diff --git a/Klasifikasi_Teks_FNN.ipynb b/Klasifikasi_Teks_FNN.ipynb new file mode 100644 index 0000000..9657087 --- /dev/null +++ b/Klasifikasi_Teks_FNN.ipynb @@ -0,0 +1,218 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "id": "f4a1399a-f23d-4060-a07e-bce5a5c7ddac", + "metadata": { + "id": "f4a1399a-f23d-4060-a07e-bce5a5c7ddac" + }, + "source": [ + "# Klasifikasi Teks menggunakan ANN\n", + "## Fahrizal Setiawan\n" + ] + }, + { + "cell_type": "code", + "execution_count": 11, + "id": "53a214ae-c9cf-4d46-925d-068f1685537b", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "53a214ae-c9cf-4d46-925d-068f1685537b", + "outputId": "f224e8ff-e3a6-49d9-fac9-cafc0202eb4c" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "=== Classification Report ===\n", + " precision recall f1-score support\n", + "\n", + " negative 0.33 1.00 0.50 1\n", + " positive 0.00 0.00 0.00 2\n", + "\n", + " accuracy 0.33 3\n", + " macro avg 0.17 0.50 0.25 3\n", + "weighted avg 0.11 0.33 0.17 3\n", + "\n", + "=== Confusion Matrix ===\n", + "[[1 0]\n", + " [2 0]]\n", + "\n", + "Prediksi untuk: barang buruk, saya kecewa\n", + "Hasil: negative\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", + " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", + "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", + " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n", + "/usr/local/lib/python3.12/dist-packages/sklearn/metrics/_classification.py:1565: UndefinedMetricWarning: Precision is ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n", + " _warn_prf(average, modifier, f\"{metric.capitalize()} is\", len(result))\n" + ] + } + ], + "source": [ + "# ---------------------------------------------------------\n", + "# Klasifikasi Teks dengan TF-IDF + Feedforward Neural Network\n", + "# ---------------------------------------------------------\n", + "\n", + "import pandas as pd\n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.feature_extraction.text import TfidfVectorizer\n", + "from sklearn.neural_network import MLPClassifier\n", + "from sklearn.metrics import classification_report, confusion_matrix\n", + "\n", + "# -----------------------------------------\n", + "# 1. Contoh Dataset\n", + "# -----------------------------------------\n", + "# Anda bisa mengganti dataset ini dengan dataset lain (CSV, JSON, dll)\n", + "\n", + "data = {\n", + " \"text\": [\n", + " \"Saya suka produk ini, luar biasa\",\n", + " \"Layanannya buruk, saya sangat kecewa\",\n", + " \"Penjual tidak responsif, sangat kecewa\",\n", + " \"Pembelian terbaik yang pernah saya lakukan\",\n", + " \"Saya benci produk ini, buang-buang uang\",\n", + " \"Kualitasnya sangat bagus, direkomendasikan\",\n", + " \"Pengalaman buruk, tidak akan membeli lagi\",\n", + "\n", + " ],\n", + " \"label\": [\n", + " \"positive\",\n", + " \"negative\",\n", + " \"negative\", # Corrected: Was positive, now negative to match sentiment\n", + " \"positive\", # Corrected: Was negative, now positive to match sentiment\n", + " \"negative\", # Corrected: Was positive, now negative to match sentiment\n", + " \"positive\", # Corrected: Was negative, now positive to match sentiment\n", + " \"negative\",\n", + " # Added missing label to match length of 'text' list\n", + " ]\n", + "}\n", + "\n", + "df = pd.DataFrame(data)\n", + "\n", + "# -----------------------------------------\n", + "# 2. Split Train & Test\n", + "# -----------------------------------------\n", + "X_train, X_test, y_train, y_test = train_test_split(\n", + " df[\"text\"], df[\"label\"], test_size=0.3, random_state=42\n", + ")\n", + "\n", + "# -----------------------------------------\n", + "# 3. TF-IDF Vectorization\n", + "# -----------------------------------------\n", + "tfidf = TfidfVectorizer(max_features=5000)\n", + "X_train_tfidf = tfidf.fit_transform(X_train)\n", + "X_test_tfidf = tfidf.transform(X_test)\n", + "\n", + "# -----------------------------------------\n", + "# 4. Feedforward ANN (MLPClassifier)\n", + "# -----------------------------------------\n", + "model = MLPClassifier(\n", + " hidden_layer_sizes=(256, 64),\n", + " activation='relu',\n", + " solver='adam',\n", + " max_iter=500,\n", + " random_state=42\n", + ")\n", + "\n", + "model.fit(X_train_tfidf, y_train)\n", + "\n", + "# -----------------------------------------\n", + "# 5. Evaluasi Model\n", + "# -----------------------------------------\n", + "y_pred = model.predict(X_test_tfidf)\n", + "\n", + "print(\"=== Classification Report ===\")\n", + "print(classification_report(y_test, y_pred))\n", + "\n", + "print(\"=== Confusion Matrix ===\")\n", + "print(confusion_matrix(y_test, y_pred))\n", + "\n", + "# -----------------------------------------\n", + "# 6. Prediksi Teks Baru\n", + "# -----------------------------------------\n", + "#sample_text = [\"barang bagus luar biasa\"]\n", + "sample_text = [\"barang buruk, saya kecewa\"]\n", + "sample_vec = tfidf.transform(sample_text)\n", + "prediction = model.predict(sample_vec)\n", + "\n", + "print(\"\\nPrediksi untuk:\", sample_text[0])\n", + "print(\"Hasil:\", prediction[0])" + ] + }, + { + "cell_type": "code", + "execution_count": 12, + "id": "9f7d90fe-4af4-446c-9547-c9312bfa6fc7", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "9f7d90fe-4af4-446c-9547-c9312bfa6fc7", + "outputId": "4a889f91-ff57-459e-8987-43a230489899" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\n", + "Prediksi untuk: saya benci barang ini\n", + "Hasil: negative\n" + ] + } + ], + "source": [ + "#sample_text = [\"barang bagus luar biasa\"]\n", + "sample_text = [\"saya benci barang ini\"]\n", + "sample_vec = tfidf.transform(sample_text)\n", + "prediction = model.predict(sample_vec)\n", + "print(\"\\nPrediksi untuk:\", sample_text[0])\n", + "print(\"Hasil:\", prediction[0])\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "d4b9a7c2-0f08-43fd-8da8-018d839a4917", + "metadata": { + "id": "d4b9a7c2-0f08-43fd-8da8-018d839a4917" + }, + "outputs": [], + "source": [] + } + ], + "metadata": { + "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": "3.12.12" + }, + "colab": { + "provenance": [] + } + }, + "nbformat": 4, + "nbformat_minor": 5 +} \ No newline at end of file