Update Demo.py

Demo.py

@@ -1,124 +1,124 @@
-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(model):
-    documentAssembler = DocumentAssembler()\
-        .setInputCol("text")\
-        .setOutputCol("document")
-        
-    use = UniversalSentenceEncoder.pretrained("tfhub_use", "en")\
-    .setInputCols(["document"])\
-    .setOutputCol("sentence_embeddings")
-
-
-    sentimentdl = SentimentDLModel.pretrained(model, "en")\
-        .setInputCols(["sentence_embeddings"])\
-        .setOutputCol("sentiment")
-
-    nlpPipeline = Pipeline(stages=[documentAssembler, use, sentimentdl])
-
-    return nlpPipeline
-
-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)[0]
-
-    return results['sentiment'][0].result
-
-# Set up the page layout
-st.markdown('<div class="main-title">State-of-the-Art Sentiment Detection with Spark NLP</div>', unsafe_allow_html=True)
-
-# Sidebar content
-model_name = st.sidebar.selectbox(
-    "Choose the pretrained model",
-    ["sentimentdl_use_imdb", "sentimentdl_use_twitter"],
-    help="For more info about the models visit: https://sparknlp.org/models"
-)
-
-# Reference notebook link in sidebar
-link = """
-<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/SENTIMENT_EN.ipynb">
-    <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
-folder_path = f"inputs/{model}"
-examples = [
-    lines[1].strip() 
-    for filename in os.listdir(folder_path) 
-    if filename.endswith('.txt') 
-    for lines in [open(os.path.join(folder_path, filename), 'r', encoding='utf-8').readlines()] 
-    if len(lines) >= 2
-]
-
-st.subheader("Detect the general sentiment expressed in a movie review or tweet by using our pretrained Spark NLP DL classifier.")
-
-selected_text = None
-result_type = 'tweet'
-if 'imdb' in model.lower() or 't5' in model.lower():
-  selected_text = st.selectbox("Select a sample IMDB review", examples)
-  result_type = 'review'
-else:
-  selected_text = st.selectbox("Select a sample Tweet", examples)
-
-custom_input = st.text_input("Try it for yourself!")
-
-if custom_input:
-    selected_text = custom_input
-elif selected_text:
-    selected_text = selected_text
-
-st.subheader('Selected Text')
-st.write(selected_text)
-
-# Initialize Spark and create pipeline
-spark = init_spark()
-pipeline = create_pipeline(model)
-output = fit_data(pipeline, selected_text)
-
-# Display output sentence
-if output in ['pos', 'positive', 'POSITIVE']:
-  st.markdown("""<h3>This seems like a <span style="color: green">{}</span> {}. <span style="font-size:35px;">&#128515;</span></h3>""".format('positive', result_type), unsafe_allow_html=True)
-elif output in ['neg', 'negative', 'NEGATIVE']:
-  st.markdown("""<h3>This seems like a <span style="color: red">{}</span> {}. <span style="font-size:35px;">&#128544;</span?</h3>""".format('negative', result_type), unsafe_allow_html=True)
-
-
+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(model):
+    documentAssembler = DocumentAssembler()\
+        .setInputCol("text")\
+        .setOutputCol("document")
+        
+    use = UniversalSentenceEncoder.pretrained("tfhub_use", "en")\
+    .setInputCols(["document"])\
+    .setOutputCol("sentence_embeddings")
+
+
+    sentimentdl = SentimentDLModel.pretrained(model, "en")\
+        .setInputCols(["sentence_embeddings"])\
+        .setOutputCol("sentiment")
+
+    nlpPipeline = Pipeline(stages=[documentAssembler, use, sentimentdl])
+
+    return nlpPipeline
+
+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)[0]
+
+    return results['sentiment'][0].result
+
+# Set up the page layout
+st.markdown('<div class="main-title">State-of-the-Art Sentiment Detection with Spark NLP</div>', unsafe_allow_html=True)
+
+# Sidebar content
+model = st.sidebar.selectbox(
+    "Choose the pretrained model",
+    ["sentimentdl_use_imdb", "sentimentdl_use_twitter"],
+    help="For more info about the models visit: https://sparknlp.org/models"
+)
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/SENTIMENT_EN.ipynb">
+    <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
+folder_path = f"inputs/{model}"
+examples = [
+    lines[1].strip() 
+    for filename in os.listdir(folder_path) 
+    if filename.endswith('.txt') 
+    for lines in [open(os.path.join(folder_path, filename), 'r', encoding='utf-8').readlines()] 
+    if len(lines) >= 2
+]
+
+st.subheader("Detect the general sentiment expressed in a movie review or tweet by using our pretrained Spark NLP DL classifier.")
+
+selected_text = None
+result_type = 'tweet'
+if 'imdb' in model.lower() or 't5' in model.lower():
+  selected_text = st.selectbox("Select a sample IMDB review", examples)
+  result_type = 'review'
+else:
+  selected_text = st.selectbox("Select a sample Tweet", examples)
+
+custom_input = st.text_input("Try it for yourself!")
+
+if custom_input:
+    selected_text = custom_input
+elif selected_text:
+    selected_text = selected_text
+
+st.subheader('Selected Text')
+st.write(selected_text)
+
+# Initialize Spark and create pipeline
+spark = init_spark()
+pipeline = create_pipeline(model)
+output = fit_data(pipeline, selected_text)
+
+# Display output sentence
+if output in ['pos', 'positive', 'POSITIVE']:
+  st.markdown("""<h3>This seems like a <span style="color: green">{}</span> {}. <span style="font-size:35px;">&#128515;</span></h3>""".format('positive', result_type), unsafe_allow_html=True)
+elif output in ['neg', 'negative', 'NEGATIVE']:
+  st.markdown("""<h3>This seems like a <span style="color: red">{}</span> {}. <span style="font-size:35px;">&#128544;</span?</h3>""".format('negative', result_type), unsafe_allow_html=True)
+
+