Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
@@ -13,7 +13,7 @@ vectorizer = joblib.load("vectorizer.joblib") # global vocabulary (used for Logi
|
|
13 |
|
14 |
# Decode label function
|
15 |
# {'business': 0, 'entertainment': 1, 'health': 2, 'politics': 3, 'sport': 4}
|
16 |
-
def
|
17 |
print('receive label encoded', input_number)
|
18 |
categories = {
|
19 |
0: 'Business',
|
@@ -85,15 +85,16 @@ def process_api(text):
|
|
85 |
SVM_Predicted = SVM_model.predict(processed_text).tolist() # SVC Model
|
86 |
# Seq_Predicted = Seq_model.predict(padded_sequence)
|
87 |
# predicted_label_index = np.argmax(Seq_Predicted)
|
88 |
-
|
89 |
-
|
90 |
-
|
91 |
-
|
92 |
-
print('
|
|
|
93 |
|
94 |
return {
|
95 |
-
'Logistic_Predicted':int(Logistic_Predicted[0]),
|
96 |
-
'SVM_Predicted': int(SVM_Predicted[0]),
|
97 |
'Article_Content': text
|
98 |
}
|
99 |
|
@@ -116,4 +117,7 @@ if url:
|
|
116 |
result = categorize(url)
|
117 |
article_content = result.get('Article_Content')
|
118 |
st.text_area("Article Content", value=article_content, height=400) # render the article content as textarea element
|
119 |
-
st.json(
|
|
|
|
|
|
|
|
13 |
|
14 |
# Decode label function
|
15 |
# {'business': 0, 'entertainment': 1, 'health': 2, 'politics': 3, 'sport': 4}
|
16 |
+
def decodedLabel(input_number):
|
17 |
print('receive label encoded', input_number)
|
18 |
categories = {
|
19 |
0: 'Business',
|
|
|
85 |
SVM_Predicted = SVM_model.predict(processed_text).tolist() # SVC Model
|
86 |
# Seq_Predicted = Seq_model.predict(padded_sequence)
|
87 |
# predicted_label_index = np.argmax(Seq_Predicted)
|
88 |
+
|
89 |
+
# ----------- Debug Logs -----------
|
90 |
+
logistic_debug = decodedLabel(int(Logistic_Predicted[0]))
|
91 |
+
svc_debug = decodedLabel(int(SVM_Predicted[0]))
|
92 |
+
print('Logistic', int(Logistic_Predicted[0]), logistic_debug)
|
93 |
+
print('SVM', int(SVM_Predicted[0]), svc_debug)
|
94 |
|
95 |
return {
|
96 |
+
'Logistic_Predicted':decodedLabel(int(Logistic_Predicted[0])),
|
97 |
+
'SVM_Predicted': decodedLabel(int(SVM_Predicted[0])),
|
98 |
'Article_Content': text
|
99 |
}
|
100 |
|
|
|
117 |
result = categorize(url)
|
118 |
article_content = result.get('Article_Content')
|
119 |
st.text_area("Article Content", value=article_content, height=400) # render the article content as textarea element
|
120 |
+
st.json({
|
121 |
+
"Logistic": result.get("Logistic_Predicted"),
|
122 |
+
"SVC": result.get("SVM_Predicted")
|
123 |
+
})
|