Spaces:
Sleeping
Sleeping
File size: 2,533 Bytes
a9200d2 882e0e7 a9200d2 882e0e7 1b95adc a9200d2 1b95adc a9200d2 22d2130 a9200d2 1b95adc a9200d2 1b95adc a9200d2 1b95adc a9200d2 1b95adc c5ccd6f a9200d2 1b95adc a9200d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 |
import pandas as pd
import json
import streamlit as st
import matplotlib.pyplot as plt
import seaborn as sns
from wordcloud import WordCloud
st.set_option('deprecation.showPyplotGlobalUse', False)
# Define the Streamlit app
st.title("Aspected-Based Sentiment Analysis with MVP")
palette_color = sns.color_palette('Set1')
# 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(f"{len(df)}+ sentiment tuples was detected")
st.write(df)
# Sentiment Distribution Chart
sentiment_distribution_perc = df["S"].value_counts(normalize=True) * 100
sentiment_distribution = df["S"].value_counts()
st.subheader("Sentiment Distribution")
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(10, 6))
ax1.pie(sentiment_distribution_perc, labels=sentiment_distribution_perc.index, autopct='%1.1f%%', startangle=140,colors=palette_color)
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")
ax2.bar(sentiment_distribution.index, sentiment_distribution.values, color=palette_color)
# ax2.xlabel("Sentiment")
# ax2.ylabel("Times")
# ax2.xticks(rotation=0) # Rotate x-axis labels if needed
st.pyplot(fig)
# 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_<lambda_0>': 'Great', 'S_<lambda_1>': 'Ok', 'S_<lambda_2>': 'Bad'})
st.subheader("Top 5 Most Mentioned Product Apsects")
st.write(grouped.sort_values(by="Freq", ascending=False).head(5))
# 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.**") |