Add Tugas.Classification/Rizky Noor Fazila-Clas-SVM-cancer

Tugas.Classification/Rizky Noor Fazila-Clas-SVM-cancer

@@ -0,0 +1,56 @@
+import pandas as pd
+import numpy as np
+from sklearn import preprocessing
+from sklearn.model_selection import train_test_split
+from sklearn import svm
+from sklearn.metrics import classification_report, f1_score
+
+# Fungsi hitung Jaccard manual (untuk sklearn lama)
+def jaccard_manual(y_true, y_pred):
+    intersection = np.logical_and(y_true == 1, y_pred == 1).sum()
+    union = np.logical_or(y_true == 1, y_pred == 1).sum()
+    return intersection / union if union != 0 else 0
+
+# ================================
+# 1. Load Data
+# ================================
+cell_df = pd.read_csv("cell_samples.csv")
+
+# ================================
+# 2. Bersihkan Kolom BareNuc
+# ================================
+cell_df = cell_df[pd.to_numeric(cell_df['BareNuc'], errors='coerce').notnull()]
+cell_df['BareNuc'] = cell_df['BareNuc'].astype('int')
+
+# ================================
+# 3. Buat Feature dan Label
+# ================================
+feature_df = cell_df[['Clump','UnifSize','UnifShape','MargAdh',
+                      'SingEpiSize','BareNuc','BlandChrom','NormNucl','Mit']].astype(float)
+
+X = np.asarray(feature_df)
+y = np.where(cell_df['Class'] == 2, 0, 1)  # 0 = Benign, 1 = Malignant
+
+# ================================
+# 4. Split Train/Test
+# ================================
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=4)
+
+# ================================
+# 5. Model SVM Kernel LINEAR
+# ================================
+model = svm.SVC(kernel='linear')
+model.fit(X_train, y_train)
+
+# ================================
+# 6. Prediksi
+# ================================
+y_pred = model.predict(X_test)
+
+# ================================
+# 7. Evaluasi
+# ================================
+print("Avg F1-score:", f1_score(y_test, y_pred, average='weighted'))
+print("Jaccard score:", jaccard_manual(y_test, y_pred))
+print("\nClassification Report:\n")
+print(classification_report(y_test, y_pred))