Spaces:
Runtime error
Runtime error
chore: update matrix
Browse files
main.py
CHANGED
|
@@ -198,13 +198,14 @@ async def confusion_matrix_image(model_type: str):
|
|
| 198 |
if hf_dataset_cache is None:
|
| 199 |
raise HTTPException(status_code=500, detail="Dataset not loaded")
|
| 200 |
|
|
|
|
| 201 |
filtered_samples = [
|
| 202 |
sample for sample in hf_dataset_cache
|
| 203 |
-
if sample.get("text") and sample
|
| 204 |
]
|
| 205 |
|
| 206 |
if not filtered_samples:
|
| 207 |
-
raise HTTPException(status_code=400, detail="No valid
|
| 208 |
|
| 209 |
texts = [sample["text"] for sample in filtered_samples]
|
| 210 |
labels = [sample["label"] for sample in filtered_samples]
|
|
@@ -213,7 +214,6 @@ async def confusion_matrix_image(model_type: str):
|
|
| 213 |
X = vectorizer.fit_transform(texts)
|
| 214 |
y = labels
|
| 215 |
|
| 216 |
-
# For consistency, even though all y == 1, we still fit
|
| 217 |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
| 218 |
|
| 219 |
if model_type == "naive-bayes":
|
|
@@ -226,7 +226,7 @@ async def confusion_matrix_image(model_type: str):
|
|
| 226 |
clf.fit(X_train, y_train)
|
| 227 |
y_pred = clf.predict(X_test)
|
| 228 |
|
| 229 |
-
cm = confusion_matrix(y_test, y_pred, labels=[0, 1])
|
| 230 |
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=["Bukan Judi", "Judi"])
|
| 231 |
|
| 232 |
buf = io.BytesIO()
|
|
|
|
| 198 |
if hf_dataset_cache is None:
|
| 199 |
raise HTTPException(status_code=500, detail="Dataset not loaded")
|
| 200 |
|
| 201 |
+
# Include all labeled samples (both 0 and 1)
|
| 202 |
filtered_samples = [
|
| 203 |
sample for sample in hf_dataset_cache
|
| 204 |
+
if sample.get("text") and sample["text"].strip()
|
| 205 |
]
|
| 206 |
|
| 207 |
if not filtered_samples:
|
| 208 |
+
raise HTTPException(status_code=400, detail="No valid samples found.")
|
| 209 |
|
| 210 |
texts = [sample["text"] for sample in filtered_samples]
|
| 211 |
labels = [sample["label"] for sample in filtered_samples]
|
|
|
|
| 214 |
X = vectorizer.fit_transform(texts)
|
| 215 |
y = labels
|
| 216 |
|
|
|
|
| 217 |
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
|
| 218 |
|
| 219 |
if model_type == "naive-bayes":
|
|
|
|
| 226 |
clf.fit(X_train, y_train)
|
| 227 |
y_pred = clf.predict(X_test)
|
| 228 |
|
| 229 |
+
cm = confusion_matrix(y_test, y_pred, labels=[0, 1])
|
| 230 |
disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=["Bukan Judi", "Judi"])
|
| 231 |
|
| 232 |
buf = io.BytesIO()
|