Upload app.py

app.py

@@ -0,0 +1,87 @@
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+import matplotlib.pyplot as plt
+import plotly.graph_objs as go
+from wordcloud import WordCloud
+from transformers import pipeline
+
+# Load the pre-trained sentiment analysis model
+sentiment_model = pipeline("sentiment-analysis", model="siebert/sentiment-roberta-large-english")
+
+# Define the Streamlit app's user interface
+# Set page title and favicon
+st.set_page_config(page_title="review Analysis", page_icon=":smiley:")
+
+# Add image and heading
+st.image("home.png", use_column_width=True)
+
+file = st.file_uploader("Drop your file here", type=["csv"])
+
+# Define the app's functionality
+if file is not None:
+    # Read the CSV file into a Pandas DataFrame
+    df = pd.read_csv(file)
+
+    # Write the total number of records
+    st.markdown(
+        f'<div style="background-color: #234A21; color: #ffffff; padding: 8px; font-size: 30px; font-family: Open-Sans; font-weight: bold; text-align: center;"> {len(df)} reviews to analyse!</div>',
+        unsafe_allow_html=True
+    )
+
+    # Apply the sentiment analysis model to each review and store the results in a new column
+    df["sentiment"] = df["review"].apply(lambda x: sentiment_model(x)[0]["label"])
+
+    # Generate pie chart
+    # Define custom colors
+    colors = ['#FFC845', '#52565E']
+
+    # Generate pie chart
+    sentiment_counts = df["sentiment"].value_counts()
+    fig = px.pie(sentiment_counts, values=sentiment_counts.values, names=sentiment_counts.index,
+                 color_discrete_sequence=colors)
+    st.plotly_chart(fig)
+
+    # Create word clouds for positive and negative reviews
+    positive_reviews = " ".join(df[df["sentiment"] == "POSITIVE"]["review"].tolist())
+    negative_reviews = " ".join(df[df["sentiment"] == "NEGATIVE"]["review"].tolist())
+
+    st.markdown(
+        f'<div style="background-color: #234A21; color: #ffffff; padding: 6px; font-size: 20px; font-family: Open-Sans; font-weight: bold; text-align: center; margin-bottom: 250px;"> Word Cloud for Positive Reviews</div>',
+        unsafe_allow_html=True
+    )
+    wc = WordCloud(width=800, height=400, background_color="white", colormap="blues").generate(positive_reviews)
+    st.image(wc.to_array())
+
+    st.markdown(
+        f'<div style="background-color: #234A21; color: #ffffff; padding: 6px; font-size: 20px; font-family: Open-Sans; font-weight: bold; text-align: center; margin-bottom: 250px; margin-top: 50px;"> Word Cloud for Negative Reviews</div>',
+        unsafe_allow_html=True
+    )
+    wc = WordCloud(width=800, height=400, background_color="white", colormap="blues").generate(negative_reviews)
+    st.image(wc.to_array())
+
+    # Display the sentiment of each review as cards
+    st.markdown(
+        f'<div style="background-color: #234A21; color: #ffffff; padding: 6px; font-size: 20px; font-family: Open-Sans; font-weight: bold; text-align: center; margin-bottom: 10px; margin-top: 10px;"> What customers said about us</div>',
+        unsafe_allow_html=True
+    )
+
+    # Define sentiment colors
+    sentiment_colors = {'POSITIVE': 'FFC845', 'NEGATIVE': '52565E'}
+
+    # Map sentiment to colors and apply to review column
+    df['review'] = df['review'].apply(lambda x: f'<span style="color: {sentiment_colors[x]}">{x}</span>')
+
+    # Create HTML table with no border and centered text
+    table_html = (df.style
+                  .set_properties(**{'text-align': 'center'})
+                  .set_table_styles(
+        [{'selector': 'th', 'props': [('border', '0px')]}, {'selector': 'td', 'props': [('border', '0px')]}])
+                  .render())
+
+    # Display the table
+    st.write(table_html, unsafe_allow_html=True)
+
+
+else:
+    st.write("Please upload a CSV file.")