app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.feature_extraction.text import CountVectorizer
import seaborn as sns
import plotly.express as px
import plotly.io as pio
import plotly.graph_objects as go

# Set page configuration
st.set_page_config(layout="wide")

# Function to load and clean data
def load_and_clean_data():
    df1 = pd.read_csv("data/reviewed_social_media_english.csv")
    df2 = pd.read_csv("data/reviewed_news_english.csv")
    df3 = pd.read_csv("data/tamil_social_media.csv")  
    df4 = pd.read_csv("data/tamil_news.csv")       

    # Concatenate dataframes and clean data
    df_combined = pd.concat([df1, df2, df3, df4])
    df_combined['Domain'] = df_combined['Domain'].replace({"MUSLIM": "Muslim", "nan": pd.NA, "None": pd.NA, "Other-Ethnic": "Other-Ethnicity"})
    df_combined['Sentiment'] = df_combined['Sentiment'].replace({"nan": pd.NA, "None": pd.NA, "No": pd.NA})

    # Drop rows with NA values in 'Domain' and 'Sentiment'
    df_combined = df_combined.dropna(subset=['Domain', 'Sentiment'])

    return df_combined

df = load_and_clean_data()

# Sidebar Filters
domain_options = df['Domain'].dropna().unique()
channel_options = df['Channel'].dropna().unique()
sentiment_options = df['Sentiment'].dropna().unique()
discrimination_options = df['Discrimination'].dropna().unique()

domain_filter = st.sidebar.multiselect('Select Domain', options=domain_options, default=domain_options)
channel_filter = st.sidebar.multiselect('Select Channel', options=channel_options, default=channel_options)
sentiment_filter = st.sidebar.multiselect('Select Sentiment', options=sentiment_options, default=sentiment_options)
discrimination_filter = st.sidebar.multiselect('Select Discrimination', options=discrimination_options, default=discrimination_options)

# Apply filters
df_filtered = df[(df['Domain'].isin(domain_filter)) & 
                 (df['Channel'].isin(channel_filter)) & 
                 (df['Sentiment'].isin(sentiment_filter)) & 
                 (df['Discrimination'].isin(discrimination_filter))]

# Define a color palette for consistent visualization styles
color_palette = px.colors.sequential.Viridis

# Page navigation
page = st.sidebar.selectbox("Choose a page", ["Overview", "Sentiment Analysis", "Discrimination Analysis", "Channel Analysis"])

# Visualisation for Domain Distribution
def create_pie_chart(df, column, title):
    fig = px.pie(df, names=column, title=title, hole=0.35)
    fig.update_layout(margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1), font=dict(size=12))
    fig.update_traces(marker=dict(colors=color_palette))
    return fig

# Visualization for Distribution of Gender versus Ethnicity
def create_gender_ethnicity_distribution_chart(df):
    df['GenderOrEthnicity'] = df['Domain'].apply(lambda x: "Gender: Women & LGBTQIA+" if x in ["Women", "LGBTQIA+"] else "Ethnicity")
    fig = px.pie(df, names='GenderOrEthnicity', title='Distribution of Gender versus Ethnicity', hole=0.35)
    fig.update_layout(margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1), font=dict(size=12))
    return fig

# Visualization for Sentiment Distribution Across Domains
def create_sentiment_distribution_chart(df):
    df['Discrimination'] = df['Discrimination'].replace({"Non Discriminative": "Non-Discriminative"})  # Assuming typo in the original script
    domain_counts = df.groupby(['Domain', 'Sentiment']).size().reset_index(name='counts')
    fig = px.bar(domain_counts, x='Domain', y='counts', color='Sentiment', title="Sentiment Distribution Across Domains", barmode='stack')
    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Domain", yaxis_title="Counts", font=dict(size=12))
    return fig

# Visualization for Correlation between Sentiment and Discrimination
def create_sentiment_discrimination_grouped_chart(df):
    crosstab_df = pd.crosstab(df['Sentiment'], df['Discrimination']).reset_index()
    melted_df = pd.melt(crosstab_df, id_vars='Sentiment', value_vars=['Yes', 'No'], var_name='Discrimination', value_name='Count')
    fig = px.bar(melted_df, x='Sentiment', y='Count', color='Discrimination', barmode='group', title="Sentiment vs. Discrimination")
    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20), xaxis_title="Sentiment", yaxis_title="Count", font=dict(size=12))
    return fig

# Function for Channel-wise Sentiment Over Time Chart
def create_channel_sentiment_over_time_chart(df):
    df['Date'] = pd.to_datetime(df['Date'])
    timeline = df.groupby([df['Date'].dt.to_period('M'), 'Channel', 'Sentiment']).size().unstack(fill_value=0)
    fig = px.line(timeline, x=timeline.index.levels[1].to_timestamp(), y=['Positive', 'Negative', 'Neutral'], color='Channel')
    fig.update_layout(title='Channel-wise Sentiment Over Time', margin=dict(l=20, r=20, t=40, b=20))
    return fig

# Function for Channel-wise Distribution of Discriminative Content Chart
def create_channel_discrimination_chart(df):
    channel_discrimination = df.groupby(['Channel', 'Discrimination']).size().unstack(fill_value=0)
    fig = px.bar(channel_discrimination, x=channel_discrimination.index, y=['Discriminative', 'Non-Discriminative'], barmode='group')
    fig.update_layout(title='Channel-wise Distribution of Discriminative Content', margin=dict(l=20, r=20, t=40, b=20))
    return fig

# Function for rendering dashboard
def render_dashboard(page, df_filtered):
    if page == "Overview":
        st.title("Overview Dashboard")
        # Create 2x2 grid for overview visualizations
        col1, col2 = st.beta_columns(2)
        with col1:
            st.plotly_chart(create_pie_chart(df_filtered, 'Domain', 'Distribution of Domains'))
        with col2:
            st.plotly_chart(create_gender_ethnicity_distribution_chart(df_filtered))

        col3, col4 = st.beta_columns(2)
        with col3:
            st.plotly_chart(create_sentiment_distribution_chart(df_filtered))
        with col4:
            st.plotly_chart(create_sentiment_discrimination_grouped_chart(df_filtered))

    elif page == "Sentiment Analysis":
        st.title("Sentiment Analysis Dashboard")
        # Implement sentiment analysis visualizations here

    elif page == "Discrimination Analysis":
        st.title("Discrimination Analysis Dashboard")
        # Implement discrimination analysis visualizations here

    elif page == "Channel Analysis":
        st.title("Channel Analysis Dashboard")
        # Create visualizations for the channel analysis page
        col1, col2 = st.columns(2)
        with col1:
            st.plotly_chart(create_channel_sentiment_over_time_chart(df_filtered))
        with col2:
            st.plotly_chart(create_channel_discrimination_chart(df_filtered))

# Render the selected dashboard page
render_dashboard(page, df_filtered)