{"id":2566,"date":"2025-09-14T15:13:43","date_gmt":"2025-09-14T15:13:43","guid":{"rendered":"https:\/\/kuliahrobot.com\/krc\/?p=2566"},"modified":"2025-09-14T15:32:12","modified_gmt":"2025-09-14T15:32:12","slug":"machine-learning-penyakit-diabetes-pima-dataset","status":"publish","type":"post","link":"https:\/\/kuliahrobot.com\/krc\/machine-learning-penyakit-diabetes-pima-dataset\/","title":{"rendered":"Machine Learning Penyakit Diabetes Pima Dataset"},"content":{"rendered":"\t\t
\n\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Machine Learning (ML) adalah salah satu cabang kecerdasan buatan (Artificial Intelligence\/AI) yang mampu membantu manusia dalam mengambil keputusan berdasarkan data. Salah satu penerapan yang sering dijadikan contoh adalah klasifikasi penyakit diabetes.\u00a0<\/strong>Dengan memanfaatkan data kesehatan pasien seperti usia, kadar gula darah, tekanan darah, dan faktor lainnya, kita dapat melatih model machine learning untuk memprediksi apakah seseorang berisiko terkena diabetes atau tidak.<\/strong><\/p>

Proyek ini sangat cocok untuk pemula karena:<\/strong><\/p>

  1. Dataset sudah tersedia secara umum dan mudah digunakan.<\/strong><\/p><\/li>

  2. Prosesnya sederhana, namun sudah mencakup konsep dasar data preprocessing, training, dan evaluasi model.<\/strong><\/p><\/li>

  3. Bisa dijalankan secara gratis menggunakan Google Colab, tanpa perlu instalasi software tambahan.<\/strong><\/p><\/li><\/ol>

    Melalui tutorial ini, kita akan mempelajari langkah demi langkah membangun model klasifikasi penyakit diabetes, mulai dari menyiapkan data, membuat model, hingga mengevaluasi hasil prediksi.<\/strong><\/p>

    \u00a0<\/strong><\/p>

    Langkah-Langkah di Google Colab<\/strong><\/p>

    1. Import Library yang Dibutuhkan<\/strong>\u00a0<\/p>

    import<\/span> pandas as<\/span> pd
    import<\/span> numpy as<\/span> np
    import<\/span> matplotlib.pyplot as<\/span> plt
    import<\/span> seaborn as<\/span> sns<\/code><\/code><\/strong><\/p>

    from<\/span> sklearn.model_selection import<\/span> train_test_split<\/strong>
    from<\/span> sklearn.preprocessing import<\/span> StandardScaler<\/strong>
    from<\/span> sklearn.linear_model import<\/span> LogisticRegression<\/strong>
    from<\/span> sklearn.metrics import<\/span> accuracy_score, classification_report, confusion_matrix<\/strong><\/p><\/div>

    2. Load Dataset<\/strong><\/p>

    Dataset Pima Indians Diabetes bisa diambil langsung dari GitHub.<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>

    url = \"https:\/\/raw.githubusercontent.com\/plotly\/datasets\/master\/diabetes.csv\"<\/span>
    data = pd.read_csv(url)<\/code><\/code><\/strong><\/p>

    # Tampilkan 5 baris pertama<\/span><\/strong>
    data.head()<\/strong><\/p><\/div>

    3. Eksplorasi Data<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>

    print<\/span>(data.info())
    print<\/span>(data.describe())<\/code><\/code><\/strong><\/p>

    # Heatmap korelasi antar fitur<\/span><\/strong>
    sns.heatmap(data.corr(), annot=True<\/span>, cmap=“coolwarm”<\/span>)<\/strong>
    plt.show()<\/strong><\/p><\/div>

    4. Pisahkan Fitur dan Label<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>

    X = data.drop(\"Outcome\"<\/span>, axis=1<\/span>) # Fitur (input)<\/span>
    y = data[\"Outcome\"<\/span>] # Label (0 = tidak diabetes, 1 = diabetes)<\/span><\/code><\/code><\/strong><\/p>

    # Split data untuk training dan testing<\/span><\/strong>
    X_train, X_test, y_train, y_test = train_test_split(<\/strong>
    X, y, test_size=0.2<\/span>, random_state=42<\/span><\/strong>
    )<\/strong><\/p><\/div>

    5. Normalisasi Data<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>
    scaler = StandardScaler()
    X_train = scaler.fit_transform(X_train)
    X_test = scaler.transform(X_test)
    <\/code><\/strong><\/div>

    6. Buat Model Machine Learning<\/strong><\/p>

    Contoh sederhana menggunakan Logistic Regression:<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>

    model = LogisticRegression()
    model.fit(X_train, y_train)<\/code><\/code><\/strong><\/p>

    y_pred = model.predict(X_test)<\/strong><\/p><\/div>

    7. Evaluasi Model<\/strong><\/p>

    \u00a0<\/div><\/div><\/div>

    print<\/span>(\"Akurasi:\"<\/span>, accuracy_score(y_test, y_pred))
    print<\/span>(\"\\nClassification Report:\\n\"<\/span>, classification_report(y_test, y_pred))<\/code><\/code><\/strong><\/p>

    # Confusion Matrix<\/span><\/strong>
    sns.heatmap(confusion_matrix(y_test, y_pred), annot=True<\/span>, fmt=‘d’<\/span>, cmap=“Blues”<\/span>)<\/strong>
    plt.xlabel(“Predicted”<\/span>)<\/strong>
    plt.ylabel(“Actual”<\/span>)<\/strong>
    plt.show()<\/strong><\/p><\/div>

    \"\ud83d\udcca\" Hasil & Kesimpulan<\/strong><\/p>

    • Model mampu memberikan akurasi sekitar 75\u201380% (tergantung data split).<\/strong><\/p><\/li>

    • Kita bisa melihat metrik precision, recall, dan f1-score untuk mengetahui performa model pada masing-masing kelas.<\/strong><\/p><\/li>

    • Visualisasi confusion matrix membantu memahami seberapa banyak prediksi benar dan salah.<\/strong><\/p><\/li><\/ul>

      Sebagai latihan tambahan, kamu bisa mencoba algoritma lain seperti:<\/strong><\/p>

      • RandomForestClassifier<\/code><\/strong><\/p><\/li>

      • KNeighborsClassifier<\/code><\/strong><\/p><\/li>

      • SVC<\/code><\/strong><\/p><\/li><\/ul>

        \u00a0<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

        Machine Learning (ML) adalah salah satu cabang kecerdasan buatan (Artificial Intelligence\/AI) yang mampu membantu manusia dalam mengambil keputusan berdasarkan data. Salah satu penerapan yang sering dijadikan contoh adalah klasifikasi penyakit diabetes.\u00a0Dengan memanfaatkan data kesehatan pasien seperti usia, kadar gula darah, tekanan darah, dan faktor lainnya, kita dapat melatih model machine learning untuk memprediksi apakah seseorang […]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-2566","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/posts\/2566","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/comments?post=2566"}],"version-history":[{"count":7,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/posts\/2566\/revisions"}],"predecessor-version":[{"id":2584,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/posts\/2566\/revisions\/2584"}],"wp:attachment":[{"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/media?parent=2566"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/categories?post=2566"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/kuliahrobot.com\/krc\/wp-json\/wp\/v2\/tags?post=2566"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}