import pandas as pd import json import streamlit as st import matplotlib.pyplot as plt import seaborn as sns from wordcloud import WordCloud # Define the Streamlit app st.title("Data Analysis and Visualization") # File upload and processing uploaded_file = st.file_uploader("Upload JSON File", type=["json"]) if uploaded_file: loaded_dict = json.load(uploaded_file) df = pd.DataFrame(loaded_dict) st.subheader("Dataframe (df)") st.write(df) # Group by and aggregate data grouped = df.groupby('A').agg({'S': ['count', lambda x: (x == 'great').sum(), lambda x: (x == 'ok').sum(), lambda x: (x == 'bad').sum()]}) grouped.columns = grouped.columns.map('_'.join) grouped = grouped.reset_index() grouped = grouped.rename(columns={'A': 'Aspect', 'S_count': 'Freq', 'S_': 'Great', 'S_': 'Ok', 'S_': 'Bad'}) st.subheader("Top Aspects by Frequency") st.write(grouped.sort_values(by="Freq", ascending=False).head(5)) # Sentiment Distribution Chart sentiment_distribution = df["S"].value_counts(normalize=True) * 100 palette_color = sns.color_palette('bright') st.subheader("Sentiment Distribution") fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 6)) ax1.pie(sentiment_distribution, labels=sentiment_distribution.index, autopct='%1.1f%%', startangle=140) ax1.axis('equal') ax1.set_title("Sentiment Distribution %") sns.countplot(x="S", data=df, palette=palette_color, ax=ax2) ax2.set_title("Sentiment Distribution Counts") st.pyplot(fig) # Word Cloud aspect_terms = " ".join(df["A"]) wordcloud = WordCloud( width=800, height=400, background_color='white', max_words=100, colormap='inferno', contour_width=3, contour_color='red', ).generate(aspect_terms) st.subheader("Word Cloud for Most Mentioned Aspects") plt.figure(figsize=(10, 5)) plt.imshow(wordcloud, interpolation='bilinear') plt.title("Most mentioned aspect terms") plt.axis("off") st.pyplot() st.sidebar.markdown("**Upload a JSON file to get started.**")