riset-teknologi-informasi/slide/slide-13-data-preprocessing.md

---
marp: true
paginate: true
class: bagian-iv
header: 'RTI — Riset Teknologi Informasi | Universitas Putra Bangsa Kebumen'
footer: 'Helmi Bahar Alim, S.Kom., M.Kom. | 2026'
---





<style>
/* UPB Theme (inline) */

/*
  ============================================================
  UPB MARP THEME — Riset Teknologi Informasi
  Universitas Putra Bangsa (UPB), Kebumen
  Fak. Sains & Teknologi | Prodi Teknik Informatika
  ------------------------------------------------------------
  Penggunaan di frontmatter slide:
    theme: upb
    class: bagian-ii          ← opsional; ganti warna Bagian
  
  Kelas per Bagian:
    (kosong / default) = Bagian I  — Biru   #2563EB
    bagian-ii          = Bagian II — Hijau  #059669
    bagian-iii         = Bagian III — Oranye #d97706
    bagian-iv          = Bagian IV — Ungu   #7c3aed

  Kelas layout khusus (gunakan via <!-- _class: ... -->):
    cover              = Cover / halaman judul
    section-header     = Pembatas antar-topik
    integrative        = Bab 8 (UTS — gradien biru-ungu)
    fullcircle         = Bab 16 penutup (gradien gelap)
  ============================================================
*/

/* ============================================================
   1. CSS CUSTOM PROPERTIES — DEFAULT (Bagian I · Biru)
   ============================================================ */
section {
  --accent:        #2563EB;
  --accent-dark:   #1e3a5f;
  --accent-light:  #eff6ff;
  --accent-border: #bfdbfe;
  --cover-grad:    linear-gradient(135deg, #1e3a5f 0%, #2563EB 100%);
  --cover-sub:     #bfdbfe;
  --cover-meta:    #93c5fd;

  font-family: 'Segoe UI', Arial, sans-serif;
  font-size: 1.1em;
  color: #1e293b;
  padding: 40px 60px;
}

/* ============================================================
   2. VARIAN WARNA PER BAGIAN
   ============================================================ */

/* Bagian II — Hijau */
section.bagian-ii {
  --accent:        #059669;
  --accent-dark:   #064e3b;
  --accent-light:  #ecfdf5;
  --accent-border: #a7f3d0;
  --cover-grad:    linear-gradient(135deg, #064e3b 0%, #059669 100%);
  --cover-sub:     #a7f3d0;
  --cover-meta:    #6ee7b7;
}

/* Bagian III — Oranye */
section.bagian-iii {
  --accent:        #d97706;
  --accent-dark:   #78350f;
  --accent-light:  #fffbeb;
  --accent-border: #fde68a;
  --cover-grad:    linear-gradient(135deg, #78350f 0%, #d97706 100%);
  --cover-sub:     #fde68a;
  --cover-meta:    #fcd34d;
}

/* Bagian IV — Ungu */
section.bagian-iv {
  --accent:        #7c3aed;
  --accent-dark:   #3b0764;
  --accent-light:  #f5f3ff;
  --accent-border: #ddd6fe;
  --cover-grad:    linear-gradient(135deg, #3b0764 0%, #7c3aed 100%);
  --cover-sub:     #ddd6fe;
  --cover-meta:    #c4b5fd;
}

/* ============================================================
   3. LAYOUT: COVER
   ============================================================ */
section.cover {
  background: var(--cover-grad);
  color: white;
  justify-content: center;
  text-align: center;
}

/* Logo dimuat dari CSS — tidak perlu tag img di markdown */
section.cover::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.cover h1 {
  color: white;
  font-size: 2em;
  margin-bottom: 8px;
  border-bottom: none;
}

section.cover h2 {
  color: var(--cover-sub);
  font-size: 1.1em;
  font-weight: normal;
}

section.cover p  { color: var(--cover-meta); font-size: 0.85em; }
section.cover strong { color: white; }

/* ============================================================
   4. LAYOUT: SECTION HEADER (pembatas topik)
   ============================================================ */
section.section-header {
  background: var(--accent);
  color: white;
  justify-content: center;
  text-align: center;
}

section.section-header h1 {
  color: white;
  font-size: 2.5em;
  border-bottom: none;
}

section.section-header h2 { color: rgba(255, 255, 255, 0.85); }

/* ============================================================
   5. LAYOUT: INTEGRATIVE (Bab 8 — UTS Checkpoint)
   ============================================================ */
section.integrative {
  background: linear-gradient(135deg, #1e3a5f 0%, #7c3aed 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.integrative::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.integrative h1 {
  color: white;
  font-size: 2.2em;
  border-bottom: none;
}

section.integrative h2   { color: #ddd6fe; font-size: 1.1em; }
section.integrative p    { color: #c4b5fd; font-size: 0.85em; }
section.integrative strong { color: white; }

/* ============================================================
   6. LAYOUT: FULLCIRCLE (Bab 16 — Penutup)
   ============================================================ */
section.fullcircle {
  background: linear-gradient(135deg, #1e293b 0%, #1e3a5f 50%, #1e293b 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.fullcircle h1 {
  color: #ddd6fe;
  font-size: 2.2em;
  border-bottom: 3px solid #7c3aed;
}

section.fullcircle blockquote {
  border-left: 5px solid #7c3aed;
  background: rgba(255, 255, 255, 0.08);
  color: #ddd6fe;
  font-style: italic;
}

/* ============================================================
   7. ELEMEN KONTEN — menggunakan CSS vars dari bagian
   ============================================================ */

h1 {
  color: var(--accent);
  border-bottom: 3px solid var(--accent);
  padding-bottom: 8px;
}

h2 { color: var(--accent-dark); font-size: 1.3em; }
h3 { color: var(--accent);      font-size: 1.05em; }

blockquote {
  border-left: 5px solid var(--accent);
  background: var(--accent-light);
  padding: 12px 20px;
  margin: 16px 0;
  color: var(--accent-dark);
  font-style: italic;
  border-radius: 0 8px 8px 0;
}

table { font-size: 0.82em; width: 100%; border-collapse: collapse; }
th    { background: var(--accent); color: white; padding: 8px 12px; }
td    { padding: 6px 12px; border-bottom: 1px solid var(--accent-border); }
tr:nth-child(even) td { background: var(--accent-light); }

code {
  background: var(--accent-light);
  color: var(--accent-dark);
  padding: 2px 6px;
  border-radius: 4px;
  font-size: 0.9em;
}

pre {
  background: #f1f5f9;
  color: #1e293b;
  padding: 16px;
  border-radius: 8px;
  border-left: 4px solid var(--accent-border);
}

ul li, ol li { margin-bottom: 6px; line-height: 1.6; }

/* ============================================================
   8. HELPER CLASSES
   ============================================================ */

/* Status / penekanan */
.warn  { color: #d97706; font-weight: bold; }
.good  { color: #059669; font-weight: bold; }
.bad   { color: #dc2626; font-weight: bold; }

/* Kotak pernyataan akhir */
.final {
  background: #fef3c7;
  border-left: 5px solid #d97706;
  padding: 14px 20px;
  border-radius: 0 8px 8px 0;
  font-size: 1.1em;
}

/* Kotak highlight */
.highlight-box {
  background: var(--accent);
  color: white;
  padding: 16px 20px;
  border-radius: 8px;
  margin: 12px 0;
}

/* Kotak checkpoint bab 8 */
.checkpoint {
  background: #f5f3ff;
  border: 2px solid #7c3aed;
  border-radius: 8px;
  padding: 16px 24px;
  margin: 16px 0;
}

/* ============================================================
   9. PAGINATION & HEADER/FOOTER
   ============================================================ */
section::after {
  font-size: 0.7em;
  color: #94a3b8;
}

section[data-marpit-advanced-background] > div:last-child { padding: 40px 60px; }
</style>

<style>
/* UPB Theme (inline) */

/*
  ============================================================
  UPB MARP THEME — Riset Teknologi Informasi
  Universitas Putra Bangsa (UPB), Kebumen
  Fak. Sains & Teknologi | Prodi Teknik Informatika
  ------------------------------------------------------------
  Penggunaan di frontmatter slide:
        class: bagian-ii          ← opsional; ganti warna Bagian
  
  Kelas per Bagian:
    (kosong / default) = Bagian I  — Biru   #2563EB
    bagian-ii          = Bagian II — Hijau  #059669
    bagian-iii         = Bagian III — Oranye #d97706
    bagian-iv          = Bagian IV — Ungu   #7c3aed

  Kelas layout khusus (gunakan via <!-- _class: ... -->):
    cover              = Cover / halaman judul
    section-header     = Pembatas antar-topik
    integrative        = Bab 8 (UTS — gradien biru-ungu)
    fullcircle         = Bab 16 penutup (gradien gelap)
  ============================================================
*/

/* ============================================================
   1. CSS CUSTOM PROPERTIES — DEFAULT (Bagian I · Biru)
   ============================================================ */
section {
  --accent:        #2563EB;
  --accent-dark:   #1e3a5f;
  --accent-light:  #eff6ff;
  --accent-border: #bfdbfe;
  --cover-grad:    linear-gradient(135deg, #1e3a5f 0%, #2563EB 100%);
  --cover-sub:     #bfdbfe;
  --cover-meta:    #93c5fd;

  font-family: 'Segoe UI', Arial, sans-serif;
  font-size: 1.1em;
  color: #1e293b;
  padding: 40px 60px;
}

/* ============================================================
   2. VARIAN WARNA PER BAGIAN
   ============================================================ */

/* Bagian II — Hijau */
section.bagian-ii {
  --accent:        #059669;
  --accent-dark:   #064e3b;
  --accent-light:  #ecfdf5;
  --accent-border: #a7f3d0;
  --cover-grad:    linear-gradient(135deg, #064e3b 0%, #059669 100%);
  --cover-sub:     #a7f3d0;
  --cover-meta:    #6ee7b7;
}

/* Bagian III — Oranye */
section.bagian-iii {
  --accent:        #d97706;
  --accent-dark:   #78350f;
  --accent-light:  #fffbeb;
  --accent-border: #fde68a;
  --cover-grad:    linear-gradient(135deg, #78350f 0%, #d97706 100%);
  --cover-sub:     #fde68a;
  --cover-meta:    #fcd34d;
}

/* Bagian IV — Ungu */
section.bagian-iv {
  --accent:        #7c3aed;
  --accent-dark:   #3b0764;
  --accent-light:  #f5f3ff;
  --accent-border: #ddd6fe;
  --cover-grad:    linear-gradient(135deg, #3b0764 0%, #7c3aed 100%);
  --cover-sub:     #ddd6fe;
  --cover-meta:    #c4b5fd;
}

/* ============================================================
   3. LAYOUT: COVER
   ============================================================ */
section.cover {
  background: var(--cover-grad);
  color: white;
  justify-content: center;
  text-align: center;
}

/* Logo dimuat dari CSS — tidak perlu tag img di markdown */
section.cover::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.cover h1 {
  color: white;
  font-size: 2em;
  margin-bottom: 8px;
  border-bottom: none;
}

section.cover h2 {
  color: var(--cover-sub);
  font-size: 1.1em;
  font-weight: normal;
}

section.cover p  { color: var(--cover-meta); font-size: 0.85em; }
section.cover strong { color: white; }

/* ============================================================
   4. LAYOUT: SECTION HEADER (pembatas topik)
   ============================================================ */
section.section-header {
  background: var(--accent);
  color: white;
  justify-content: center;
  text-align: center;
}

section.section-header h1 {
  color: white;
  font-size: 2.5em;
  border-bottom: none;
}

section.section-header h2 { color: rgba(255, 255, 255, 0.85); }

/* ============================================================
   5. LAYOUT: INTEGRATIVE (Bab 8 — UTS Checkpoint)
   ============================================================ */
section.integrative {
  background: linear-gradient(135deg, #1e3a5f 0%, #7c3aed 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.integrative::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.integrative h1 {
  color: white;
  font-size: 2.2em;
  border-bottom: none;
}

section.integrative h2   { color: #ddd6fe; font-size: 1.1em; }
section.integrative p    { color: #c4b5fd; font-size: 0.85em; }
section.integrative strong { color: white; }

/* ============================================================
   6. LAYOUT: FULLCIRCLE (Bab 16 — Penutup)
   ============================================================ */
section.fullcircle {
  background: linear-gradient(135deg, #1e293b 0%, #1e3a5f 50%, #1e293b 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.fullcircle h1 {
  color: #ddd6fe;
  font-size: 2.2em;
  border-bottom: 3px solid #7c3aed;
}

section.fullcircle blockquote {
  border-left: 5px solid #7c3aed;
  background: rgba(255, 255, 255, 0.08);
  color: #ddd6fe;
  font-style: italic;
}

/* ============================================================
   7. ELEMEN KONTEN — menggunakan CSS vars dari bagian
   ============================================================ */

h1 {
  color: var(--accent);
  border-bottom: 3px solid var(--accent);
  padding-bottom: 8px;
}

h2 { color: var(--accent-dark); font-size: 1.3em; }
h3 { color: var(--accent);      font-size: 1.05em; }

blockquote {
  border-left: 5px solid var(--accent);
  background: var(--accent-light);
  padding: 12px 20px;
  margin: 16px 0;
  color: var(--accent-dark);
  font-style: italic;
  border-radius: 0 8px 8px 0;
}

table { font-size: 0.82em; width: 100%; border-collapse: collapse; }
th    { background: var(--accent); color: white; padding: 8px 12px; }
td    { padding: 6px 12px; border-bottom: 1px solid var(--accent-border); }
tr:nth-child(even) td { background: var(--accent-light); }

code {
  background: var(--accent-light);
  color: var(--accent-dark);
  padding: 2px 6px;
  border-radius: 4px;
  font-size: 0.9em;
}

pre {
  background: #f1f5f9;
  color: #1e293b;
  padding: 16px;
  border-radius: 8px;
  border-left: 4px solid var(--accent-border);
}

ul li, ol li { margin-bottom: 6px; line-height: 1.6; }

/* ============================================================
   8. HELPER CLASSES
   ============================================================ */

/* Status / penekanan */
.warn  { color: #d97706; font-weight: bold; }
.good  { color: #059669; font-weight: bold; }
.bad   { color: #dc2626; font-weight: bold; }

/* Kotak pernyataan akhir */
.final {
  background: #fef3c7;
  border-left: 5px solid #d97706;
  padding: 14px 20px;
  border-radius: 0 8px 8px 0;
  font-size: 1.1em;
}

/* Kotak highlight */
.highlight-box {
  background: var(--accent);
  color: white;
  padding: 16px 20px;
  border-radius: 8px;
  margin: 12px 0;
}

/* Kotak checkpoint bab 8 */
.checkpoint {
  background: #f5f3ff;
  border: 2px solid #7c3aed;
  border-radius: 8px;
  padding: 16px 24px;
  margin: 16px 0;
}

/* ============================================================
   9. PAGINATION & HEADER/FOOTER
   ============================================================ */
section::after {
  font-size: 0.7em;
  color: #94a3b8;
}

section[data-marpit-advanced-background] > div:last-child { padding: 40px 60px; }
</style>

<style>
/* UPB Theme (inline) */

/*
  ============================================================
  UPB MARP THEME — Riset Teknologi Informasi
  Universitas Putra Bangsa (UPB), Kebumen
  Fak. Sains & Teknologi | Prodi Teknik Informatika
  ------------------------------------------------------------
  Penggunaan di frontmatter slide:
        class: bagian-ii          ← opsional; ganti warna Bagian
  
  Kelas per Bagian:
    (kosong / default) = Bagian I  — Biru   #2563EB
    bagian-ii          = Bagian II — Hijau  #059669
    bagian-iii         = Bagian III — Oranye #d97706
    bagian-iv          = Bagian IV — Ungu   #7c3aed

  Kelas layout khusus (gunakan via <!-- _class: ... -->):
    cover              = Cover / halaman judul
    section-header     = Pembatas antar-topik
    integrative        = Bab 8 (UTS — gradien biru-ungu)
    fullcircle         = Bab 16 penutup (gradien gelap)
  ============================================================
*/

/* ============================================================
   1. CSS CUSTOM PROPERTIES — DEFAULT (Bagian I · Biru)
   ============================================================ */
section {
  --accent:        #2563EB;
  --accent-dark:   #1e3a5f;
  --accent-light:  #eff6ff;
  --accent-border: #bfdbfe;
  --cover-grad:    linear-gradient(135deg, #1e3a5f 0%, #2563EB 100%);
  --cover-sub:     #bfdbfe;
  --cover-meta:    #93c5fd;

  font-family: 'Segoe UI', Arial, sans-serif;
  font-size: 1.1em;
  color: #1e293b;
  padding: 40px 60px;
}

/* ============================================================
   2. VARIAN WARNA PER BAGIAN
   ============================================================ */

/* Bagian II — Hijau */
section.bagian-ii {
  --accent:        #059669;
  --accent-dark:   #064e3b;
  --accent-light:  #ecfdf5;
  --accent-border: #a7f3d0;
  --cover-grad:    linear-gradient(135deg, #064e3b 0%, #059669 100%);
  --cover-sub:     #a7f3d0;
  --cover-meta:    #6ee7b7;
}

/* Bagian III — Oranye */
section.bagian-iii {
  --accent:        #d97706;
  --accent-dark:   #78350f;
  --accent-light:  #fffbeb;
  --accent-border: #fde68a;
  --cover-grad:    linear-gradient(135deg, #78350f 0%, #d97706 100%);
  --cover-sub:     #fde68a;
  --cover-meta:    #fcd34d;
}

/* Bagian IV — Ungu */
section.bagian-iv {
  --accent:        #7c3aed;
  --accent-dark:   #3b0764;
  --accent-light:  #f5f3ff;
  --accent-border: #ddd6fe;
  --cover-grad:    linear-gradient(135deg, #3b0764 0%, #7c3aed 100%);
  --cover-sub:     #ddd6fe;
  --cover-meta:    #c4b5fd;
}

/* ============================================================
   3. LAYOUT: COVER
   ============================================================ */
section.cover {
  background: var(--cover-grad);
  color: white;
  justify-content: center;
  text-align: center;
}

/* Logo dimuat dari CSS — tidak perlu tag img di markdown */
section.cover::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.cover h1 {
  color: white;
  font-size: 2em;
  margin-bottom: 8px;
  border-bottom: none;
}

section.cover h2 {
  color: var(--cover-sub);
  font-size: 1.1em;
  font-weight: normal;
}

section.cover p  { color: var(--cover-meta); font-size: 0.85em; }
section.cover strong { color: white; }

/* ============================================================
   4. LAYOUT: SECTION HEADER (pembatas topik)
   ============================================================ */
section.section-header {
  background: var(--accent);
  color: white;
  justify-content: center;
  text-align: center;
}

section.section-header h1 {
  color: white;
  font-size: 2.5em;
  border-bottom: none;
}

section.section-header h2 { color: rgba(255, 255, 255, 0.85); }

/* ============================================================
   5. LAYOUT: INTEGRATIVE (Bab 8 — UTS Checkpoint)
   ============================================================ */
section.integrative {
  background: linear-gradient(135deg, #1e3a5f 0%, #7c3aed 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.integrative::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.integrative h1 {
  color: white;
  font-size: 2.2em;
  border-bottom: none;
}

section.integrative h2   { color: #ddd6fe; font-size: 1.1em; }
section.integrative p    { color: #c4b5fd; font-size: 0.85em; }
section.integrative strong { color: white; }

/* ============================================================
   6. LAYOUT: FULLCIRCLE (Bab 16 — Penutup)
   ============================================================ */
section.fullcircle {
  background: linear-gradient(135deg, #1e293b 0%, #1e3a5f 50%, #1e293b 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.fullcircle h1 {
  color: #ddd6fe;
  font-size: 2.2em;
  border-bottom: 3px solid #7c3aed;
}

section.fullcircle blockquote {
  border-left: 5px solid #7c3aed;
  background: rgba(255, 255, 255, 0.08);
  color: #ddd6fe;
  font-style: italic;
}

/* ============================================================
   7. ELEMEN KONTEN — menggunakan CSS vars dari bagian
   ============================================================ */

h1 {
  color: var(--accent);
  border-bottom: 3px solid var(--accent);
  padding-bottom: 8px;
}

h2 { color: var(--accent-dark); font-size: 1.3em; }
h3 { color: var(--accent);      font-size: 1.05em; }

blockquote {
  border-left: 5px solid var(--accent);
  background: var(--accent-light);
  padding: 12px 20px;
  margin: 16px 0;
  color: var(--accent-dark);
  font-style: italic;
  border-radius: 0 8px 8px 0;
}

table { font-size: 0.82em; width: 100%; border-collapse: collapse; }
th    { background: var(--accent); color: white; padding: 8px 12px; }
td    { padding: 6px 12px; border-bottom: 1px solid var(--accent-border); }
tr:nth-child(even) td { background: var(--accent-light); }

code {
  background: var(--accent-light);
  color: var(--accent-dark);
  padding: 2px 6px;
  border-radius: 4px;
  font-size: 0.9em;
}

pre {
  background: #f1f5f9;
  color: #1e293b;
  padding: 16px;
  border-radius: 8px;
  border-left: 4px solid var(--accent-border);
}

ul li, ol li { margin-bottom: 6px; line-height: 1.6; }

/* ============================================================
   8. HELPER CLASSES
   ============================================================ */

/* Status / penekanan */
.warn  { color: #d97706; font-weight: bold; }
.good  { color: #059669; font-weight: bold; }
.bad   { color: #dc2626; font-weight: bold; }

/* Kotak pernyataan akhir */
.final {
  background: #fef3c7;
  border-left: 5px solid #d97706;
  padding: 14px 20px;
  border-radius: 0 8px 8px 0;
  font-size: 1.1em;
}

/* Kotak highlight */
.highlight-box {
  background: var(--accent);
  color: white;
  padding: 16px 20px;
  border-radius: 8px;
  margin: 12px 0;
}

/* Kotak checkpoint bab 8 */
.checkpoint {
  background: #f5f3ff;
  border: 2px solid #7c3aed;
  border-radius: 8px;
  padding: 16px 24px;
  margin: 16px 0;
}

/* ============================================================
   9. PAGINATION & HEADER/FOOTER
   ============================================================ */
section::after {
  font-size: 0.7em;
  color: #94a3b8;
}

section[data-marpit-advanced-background] > div:last-child { padding: 40px 60px; }
</style>

<style>
/* UPB Theme (inline) */

/*
  ============================================================
  UPB MARP THEME — Riset Teknologi Informasi
  Universitas Putra Bangsa (UPB), Kebumen
  Fak. Sains & Teknologi | Prodi Teknik Informatika
  ------------------------------------------------------------
  Penggunaan di frontmatter slide:
        class: bagian-ii          ← opsional; ganti warna Bagian
  
  Kelas per Bagian:
    (kosong / default) = Bagian I  — Biru   #2563EB
    bagian-ii          = Bagian II — Hijau  #059669
    bagian-iii         = Bagian III — Oranye #d97706
    bagian-iv          = Bagian IV — Ungu   #7c3aed

  Kelas layout khusus (gunakan via <!-- _class: ... -->):
    cover              = Cover / halaman judul
    section-header     = Pembatas antar-topik
    integrative        = Bab 8 (UTS — gradien biru-ungu)
    fullcircle         = Bab 16 penutup (gradien gelap)
  ============================================================
*/

/* ============================================================
   1. CSS CUSTOM PROPERTIES — DEFAULT (Bagian I · Biru)
   ============================================================ */
section {
  --accent:        #2563EB;
  --accent-dark:   #1e3a5f;
  --accent-light:  #eff6ff;
  --accent-border: #bfdbfe;
  --cover-grad:    linear-gradient(135deg, #1e3a5f 0%, #2563EB 100%);
  --cover-sub:     #bfdbfe;
  --cover-meta:    #93c5fd;

  font-family: 'Segoe UI', Arial, sans-serif;
  font-size: 1.1em;
  color: #1e293b;
  padding: 40px 60px;
}

/* ============================================================
   2. VARIAN WARNA PER BAGIAN
   ============================================================ */

/* Bagian II — Hijau */
section.bagian-ii {
  --accent:        #059669;
  --accent-dark:   #064e3b;
  --accent-light:  #ecfdf5;
  --accent-border: #a7f3d0;
  --cover-grad:    linear-gradient(135deg, #064e3b 0%, #059669 100%);
  --cover-sub:     #a7f3d0;
  --cover-meta:    #6ee7b7;
}

/* Bagian III — Oranye */
section.bagian-iii {
  --accent:        #d97706;
  --accent-dark:   #78350f;
  --accent-light:  #fffbeb;
  --accent-border: #fde68a;
  --cover-grad:    linear-gradient(135deg, #78350f 0%, #d97706 100%);
  --cover-sub:     #fde68a;
  --cover-meta:    #fcd34d;
}

/* Bagian IV — Ungu */
section.bagian-iv {
  --accent:        #7c3aed;
  --accent-dark:   #3b0764;
  --accent-light:  #f5f3ff;
  --accent-border: #ddd6fe;
  --cover-grad:    linear-gradient(135deg, #3b0764 0%, #7c3aed 100%);
  --cover-sub:     #ddd6fe;
  --cover-meta:    #c4b5fd;
}

/* ============================================================
   3. LAYOUT: COVER
   ============================================================ */
section.cover {
  background: var(--cover-grad);
  color: white;
  justify-content: center;
  text-align: center;
}

/* Logo dimuat dari CSS — tidak perlu tag img di markdown */
section.cover::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.cover h1 {
  color: white;
  font-size: 2em;
  margin-bottom: 8px;
  border-bottom: none;
}

section.cover h2 {
  color: var(--cover-sub);
  font-size: 1.1em;
  font-weight: normal;
}

section.cover p  { color: var(--cover-meta); font-size: 0.85em; }
section.cover strong { color: white; }

/* ============================================================
   4. LAYOUT: SECTION HEADER (pembatas topik)
   ============================================================ */
section.section-header {
  background: var(--accent);
  color: white;
  justify-content: center;
  text-align: center;
}

section.section-header h1 {
  color: white;
  font-size: 2.5em;
  border-bottom: none;
}

section.section-header h2 { color: rgba(255, 255, 255, 0.85); }

/* ============================================================
   5. LAYOUT: INTEGRATIVE (Bab 8 — UTS Checkpoint)
   ============================================================ */
section.integrative {
  background: linear-gradient(135deg, #1e3a5f 0%, #7c3aed 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.integrative::before {
  content: '';
  display: block;
  width: 90px;
  height: 90px;
  background: white url('theme/logo-upb.png') center / contain no-repeat;
  border-radius: 8px;
  padding: 6px;
  margin: 0 auto 14px;
  box-sizing: border-box;
}

section.integrative h1 {
  color: white;
  font-size: 2.2em;
  border-bottom: none;
}

section.integrative h2   { color: #ddd6fe; font-size: 1.1em; }
section.integrative p    { color: #c4b5fd; font-size: 0.85em; }
section.integrative strong { color: white; }

/* ============================================================
   6. LAYOUT: FULLCIRCLE (Bab 16 — Penutup)
   ============================================================ */
section.fullcircle {
  background: linear-gradient(135deg, #1e293b 0%, #1e3a5f 50%, #1e293b 100%);
  color: white;
  justify-content: center;
  text-align: center;
}

section.fullcircle h1 {
  color: #ddd6fe;
  font-size: 2.2em;
  border-bottom: 3px solid #7c3aed;
}

section.fullcircle blockquote {
  border-left: 5px solid #7c3aed;
  background: rgba(255, 255, 255, 0.08);
  color: #ddd6fe;
  font-style: italic;
}

/* ============================================================
   7. ELEMEN KONTEN — menggunakan CSS vars dari bagian
   ============================================================ */

h1 {
  color: var(--accent);
  border-bottom: 3px solid var(--accent);
  padding-bottom: 8px;
}

h2 { color: var(--accent-dark); font-size: 1.3em; }
h3 { color: var(--accent);      font-size: 1.05em; }

blockquote {
  border-left: 5px solid var(--accent);
  background: var(--accent-light);
  padding: 12px 20px;
  margin: 16px 0;
  color: var(--accent-dark);
  font-style: italic;
  border-radius: 0 8px 8px 0;
}

table { font-size: 0.82em; width: 100%; border-collapse: collapse; }
th    { background: var(--accent); color: white; padding: 8px 12px; }
td    { padding: 6px 12px; border-bottom: 1px solid var(--accent-border); }
tr:nth-child(even) td { background: var(--accent-light); }

code {
  background: var(--accent-light);
  color: var(--accent-dark);
  padding: 2px 6px;
  border-radius: 4px;
  font-size: 0.9em;
}

pre {
  background: #f1f5f9;
  color: #1e293b;
  padding: 16px;
  border-radius: 8px;
  border-left: 4px solid var(--accent-border);
}

ul li, ol li { margin-bottom: 6px; line-height: 1.6; }

/* ============================================================
   8. HELPER CLASSES
   ============================================================ */

/* Status / penekanan */
.warn  { color: #d97706; font-weight: bold; }
.good  { color: #059669; font-weight: bold; }
.bad   { color: #dc2626; font-weight: bold; }

/* Kotak pernyataan akhir */
.final {
  background: #fef3c7;
  border-left: 5px solid #d97706;
  padding: 14px 20px;
  border-radius: 0 8px 8px 0;
  font-size: 1.1em;
}

/* Kotak highlight */
.highlight-box {
  background: var(--accent);
  color: white;
  padding: 16px 20px;
  border-radius: 8px;
  margin: 12px 0;
}

/* Kotak checkpoint bab 8 */
.checkpoint {
  background: #f5f3ff;
  border: 2px solid #7c3aed;
  border-radius: 8px;
  padding: 16px 24px;
  margin: 16px 0;
}

/* ============================================================
   9. PAGINATION & HEADER/FOOTER
   ============================================================ */
section::after {
  font-size: 0.7em;
  color: #94a3b8;
}

section[data-marpit-advanced-background] > div:last-child { padding: 40px 60px; }
</style>

<!-- _class: cover bagian-iv -->


# Bab 13 — Data Preprocessing

## Mengubah Data Mentah menjadi Siap Analisis

*Pertemuan 13 (M13) &nbsp;|&nbsp; Sub-CPMK 4.2 &nbsp;|&nbsp; CPMK04 &nbsp;|&nbsp; CPL07*

Fase: **Analyzing & Communicating** (M12–M16) &nbsp;·&nbsp; Bagian IV

**Universitas Putra Bangsa** &nbsp;|&nbsp; Fak. Sains & Teknologi &nbsp;·&nbsp; Prodi Teknik Informatika

---

## Agenda Pertemuan 13

1. Preprocessing vs Validasi — perbedaan yang kritis
2. Data Refinement Pipeline
3. Data Cleaning — missing values, duplikat, error
4. Data Transformation — encoding, agregasi, feature creation
5. Normalization & Scaling
6. Empat Prinsip Preprocessing
7. Cognitive Traps & Studi Kasus
8. Output Praktis: Dataset Bersih + Dokumentasi Preprocessing

---

## Capaian Pembelajaran

Setelah pertemuan ini, mahasiswa mampu:

- Membedakan **validasi data** (Bab 11) vs **preprocessing data** (Bab 13)
- Menerapkan teknik **data cleaning**: missing values, duplikat, outlier handling
- Melakukan **transformasi data** yang sesuai (encoding, normalisasi, agregasi)
- Mendokumentasikan setiap langkah preprocessing untuk **reproduksi**
- Menerapkan **4 prinsip preprocessing** agar tidak memperkenalkan bias

> Sub-CPMK 4.2 → Melakukan preprocessing data untuk analisis (CPL07)

---

## Data Refinement Pipeline

*Dari data tervalidasi hingga siap dianalisis*

<div class="highlight-box">

**Raw Data Tervalidasi** (Bab 11) &darr; Cleaning (hapus noise, missing, duplikat) &darr; Transformation (ubah format/representasi) &darr; Normalization (sesuaikan skala/distribusi) &darr; **Processed Data** &darr; Analysis Ready (input Bab 14)

</div>

> **Prinsip fundamental:** Preprocessing harus **dapat direproduksi** dan **terdokumentasi**. Tidak boleh ada langkah yang dilakukan tanpa jejak.

---

## Validasi vs Preprocessing — Garis yang Jelas

*Perbedaan yang sering tertukar*

| Aspek | Validasi (Bab 11) | Preprocessing (Bab 13) |
|-------|-----------------|----------------------|
| **Tujuan** | Memastikan data benar | Mempersiapkan data untuk analisis |
| **Pertanyaan** | "Apakah data ini valid?" | "Bagaimana mengoptimalkan data untuk analisis?" |
| **Tindakan** | Identifikasi masalah + keputusan | Transformasi + normalisasi |
| **Output** | Dataset valid + catatan anomali | Dataset siap analisis |
| **Urutan** | **Pertama** | **Kedua** (setelah validasi) |

> Jika preprocessing dilakukan sebelum validasi → kita mungkin "memperbaiki" data yang seharusnya diinvestigasi lebih lanjut.

---

## Data Cleaning — Tiga Masalah Utama

### 1. Missing Values
```python
# Identifikasi
print(df.isnull().sum())

# Strategi penanganan (pilih berdasarkan konteks):
# a. Drop baris jika jumlah kecil dan tidak sistemik
df.dropna(subset=['f1_micro'], inplace=True)

# b. Impute dengan mean (hanya untuk data kontinu, non-kritis)
df['time_sec'].fillna(df['time_sec'].mean(), inplace=True)

# c. Flag sebagai missing category (untuk data kategoris)
df['hardware'].fillna('unknown', inplace=True)
```

### 2. Duplikat (run yang ter-log dua kali)
```python
df.drop_duplicates(subset=['run_id'], keep='first', inplace=True)
```

### 3. Format Error (nilai "N/A" teks di kolom numerik)
```python
df['time_sec'] = pd.to_numeric(df['time_sec'], errors='coerce')
```

---

## Data Transformation

*Mengubah representasi data untuk memudahkan analisis*

### Encoding Variabel Kategoris
```python
# Label encoding (untuk variabel ordinal)
scenario_map = {'baseline': 0, '+attention': 1, '+ensemble': 2}
df['scenario_code'] = df['scenario'].map(scenario_map)

# One-hot encoding (untuk variabel nominal, tanpa urutan)
df_encoded = pd.get_dummies(df, columns=['hardware'])
```

### Agregasi
```python
# Hitung statistik per skenario (dari 10 run ke 1 baris per skenario)
summary = df.groupby('scenario').agg({
    'f1_micro': ['mean', 'std', 'min', 'max'],
    'time_sec': ['mean', 'std']
}).round(4)
```

---

## Normalization & Scaling

*Mengapa diperlukan dan kapan digunakan*

| Teknik | Formula | Kapan Digunakan |
|--------|---------|----------------|
| Min-Max Normalization | $x' = \frac{x - x_{min}}{x_{max} - x_{min}}$ | Ketika distribusi tidak diketahui, butuh skala [0,1] |
| Z-Score Standardization | $z = \frac{x - \mu}{\sigma}$ | Ketika data asumsi distribusi normal, ML yang sensitif skala |
| Log Transformation | $x' = \log(x)$ | Data sangat skewed (mis. execution time) |
| Robust Scaling | $x' = \frac{x - Q2}{Q3 - Q1}$ | Ada outlier yang tidak bisa dibuang |

> **Penting:** Fit scaler HANYA pada training data, apply ke test data. Jangan fit pada seluruh dataset → data leakage!

---

## Empat Prinsip Preprocessing

*Standar yang membedakan preprocessing ilmiah dari ad-hoc*

**1. Consistency** — Terapkan langkah yang sama persis ke semua skenario
```python
# Satu fungsi preprocessing, dipanggil untuk setiap skenario
def preprocess(df): return pipeline.fit_transform(df)
```

**2. Transparency** — Setiap langkah terdokumentasi dengan alasan
```
[STEP-01] Normalisasi waktu eksekusi dengan log transform.
          Alasan: distribusi sangat right-skewed (skewness=4.3).
```

**3. Reproducibility** — Simpan pipeline sebagai kode, bukan manual
```python
joblib.dump(pipeline, 'preprocessing_pipeline.pkl')
```

**4. Minimal Distortion** — Jangan hapus karakteristik penting dari data
> Normalisasi boleh mengubah skala, tidak boleh mengubah urutan atau hubungan relatif.

---

<!-- _class: section-header bagian-iv -->

# Cognitive Traps
## Bab 13 — Data Preprocessing

---

## Cognitive Traps — Bab 13

**"Preprocessing dilakukan dulu sebelum memahami data"**
Preprocessing tanpa pemahaman konteks dapat memperkenalkan bias yang tidak disadari. Selalu lakukan exploratory analysis terlebih dahulu, baru tentukan preprocessing yang tepat.

**"Normalisasi selalu diperlukan"**
Beberapa algoritma (decision tree, random forest) tidak sensitif terhadap skala. Normalisasi tidak selalu meningkatkan performa. Pilih berdasarkan kebutuhan algoritma, bukan habit.

**"Data leakage tidak masalah karena kita tahu hasilnya"**
Data leakage (fit scaler pada entire dataset termasuk test) adalah invalidasi hasil yang fundamental. Hasil yang tinggi karena data leakage bukan prestasi — itu artifact.

**"Langkah preprocessing tidak perlu didokumentasikan satu per satu"**
Jika preprocessing tidak terdokumentasi, penelitian tidak dapat direproduksi. Penelitian yang tidak dapat direproduksi tidak dapat diverifikasi. Ini adalah standar minimum publikasi ilmiah.

---

## Studi Kasus 1 — Data Leakage (Basic)

**Konteks:** Mahasiswa melakukan normalisasi sebelum train/test split.

```python
# Data Leakage
from sklearn.preprocessing import StandardScaler

scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)  # Fit pada SEMUA data, termasuk test!

X_train, X_test = train_test_split(X_scaled, test_size=0.2)

# Masalah: scaler telah "melihat" test data → test data tidak independen lagi
```

```python
# Benar
from sklearn.preprocessing import StandardScaler
from sklearn.pipeline import Pipeline

X_train, X_test = train_test_split(X, test_size=0.2)

scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)   # Fit HANYA pada training
X_test_scaled  = scaler.transform(X_test)        # Transform saja test data
```

---

## Studi Kasus 2 — Inconsistent Preprocessing (Advanced)

**Konteks:** Researcher membandingkan Model A dan Model B. 

**Masalah:**
- Model A: preprocessing dengan normalisasi Min-Max
- Model B: preprocessing dengan standardisasi Z-score 
- Kedua model dibandingkan sebagai "perbandingan arsitektur"

**Tapi preprocessing yang berbeda = bukan hanya arsitektur yang berbeda!**

Model B mungkin lebih baik bukan karena arsitekturnya, tapi karena Z-score lebih cocok dengan distribusi data ini.

**Solusi:**
1. Tentukan satu pipeline preprocessing yang sama untuk semua model yang dibandingkan
2. Jika ingin membandingkan teknik preprocessing → buat itu sebagai variabel eksperimen eksplisit

---

## Dokumentasi Preprocessing

*Format standar yang harus ada dalam laporan*

```
PREPROCESSING DOCUMENTATION

Dataset: exp03_summary_validated.csv (setelah validasi Bab 11)
Tanggal preprocessing: 2026-05-05
Peneliti: [Nama]

LANGKAH PREPROCESSING:

[STEP-01] Log transform pada kolom 'time_sec'
  Alasan: skewness = 4.3 (right-skewed). Log transform menurunkan ke 0.8.
  Kode: df['time_sec'] = np.log1p(df['time_sec'])

[STEP-02] One-hot encoding pada kolom 'scenario'  
  Alasan: variabel nominal (tidak ada urutan).
  Output: 3 kolom dummy (attendance_baseline, +attention, +ensemble)

[STEP-03] Min-Max normalization pada seluruh fitur numerik
  Alasan: SVM dan neural network sensitif terhadap skala.
  Penting: Scaler di-fit HANYA pada training fold (cross-validation).

OUTPUT: exp03_processed.csv + preprocessing_pipeline.pkl
```

---

## Ringkasan Pertemuan 13

| Konsep | Inti |
|--------|------|
| Preprocessing vs Validasi | Validasi dulu (cek kebenaran), preprocessing kemudian (siapkan analisis) |
| Cleaning | Missing (drop/impute/flag) + Duplikat + Format Error |
| Transformation | Encoding kategoris + Agregasi runs → per-skenario |
| Normalization | Min-Max/Z-score/Log/Robust sesuai konteks + hindari data leakage |
| 4 Prinsip | Consistency · Transparency · Reproducibility · Minimal Distortion |

---

## Final Statement & Output Praktis

<div class="final">
"Preprocessing yang tidak terdokumentasi adalah black box — tidak ada yang bisa memverifikasi apakah transformasi yang dilakukan valid atau tidak, termasuk penelitinya sendiri setelah 6 bulan."
</div>

### Output Praktis M13

Kumpulkan:

1. **Dataset bersih** (`exp_processed.csv` — siap untuk analisis)
2. **Preprocessing pipeline** (kode Python / file `.pkl`)
3. **Dokumentasi preprocessing** (format [STEP-XX] lengkap dengan alasan)

---

## Referensi Utama — Bab 13

- Famili, A., Shen, W. M., Weber, R., & Simoudis, E. (1997). Data preprocessing and intelligent data analysis. *Intelligent Data Analysis, 1*(1), 3–23.

- Garcia, S., Luengo, J., & Herrera, F. (2015). *Data preprocessing in data mining*. Springer.

- Kaufman, S., Rosset, S., Perlich, C., & Stitelman, O. (2012). Leakage in data mining: Formulation, detection, and avoidance. *ACM Transactions on Knowledge Discovery from Data, 6*(4), 1–21.

- Géron, A. (2022). *Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow* (3rd ed.). O'Reilly Media.