import pandas as pd
import re
import nltk
import gradio as gr
import matplotlib.pyplot as plt
import seaborn as sns
from nltk.sentiment import SentimentIntensityAnalyzer

nltk.download("vader_lexicon")
sia = SentimentIntensityAnalyzer()

def clean_text(text):
    if not isinstance(text, str):
        return ""
    text = re.sub(r"http\S+", "", text)
    text = re.sub(r"@\w+|#\w+", "", text)
    text = re.sub(r"[^\w\s]", "", text)
    text = text.lower().strip()
    return text

def get_sentiment_label(score, pos_thresh, neg_thresh):
    if score >= pos_thresh:
        return "Positive"
    elif score <= neg_thresh:
        return "Negative"
    else:
        return "Neutral"

def analyze_sentiment(file, text_column, pos_thresh, neg_thresh):
    try:
        df = pd.read_csv(file.name)
    except Exception as e:
        return f"Error reading CSV file: {e}", None, None, None, None

    if text_column not in df.columns:
        return "Selected column not found.", None, None, None, None

    df["clean_text"] = df[text_column].apply(clean_text)
    df["compound"] = df["clean_text"].apply(lambda x: sia.polarity_scores(x)["compound"])
    df["sentiment"] = df["compound"].apply(lambda score: get_sentiment_label(score, pos_thresh, neg_thresh))

    # Save CSV
    output_file = "VADER_sentiment_results.csv"
    df.to_csv(output_file, index=False)

    # Plot 1: Sentiment distribution
    plt.figure(figsize=(6, 4))
    sns.countplot(data=df, x="sentiment", palette="Set2")
    plt.title("Sentiment Distribution")
    plt.tight_layout()
    sentiment_fig = "sentiment_dist.png"
    plt.savefig(sentiment_fig)
    plt.close()

    # Plot 2: Compound score histogram
    plt.figure(figsize=(6, 4))
    sns.histplot(df["compound"], bins=30, kde=True, color="skyblue")
    plt.title("Compound score distribution")
    plt.xlabel("Compound score")
    plt.tight_layout()
    compound_fig = "compound_dist.png"
    plt.savefig(compound_fig)
    plt.close()

    # Sample preview
    preview = df[[text_column, "compound", "sentiment"]].head(10)

    return f"Sentiment analysis complete. Processed {len(df)} rows.", preview, output_file, sentiment_fig, compound_fig

def get_text_columns(file):
    try:
        df = pd.read_csv(file.name, nrows=1)
        text_columns = df.select_dtypes(include='object').columns.tolist()
        if not text_columns:
            return gr.update(choices=[], value=None, label="⚠️ No text columns found!")
        return gr.update(choices=text_columns, value=text_columns[0])
    except Exception:
        return gr.update(choices=[], value=None, label="⚠️ Error reading file")

with gr.Blocks() as app:
    gr.Markdown("## Sentiment analysis with VADER")
    gr.Markdown("Upload a CSV, choose a text column, adjust sentiment thresholds, and run analysis.")
    gr.Markdown("**Citation:** Mat Roni, S. (2025). *Sentiment analysis with VADER on Gradio* (version 1.0) [software]. https://huggingface.co/spaces/pvaluedotone/VADER_sentiment_analysis")

    with gr.Row():
        file_input = gr.File(label="Upload CSV", file_types=[".csv"])
        column_dropdown = gr.Dropdown(label="Select Text Column", choices=[], interactive=True)

    file_input.change(get_text_columns, inputs=file_input, outputs=column_dropdown)

    with gr.Row():
        pos_thresh_slider = gr.Slider(minimum=0.0, maximum=1.0, value=0.05, step=0.01, label="Positive Threshold")
        neg_thresh_slider = gr.Slider(minimum=-1.0, maximum=0.0, value=-0.05, step=0.01, label="Negative Threshold")

    analyze_button = gr.Button("Run Sentiment Analysis")

    status_box = gr.Textbox(label="Status")
    data_output = gr.Dataframe(label="Sample Output (Top 10)")
    file_output = gr.File(label="Download Full Results")
    sentiment_plot = gr.Image(label="Sentiment Label Distribution")
    compound_plot = gr.Image(label="Compound Score Distribution")

    analyze_button.click(
        fn=analyze_sentiment,
        inputs=[file_input, column_dropdown, pos_thresh_slider, neg_thresh_slider],
        outputs=[status_box, data_output, file_output, sentiment_plot, compound_plot]
    )

app.launch(debug=True, share=True)