strateg17 commited on
Commit
2288676
·
verified ·
1 Parent(s): c163fa4

Upload 6 files

Browse files
Files changed (5) hide show
  1. .gitattributes +2 -0
  2. app.py +10 -13
  3. lgbm_model.pkl +3 -0
  4. requirements.txt +3 -2
  5. vectorizer.pkl +3 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ vectorizer.pkl filter=lfs diff=lfs merge=lfs -text
37
+ lgbm_model.pkl filter=lfs diff=lfs merge=lfs -text
app.py CHANGED
@@ -1,29 +1,26 @@
1
  import gradio as gr
2
- import lightgbm as lgb
3
  import joblib
 
 
4
 
5
- # Load your trained model (assuming it's saved as 'lgbm_model.pkl')
6
  model = joblib.load('lgbm_model.pkl')
 
7
 
8
  def classify_text(text):
9
- # Convert the input text to the appropriate format for your model
10
- # For simplicity, let's assume you have a function `preprocess_text` for this
11
- # processed_text = preprocess_text(text)
12
 
13
- # If your model expects numerical features, convert text to numerical features
14
- # For example:
15
- # features = text_to_features(processed_text)
16
-
17
- # Here, we assume the model can take raw text directly for simplicity
18
- prediction = model.predict([text])
19
 
20
  return int(prediction[0])
21
 
22
  # Create the Gradio interface
23
  iface = gr.Interface(
24
  fn=classify_text,
25
- inputs=gr.inputs.Textbox(lines=2, placeholder="Enter text here..."),
26
- outputs=gr.outputs.Label(num_top_classes=1),
27
  title="Fake News Classifier",
28
  description="Enter text to classify if it's fake (1) or not fake (0).",
29
  examples=["This is a sample news article."]
 
1
  import gradio as gr
 
2
  import joblib
3
+ # from lightgbm import LGBMClassifier
4
+ # from sklearn.feature_extraction.text import TfidfVectorizer
5
 
6
+ # Load your trained model and vectorizer (assuming they're saved as 'lgbm_model.pkl' and 'vectorizer.pkl')
7
  model = joblib.load('lgbm_model.pkl')
8
+ vectorizer = joblib.load('vectorizer.pkl')
9
 
10
  def classify_text(text):
11
+ # Transform the input text using the loaded vectorizer
12
+ text_vector = vectorizer.transform([text])
 
13
 
14
+ # Predict using the loaded model
15
+ prediction = model.predict(text_vector)
 
 
 
 
16
 
17
  return int(prediction[0])
18
 
19
  # Create the Gradio interface
20
  iface = gr.Interface(
21
  fn=classify_text,
22
+ inputs=gr.Textbox(lines=2, placeholder="Enter text here..."),
23
+ outputs=gr.Label(),
24
  title="Fake News Classifier",
25
  description="Enter text to classify if it's fake (1) or not fake (0).",
26
  examples=["This is a sample news article."]
lgbm_model.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe30081cb2fde05af377490a08d9b2ed7bb40c1353f3ae980ac2c5258c4a9320
3
+ size 2790788
requirements.txt CHANGED
@@ -1,2 +1,3 @@
1
- joblib
2
- lightgbm
 
 
1
+ joblib==4.1.0
2
+ sklearn==1.2.2
3
+ lightgbm==4.1.0
vectorizer.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffde94fdae46050354244414d5b546e62393226a671057d83da2ccbabda59495
3
+ size 304927