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")


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")       

    # Normalize Text and Drop irrelevant data
    frames = [df1, df2, df3, df4]
    for frame in frames:
        frame['Domain'].replace("MUSLIM", "Muslim", inplace=True)
        frame.drop(frame[frame['Domain'] == 'Not relevant'].index, inplace=True)
        frame.drop(frame[frame['Domain'] == 'None'].index, inplace=True)
        frame.drop(frame[frame['Discrimination'] == 'None'].index, inplace=True)
        frame.drop(frame[frame['Sentiment'] == 'None'].index, inplace=True)

    # Concatenate/merge dataframes
    df_combined = pd.concat(frames)
    return df_combined

df = load_and_clean_data()

# Normalize Text
df1['Domain'].replace("MUSLIM", "Muslim", inplace=True)
df2['Domain'].replace("MUSLIM", "Muslim", inplace=True)
df3['Domain'].replace("MUSLIM", "Muslim", inplace=True)
df4['Domain'].replace("MUSLIM", "Muslim", inplace=True)

# Drop irrelevant data
frames = [df1, df2, df3, df4]
for df in frames:
    df = df[df['Domain'] != 'Not relevant']
    df = df[df['Domain'] != 'None']
    df = df[df['Discrimination'] != 'None']
    df = df[df['Sentiment'] != 'None']

# Concatenate/merge dataframes
df = pd.concat(frames)

# Visualization function
def create_visualizations(df):
    # [Existing visualization code]
    pass

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

if page == "Overview":
    create_visualizations(df)  # Placeholder for overview visualizations
elif page == "Sentiment Analysis":
    create_visualizations(df)  # Placeholder for sentiment analysis visualizations
elif page == "Discrimination Analysis":
    create_visualizations(df)  # Placeholder for discrimination analysis visualizations
elif page == "Channel Analysis":
    create_visualizations(df)  # Placeholder for channel analysis visualizations

# [Place the rest of the code for the visualizations here]


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

# Function for Domain Distribution Chart
def create_domain_distribution_chart(df):
    fig = px.pie(df, names='Domain', title='Distribution of Domains', hole=0.35)
    fig.update_layout(title_x=0.5, margin=dict(l=20, r=20, t=30, b=20), legend=dict(x=0.1, y=1))
    fig.update_traces(marker=dict(colors=color_palette))
    return fig

# Function for Sentiment Distribution Across Domains Chart
def create_sentiment_distribution_chart(df):
    # ... [Include the existing code for the Sentiment Distribution chart]
    fig.update_layout(margin=dict(l=20, r=20, t=40, b=20))
    return fig

# ... [Define other chart functions following the same pattern]

# 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

# Dashboard Layout
def render_dashboard():
    # Overview page layout
    if page == "Overview":
        st.header("Overview of Domains and Sentiments")
        col1, col2 = st.beta_columns(2)
        with col1:
            st.plotly_chart(create_domain_distribution_chart(df))
        with col2:
            st.plotly_chart(create_sentiment_distribution_chart(df))
        # ... [Additional overview charts]

    # ... [Other pages]

# Define Sidebar Filters
domain_options = df['Domain'].unique()
channel_options = df['Channel'].unique()
sentiment_options = df['Sentiment'].unique()
discrimination_options = df['Discrimination'].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 the filters to the dataframe
df_filtered = df[(df['Domain'].isin(domain_filter)) & 
                 (df['Channel'].isin(channel_filter)) & 
                 (df['Sentiment'].isin(sentiment_filter)) & 
                 (df['Discrimination'].isin(discrimination_filter))]

# Render the dashboard with filtered data
render_dashboard(df_filtered)