Awlly commited on
Commit
2f2be53
·
1 Parent(s): acd5d65

adjusted visuals of the app

Browse files
__pycache__/preprocessing.cpython-310.pyc ADDED
Binary file (2.36 kB). View file
 
app.py CHANGED
@@ -1,14 +1,14 @@
1
  import streamlit as st
2
- from transformers import AutoTokenizer, AutoModelForSequenceClassification
3
 
4
- from app_pages import page1_model_comparison, page2_rubert_toxicity, page3_gpt_model
5
 
6
- st.sidebar.title('Navigation')
7
- selection = st.sidebar.radio("Go to", ["Model Comparison", "RuBERT Toxicity Detection", "GPT Model"])
8
 
9
- if selection == "Model Comparison":
10
- page1_model_comparison.run()
11
- elif selection == "RuBERT Toxicity Detection":
12
- page2_rubert_toxicity.run()
13
- elif selection == "GPT Model":
14
- page3_gpt_model.run()
 
1
  import streamlit as st
2
+ # from transformers import AutoTokenizer, AutoModelForSequenceClassification
3
 
4
+ # from app_pages import page1_model_comparison, page2_rubert_toxicity, page3_gpt_model
5
 
6
+ st.title('LSTM Team Natuaral Language Processing Project')
7
+ # selection = st.sidebar.radio("Go to", ["Model Comparison", "RuBERT Toxicity Detection", "GPT Model"])
8
 
9
+ # if selection == "Model Comparison":
10
+ # page1_model_comparison.run()
11
+ # elif selection == "RuBERT Toxicity Detection":
12
+ # page2_rubert_toxicity.run()
13
+ # elif selection == "GPT Model":
14
+ # page3_gpt_model.run()
app_pages/page1_model_comparison.py DELETED
@@ -1,43 +0,0 @@
1
- import streamlit as st
2
- from app_models.rubert_MODEL import classify_text
3
- from app_models.bag_of_words_MODEL import predict
4
- from app_models.lstm_MODEL import predict_review
5
- import time
6
-
7
- class_prefix = 'This review is likely...'
8
-
9
- def run():
10
- st.title("Movie Review Classification")
11
- st.write("This page will compare three models: Bag of Words/TF-IDF, LSTM, and BERT.")
12
-
13
- # Example placeholder for user input
14
- user_input = st.text_area("")
15
-
16
-
17
- if st.button('Classify with All Models'):
18
- # Measure and display Bag of Words/TF-IDF prediction time
19
- start_time = time.time()
20
- bow_tfidf_result = predict(user_input)
21
- end_time = time.time()
22
- st.write(f'{class_prefix} {bow_tfidf_result} according to Bag of Words/TF-IDF. Time taken: {end_time - start_time:.2f} seconds.')
23
-
24
- # Measure and display LSTM prediction time
25
- start_time = time.time()
26
- lstm_result = predict_review(user_input)
27
- end_time = time.time()
28
- st.write(f'{class_prefix} {lstm_result} according to LSTM. Time taken: {end_time - start_time:.2f} seconds.')
29
-
30
- # Measure and display ruBERT prediction time
31
- start_time = time.time()
32
- rubert_result = classify_text(user_input)
33
- end_time = time.time()
34
- st.write(f'{class_prefix} {rubert_result} according to ruBERT. Time taken: {end_time - start_time:.2f} seconds.')
35
-
36
-
37
- # Placeholder buttons for model selection
38
- # if st.button('Classify with BoW/TF-IDF'):
39
- # st.write(f'{class_prefix}{predict(user_input)}')
40
- # if st.button('Classify with LSTM'):
41
- # st.write(f'{class_prefix}{predict_review(user_input)}')
42
- # if st.button('Classify with ruBERT'):
43
- # st.write(f'{class_prefix}{classify_text(user_input)}')
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app_pages/page2_rubert_toxicity.py DELETED
@@ -1,20 +0,0 @@
1
- import streamlit as st
2
-
3
- from app_models.toxicity_MODEL import text2toxicity
4
-
5
-
6
- def run():
7
- st.title('Toxicity Detection')
8
- st.write('This tool classifies text as toxic or non-toxic using RuBERT.')
9
-
10
- user_input = st.text_area("Enter text to classify", "Type your text here...")
11
-
12
- if st.button('Classify'):
13
- toxicity_score = text2toxicity(user_input)
14
- st.write('Toxicity score:', toxicity_score)
15
-
16
- # Optional: Interpret the score for the user
17
- if toxicity_score > 0.5:
18
- st.write("This text is likely to be considered toxic.")
19
- else:
20
- st.write("This text is likely to be considered non-toxic.")
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
app_pages/page3_gpt_model.py DELETED
@@ -1,15 +0,0 @@
1
- import streamlit as st
2
- from app_models.gpt_MODEL import generate_text
3
-
4
-
5
- def run():
6
- st.title('GPT Text Generation')
7
- prompt_text = st.text_area("Input Text", "Type here...")
8
- length = st.slider("Length of Generated Text", min_value=50, max_value=500, value=200)
9
- temperature = st.slider("Temperature", min_value=0.1, max_value=2.0, value=0.7, step=0.1)
10
- beams = st.slider("Number of Generations", min_value=2, max_value=10, value=4, step=1)
11
-
12
- if st.button('Generate Text'):
13
- with st.spinner('Generating...'):
14
- generated_text = generate_text(prompt_text, length, temperature, beams)
15
- st.text_area("Generated Text", generated_text, height=250)
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
models/__pycache__/bag_of_words_MODEL.cpython-310.pyc ADDED
Binary file (626 Bytes). View file
 
models/__pycache__/gpt_MODEL.cpython-310.pyc ADDED
Binary file (1.04 kB). View file
 
models/__pycache__/lstm_MODEL.cpython-310.pyc ADDED
Binary file (3.49 kB). View file
 
models/__pycache__/rubert_MODEL.cpython-310.pyc ADDED
Binary file (1.39 kB). View file
 
models/__pycache__/toxicity_MODEL.cpython-310.pyc ADDED
Binary file (981 Bytes). View file
 
{app_models → models}/bag_of_words_MODEL.py RENAMED
File without changes
{app_models → models}/gpt_MODEL.py RENAMED
File without changes
{app_models → models}/lstm_MODEL.py RENAMED
File without changes
{app_models → models}/rubert_MODEL.py RENAMED
File without changes
{app_models → models}/toxicity_MODEL.py RENAMED
File without changes
pages/PalanikGPT.py ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from models.gpt_MODEL import generate_text
3
+
4
+
5
+ st.title('GPT Text Generation')
6
+ prompt_text = st.text_area("Input Text", "Type here...")
7
+ length = st.slider("Length of Generated Text", min_value=50, max_value=500, value=200)
8
+ temperature = st.slider("Temperature", min_value=0.1, max_value=2.0, value=0.7, step=0.1)
9
+ beams = st.slider("Number of Generations", min_value=2, max_value=10, value=4, step=1)
10
+
11
+ if st.button('Generate Text'):
12
+ with st.spinner('Generating...'):
13
+ generated_text = generate_text(prompt_text, length, temperature, beams)
14
+ st.text_area("Generated Text", generated_text, height=250)
pages/ReviewClassification.py ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from models.rubert_MODEL import classify_text
3
+ from models.bag_of_words_MODEL import predict
4
+ from models.lstm_MODEL import predict_review
5
+ import time
6
+
7
+ class_prefix = 'This review is likely...'
8
+
9
+
10
+ st.title("Movie Review Classification")
11
+ st.write("This page will compare three models: Bag of Words/TF-IDF, LSTM, and BERT.")
12
+
13
+ # Example placeholder for user input
14
+ user_input = st.text_area("")
15
+
16
+
17
+ if st.button('Classify with All Models'):
18
+ # Measure and display Bag of Words/TF-IDF prediction time
19
+ start_time = time.time()
20
+ bow_tfidf_result = predict(user_input)
21
+ end_time = time.time()
22
+ st.write(f'{class_prefix} {bow_tfidf_result} according to Bag of Words/TF-IDF. Time taken: {end_time - start_time:.2f} seconds.')
23
+
24
+ # Measure and display LSTM prediction time
25
+ start_time = time.time()
26
+ lstm_result = predict_review(user_input)
27
+ end_time = time.time()
28
+ st.write(f'{class_prefix} {lstm_result} according to LSTM. Time taken: {end_time - start_time:.2f} seconds.')
29
+
30
+ # Measure and display ruBERT prediction time
31
+ start_time = time.time()
32
+ rubert_result = classify_text(user_input)
33
+ end_time = time.time()
34
+ st.write(f'{class_prefix} {rubert_result} according to ruBERT. Time taken: {end_time - start_time:.2f} seconds.')
35
+
36
+
37
+ # Placeholder buttons for model selection
38
+ # if st.button('Classify with BoW/TF-IDF'):
39
+ # st.write(f'{class_prefix}{predict(user_input)}')
40
+ # if st.button('Classify with LSTM'):
41
+ # st.write(f'{class_prefix}{predict_review(user_input)}')
42
+ # if st.button('Classify with ruBERT'):
43
+ # st.write(f'{class_prefix}{classify_text(user_input)}')
pages/ToxicCommentDetector.py ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+
3
+ from models.toxicity_MODEL import text2toxicity
4
+
5
+
6
+ st.title('Toxicity Detection')
7
+ st.write('This tool classifies text as toxic or non-toxic using RuBERT.')
8
+
9
+ user_input = st.text_area("Enter text to classify", "Type your text here...")
10
+
11
+ if st.button('Classify'):
12
+ toxicity_score = text2toxicity(user_input)
13
+ st.write('Toxicity score:', toxicity_score)
14
+
15
+ # Optional: Interpret the score for the user
16
+ if toxicity_score > 0.5:
17
+ st.write("This text is likely to be considered toxic.")
18
+ else:
19
+ st.write("This text is likely to be considered non-toxic.")