as sim
In (12]:
linkcode
#let's define a function for the multiple regression
def linear Regression(x.y):

x= [Link] constant(x)

#defining the model, fitting the model and printing the results
multiple model [Link](y,x).fit(0
print(multiple [Link]())
thcalling the linear regression function
linear Regression(X.y)
OLS Regressi on Results

Dep. Variable: roughness R-squared:

0.875
Madel: oLS Adj. R-squared:
0.851
Method: Least squares F-statistic:
35.95
Date: Thu, 07 Jul 2022 Prob (F-statistic) :
.83e-16
Time: 12:50:37 LOg-Iikelihood:
-248.19
No. Observations: 50 AIC:
514.4
Df Residuals: 41 BIC:
531.6
Df Model:
Covariance Type: nonrobust

coef std err t P>|t|

025 0.975

const -0.9534 0.159 -6.006 0.000 -1

274 -0.633
layer height 1269.4449 87.648 14.483 0.000 1092.
4371:
1446.453
wall thickness 2.3342 2.189 1.066 0.293 2
087 6.756
infill density -0.0423 0.234 -0.181 0.857 -0.
515 0.430
infill pattern -0.1255 1l.280 -0.011 0.991 -22.
907 22.656

nozzl_e
948
temperature
20.164
bed temperature
15.0562

-55.6225
2.529

9.279
5.953

-5.995
0.000

0.000
9.

-74.
362 -36.883
0.6496 0.206 3.153 0.003
print speed
233 1.066
aterial 298.4514 58.364 5.114 0.000 180.
582 416.321
speed 7.8989 1.238 6.379 0.000 5
398 10.399
**=e=

Ornn ibus: 7.107 Durbin-Watson:

1.467
Prob (0mnibus)! 0.575 Jarque-Bera (JB) :

0.749
Skew: 0.300 Prob (JB) :
0.688
Kurtosis: 3.018 Cond. No. 3
.59e+18
Notes:
(1] Standard Errors assume that the covariance matrix of the errors is
correctly specified.
[2] The smallest eigenvalue is 2.48e-31. This might indicate that there
are

strong multicollinearity problems or that the design matrix is singular

#check X
[Link]()

layer height wall thickness infil_ density infil pattern nozzle_temperature bed_termperature prin
0 0.02 0 220 60 40
1 0.02 90 1 225 65 40
2 0.02 80 230 70 40
3 0.02 1 240 75 40
4 002 6 90 250 80 40

X= [Link](['wall thickness", infill density,infill pattem'), axis = 1)

In [16]:
linkcode
[Link]()

layer_height nozze_temperature bed_temperature print_speed material fan speed

0 0.02 220 60 40 0
1 0.02 225 65 40 25
2 0.02 230 70 40 50
3 0.02 240 7 40 75
4 0.02 250 40 0 100
#calling the linear regression function
linear Regression(X,y)
OLS Regression Results

Dep. Variable: roughness R-squared:

0.872
Model: OLS Adj. R-squared:
0.857
Method: Least Squares F-statistic:
59.78
Prob (F-statistic) : 1
Date: Thu, 07 Jul 2022
.67e-18
Time: 12:50:37 Log-Li kelihood:
-248.88
No. Observations: 50 AIC:
509.8
Df Residuals : 44 BIC:
521.2
DE Mode l: 5
Covariance Type: nonrobust

Coef std err t P>|t| (0.

025 0.975]

-0.9307 0.151 -6.172 O.000

Const
235 -0.627
layer height 1246.5353 83.178 14.986 0.000 1078.
901 1414.169
nozzle temperature 14.7774 2.398 6.163 0.000 9.
945 19.610
bed temperature -54.3045 8.815 -6.160 0.000 -72.
070 -36.539
print speed 0.5538 0.180 3.070 0.004 0
190 0.917
material 294.1610 56.159 5.238 0.000 180.
407.341
fan speed 7.6993 1.177 6.542 0.000 5.
328 10.071

Omnibus: 0.850 Durbin-Watson:

1.367
0.654 Jarque-Bera (JB):
Prob (0mnibus) :
0.720
Skew: 0.285 Prob (JB) :
0.698
2.857 Cond. No. 3
Kurtosis:
.59e+18

Notes:
(1) Standard Errors assume that the covariance matrix of the errOrs is
correctly specified.
 [2] The smallest eigenvalue is 2.37e-31. This might indicate that there
are

strong multicollinearity problems or that the design matrix is singular

Xhead()

layer_height nozzle temperature bed_temperature print_speed material fan_speed

0

2
1
0 02
0.02
0 02
220
225
230
60

65
70
1....
40

40
40 50
3 0.02 240 75 40 75
4 0 02 250 80 40 100

Hget the interaction terms by multiplying values

1nter mn
X('material']*X['nozzle temperature']
inter bn X['bed temperature"]'X['nozzle_temperature'])
inter fn = X['fan speed']*X['nozzle temperature"
inter fb Xi'fan speed']*X['bed_temperature"]
In [21]:
linkcode
#adding these interaction terms to dataset using .concat() function of pandas
hwe will call this dataset as interaction

interaction = [Link]([X,inter mn,inter bn,inter fn,inter fb]. axis = )

#chenge column names of this interaction terms

interaction [Link](columns = (0:interct mn', 1:interact bn', 2:interact fn',
3:interact fb'})
[Link]( 10)
 layer height nozzle temperature bed_temperature print _speed material fan_speed interct _mn
0.02 220 60 40 0
1 0 02 225 65 40 25
2 0.02 230 70 40 0 50
3 0.02 240 7 40 75

4 0.02 250 80 40 0 100

5 0.02 200 60 40 1 0 200

6 0.02 205 65 40 1 25 205
7 D.02 210 70 40 1 50 210

0.02 215 75 40 75 215

9 0.02 220 80 40 1 100 220

# NOw let's fit this model to the linear regression function

linear Regression(interaction,y)
OS Regression Result.s

Dep. Variable: roughness R-squared:

0.925
Model: Adj. R-squared:
0.910
Method: Least Sauares F-statistic:
63.22
Date: Thu, 07 Jul 2022 Prob (F-statistic): 1
.31e-20
Time: 12:50:38 Log-Li kelihood:
-235.45
No. Observations: 50 AIC:
488.9
Df Residuals: 41 BIC:
506.1
Df Model: 8
Covariance Type: nonrobust

coef std err t P>|t| [0.

025 0.975]

const -1.0735 0.923 -1,163 0.252 -2.

938 0.791
1246.5353 65.870 18.924 0.000 1113.
layer height
508 1379. 562
 0.0050 0.004 1.146 0.259 -0.
nozzle teperature
004 0.014
bed temperature -57.8032 50.004 -1.156 0.254 -158.
788 43.182
0.143 3.B77 0.000 0.
print speed 0,5538
265 0.842
material 5516.1791 2836.453 1.945 0.059 -212.
153 1.12e+04
fan speed 33.0427 27.526 1.200 0.237 -22.
546 89.632
0.054 -51.
interct mn -25.7036 12.956 -1.984
869 0,462
interact bn 0.2588 0.227 1.138 0.262 -0
201 0.718
interact_ fn -0.2032 0.174 -1.169 0.249 -0
554 0..148
1.206 0.235
interact_b0.444
112
0.1662 0.138

Omnibus: 0.934 Durbin-Watson:

1.345
Prob (0mn ibus): 0.627 Jarque-Bera (JB):
0.333
Skew: 0.132 Prob (JB):
0.847
KurtOsis: 3.300 Cond. No.
.80e+20

Notes:
[1] Standard Errors assune that the covariance matrix of the errors is
correctly specified
[21 The smallest eigenvalue is 9.58e-32. This might indicate that there
are
strong multicollinearity problems or that the desgn matrix is singular

X [Link](('roughness', tension_strenght', elongation), axis = 1)

X,head()

layer height wall_thickness infilldensity infil pattern nozzle_lemperature bed temperature prin
0 0 02 90 220 60 4

0.02 7 90 225 6 40
2 02 80 230 70 40

3 0 02 70 240 75 40
0 90 250 80
printer['tension strenght']

Strenght, dtype: int64

linear Regression(X,y)
OLS RegresS1on Kes:

Dep. Variable: tension strenght R-squared:

0.673
Model: OLS Adj. R-squared:
0.609
Method: Least Squares F-statistic:
10.55
6
Date: Thu, 07 Jul 2022 Prob (F-statistic) :
.9le-09
Time: 12:50: 38 Log-Likelihood:
-151. 94

No. Observations: 50 AIC:

321.9
Df Residuals: 41 BIC:
339.1
Df Model:
Covariance Type: nonrobust

coef std crr P>|t| [0.

025 0.975]

const 0.0663 C.023 2.863 0.007 0

020 0.113
layer height 55.5972 12.788 4.348 0.000 29
772 81.423
wall thickness 1.0687 0.319 3.346 0.002
424 1.714
infill density 0.1629 0.034 4.769 0.000 0.
094 0.232
infill pattern -1.1427 1.646 -0.694 0.491 -4
466 2.181
nozzle temperature -1.0468 0.369 -2.837 0.007 -1.
792 -0.302
bed temperature
131
3.8647 1.354 855 0.007 1..
6.599
print speed -0.0156 0.030 -0.519 0.607 -0
076 0.045
material -17.3051 8.515 -2.032 0.049 -34.
502 -0.108
fan speed -0.5719 0.181 -3.166 0.003 -0.
937 -0.207

Omnibus: 0.265 Durbin-Watson:

1.461
Prob (0mnibus): 0.876 Jargue-Bera (JB):
0.456
Skew: 0.060 Prob (JB):
0.796
Kurtosis: 2.548 Cond. No.
.59e+18
Notes:
[1) Standard Errors assume that the covariance matrix of the errors is
correctly specified.
[2] The smallest eigenvalue is 2.48e-31. This míght indicate that there
are

strong muiticollinearity problems or that the design matrix is singular

X =[Link](["infill pattern, print_speed, material'], axis = 1)

[Link])

layer height wallthickness infill_density nozzle temperature bed_temperature fan speed

0.02 90 220 60 0
1 0.02 7 90 225 65 25
0.02 B0 230 70 50
3 0.02 70 240 75 75
0.02 6 90 250 80 100

linear Regression(X,y)
OLS Regression Results

Dep. Variable: tension strenght R-squared:

0.634
Model: OLS Adj. R-squared:
0593
Method: Least Squares F-statistic:
15.27
Dat.e: Thç, 07 Jul 2022 Prob (F-statistic): 1
.07e-08
Time: 12:50+38 Log-Li kelihood:
-154.73
No. Observations: 50 AIC:
321.5
DE Residuals: 44 BIC:
332.9
DE Model: 5
Covariance Type: nonrobust

Coef std err P>|t| [0.

025 0.975]
const 0.0191l 0.004 4.358 0.000 0.
010 0.028
layer height 56.6997 12.886 4.400 0.000 30.
730 82.669
wall_thickness 1.1478 0.290 3.965 0.000 0.
564 1.731
infill density 0.1543 0.034 4.537 0.000
086 0.223
nozzle tempcrature -0.3028 0.073 -4,141 0.000 -0.
450 -0.155
bed temperature
t 1.1021 0.255 4.318 0.000
588 1.617
fan speed -0.2052 0.043 -4.812 0.000 -0.
-0.119

Omnibus: 0.429 Durbin-Watson:

1.310
Prob(Omnibus) : 0.807 Jarque-Bera (JB) :
0.404
Skew: 0.202 Prob (JB) :
0.817
Kurtosis: 2.824 Cond. No. 3
.43e+18

Notes:
(1] Standard Errors assume that the covariance matrix of the errors is
correctly specified.
[21 The smallest eigenvalue is 2.54e-31 This might indicate that there
are

strong multicollinearity problems or that the destgn matrix is singular

interaction [Link]([X,inter mn,inter bn,inter fn,inter fb], axis 1)

interaction = [Link](columns = {0:'interct mn', 1:'interact bn', 2:interact fn'.
3:'interact fb')

[Link]()
 layer height wall_thickness infill density nozzie temperature bed femperature fan speed interc

0.02 90 220 60
0 02 7 225 65 25 0

0 02 1 80 230 70 50
3 002 4 70 240 75 75

0.02 6 250 80 100

linear Regression(interaction,v)
OLS Regression Results

Dep. Variable: tension strenght R-squared:

0.718
Model: OLS Adj. R-squared:
0.663
Method: Least Squares F-statistic:
13.03
Date: Thu, 07 Jul 2022 Prob (F-statistic) :
06e-09
Time : 12:50:38 Log-Li kelihood:
-148.27
No. Observations: 50 AIC:
314.5
Kesiduals: 41 BIC:
331.
Df Model:
nonrobust
Covariance Type:

coef std err t P>|t| [0.

025 0.975]

const -0.0870 0.068 -1.280 0.208 -0.

224 0.050
layer height 56.6017 11.739 4.822 0.000 32.
995 80.309
wall thickness 1.1373 0.268 4.242 0.000
596 1.679
0.1587 0.032 4.928
infill_ density 0.000
O94 0.224
nozzle temperature 0.0004 0.000 1.319 0.194 -0.
000 0.001
bed temperatUre -4.7917 3.832 -1.251 0.218 -12.
530 2.946
tan_speed 2.1355 1.273 1.678 0.101 -0.
435 4.706
interct mn 0.1191 0.096 1.235 0.224 -0.
076 0.314
interact bn 0.0221 0.017 1.263 0.214 -0.
013 0.057
 0.050 -0.
-0.0138 0.007 -2.022
1nteract fn
028 -1.34e-05 1.830 0.075 -6.
0.0077 0.004
interact fb
001 0.016

0.134 Durbii-Watson:
Omn ibus:
1.472 Jarque-Bera (JB):
Prob (Omnibus) : 0.935
0.207 Prob (JB) :
-0.114
Skew:
0.902
2.782 Cond. No.
Kurtosis:
.90e+20

matrix Of the errors 1s

assume that the covariance
Notes :
[1] Standard Errors
correctly specified. might indicate that there
The smallest eigenvalue is 6.34ce-32. This
[21 singular
that the design matrix ís
multicoll inearity problems or
are
strong

[Link]()

bed temperature prin

infiIL_density infill pattern nozzle temperature
layer height wall thickness 60 40
220
90 40
o 02 6
225
90 40
1 0.02 230 70
80 0
40
2 002 75
70
240
40
B0
3 0.07 250
90
0 02

linear Regression(X.y) OLS Regression Results

R-squared:
tension strenght
Dep. Variable:
Adi. R-squared:
0.673 oLS
Model: F-statistic:
0.609 Least Squares
Method:
10.55
Date: Thu, 07 Jul 2022 Prob (E-statistic) :
.9le-08
Time: 12:50:39 Log-Likelihood:
-151.94
No. Observations :
50 AIC:
321.9
Df Residuals:
41 BIC:
339.1
Df Model: 8
Covariance Type: nonrobust

Coef std err t P>|t| [0.

025 0.975]

const
0.0663 0.023 2.863 0.007
020 0.113
layer height 55.5972 12.788 4.348 0.000 29.
772 81.423
wall thickness 1.068 0.319 3.346 0.002 0.
424 1.714
in 1 _density 0.1629 0.034 4.769 0.000 0.
0.232
infill pattern -1.1427 1.646 -0.694 0.491 -4
466 2.181
nozzle temperature -1.0468 0.369 -2.837 0.007 -1.
792 -0.302
bed temperature 3.8647 1.354 2.855 0.007
131 6.599
print speed -0.0156 0.030 -0.519 0.607 -0
076 0.045
material -17.3051 8.515 -2.032 0.049 -34.
502 -0.108
tan speed -0.5719 0.181 -3.166 0.003 -0.
937 -0.207

Omn ibus: 5.265 Durbin-Watson:

1.461
Prob (0mnibus ): 0.876 Jarque-Bera (JB):
0.456
Skew: 0.060 Prob (JB):
0.796
Kurtosis: 2.548 Cond. No. 3
.59e+18

Notes:
[1] Standard Errors assume that the covariance matrix of the errors
correctly specified.
(2] The smallest eigenvalue is 2.48e-31. This might indicate that there
are

strong multicollinearity problems or that the design matrix is singular

In [33]:
linkcode
X= [Link](['infill pattern" print _speed'], axis
[Link])

layer_heght wal thickness infil_density nozzle_ternperature bed_temperature matenal fan spe

0 0 02 8 90 220 60
0.02 90 225 65 2
0.02 80 230 70 0 50
0 02 4 70 240 75 75
0.02 6 90 250 80 100
4

Iinear Regression(X,y)
OLS Regression Results

Dep. Variable: tension strenght R-squared:

0.667
Model: OLS Adj. R-squared:
0.620
Method: Least Squares F-statistic:
14.33
Date : Thu, 07 Jul 2022 Prob (E-statistic) :
.78e-09
Time: 12:50: 39 Log-Likelihood:
-152.42
No. Observations: 50 AIC:
318.8
Df Residuals: 43 BIC:
332.2
DE Model: 6
Covariance Type: nonrobust

Coef std err P>|t|

025 0.9751

Const 0.0646 0.023 2.840 0.007

019 0.111
layer_height 56.3670 12.448 4.528 0.000 31.
262 81.472
wall thickness 1.1117 0.280 3.967 0.000
547 1.677
infill density 0.1664 0.033 4.985 0.000
099 0.234
nozzle temperature -1.0289 0.363 -2.833 0.007 -1.
761 -0.296
bed temperature 3.7661 1.330 2.831 0.007 1.
084 6.449
material -17.1036 8.392 -2.038 0.048 -34.
028 -0.180
fan -0.5565 0.177 -3.140 O.003 -0.
914 -0.199

Omnibus: 0.578 [Link]:

1.501
Prob (Omnibus) : 0.749 Jarque-Bera (JB):
0.710
Skew: 0.195 Prob (JB):
0.701
Kurtosis: 2.566 Cond. No.
,42e+18

Notes :

1] Standard Errors as sune that the covariance matrix of the errors is

correctly specified.
(21 The smallest eigenvalue is l.02e-31. This might indi cate that there
are

Strong multicollinearity problems or that the design matrix is singular

In [35) :
linkcode
interaction = [Link]([X,inter_mn,inter bn,inter fn,inter fb), axis = l)
interaction = [Link](columns {0:interctmn, 1:interact_bn', 2:interact_fn'.
3:'interact_fb'})
[Link]()

layer_height walt_thickness infilldensity nozzle temperature bed_temperalure material fan spe

0 0.02 90 220 60

1 0.02 7 90 225 65 0 25
2 0.02 80 230 70 50
3 0.02 70 240 75 75
4 0.02 90 250 80 100

linear Regression(interaction,y)
OLS Regression Results

Dep. Variable: tension strenght. R-squared:

0.718
Model: OLS Adj. R-squared:
0.654
Method: Least Squares F-statistic:
11.30
Date: Thu, 07 Jul 2022 Prob (E-statistic): 1
.54e-08
Time: 12:50:39 Log-Likelihood:
-148.26
No. Observations: 50 AIC:
316.5
Df Residuals: 40 BIC:
335.6
DE Model: 9
Covariancee Ype : nonrobust

coef std err P>|t| (0.

025 0.975]

Const -0.0781 0.164 -0.477 0.636 -0.

400 0.253
layer height 56.6034 11.884 4.763 0.000 32.
585 80.622
wall thickness 1.1375 0.271 4.191 0.000
589 1.686
infill density 0.1587 0.033 4.868 0.000
093 0.225
nozzle_temperature 0.0004 0.001 0.482 0.633 -0
001 0.002
bed temperature
229 13.595
-4.3166 8.863 -0.487 0.629 -22
material -29.9509 502.401 -0.060 0.953 -1045.
341 985.440
fan speed 1.8551 4.876 0.380 0.706 -8.
000 11.711
interct mn 0.2557 2.295 0.111 0.912 -4.
382 4.893
interact bn 0.0199 0.040 0.494 0.624 -0.
062 0.101
interact fn -0.0120 C.037 -0.389 0.700 -0
074 0.050
interact fb 0.0062 0.024 0.256 0.800
043 0.056

Omnibus : 0.143 Durbin-Watson:

1.471
Prob(Omnibus): 0.931 Jarque-Bera (JB) :
0.217
Skew : -0.118 Prob (JB) :
0.897
Kurtosis: 2.779 Cond, No.
.64e+20

Notes:
[1] Standard Errors assume that the covarlance natrix of the errors is
correctly specified.
[2] The smallest eigenvalue is 6.94e-32. Thin might indicate that there
are