Update Demo.py

Demo.py

@@ -1,117 +1,127 @@
-import streamlit as st
-import sparknlp
-import os
-import pandas as pd
-
-from sparknlp.base import *
-from sparknlp.annotator import *
-from pyspark.ml import Pipeline
-from sparknlp.pretrained import PretrainedPipeline
-
-# Page configuration
-st.set_page_config(
-    layout="wide", 
-    page_title="Spark NLP Demos App", 
-    initial_sidebar_state="auto"
-)
-
-# CSS for styling
-st.markdown("""
-    <style>
-        .main-title {
-            font-size: 36px;
-            color: #4A90E2;
-            font-weight: bold;
-            text-align: center;
-        }
-        .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():
-    document_assembler = DocumentAssembler() \
-        .setInputCol("text") \
-        .setOutputCol("document")
-
-    tokenizer = Tokenizer() \
-        .setInputCols(["document"]) \
-        .setOutputCol("token")
-
-    postagger = PerceptronModel.pretrained("pos_anc", "en") \
-        .setInputCols(["document", "token"]) \
-        .setOutputCol("pos")
-
-    pipeline = Pipeline(stages=[document_assembler, tokenizer, postagger])
-    return pipeline
-
-def fit_data(pipeline, data):
-    empty_df = spark.createDataFrame([['']]).toDF('text')
-    pipeline_model = pipeline.fit(empty_df)
-    model = LightPipeline(pipeline_model)
-    results = model.fullAnnotate(data)
-    return results
-
-# Set up the page layout
-st.markdown('<div class="main-title">State-of-the-Art Part-of-Speech Tagging with Spark NLP</div>', unsafe_allow_html=True)
-
-# Sidebar content
-model_name = st.sidebar.selectbox(
-    "Choose the pretrained model",
-    ['pos_anc'],
-    help="For more info about the models visit: https://sparknlp.org/models"
-)
-
-# Reference notebook link in sidebar
-link = """
-<a href="https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/coreference-resolution/Coreference_Resolution_SpanBertCorefModel.ipynb#L117">
-    <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)
-
-# Load examples
-examples = [
-    "Alice went to the market. She bought some fresh vegetables there. The tomatoes she purchased were particularly ripe.",
-    "Dr. Smith is a renowned surgeon. He has performed over a thousand successful operations. His colleagues respect him a lot.",
-    "The company announced a new product launch. It is expected to revolutionize the industry. The CEO was very excited about it.",
-    "Jennifer enjoys hiking. She goes to the mountains every weekend. Her favorite spot is the Blue Ridge Mountains.",
-    "The team won the championship. They celebrated their victory with a huge party. Their coach praised their hard work and dedication.",
-    "Michael is studying computer science. He finds artificial intelligence fascinating. His dream is to work at a leading tech company.",
-    "Tom is a skilled guitarist. He plays in a local band. His performances are always energetic and captivating."
-]
-
-# st.subheader("Automatically detect phrases expressing dates and normalize them with respect to a reference date.")
-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.subheader('Full example text')
-st.write(text_to_analyze)
-
-# Initialize Spark and create pipeline
-spark = init_spark()
-pipeline = create_pipeline()
-output = fit_data(pipeline, text_to_analyze)
-
-# Display matched sentence
-st.subheader("Processed output:")
-
-results = {
-    'Token': [t.result for t in output[0]['token']],
-    'Begin': [p.begin for p in output[0]['pos']],
-    'End': [p.end for p in output[0]['pos']],
-    'POS': [p.result for p in output[0]['pos']]
-}
-
-df = pd.DataFrame(results)
-df.index += 1
-st.dataframe(df)
+import streamlit as st
+import sparknlp
+import os
+import pandas as pd
+
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+from sparknlp.pretrained import PretrainedPipeline
+
+# Page configuration
+st.set_page_config(
+    layout="wide", 
+    page_title="Spark NLP Demos App", 
+    initial_sidebar_state="auto"
+)
+
+# CSS for styling
+st.markdown("""
+    <style>
+        .main-title {
+            font-size: 36px;
+            color: #4A90E2;
+            font-weight: bold;
+            text-align: center;
+        }
+        .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():
+    document_assembler = DocumentAssembler() \
+        .setInputCol("text") \
+        .setOutputCol("document")
+
+    tokenizer = Tokenizer() \
+        .setInputCols(["document"]) \
+        .setOutputCol("token")
+
+    postagger = PerceptronModel.pretrained("pos_anc", "en") \
+        .setInputCols(["document", "token"]) \
+        .setOutputCol("pos")
+
+    pipeline = Pipeline(stages=[document_assembler, tokenizer, postagger])
+    return pipeline
+
+def fit_data(pipeline, data):
+    empty_df = spark.createDataFrame([['']]).toDF('text')
+    pipeline_model = pipeline.fit(empty_df)
+    model = LightPipeline(pipeline_model)
+    results = model.fullAnnotate(data)
+    return results
+
+# Set up the page layout
+st.markdown('<div class="main-title">State-of-the-Art Part-of-Speech Tagging with Spark NLP</div>', unsafe_allow_html=True)
+
+# Sidebar content
+model_name = st.sidebar.selectbox(
+    "Choose the pretrained model",
+    ['pos_anc'],
+    help="For more info about the models visit: https://sparknlp.org/models"
+)
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://github.com/JohnSnowLabs/spark-nlp/blob/master/examples/python/annotation/text/english/coreference-resolution/Coreference_Resolution_SpanBertCorefModel.ipynb#L117">
+    <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)
+
+# Load examples
+examples = [
+    "Alice went to the market. She bought some fresh vegetables there. The tomatoes she purchased were particularly ripe.",
+    "Dr. Smith is a renowned surgeon. He has performed over a thousand successful operations. His colleagues respect him a lot.",
+    "The company announced a new product launch. It is expected to revolutionize the industry. The CEO was very excited about it.",
+    "Jennifer enjoys hiking. She goes to the mountains every weekend. Her favorite spot is the Blue Ridge Mountains.",
+    "The team won the championship. They celebrated their victory with a huge party. Their coach praised their hard work and dedication.",
+    "Michael is studying computer science. He finds artificial intelligence fascinating. His dream is to work at a leading tech company.",
+    "Tom is a skilled guitarist. He plays in a local band. His performances are always energetic and captivating."
+]
+
+# st.subheader("Automatically detect phrases expressing dates and normalize them with respect to a reference date.")
+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.subheader('Full example text')
+st.write(text_to_analyze)
+
+# Initialize Spark and create pipeline
+spark = init_spark()
+pipeline = create_pipeline()
+output = fit_data(pipeline, text_to_analyze)
+
+# Display matched sentence
+st.subheader("Processed output:")
+
+results = {
+    'Token': [t.result for t in output[0]['token']],
+    'Begin': [p.begin for p in output[0]['pos']],
+    'End': [p.end for p in output[0]['pos']],
+    'POS': [p.result for p in output[0]['pos']]
+}
+
+df = pd.DataFrame(results)
+df.index += 1
+st.dataframe(df)
+
+from annotated_text import annotated_text
+
+# Create annotated text
+annotated_tokens = []
+for token, pos in zip(results['Token'], results['POS']):
+    annotated_tokens.append((token, pos.lower()))
+
+# Annotate the entire text with annotated tokens
+annotated_text(*annotated_tokens)