Compare commits

...

3 Commits

7 changed files with 117 additions and 97 deletions

View File

@@ -20,54 +20,60 @@
\@writefile{toc}{\contentsline {section}{\numberline {2}Data analysis}{1}{section.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.1}Dataset}{1}{subsection.2.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.2}Data cleaning and feature engineering}{1}{subsection.2.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Handling missing values}{1}{subsection.2.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.3}Handling missing values}{2}{subsection.2.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {2.4}Training, validation and test sets}{2}{subsection.2.4}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {3}Model selection}{2}{section.3}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {4}Model Training and Hyperparameter Tuning}{2}{section.4}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {5}Model Evaluations}{2}{section.5}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Analyzing the Confusion Matricies}{2}{subsection.5.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {5.2}Analyzing Weighted Performance Metrics}{2}{subsection.5.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {3.1}Data cleaning and feature engineering}{2}{subsection.3.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {3.2}Handling missing values}{2}{subsection.3.2}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {3.3}Training, validation and test sets}{2}{subsection.3.3}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {4}Model selection}{2}{section.4}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {5}Model Training and Hyperparameter Tuning}{3}{section.5}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {5.1}Models and methods used}{3}{subsection.5.1}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {5.2}Caveats and restrictions}{3}{subsection.5.2}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {6}Model Evaluations}{3}{section.6}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {6.1}Analyzing the Confusion Matricies}{3}{subsection.6.1}\protected@file@percent }
\providecommand*\caption@xref[2]{\@setref\relax\@undefined{#1}}
\newlabel{fig:featureImportanceDT}{{1(a)}{3}{\relax }{figure.caption.1}{}}
\newlabel{fig:featureImportanceDT@cref}{{[subfigure][1][1]1(a)}{[1][2][]3}}
\newlabel{sub@fig:featureImportanceDT}{{(a)}{3}{\relax }{figure.caption.1}{}}
\newlabel{sub@fig:featureImportanceDT@cref}{{[subfigure][1][1]1(a)}{[1][2][]3}}
\newlabel{fig:featureImportanceRF}{{1(b)}{3}{\relax }{figure.caption.1}{}}
\newlabel{fig:featureImportanceRF@cref}{{[subfigure][2][1]1(b)}{[1][2][]3}}
\newlabel{sub@fig:featureImportanceRF}{{(b)}{3}{\relax }{figure.caption.1}{}}
\newlabel{sub@fig:featureImportanceRF@cref}{{[subfigure][2][1]1(b)}{[1][2][]3}}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces The confusion matricies of the Decision Tree model and the Random Forest model on the test data.\relax }}{3}{figure.caption.1}\protected@file@percent }
\newlabel{fig:}{{1}{3}{The confusion matricies of the Decision Tree model and the Random Forest model on the test data.\relax }{figure.caption.1}{}}
\newlabel{fig:@cref}{{[figure][1][]1}{[1][2][]3}}
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces The performance metrics of the models on the validation data.\relax }}{3}{table.caption.2}\protected@file@percent }
\newlabel{perfmetric}{{1}{3}{The performance metrics of the models on the validation data.\relax }{table.caption.2}{}}
\newlabel{perfmetric@cref}{{[table][1][]1}{[1][2][]3}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces The performance metrics of the models on the test data.\relax }}{3}{table.caption.3}\protected@file@percent }
\newlabel{perfmetrictest}{{2}{3}{The performance metrics of the models on the test data.\relax }{table.caption.3}{}}
\newlabel{perfmetrictest@cref}{{[table][2][]2}{[1][2][]3}}
\@writefile{toc}{\contentsline {subsection}{\numberline {5.3}Analyzing the Performance}{3}{subsection.5.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {5.4}Overfitting and Underfitting}{3}{subsection.5.4}\protected@file@percent }
\newlabel{fig:featureImportanceDT}{{1(a)}{4}{\relax }{figure.caption.1}{}}
\newlabel{fig:featureImportanceDT@cref}{{[subfigure][1][1]1(a)}{[1][3][]4}}
\newlabel{sub@fig:featureImportanceDT}{{(a)}{4}{\relax }{figure.caption.1}{}}
\newlabel{sub@fig:featureImportanceDT@cref}{{[subfigure][1][1]1(a)}{[1][3][]4}}
\newlabel{fig:featureImportanceRF}{{1(b)}{4}{\relax }{figure.caption.1}{}}
\newlabel{fig:featureImportanceRF@cref}{{[subfigure][2][1]1(b)}{[1][3][]4}}
\newlabel{sub@fig:featureImportanceRF}{{(b)}{4}{\relax }{figure.caption.1}{}}
\newlabel{sub@fig:featureImportanceRF@cref}{{[subfigure][2][1]1(b)}{[1][3][]4}}
\@writefile{lof}{\contentsline {figure}{\numberline {1}{\ignorespaces The confusion matricies of the Decision Tree model and the Random Forest model on the test data.\relax }}{4}{figure.caption.1}\protected@file@percent }
\newlabel{fig:}{{1}{4}{The confusion matricies of the Decision Tree model and the Random Forest model on the test data.\relax }{figure.caption.1}{}}
\newlabel{fig:@cref}{{[figure][1][]1}{[1][3][]4}}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.2}Analyzing Weighted Performance Metrics}{4}{subsection.6.2}\protected@file@percent }
\@writefile{lot}{\contentsline {table}{\numberline {1}{\ignorespaces The performance metrics of the models on the validation data.\relax }}{4}{table.caption.2}\protected@file@percent }
\newlabel{perfmetric}{{1}{4}{The performance metrics of the models on the validation data.\relax }{table.caption.2}{}}
\newlabel{perfmetric@cref}{{[table][1][]1}{[1][4][]4}}
\@writefile{lot}{\contentsline {table}{\numberline {2}{\ignorespaces The performance metrics of the models on the test data.\relax }}{4}{table.caption.3}\protected@file@percent }
\newlabel{perfmetrictest}{{2}{4}{The performance metrics of the models on the test data.\relax }{table.caption.3}{}}
\newlabel{perfmetrictest@cref}{{[table][2][]2}{[1][4][]4}}
\@writefile{toc}{\contentsline {subsection}{\numberline {6.3}Analyzing the Performance}{5}{subsection.6.3}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {6.4}Overfitting and Underfitting}{5}{subsection.6.4}\protected@file@percent }
\@writefile{toc}{\contentsline {subsection}{\numberline {6.5}Feature Importance}{5}{subsection.6.5}\protected@file@percent }
\newlabel{fig:featureImportanceDT}{{2(a)}{5}{\relax }{figure.caption.4}{}}
\newlabel{fig:featureImportanceDT@cref}{{[subfigure][1][2]2(a)}{[1][5][]5}}
\newlabel{sub@fig:featureImportanceDT}{{(a)}{5}{\relax }{figure.caption.4}{}}
\newlabel{sub@fig:featureImportanceDT@cref}{{[subfigure][1][2]2(a)}{[1][5][]5}}
\newlabel{fig:featureImportanceRF}{{2(b)}{5}{\relax }{figure.caption.4}{}}
\newlabel{fig:featureImportanceRF@cref}{{[subfigure][2][2]2(b)}{[1][5][]5}}
\newlabel{sub@fig:featureImportanceRF}{{(b)}{5}{\relax }{figure.caption.4}{}}
\newlabel{sub@fig:featureImportanceRF@cref}{{[subfigure][2][2]2(b)}{[1][5][]5}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces The feature importance graphs for the Decision Tree model and the Random Forest model.\relax }}{5}{figure.caption.4}\protected@file@percent }
\newlabel{fig:}{{2}{5}{The feature importance graphs for the Decision Tree model and the Random Forest model.\relax }{figure.caption.4}{}}
\newlabel{fig:@cref}{{[figure][2][]2}{[1][5][]5}}
\bibstyle{model1-num-names}
\bibcite{Steinhaus:Mathematical}{1}
\bibcite{Greivenkamp:FieldGuide}{2}
\bibcite{Pedrotti:Introduction}{3}
\bibcite{Davis:ChemWiki}{4}
\@writefile{toc}{\contentsline {subsection}{\numberline {5.5}Feature Importance}{4}{subsection.5.5}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{\numberline {6}Summary}{4}{section.6}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{References}{4}{section.6}\protected@file@percent }
\newlabel{fig:featureImportanceDT}{{2(a)}{4}{\relax }{figure.caption.4}{}}
\newlabel{fig:featureImportanceDT@cref}{{[subfigure][1][2]2(a)}{[1][4][]4}}
\newlabel{sub@fig:featureImportanceDT}{{(a)}{4}{\relax }{figure.caption.4}{}}
\newlabel{sub@fig:featureImportanceDT@cref}{{[subfigure][1][2]2(a)}{[1][4][]4}}
\newlabel{fig:featureImportanceRF}{{2(b)}{4}{\relax }{figure.caption.4}{}}
\newlabel{fig:featureImportanceRF@cref}{{[subfigure][2][2]2(b)}{[1][4][]4}}
\newlabel{sub@fig:featureImportanceRF}{{(b)}{4}{\relax }{figure.caption.4}{}}
\newlabel{sub@fig:featureImportanceRF@cref}{{[subfigure][2][2]2(b)}{[1][4][]4}}
\@writefile{lof}{\contentsline {figure}{\numberline {2}{\ignorespaces The feature importance graphs for the Decision Tree model and the Random Forest model.\relax }}{4}{figure.caption.4}\protected@file@percent }
\newlabel{fig:}{{2}{4}{The feature importance graphs for the Decision Tree model and the Random Forest model.\relax }{figure.caption.4}{}}
\newlabel{fig:@cref}{{[figure][2][]2}{[1][4][]4}}
\ttl@finishall
\newlabel{LastPage}{{}{4}{}{page.4}{}}
\xdef\lastpage@lastpage{4}
\xdef\lastpage@lastpageHy{4}
\gdef \@abspage@last{4}
\@writefile{toc}{\contentsline {section}{\numberline {7}Summary}{6}{section.7}\protected@file@percent }
\@writefile{toc}{\contentsline {section}{References}{6}{section.7}\protected@file@percent }
\newlabel{LastPage}{{}{6}{}{page.6}{}}
\xdef\lastpage@lastpage{6}
\xdef\lastpage@lastpageHy{6}
\gdef \@abspage@last{6}

View File

@@ -1,6 +1,6 @@
# Fdb version 4
["pdflatex"] 1761667677.49056 "/home/jaknyst/Documents/MLPproject/Report/MLPproject.tex" "MLPproject.pdf" "MLPproject" 1761667678.57369 0
"/home/jaknyst/Documents/MLPproject/Report/MLPproject.tex" 1761667676.18911 19065 228243c289e2ad8172afdd84483c70d8 ""
["pdflatex"] 1761825977.46345 "/home/jaknyst/Documents/MLPproject/Report/MLPproject.tex" "MLPproject.pdf" "MLPproject" 1761825979.44337 0
"/home/jaknyst/Documents/MLPproject/Report/MLPproject.tex" 1761825974.63055 26288 f774e507a7e6764abdedfc00057099d7 ""
"/usr/share/texlive/texmf-dist/fonts/enc/dvips/base/8r.enc" 1721433600 4850 80dc9bab7f31fb78a000ccfed0e27cab ""
"/usr/share/texlive/texmf-dist/fonts/map/fontname/texfonts.map" 1577235249 3524 cb3e574dea2d1052e39280babc910dc8 ""
"/usr/share/texlive/texmf-dist/fonts/tfm/adobe/helvetic/phvb7t.tfm" 1136768653 2240 eb56c13537f4d8a0bd3fafc25572b1bd ""
@@ -134,10 +134,10 @@
"/var/lib/texmf/web2c/pdftex/pdflatex.fmt" 1760289849 7753794 892d611f76aecccd13eb485815d0543e ""
"CM_dt.png" 1761561428.73434 87433 ef7840e96e2e4e7d41f9d29d01517aa6 ""
"CM_rf.png" 1761561428.73495 88928 d3d0474bb68254ae0bba2e635ab99231 ""
"MLPproject.aux" 1761667678.47436 5727 94a1bcabbe387b476e26c782e4451f3d "pdflatex"
"MLPproject.out" 1761667678.47528 2690 efc895524c82e0378e07184e5720ac35 "pdflatex"
"MLPproject.tex" 1761667676.18911 19065 228243c289e2ad8172afdd84483c70d8 ""
"MLPproject.toc" 1761667678.47528 1375 6a3d7bab2edeea22735da861f6b6003c "pdflatex"
"MLPproject.aux" 1761825979.2759 6515 6007d19cad9448bda42bad5839bdf8e5 "pdflatex"
"MLPproject.out" 1761825979.2779 3852 caf78b736930e985ead6848b8c813653 "pdflatex"
"MLPproject.tex" 1761825974.63055 26288 f774e507a7e6764abdedfc00057099d7 ""
"MLPproject.toc" 1761825979.27929 1917 6fbe84ece41f0003e5c72512bad2b6c9 "pdflatex"
"SelfArx.cls" 1761123180.54708 7316 506603b27aab6da8087bc0f1ee693041 ""
"featureImportanceDT.png" 1761328898.24566 60078 4a2e56e2a45ae2ae5e41b9830c1bbcea ""
"featureImportanceRF.png" 1761328962.51602 61794 6b3eefc625dd3da8a3dbf302174c614c ""

View File

@@ -1,4 +1,4 @@
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) (preloaded format=pdflatex 2025.10.12) 28 OCT 2025 17:07
This is pdfTeX, Version 3.141592653-2.6-1.40.25 (TeX Live 2023) (preloaded format=pdflatex 2025.10.12) 30 OCT 2025 13:06
entering extended mode
restricted \write18 enabled.
file:line:error style messages enabled.
@@ -688,75 +688,77 @@ File: ts1ptm.fd 2001/06/04 font definitions for TS1/ptm.
) [1{/var/lib/texmf/fonts/map/pdftex/updmap/pdftex.map}{/usr/share/texlive/texmf-dist/fonts/enc/dvips/base/8r.enc}
]
<CM_dt.png, id=108, 462.528pt x 346.896pt>
] [2]
<CM_dt.png, id=150, 462.528pt x 346.896pt>
File: CM_dt.png Graphic file (type png)
<use CM_dt.png>
Package pdftex.def Info: CM_dt.png used on input line 101.
Package pdftex.def Info: CM_dt.png used on input line 118.
(pdftex.def) Requested size: 242.41745pt x 181.81612pt.
<CM_rf.png, id=110, 462.528pt x 346.896pt>
<CM_rf.png, id=152, 462.528pt x 346.896pt>
File: CM_rf.png Graphic file (type png)
<use CM_rf.png>
Package pdftex.def Info: CM_rf.png used on input line 108.
Package pdftex.def Info: CM_rf.png used on input line 125.
(pdftex.def) Requested size: 242.41745pt x 181.81612pt.
[2] [3 <./CM_dt.png> <./CM_rf.png>]
<featureImportanceDT.png, id=132, 416.2752pt x 393.8715pt>
[3] [4 <./CM_dt.png> <./CM_rf.png>]
<featureImportanceDT.png, id=173, 416.2752pt x 393.8715pt>
File: featureImportanceDT.png Graphic file (type png)
<use featureImportanceDT.png>
Package pdftex.def Info: featureImportanceDT.png used on input line 163.
Package pdftex.def Info: featureImportanceDT.png used on input line 182.
(pdftex.def) Requested size: 218.17422pt x 206.43103pt.
<featureImportanceRF.png, id=133, 422.0568pt x 393.8715pt>
<featureImportanceRF.png, id=174, 422.0568pt x 393.8715pt>
File: featureImportanceRF.png Graphic file (type png)
<use featureImportanceRF.png>
Package pdftex.def Info: featureImportanceRF.png used on input line 170.
Package pdftex.def Info: featureImportanceRF.png used on input line 189.
(pdftex.def) Requested size: 218.17422pt x 203.60634pt.
Underfull \hbox (badness 1448) in paragraph at lines 206--210
[5 <./featureImportanceDT.png> <./featureImportanceRF.png>]
Underfull \hbox (badness 1448) in paragraph at lines 225--229
[]\OT1/ptm/m/n/10 (+20) UC Davis ChemWiki, Prop-a-ga-tion of Er-ror, Avail-
[]
Underfull \hbox (badness 7649) in paragraph at lines 206--210
Underfull \hbox (badness 7649) in paragraph at lines 225--229
\OT1/ptm/m/n/10 (+20) able at: [][]$https : / / chem . libretexts . org / Textbook[]Maps /
[]
Underfull \hbox (badness 10000) in paragraph at lines 206--210
Underfull \hbox (badness 10000) in paragraph at lines 225--229
\OT1/ptm/m/n/10 (+20) Analytical[]Chemistry / Supplemental[]Modules[]
[]
Underfull \hbox (badness 10000) in paragraph at lines 206--210
Underfull \hbox (badness 10000) in paragraph at lines 225--229
\OT1/ptm/m/n/10 (+20) (Analytical[]Chemistry ) /Quantifying[]Nature /
[]
Underfull \hbox (badness 10000) in paragraph at lines 206--210
Underfull \hbox (badness 10000) in paragraph at lines 225--229
\OT1/ptm/m/n/10 (+20) Signi^^Lcant[]Digits / Propagation[]of[]Error$[][], (Ac-cessed:
[]
[4 <./featureImportanceDT.png> <./featureImportanceRF.png>]
[6
]
enddocument/afterlastpage: lastpage setting LastPage.
(./MLPproject.aux)
LaTeX Warning: There were multiply-defined labels.
Package rerunfilecheck Info: File `MLPproject.out' has not changed.
(rerunfilecheck) Checksum: EFC895524C82E0378E07184E5720AC35;2690.
(rerunfilecheck) Checksum: CAF78B736930E985EAD6848B8C813653;3852.
)
Here is how much of TeX's memory you used:
19072 strings out of 476041
322455 string characters out of 5793173
1876388 words of memory out of 6000000
38913 multiletter control sequences out of 15000+600000
571503 words of font info for 300 fonts, out of 8000000 for 9000
19092 strings out of 476041
322688 string characters out of 5793173
1878388 words of memory out of 6000000
38919 multiletter control sequences out of 15000+600000
571741 words of font info for 304 fonts, out of 8000000 for 9000
1137 hyphenation exceptions out of 8191
75i,12n,77p,1611b,605s stack positions out of 10000i,1000n,20000p,200000b,200000s
75i,13n,77p,1644b,605s stack positions out of 10000i,1000n,20000p,200000b,200000s
</usr/share/texlive/texmf-dist/fonts/type1/urw/helvetic/uhvb8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/helvetic/uhvr8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/helvetic/uhvro8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/times/utmb8a.pfb></usr/share/texlive/texmf-dist/fonts/type1/urw/times/utmr8a.pfb>
Output written on MLPproject.pdf (4 pages, 294157 bytes).
Output written on MLPproject.pdf (6 pages, 301321 bytes).
PDF statistics:
181 PDF objects out of 1000 (max. 8388607)
139 compressed objects within 2 object streams
28 named destinations out of 1000 (max. 500000)
98453 words of extra memory for PDF output out of 106986 (max. 10000000)
228 PDF objects out of 1000 (max. 8388607)
178 compressed objects within 2 object streams
36 named destinations out of 1000 (max. 500000)
98501 words of extra memory for PDF output out of 106986 (max. 10000000)

View File

@@ -5,12 +5,18 @@
\BOOKMARK [2][-]{subsection.2.3}{\376\377\000H\000a\000n\000d\000l\000i\000n\000g\000\040\000m\000i\000s\000s\000i\000n\000g\000\040\000v\000a\000l\000u\000e\000s}{section.2}% 5
\BOOKMARK [2][-]{subsection.2.4}{\376\377\000T\000r\000a\000i\000n\000i\000n\000g\000,\000\040\000v\000a\000l\000i\000d\000a\000t\000i\000o\000n\000\040\000a\000n\000d\000\040\000t\000e\000s\000t\000\040\000s\000e\000t\000s}{section.2}% 6
\BOOKMARK [1][-]{section.3}{\376\377\000M\000o\000d\000e\000l\000\040\000s\000e\000l\000e\000c\000t\000i\000o\000n}{}% 7
\BOOKMARK [1][-]{section.4}{\376\377\000M\000o\000d\000e\000l\000\040\000T\000r\000a\000i\000n\000i\000n\000g\000\040\000a\000n\000d\000\040\000H\000y\000p\000e\000r\000p\000a\000r\000a\000m\000e\000t\000e\000r\000\040\000T\000u\000n\000i\000n\000g}{}% 8
\BOOKMARK [1][-]{section.5}{\376\377\000M\000o\000d\000e\000l\000\040\000E\000v\000a\000l\000u\000a\000t\000i\000o\000n\000s}{}% 9
\BOOKMARK [2][-]{subsection.5.1}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000t\000h\000e\000\040\000C\000o\000n\000f\000u\000s\000i\000o\000n\000\040\000M\000a\000t\000r\000i\000c\000i\000e\000s}{section.5}% 10
\BOOKMARK [2][-]{subsection.5.2}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000W\000e\000i\000g\000h\000t\000e\000d\000\040\000P\000e\000r\000f\000o\000r\000m\000a\000n\000c\000e\000\040\000M\000e\000t\000r\000i\000c\000s}{section.5}% 11
\BOOKMARK [2][-]{subsection.5.3}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000t\000h\000e\000\040\000P\000e\000r\000f\000o\000r\000m\000a\000n\000c\000e}{section.5}% 12
\BOOKMARK [2][-]{subsection.5.4}{\376\377\000O\000v\000e\000r\000f\000i\000t\000t\000i\000n\000g\000\040\000a\000n\000d\000\040\000U\000n\000d\000e\000r\000f\000i\000t\000t\000i\000n\000g}{section.5}% 13
\BOOKMARK [2][-]{subsection.5.5}{\376\377\000F\000e\000a\000t\000u\000r\000e\000\040\000I\000m\000p\000o\000r\000t\000a\000n\000c\000e}{section.5}% 14
\BOOKMARK [1][-]{section.6}{\376\377\000S\000u\000m\000m\000a\000r\000y}{}% 15
\BOOKMARK [1][-]{section.6}{\376\377\000R\000e\000f\000e\000r\000e\000n\000c\000e\000s}{}% 16
\BOOKMARK [2][-]{subsection.3.1}{\376\377\000D\000a\000t\000a\000\040\000c\000l\000e\000a\000n\000i\000n\000g\000\040\000a\000n\000d\000\040\000f\000e\000a\000t\000u\000r\000e\000\040\000e\000n\000g\000i\000n\000e\000e\000r\000i\000n\000g}{section.3}% 8
\BOOKMARK [2][-]{subsection.3.2}{\376\377\000H\000a\000n\000d\000l\000i\000n\000g\000\040\000m\000i\000s\000s\000i\000n\000g\000\040\000v\000a\000l\000u\000e\000s}{section.3}% 9
\BOOKMARK [2][-]{subsection.3.3}{\376\377\000T\000r\000a\000i\000n\000i\000n\000g\000,\000\040\000v\000a\000l\000i\000d\000a\000t\000i\000o\000n\000\040\000a\000n\000d\000\040\000t\000e\000s\000t\000\040\000s\000e\000t\000s}{section.3}% 10
\BOOKMARK [1][-]{section.4}{\376\377\000M\000o\000d\000e\000l\000\040\000s\000e\000l\000e\000c\000t\000i\000o\000n}{}% 11
\BOOKMARK [1][-]{section.5}{\376\377\000M\000o\000d\000e\000l\000\040\000T\000r\000a\000i\000n\000i\000n\000g\000\040\000a\000n\000d\000\040\000H\000y\000p\000e\000r\000p\000a\000r\000a\000m\000e\000t\000e\000r\000\040\000T\000u\000n\000i\000n\000g}{}% 12
\BOOKMARK [2][-]{subsection.5.1}{\376\377\000M\000o\000d\000e\000l\000s\000\040\000a\000n\000d\000\040\000m\000e\000t\000h\000o\000d\000s\000\040\000u\000s\000e\000d}{section.5}% 13
\BOOKMARK [2][-]{subsection.5.2}{\376\377\000C\000a\000v\000e\000a\000t\000s\000\040\000a\000n\000d\000\040\000r\000e\000s\000t\000r\000i\000c\000t\000i\000o\000n\000s}{section.5}% 14
\BOOKMARK [1][-]{section.6}{\376\377\000M\000o\000d\000e\000l\000\040\000E\000v\000a\000l\000u\000a\000t\000i\000o\000n\000s}{}% 15
\BOOKMARK [2][-]{subsection.6.1}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000t\000h\000e\000\040\000C\000o\000n\000f\000u\000s\000i\000o\000n\000\040\000M\000a\000t\000r\000i\000c\000i\000e\000s}{section.6}% 16
\BOOKMARK [2][-]{subsection.6.2}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000W\000e\000i\000g\000h\000t\000e\000d\000\040\000P\000e\000r\000f\000o\000r\000m\000a\000n\000c\000e\000\040\000M\000e\000t\000r\000i\000c\000s}{section.6}% 17
\BOOKMARK [2][-]{subsection.6.3}{\376\377\000A\000n\000a\000l\000y\000z\000i\000n\000g\000\040\000t\000h\000e\000\040\000P\000e\000r\000f\000o\000r\000m\000a\000n\000c\000e}{section.6}% 18
\BOOKMARK [2][-]{subsection.6.4}{\376\377\000O\000v\000e\000r\000f\000i\000t\000t\000i\000n\000g\000\040\000a\000n\000d\000\040\000U\000n\000d\000e\000r\000f\000i\000t\000t\000i\000n\000g}{section.6}% 19
\BOOKMARK [2][-]{subsection.6.5}{\376\377\000F\000e\000a\000t\000u\000r\000e\000\040\000I\000m\000p\000o\000r\000t\000a\000n\000c\000e}{section.6}% 20
\BOOKMARK [1][-]{section.7}{\376\377\000S\000u\000m\000m\000a\000r\000y}{}% 21
\BOOKMARK [1][-]{section.7}{\376\377\000R\000e\000f\000e\000r\000e\000n\000c\000e\000s}{}% 22

Binary file not shown.

Binary file not shown.

View File

@@ -3,16 +3,22 @@
\contentsline {section}{\numberline {2}Data analysis}{1}{section.2}%
\contentsline {subsection}{\numberline {2.1}Dataset}{1}{subsection.2.1}%
\contentsline {subsection}{\numberline {2.2}Data cleaning and feature engineering}{1}{subsection.2.2}%
\contentsline {subsection}{\numberline {2.3}Handling missing values}{1}{subsection.2.3}%
\contentsline {subsection}{\numberline {2.3}Handling missing values}{2}{subsection.2.3}%
\contentsline {subsection}{\numberline {2.4}Training, validation and test sets}{2}{subsection.2.4}%
\contentsline {section}{\numberline {3}Model selection}{2}{section.3}%
\contentsline {section}{\numberline {4}Model Training and Hyperparameter Tuning}{2}{section.4}%
\contentsline {section}{\numberline {5}Model Evaluations}{2}{section.5}%
\contentsline {subsection}{\numberline {5.1}Analyzing the Confusion Matricies}{2}{subsection.5.1}%
\contentsline {subsection}{\numberline {5.2}Analyzing Weighted Performance Metrics}{2}{subsection.5.2}%
\contentsline {subsection}{\numberline {5.3}Analyzing the Performance}{3}{subsection.5.3}%
\contentsline {subsection}{\numberline {5.4}Overfitting and Underfitting}{3}{subsection.5.4}%
\contentsline {subsection}{\numberline {5.5}Feature Importance}{4}{subsection.5.5}%
\contentsline {section}{\numberline {6}Summary}{4}{section.6}%
\contentsline {section}{References}{4}{section.6}%
\contentsline {subsection}{\numberline {3.1}Data cleaning and feature engineering}{2}{subsection.3.1}%
\contentsline {subsection}{\numberline {3.2}Handling missing values}{2}{subsection.3.2}%
\contentsline {subsection}{\numberline {3.3}Training, validation and test sets}{2}{subsection.3.3}%
\contentsline {section}{\numberline {4}Model selection}{2}{section.4}%
\contentsline {section}{\numberline {5}Model Training and Hyperparameter Tuning}{3}{section.5}%
\contentsline {subsection}{\numberline {5.1}Models and methods used}{3}{subsection.5.1}%
\contentsline {subsection}{\numberline {5.2}Caveats and restrictions}{3}{subsection.5.2}%
\contentsline {section}{\numberline {6}Model Evaluations}{3}{section.6}%
\contentsline {subsection}{\numberline {6.1}Analyzing the Confusion Matricies}{3}{subsection.6.1}%
\contentsline {subsection}{\numberline {6.2}Analyzing Weighted Performance Metrics}{4}{subsection.6.2}%
\contentsline {subsection}{\numberline {6.3}Analyzing the Performance}{5}{subsection.6.3}%
\contentsline {subsection}{\numberline {6.4}Overfitting and Underfitting}{5}{subsection.6.4}%
\contentsline {subsection}{\numberline {6.5}Feature Importance}{5}{subsection.6.5}%
\contentsfinish
\contentsline {section}{\numberline {7}Summary}{6}{section.7}%
\contentsline {section}{References}{6}{section.7}%