394 lines
15 KiB
Plaintext
394 lines
15 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "JVPdWpz3hhbj"
|
|
},
|
|
"source": [
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "4Mvva3v65h1v"
|
|
},
|
|
"source": [
|
|
"# **UNIGRAM**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {
|
|
"id": "1cub_VJnUJMl",
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"outputId": "a712acbd-01e2-4c9e-f2c0-d7d33f3bc9fb"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Corpus: Jangan pernah berhenti belajar, karena hidup tak pernah berhenti mengajarkan\n",
|
|
"Tokens (10): ['jangan', 'pernah', 'berhenti', 'belajar,', 'karena', 'hidup', 'tak', 'pernah', 'berhenti', 'mengajarkan']\n",
|
|
"\n",
|
|
"Frekuensi Unigram dalam kalimat\n",
|
|
" ('jangan'): 1\n",
|
|
" ('pernah'): 2\n",
|
|
" ('berhenti'): 2\n",
|
|
" ('belajar,'): 1\n",
|
|
" ('karena'): 1\n",
|
|
" ('hidup'): 1\n",
|
|
" ('tak'): 1\n",
|
|
" ('mengajarkan'): 1\n",
|
|
"\n",
|
|
"Total unigram dalam 1 kalimat: 10\n",
|
|
"\n",
|
|
"Probabilitas masing-masing unigram:\n",
|
|
" P(jangan) = 0.10 (10.00%)\n",
|
|
" P(pernah) = 0.20 (20.00%)\n",
|
|
" P(berhenti) = 0.20 (20.00%)\n",
|
|
" P(belajar,) = 0.10 (10.00%)\n",
|
|
" P(karena) = 0.10 (10.00%)\n",
|
|
" P(hidup) = 0.10 (10.00%)\n",
|
|
" P(tak) = 0.10 (10.00%)\n",
|
|
" P(mengajarkan) = 0.10 (10.00%)\n",
|
|
"\n",
|
|
"Probabilitas Keseluruhan Kalimat (Model Unigram):\n",
|
|
" P(jangan pernah berhenti belajar, karena hidup tak pernah berhenti mengajarkan) = P(jangan)=0.10 x P(pernah)=0.20 x P(berhenti)=0.20 x P(belajar,)=0.10 x P(karena)=0.10 x P(hidup)=0.10 x P(tak)=0.10 x P(pernah)=0.20 x P(berhenti)=0.20 x P(mengajarkan)=0.10 = 0.0000 (0.00%)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from collections import Counter\n",
|
|
"from IPython.display import clear_output\n",
|
|
"import math\n",
|
|
"\n",
|
|
"# 1. Input Kalimat dan Tokenisasi\n",
|
|
"kalimat = input(\"Masukkan kalimat: Jangan pernah berhenti belajar, karena hidup tak pernah berhenti mengajarkan \").strip()\n",
|
|
"\n",
|
|
"# Bersihkan output (khusus lingkungan notebook)\n",
|
|
"try:\n",
|
|
" clear_output()\n",
|
|
"except:\n",
|
|
" pass\n",
|
|
"\n",
|
|
"print(f\"Corpus: {kalimat}\")\n",
|
|
"\n",
|
|
"# Tokenize\n",
|
|
"tokens = kalimat.lower().split()\n",
|
|
"print(f\"Tokens ({len(tokens)}): {tokens}\")\n",
|
|
"\n",
|
|
"# 2. Hitung Frekuensi Unigram\n",
|
|
"unigram_counts = Counter(tokens)\n",
|
|
"total_tokens = sum(unigram_counts.values())\n",
|
|
"\n",
|
|
"print(\"\\nFrekuensi Unigram dalam kalimat\")\n",
|
|
"for pair, count in unigram_counts.items():\n",
|
|
" print(f\" ('{pair}'): {count}\")\n",
|
|
"print(f\"\\nTotal unigram dalam 1 kalimat: {total_tokens}\")\n",
|
|
"\n",
|
|
"# 3. Hitung Probabilitas Unigram: P(wi) = Count(wi) / Total Kata\n",
|
|
"unigram_probabilities = {}\n",
|
|
"for word, count in unigram_counts.items():\n",
|
|
" prob = count / total_tokens\n",
|
|
" unigram_probabilities[word] = prob\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas masing-masing unigram:\")\n",
|
|
"for word, prob in unigram_probabilities.items():\n",
|
|
" print(f\" P({word}) = {prob:.2f} ({prob*100:.2f}%)\")\n",
|
|
"\n",
|
|
"# 4. Hitung Probabilitas Kalimat Keseluruhan (P(kalimat) = P(w1) * P(w2) * ...)\n",
|
|
"p_kalimat = 1\n",
|
|
"prob_parts = []\n",
|
|
"\n",
|
|
"# Loop untuk menghitung probabilitas total dan membangun string rumus detail\n",
|
|
"for word in tokens:\n",
|
|
" prob_value = unigram_probabilities[word]\n",
|
|
" p_kalimat *= prob_value\n",
|
|
" # Format: P(word)=prob_value\n",
|
|
" prob_parts.append(f\"P({word})={prob_value:.2f}\")\n",
|
|
"\n",
|
|
"# Gabungkan bagian-bagian rumus untuk mendapatkan prob_str detail\n",
|
|
"prob_str = \" x \".join(prob_parts)\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas Keseluruhan Kalimat (Model Unigram):\")\n",
|
|
"print(f\" P({' '.join(tokens)}) = {prob_str} = {p_kalimat:.4f} ({p_kalimat*100:.2f}%)\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "Vstwt996-FrS"
|
|
},
|
|
"source": [
|
|
"# **BIGRAM**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "XRIY4qgTVbjl",
|
|
"outputId": "4eff35ea-8a13-4b4a-fd8f-e0f3518c1add"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Corpus: ilmu adalah cahaya, dan belajar adalah menyalakan lentera dalam kegelapan\n",
|
|
"Tokens (10): ['ilmu', 'adalah', 'cahaya,', 'dan', 'belajar', 'adalah', 'menyalakan', 'lentera', 'dalam', 'kegelapan']\n",
|
|
"\n",
|
|
"Frekuensi Bigram dalam kalimat:\n",
|
|
" ('ilmu', 'adalah'): 1\n",
|
|
" ('adalah', 'cahaya,'): 1\n",
|
|
" ('cahaya,', 'dan'): 1\n",
|
|
" ('dan', 'belajar'): 1\n",
|
|
" ('belajar', 'adalah'): 1\n",
|
|
" ('adalah', 'menyalakan'): 1\n",
|
|
" ('menyalakan', 'lentera'): 1\n",
|
|
" ('lentera', 'dalam'): 1\n",
|
|
" ('dalam', 'kegelapan'): 1\n",
|
|
"\n",
|
|
"Total bigram dalam 1 kalimat: 9\n",
|
|
"\n",
|
|
"Probabilitas masing-masing bigram:\n",
|
|
" P(adalah|ilmu) = 1.00 (100.00%)\n",
|
|
" P(cahaya,|adalah) = 0.50 (50.00%)\n",
|
|
" P(dan|cahaya,) = 1.00 (100.00%)\n",
|
|
" P(belajar|dan) = 1.00 (100.00%)\n",
|
|
" P(adalah|belajar) = 1.00 (100.00%)\n",
|
|
" P(menyalakan|adalah) = 0.50 (50.00%)\n",
|
|
" P(lentera|menyalakan) = 1.00 (100.00%)\n",
|
|
" P(dalam|lentera) = 1.00 (100.00%)\n",
|
|
" P(kegelapan|dalam) = 1.00 (100.00%)\n",
|
|
"\n",
|
|
"Probabilitas Keseluruhan Kalimat (Model Bigram):\n",
|
|
" P(ilmu adalah cahaya, dan belajar adalah menyalakan lentera dalam kegelapan) = P(ilmu)=0.10 x P(adalah|ilmu)=1.00 x P(cahaya,|adalah)=0.50 x P(dan|cahaya,)=1.00 x P(belajar|dan)=1.00 x P(adalah|belajar)=1.00 x P(menyalakan|adalah)=0.50 x P(lentera|menyalakan)=1.00 x P(dalam|lentera)=1.00 x P(kegelapan|dalam)=1.00 = 0.025000 (2.50%)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from collections import Counter\n",
|
|
"from IPython.display import clear_output\n",
|
|
"import math\n",
|
|
"\n",
|
|
"# 1. Input Kalimat dan Tokenisasi\n",
|
|
"kalimat = input(\"Masukkan kalimat: Ilmu adalah cahaya, dan belajar adalah menyalakan lentera dalam kegelapan \").strip()\n",
|
|
"\n",
|
|
"# Bersihkan output (khusus lingkungan notebook)\n",
|
|
"try:\n",
|
|
" clear_output()\n",
|
|
"except:\n",
|
|
" pass\n",
|
|
"\n",
|
|
"print(f\"Corpus: {kalimat}\")\n",
|
|
"\n",
|
|
"# Tokenisasi\n",
|
|
"tokens = kalimat.lower().split()\n",
|
|
"print(f\"Tokens ({len(tokens)}): {tokens}\")\n",
|
|
"\n",
|
|
"# 2. Hitung Frekuensi Unigram dan Bigram\n",
|
|
"unigram_counts = Counter(tokens)\n",
|
|
"bigrams = [(tokens[i], tokens[i+1]) for i in range(len(tokens) - 1)]\n",
|
|
"bigram_counts = Counter(bigrams)\n",
|
|
"\n",
|
|
"print(\"\\nFrekuensi Bigram dalam kalimat:\")\n",
|
|
"for pair, count in bigram_counts.items():\n",
|
|
" print(f\" {pair}: {count}\")\n",
|
|
"print(f\"\\nTotal bigram dalam 1 kalimat: {sum(bigram_counts.values())}\")\n",
|
|
"\n",
|
|
"# 3. Hitung Probabilitas Bigram: P(w2 | w1) = Count(w1,w2) / Count(w1)\n",
|
|
"bigram_probabilities = {}\n",
|
|
"for (w1, w2), count in bigram_counts.items():\n",
|
|
" prob = count / unigram_counts[w1]\n",
|
|
" bigram_probabilities[(w1, w2)] = prob\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas masing-masing bigram:\")\n",
|
|
"for (w1, w2), prob in bigram_probabilities.items():\n",
|
|
" print(f\" P({w2}|{w1}) = {prob:.2f} ({prob*100:.2f}%)\")\n",
|
|
"\n",
|
|
"# 4. Hitung Probabilitas Kalimat Keseluruhan (Model Bigram)\n",
|
|
"# P(kalimat) = P(w1) * P(w2|w1) * P(w3|w2) * ...\n",
|
|
"total_tokens = sum(unigram_counts.values())\n",
|
|
"p_w1 = unigram_counts.get(tokens[0], 0) / total_tokens # P(w1)\n",
|
|
"p_kalimat = p_w1 # Inisialisasi dengan P(w1)\n",
|
|
"\n",
|
|
"prob_str_parts = [f\"P({tokens[0]})={p_w1:.2f}\"] # Tambahkan P(w1) ke rumus\n",
|
|
"\n",
|
|
"for i in range(1, len(tokens)):\n",
|
|
" pair = (tokens[i-1], tokens[i])\n",
|
|
" p = bigram_probabilities.get(pair, 0)\n",
|
|
" p_kalimat *= p\n",
|
|
" prob_str_parts.append(f\"P({pair[1]}|{pair[0]})={p:.2f}\")\n",
|
|
"\n",
|
|
"# Gabungkan rumus perkalian untuk ditampilkan\n",
|
|
"prob_str = \" x \".join(prob_str_parts)\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas Keseluruhan Kalimat (Model Bigram):\")\n",
|
|
"print(f\" P({' '.join(tokens)}) = {prob_str} = {p_kalimat:.6f} ({p_kalimat*100:.2f}%)\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "E6n1IU8X-G9S"
|
|
},
|
|
"source": [
|
|
"# **TRIGRAM**"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {
|
|
"colab": {
|
|
"base_uri": "https://localhost:8080/"
|
|
},
|
|
"id": "BIRARsj2FHJg",
|
|
"outputId": "6e09b998-b787-4c91-a710-57a809bf2223"
|
|
},
|
|
"outputs": [
|
|
{
|
|
"output_type": "stream",
|
|
"name": "stdout",
|
|
"text": [
|
|
"Corpus: belajar adalah kunci membuka pintu kesuksesan\n",
|
|
"Tokens (6): ['belajar', 'adalah', 'kunci', 'membuka', 'pintu', 'kesuksesan']\n",
|
|
"\n",
|
|
"Frekuensi Trigram dalam kalimat:\n",
|
|
" ('belajar', 'adalah', 'kunci'): 1\n",
|
|
" ('adalah', 'kunci', 'membuka'): 1\n",
|
|
" ('kunci', 'membuka', 'pintu'): 1\n",
|
|
" ('membuka', 'pintu', 'kesuksesan'): 1\n",
|
|
"\n",
|
|
"Total trigram dalam 1 kalimat: 4\n",
|
|
"\n",
|
|
"Probabilitas masing-masing trigram:\n",
|
|
" P(kunci|belajar,adalah) = 1.00 (100.00%)\n",
|
|
" P(membuka|adalah,kunci) = 1.00 (100.00%)\n",
|
|
" P(pintu|kunci,membuka) = 1.00 (100.00%)\n",
|
|
" P(kesuksesan|membuka,pintu) = 1.00 (100.00%)\n",
|
|
"\n",
|
|
"Probabilitas Keseluruhan Kalimat (Model Trigram):\n",
|
|
" P(belajar adalah kunci membuka pintu kesuksesan) = P(belajar)=0.17 x P(adalah|belajar)=1.00 x P(kunci|belajar,adalah)=1.00 x P(membuka|adalah,kunci)=1.00 x P(pintu|kunci,membuka)=1.00 x P(kesuksesan|membuka,pintu)=1.00 = 0.166667 (16.67%)\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from collections import Counter\n",
|
|
"from IPython.display import clear_output\n",
|
|
"import math\n",
|
|
"\n",
|
|
"# 1. Input Kalimat dan Tokenisasi\n",
|
|
"kalimat = input(\"Masukkan kalimat: Belajar adalah kunci membuka pintu kesuksesan\").strip()\n",
|
|
"\n",
|
|
"# Bersihkan output (khusus lingkungan notebook)\n",
|
|
"try:\n",
|
|
" clear_output()\n",
|
|
"except:\n",
|
|
" pass\n",
|
|
"\n",
|
|
"print(f\"Corpus: {kalimat}\")\n",
|
|
"\n",
|
|
"# Tokenisasi\n",
|
|
"tokens = kalimat.lower().split()\n",
|
|
"print(f\"Tokens ({len(tokens)}): {tokens}\")\n",
|
|
"\n",
|
|
"# 2. Hitung Frekuensi Bigram dan Trigram\n",
|
|
"bigrams = [(tokens[i], tokens[i+1]) for i in range(len(tokens) - 1)]\n",
|
|
"trigrams = [(tokens[i], tokens[i+1], tokens[i+2]) for i in range(len(tokens) - 2)]\n",
|
|
"\n",
|
|
"bigram_counts = Counter(bigrams)\n",
|
|
"trigram_counts = Counter(trigrams)\n",
|
|
"\n",
|
|
"print(\"\\nFrekuensi Trigram dalam kalimat:\")\n",
|
|
"for tg, count in trigram_counts.items():\n",
|
|
" print(f\" {tg}: {count}\")\n",
|
|
"print(f\"\\nTotal trigram dalam 1 kalimat: {sum(trigram_counts.values())}\")\n",
|
|
"\n",
|
|
"# 3. Hitung Probabilitas Trigram: P(w3 | w1, w2) = Count(w1,w2,w3) / Count(w1,w2)\n",
|
|
"trigram_probabilities = {}\n",
|
|
"for (w1, w2, w3), count in trigram_counts.items():\n",
|
|
" # Hindari pembagian dengan nol (jika ada bigram yang tidak muncul)\n",
|
|
" if bigram_counts[(w1, w2)] > 0:\n",
|
|
" prob = count / bigram_counts[(w1, w2)]\n",
|
|
" else:\n",
|
|
" prob = 0\n",
|
|
" trigram_probabilities[(w1, w2, w3)] = prob\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas masing-masing trigram:\")\n",
|
|
"for (w1, w2, w3), prob in trigram_probabilities.items():\n",
|
|
" print(f\" P({w3}|{w1},{w2}) = {prob:.2f} ({prob*100:.2f}%)\")\n",
|
|
"\n",
|
|
"# Tambahkan perhitungan Unigram Count (dibutuhkan untuk P(w1) dan P(w2|w1))\n",
|
|
"unigram_counts = Counter(tokens)\n",
|
|
"total_tokens = sum(unigram_counts.values())\n",
|
|
"\n",
|
|
"# 4. Hitung Probabilitas Kalimat Keseluruhan (Model Trigram)\n",
|
|
"# P(kalimat) = P(w1) * P(w2|w1) * P(w3|w1,w2) * ...\n",
|
|
"\n",
|
|
"# a. P(w1)\n",
|
|
"p_w1 = unigram_counts.get(tokens[0], 0) / total_tokens if total_tokens > 0 else 0\n",
|
|
"\n",
|
|
"# b. P(w2|w1) (Menggunakan Bigram tanpa smoothing)\n",
|
|
"if len(tokens) > 1:\n",
|
|
" count_w1 = unigram_counts.get(tokens[0], 1) # Hindari pembagian dengan 0\n",
|
|
" p_w2_w1 = bigram_counts.get((tokens[0], tokens[1]), 0) / count_w1\n",
|
|
"else:\n",
|
|
" p_w2_w1 = 1.0 # Jika hanya 1 kata\n",
|
|
"\n",
|
|
"p_kalimat = p_w1 * p_w2_w1 # Inisialisasi dengan P(w1) * P(w2|w1)\n",
|
|
"\n",
|
|
"# Daftar bagian rumus untuk ditampilkan\n",
|
|
"prob_str_parts = [f\"P({tokens[0]})={p_w1:.2f}\"]\n",
|
|
"if len(tokens) > 1:\n",
|
|
" prob_str_parts.append(f\"P({tokens[1]}|{tokens[0]})={p_w2_w1:.2f}\")\n",
|
|
"\n",
|
|
"# c. Perkalian Trigram P(wi | wi-2, wi-1) untuk i >= 3\n",
|
|
"for i in range(len(tokens) - 2):\n",
|
|
" triplet = (tokens[i], tokens[i+1], tokens[i+2])\n",
|
|
" p = trigram_probabilities.get(triplet, 0)\n",
|
|
" p_kalimat *= p\n",
|
|
" prob_str_parts.append(f\"P({triplet[2]}|{triplet[0]},{triplet[1]})={p:.2f}\")\n",
|
|
"\n",
|
|
"prob_str = \" x \".join(prob_str_parts)\n",
|
|
"\n",
|
|
"print(\"\\nProbabilitas Keseluruhan Kalimat (Model Trigram):\")\n",
|
|
"print(f\" P({' '.join(tokens)}) = {prob_str} = {p_kalimat:.6f} ({p_kalimat*100:.2f}%)\")\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"colab": {
|
|
"provenance": []
|
|
},
|
|
"kernelspec": {
|
|
"display_name": "Python 3 (ipykernel)",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.12.2"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0
|
|
} |