import streamlit as st
import pandas as pd
import csv
import sys

# Increase the field size limit
csv.field_size_limit(sys.maxsize)

# Load the CSV data
@st.cache_data
def load_data(file_path):
    def custom_csv_parser(file_path):
        parsed_data = []
        with open(file_path, 'r', newline='', encoding='utf-8') as csvfile:
            reader = csv.reader(csvfile, delimiter=',', quotechar='"', quoting=csv.QUOTE_MINIMAL)
            header = next(reader)
            parsed_data.append(header)
            num_columns = len(header)
            for line_number, row in enumerate(reader, start=1):
                if len(row) == num_columns:
                    parsed_data.append(row)
                else:
                    # Print the line number (0th value of the line)
                    print(f"Line number {line_number} (row 0th value: {row[0] if row else 'Empty'}) has mismatched columns")
                    # Handle rows with mismatched columns
                    if len(row) < num_columns:
                        row.extend([''] * (num_columns - len(row)))  # Pad with empty strings
                    else:
                        row = row[:num_columns]  # Truncate to the correct number of columns
                    parsed_data.append(row)
        return pd.DataFrame(parsed_data[1:], columns=parsed_data[0])

    return custom_csv_parser(file_path)

# Paginate function
def paginate_data(df, page_number, page_size):
    start_index = page_number * page_size
    end_index = start_index + page_size
    return df[start_index:end_index]

# Streamlit app
def main():
    st.title("Emotion Filter and Pagination App")

    # Load the data
    file_path = 'emo_inferred_full.csv'  # Ensure this is the correct path to your uploaded CSV file
    df = load_data(file_path)

    # Dropdown for selecting emotion
    unique_emotions =  ["admiration", "amusement", "anger", "annoyance", "approval",
                  "caring", "confusion", "curiosity", "desire", "disappointment",
                  "disapproval", "disgust", "embarrassment", "excitement", "fear",
                  "gratitude", "grief", "joy", "love", "nervousness", "optimism",
                  "pride", "realization", "relief", "remorse", "sadness", "surprise",
                  "neutral"]
    selected_emotion = st.selectbox('Select Emotion', unique_emotions)

    # Filter the data based on the selected emotion and sort by score
    filtered_data = df[df['emotion'] == selected_emotion].sort_values(by='emoscore', ascending=False).head(100)

    # Pagination settings
    page_size = 10
    total_pages = (len(filtered_data) // page_size) + 1
    page_number = st.number_input('Page number', 0, total_pages - 1, 0)

    # Paginate data
    paginated_data = paginate_data(filtered_data, page_number, page_size)

    # Display total counts of each emotion
    emotion_counts = df['emotion'].value_counts()
    st.write("### Total Emails of Each Emotion")
    st.write(emotion_counts)

    # Display the paginated data
    st.write(f"Showing page {page_number + 1} of {total_pages}")
    st.write(paginated_data)

if __name__ == "__main__":
    main()