app.py

import gradio as gr
import pandas as pd
import plotly.graph_objects as go

def get_covered_languages():
    #Load data
    all_languages = pd.read_csv('data/merged_language_list_with_duplicates.csv')
    with open("data/covered_languages.txt") as f:
        covered_languages = f.read().splitlines()

    # Split strings with commas and flatten the list
    covered_languages = [lang.strip() for sublist in covered_languages for lang in sublist.split(',')]
    covered_languages = list(set(covered_languages))

    # Get language codes
    covered_language_codes = [all_languages.loc[all_languages['Language'] == lang, 'Code'].values[0] for lang in covered_languages if lang in all_languages['Language'].values]
    assert len(covered_language_codes) == len(covered_languages), "Mismatch between covered languages and their codes"
    return covered_language_codes
    
def build_dataframes(covered_language_codes):
    # Load data
    clean_languages = pd.read_csv('data/merged_language_list_clean.csv')

    # Create a dataframe for languages with a lead
    languages_with_lead = clean_languages[clean_languages['Code'].isin(covered_language_codes)]

    # Create a dataframe for languages without a lead
    languages_without_lead = clean_languages[~clean_languages['Code'].isin(covered_language_codes)]
    return languages_with_lead, languages_without_lead

def create_progress_bar(progress):
    top_labels = ['With lead', 'Without lead']

    colors = ['rgba(38, 24, 74, 0.8)', 'rgba(190, 192, 213, 1)']

    x_data = [len(languages_with_lead), len(languages_without_lead)]

    y_data = ['Progress']

    fig = go.Figure()

    for i in range(0, len(x_data[0])):
        for xd, yd in zip(x_data, y_data):
            fig.add_trace(go.Bar(
                x=[xd[i]], y=[yd],
                orientation='h',
                marker=dict(
                    color=colors[i],
                    line=dict(color='rgb(248, 248, 249)', width=1)
                ),
                hoverinfo='text',
                hovertext=f"{top_labels[i]} records: {xd[i]}"
            ))

    fig.update_layout(
        xaxis=dict(
            showgrid=False,
            showline=False,
            showticklabels=False,
            zeroline=False,
            domain=[0.15, 1]

        ),
        yaxis=dict(
            showgrid=False,
            showline=False,
            showticklabels=False,
            zeroline=False,
            domain=[0.15, 0.5]
        ),
        barmode='stack',
        paper_bgcolor='rgb(248, 248, 255)',
        plot_bgcolor='rgb(248, 248, 255)',
        margin=dict(l=120, r=10, t=140, b=80),
        showlegend=False
    )

    annotations = []

    for yd, xd in zip(y_data, x_data):
        # labeling the y-axis
        annotations.append(dict(xref='paper', yref='y',
                                x=0.14, y=yd,
                                xanchor='right',
                                text=str(yd),
                                font=dict(family='Arial', size=14,
                                        color='rgb(67, 67, 67)'),
                                showarrow=False, align='right'))
        # labeling the first percentage of each bar (x_axis)
        if xd[0] > 0:
            annotations.append(dict(xref='x', yref='y',
                                    x=xd[0] / 2, y=yd,
                                    text=str(xd[0]),
                                    font=dict(family='Arial', size=14,
                                            color='rgb(248, 248, 255)'),
                                    showarrow=False))
        space = xd[0]
        for i in range(1, len(xd)):
            if xd[i] > 0:
                # labeling the rest of percentages for each bar (x_axis)
                annotations.append(dict(xref='x', yref='y',
                                        x=space + (xd[i]/2), y=yd,
                                        text=str(xd[i]),
                                        font=dict(family='Arial', size=14,
                                                color='rgb(248, 248, 255)'),
                                        showarrow=False))
                space += xd[i]

    fig.update_layout(annotations=annotations, height=80)  
    return fig

with gr.Blocks() as demo:
    gr.Markdown("## Language Leads Dashboard")
    languages_with_lead, languages_without_lead = build_dataframes(get_covered_languages())
    with gr.Row():
        progress_bar_output = gr.Plot(label="Language Stats")
    with gr.Tab("Looking for leads!"):
        gr.Markdown("These languages don't have a lead yet! Would you like to lead one of them? Sign up using [this form](https://forms.gle/mFCMXNRjxvyFvW5q9).")
        gr.DataFrame(languages_without_lead)
    with gr.Tab("Languages with leads"):
        gr.Markdown("We found at least one lead for these languages:")
        gr.DataFrame(languages_with_lead)

demo.launch()