classification only

app.py

@@ -4,35 +4,16 @@ import spacy
 from spacy import displacy
 import plotly.express as px
 import numpy as np
-st.set_page_config(page_title="NLP Prototype")
-st.title("Natural Language Processing Prototype")
+st.set_page_config(page_title="Text Classification'")
+st.title("Text Classification'")
 st.write("_This web application is intended for educational use, please do not upload any sensitive information._")
-st.subheader("__Which natural language processing task would you like to try?__")
-st.write("- __Sentiment Analysis:__ Identifying whether a piece of text has a positive or negative sentiment.")
-st.write("- __Named Entity Recognition:__ Identifying all geopolitical entities, organizations, people, locations, or dates in a body of text.")
-st.write("- __Text Classification:__ Placing a piece of text into one or more categories.")
-st.write("- __Text Summarization:__ Condensing larger bodies of text into smaller bodies of text.")
-option = st.selectbox('Please select from the list',('','Sentiment Analysis','Named Entity Recognition', 'Text Classification','Text Summarization'))
-@st.cache(allow_output_mutation=True, show_spinner=False)
-def Loading_Model_1():
-    sum2 = pipeline("summarization",framework="pt")
-    return sum2
+st.write("Placing a piece of text into one or more categories.")
+
 @st.cache(allow_output_mutation=True, show_spinner=False)
-def Loading_Model_2():
+def Loading_Classifier():
     class1 = pipeline("zero-shot-classification",framework="pt")
     return class1
-@st.cache(allow_output_mutation=True, show_spinner=False)
-def Loading_Model_3():
-    sentiment = pipeline("sentiment-analysis", framework="pt")
-    return sentiment
-@st.cache(allow_output_mutation=True, show_spinner=False)
-def Loading_Model_4():
-    nlp = spacy.load('en_core_web_sm')
-    return nlp
-@st.cache(allow_output_mutation=True)
-def entRecognizer(entDict, typeEnt):
-    entList = [ent for ent in entDict if entDict[ent] == typeEnt]
-    return entList
+
 def plot_result(top_topics, scores):
     top_topics = np.array(top_topics)
     scores = np.array(scores)
@@ -47,70 +28,18 @@ def plot_result(top_topics, scores):
     fig.update(layout_coloraxis_showscale=False)
     fig.update_traces(texttemplate='%{text:0.1f}%', textposition='outside')
     st.plotly_chart(fig)
-with st.spinner(text="Please wait for the models to load. This should take approximately 60 seconds."):
-    sum2 = Loading_Model_1()
-    class1 = Loading_Model_2()
-    sentiment = Loading_Model_3()
-    nlp = Loading_Model_4()
-if option == 'Text Classification':
-    cat1 = st.text_input('Enter each possible category name (separated by a comma). Maximum 5 categories.')
-    text = st.text_area('Enter Text Below:', height=200)
-    submit = st.button('Generate')
-    if submit:
-        st.subheader("Classification Results:")
-        labels1 = cat1.strip().split(',')
-        result = class1(text, candidate_labels=labels1)
-        cat1name = result['labels'][0]
-        cat1prob = result['scores'][0]
-        st.write('Category: {} | Probability: {:.1f}%'.format(cat1name,(cat1prob*100)))
-        plot_result(result['labels'][::-1][-10:], result['scores'][::-1][-10:])
 
-if option == 'Text Summarization':
-    max_lengthy = st.slider('Maximum summary length (words)', min_value=30, max_value=150, value=60, step=10)
-    num_beamer = st.slider('Speed vs quality of summary (1 is fastest)', min_value=1, max_value=8, value=4, step=1)
-    text = st.text_area('Enter Text Below (maximum 800 words):', height=300)
-    submit = st.button('Generate')
-    if submit:
-        st.subheader("Summary:")
-        with st.spinner(text="This may take a moment..."):
-            summWords = sum2(text, max_length=max_lengthy, min_length=15, num_beams=num_beamer, do_sample=True, early_stopping=True, repetition_penalty=1.5, length_penalty=1.5)
-        text2 =summWords[0]["summary_text"]
-        st.write(text2)
-if option == 'Sentiment Analysis':
-    text = st.text_area('Enter Text Below:', height=200)
-    submit = st.button('Generate')
-    if submit:
-        st.subheader("Sentiment:")
-        result = sentiment(text)
-        sent = result[0]['label']
-        cert = result[0]['score']
-        st.write('Text Sentiment: {} | Probability: {:.1f}%'.format(sent,(cert*100)))
-if option == 'Named Entity Recognition':
-    text = st.text_area('Enter Text Below:', height=300)
-    submit = st.button('Generate')
-    if submit:
-        entities = []
-        entityLabels = []
-        doc = nlp(text)
-        for ent in doc.ents:
-            entities.append(ent.text)
-            entityLabels.append(ent.label_)
-        entDict = dict(zip(entities, entityLabels))
-        entOrg = entRecognizer(entDict, "ORG")
-        entPerson = entRecognizer(entDict, "PERSON")
-        entDate = entRecognizer(entDict, "DATE")
-        entGPE = entRecognizer(entDict, "GPE")
-        entLoc = entRecognizer(entDict, "LOC")
-        options = {"ents": ["ORG", "GPE", "PERSON", "LOC", "DATE"]}
-        HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
+with st.spinner(text="Please wait for the models to load. This could take up to 60 seconds."):
+    class1 = Loading_Classifier()
 
-        st.subheader("List of Named Entities:")
-        st.write("Geopolitical Entities (GPE): " + str(entGPE))
-        st.write("People (PERSON): " + str(entPerson))
-        st.write("Organizations (ORG): " + str(entOrg))
-        st.write("Dates (DATE): " + str(entDate))
-        st.write("Locations (LOC): " + str(entLoc))
-        st.subheader("Original Text with Entities Highlighted")
-        html = displacy.render(doc, style="ent", options=options)
-        html = html.replace("\n", " ")
-        st.write(HTML_WRAPPER.format(html), unsafe_allow_html=True)
+cat1 = st.text_input('Enter each possible category name (separated by a comma). Maximum 5 categories.')
+text = st.text_area('Enter Text Below:', height=200)
+submit = st.button('Generate')
+if submit:
+    st.subheader("Classification Results:")
+    labels1 = cat1.strip().split(',')
+    result = class1(text, candidate_labels=labels1)
+    cat1name = result['labels'][0]
+    cat1prob = result['scores'][0]
+    st.write('Category: {} | Probability: {:.1f}%'.format(cat1name,(cat1prob*100)))
+    plot_result(result['labels'][::-1][-10:], result['scores'][::-1][-10:])