Update Demo.py

Demo.py

@@ -1,109 +1,109 @@
-import streamlit as st
-import sparknlp
-
-from sparknlp.base import *
-from sparknlp.annotator import *
-from pyspark.ml import Pipeline
-
-# Page configuration
-st.set_page_config(
-    layout="wide", 
-    initial_sidebar_state="auto"
-)
-
-# CSS for styling
-st.markdown("""
-    <style>
-        .main-title {
-            font-size: 36px;
-            color: #4A90E2;
-            font-weight: bold;
-            text-align: center;
-        }
-        .section {
-            background-color: #f9f9f9;
-            padding: 10px;
-            border-radius: 10px;
-            margin-top: 10px;
-        }
-        .section p, .section ul {
-            color: #666666;
-        }
-    </style>
-""", unsafe_allow_html=True)
-
-@st.cache_resource
-def init_spark():
-    return sparknlp.start()
-
-@st.cache_resource
-def create_pipeline():
-    documentAssembler = DocumentAssembler() \
-        .setInputCol("text") \
-        .setOutputCol("documents")
-        
-    t5 = T5Transformer.pretrained("t5_grammar_error_corrector") \
-        .setTask("gec:") \
-        .setInputCols(["documents"])\
-        .setMaxOutputLength(200)\
-        .setOutputCol("corrections")
-
-    pipeline = Pipeline().setStages([documentAssembler, t5])
-    return pipeline
-
-def fit_data(pipeline, data):
-    df = spark.createDataFrame([[data]]).toDF("text")
-    result = pipeline.fit(df).transform(df)
-    return result.select('corrections.result').collect()
-
-# Sidebar content
-model = st.sidebar.selectbox(
-    "Choose the pretrained model",
-    ['t5_grammar_error_corrector'],
-    help="For more info about the models visit: https://sparknlp.org/models"
-)
-
-# Set up the page layout
-title = "Correct Sentences Grammar"
-sub_title = "This demo uses a text-to-text model fine-tuned to correct grammatical errors when the task is set to “gec:”. It is based on Prithiviraj Damodaran’s Gramformer model."
-
-st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
-st.markdown(f'<div style="text-align: center; color: #666666;">{sub_title}</div>', unsafe_allow_html=True)
-
-# Reference notebook link in sidebar
-link = """
-<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/T5_LINGUISTIC.ipynb#scrollTo=QAZ3vOX_SW7B">
-    <img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>
-</a>
-"""
-st.sidebar.markdown('Reference notebook:')
-st.sidebar.markdown(link, unsafe_allow_html=True)
-
-# Define the exampless
-examples = [
-    "She don't knows nothing about what's happening in the office.",
-    "They was playing soccer yesterday when it start raining heavily.",
-    "This car are more faster than that one, but it costed less money.",
-    "I seen him go to the store, but he don't buy nothing from there.",
-    "We was going to the park but it start raining before we could leave."
-]
-
-# Text selection and analysis
-selected_text = st.selectbox("Select an example", examples)
-custom_input = st.text_input("Try it with your own sentence!")
-
-text_to_analyze = custom_input if custom_input else selected_text
-
-st.write('Text to be converted to SQL query:')
-HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
-st.markdown(HTML_WRAPPER.format(text_to_analyze), unsafe_allow_html=True)
-
-# Initialize Spark and create pipeline
-spark = init_spark()
-pipeline = create_pipeline()
-output = fit_data(pipeline, text_to_analyze)
-
-# Display transformed sentence
-st.write("Predicted Sentence:")
-output_text = "".join(output[0][0])
+import streamlit as st
+import sparknlp
+
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+# Page configuration
+st.set_page_config(
+    layout="wide", 
+    initial_sidebar_state="auto"
+)
+
+# CSS for styling
+st.markdown("""
+    <style>
+        .main-title {
+            font-size: 36px;
+            color: #4A90E2;
+            font-weight: bold;
+            text-align: center;
+        }
+        .section {
+            background-color: #f9f9f9;
+            padding: 10px;
+            border-radius: 10px;
+            margin-top: 10px;
+        }
+        .section p, .section ul {
+            color: #666666;
+        }
+    </style>
+""", unsafe_allow_html=True)
+
+@st.cache_resource
+def init_spark():
+    return sparknlp.start()
+
+@st.cache_resource
+def create_pipeline():
+    documentAssembler = DocumentAssembler() \
+        .setInputCol("text") \
+        .setOutputCol("documents")
+        
+    t5 = T5Transformer.pretrained("t5_grammar_error_corrector") \
+        .setTask("gec:") \
+        .setInputCols(["documents"])\
+        .setMaxOutputLength(200)\
+        .setOutputCol("corrections")
+
+    pipeline = Pipeline().setStages([documentAssembler, t5])
+    return pipeline
+
+def fit_data(pipeline, data):
+    df = spark.createDataFrame([[data]]).toDF("text")
+    result = pipeline.fit(df).transform(df)
+    return result.select('corrections.result').collect()
+
+# Sidebar content
+model = st.sidebar.selectbox(
+    "Choose the pretrained model",
+    ['t5_grammar_error_corrector'],
+    help="For more info about the models visit: https://sparknlp.org/models"
+)
+
+# Set up the page layout
+title = "Correct Sentences Grammar"
+sub_title = "This demo uses a text-to-text model fine-tuned to correct grammatical errors when the task is set to “gec:”. It is based on Prithiviraj Damodaran’s Gramformer model."
+
+st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
+st.markdown(f'<div style="text-align: center; color: #666666;">{sub_title}</div>', unsafe_allow_html=True)
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/T5_LINGUISTIC.ipynb#scrollTo=QAZ3vOX_SW7B">
+    <img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>
+</a>
+"""
+st.sidebar.markdown('Reference notebook:')
+st.sidebar.markdown(link, unsafe_allow_html=True)
+
+# Define the exampless
+examples = [
+    "She don't knows nothing about what's happening in the office.",
+    "They was playing soccer yesterday when it start raining heavily.",
+    "This car are more faster than that one, but it costed less money.",
+    "I seen him go to the store, but he don't buy nothing from there.",
+    "We was going to the park but it start raining before we could leave."
+]
+
+# Text selection and analysis
+selected_text = st.selectbox("Select an example", examples)
+custom_input = st.text_input("Try it with your own sentence!")
+
+text_to_analyze = custom_input if custom_input else selected_text
+
+st.write('Text to analyze:')
+HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
+st.markdown(HTML_WRAPPER.format(text_to_analyze), unsafe_allow_html=True)
+
+# Initialize Spark and create pipeline
+spark = init_spark()
+pipeline = create_pipeline()
+output = fit_data(pipeline, text_to_analyze)
+
+# Display transformed sentence
+st.write("Predicted Sentence:")
+output_text = "".join(output[0][0])
 st.markdown(f'<div class="scroll">{output_text}</div>', unsafe_allow_html=True)