Py.Cafe

from dash import Dash, dcc, html, Input, Output
import pandas as pd
import plotly.express as px
import plotly.graph_objects as go

# Load the data
file_path = "https://raw.githubusercontent.com/plotly/Figure-Friday/main/2025/week-4/Post45_NEAData_Final.csv"

data = pd.read_csv(file_path, on_bad_lines='skip')
print(data.columns)
# Initialize the Dash app
app = Dash(__name__)

# Preprocess the data
# Melt certifications data for better grouping
certification_columns = {
    'ba': "Bachelor's Degree",
    'ba2': "Additional Bachelor's Degree",
    'ma': "Master's Degree",
    'ma2': "Additional Master's Degree",
    'phd': "PhD",
    'mfa': "MFA",
    'mfa2': "Additional MFA"
}

certifications = data.melt(
    id_vars=['gender'], 
    value_vars=list(certification_columns.keys()),
    var_name='certification_type', 
    value_name='institution'
).dropna(subset=['institution'])

# Map the abbreviated certification names to full names
certifications['certification_type'] = certifications['certification_type'].map(certification_columns)

# Prepare data for the Choropleth map
# Combine year columns F and G into a single year column for counting
choropleth_data = data.copy()
choropleth_data['grant_year'] = choropleth_data['other_nea_grant'].fillna(choropleth_data['nea_grant_year'])

# Clean grant_year column by handling cases like "1979, 1989" or "1987;1979"
def clean_grant_year(value):
    if isinstance(value, str):
        for delimiter in [',', ';']:
            if delimiter in value:
                return int(value.split(delimiter)[0].strip())  # Take the first year
        try:
            return int(value.strip())  # Handle single-year strings
        except ValueError:
            return None
    try:
        return int(value)  # Handle numeric values
    except ValueError:
        return None

choropleth_data['grant_year'] = choropleth_data['grant_year'].apply(clean_grant_year)
choropleth_data = choropleth_data.dropna(subset=['grant_year'])
choropleth_data = choropleth_data.groupby(['us_state', 'grant_year']).size().reset_index(name='count')

# Prepare data for gender trends over years
gender_trends = data.copy()
gender_trends['grant_year'] = gender_trends['other_nea_grant'].fillna(gender_trends['nea_grant_year'])
gender_trends['grant_year'] = gender_trends['grant_year'].apply(clean_grant_year)
gender_trends = gender_trends.dropna(subset=['grant_year', 'gender'])
gender_trends = gender_trends.groupby(['grant_year', 'gender']).size().reset_index(name='count')

# Prepare data for Pareto chart
gender_by_university = certifications.groupby(['institution', 'gender']).size().reset_index(name='count')
university_totals = gender_by_university.groupby('institution')['count'].sum().reset_index()
university_totals = university_totals.sort_values(by='count', ascending=False)
university_totals['cumulative_percentage'] = university_totals['count'].cumsum() / university_totals['count'].sum() * 100

# Layout of the Dash app
app.layout = html.Div([
    html.H1('NEA Data Visualizations', style={'textAlign': 'center', 'color': 'white'}),

    dcc.Tabs([
        dcc.Tab(label='Certifications', children=[
            html.Div([
                html.H2('Certifications by Gender', style={'color': 'white'}),
                dcc.Graph(id='certifications-by-gender'),
            ], style={'margin': '20px'}),

            html.Div([
                html.H2('Gender by University - Pareto Chart', style={'color': 'white'}),
                dcc.Graph(id='pareto-gender-by-university'),
            ], style={'margin': '20px'})
        ]),

        dcc.Tab(label='Grants', children=[
            html.Div([
                html.H2('NEA Grants Heatmap by State', style={'color': 'white'}),
                dcc.Graph(id='heatmap-grants-by-state'),
            ], style={'margin': '20px'}),

            html.Div([
                html.H2('NEA Grants Choropleth Map', style={'color': 'white'}),
                dcc.Graph(id='choropleth-map'),
            ], style={'margin': '20px'})
        ]),

        dcc.Tab(label='Trends', children=[
            html.Div([
                html.H2('Male vs Female Grants Over the Years', style={'color': 'white'}),
                dcc.Graph(id='gender-trends'),
            ], style={'margin': '20px'})
        ])
    ])
], style={'backgroundColor': '#1e1e1e', 'padding': '20px'})

# Callbacks to generate the graphs
@app.callback(
    Output('certifications-by-gender', 'figure'),
    Input('certifications-by-gender', 'id')
)
def update_certifications_by_gender(_):
    fig = px.histogram(
        certifications, 
        x='certification_type', 
        color='gender',
        title='Count of Certifications by Gender',
        barmode='group'
    )
    fig.update_layout(
        plot_bgcolor='#1e1e1e',
        paper_bgcolor='#1e1e1e',
        font_color='white'
    )
    return fig


@app.callback(
    Output('pareto-gender-by-university', 'figure'),
    Input('pareto-gender-by-university', 'id')
)
def update_pareto_gender_by_university(_):
    fig = go.Figure()

    # Add bar chart
    fig.add_bar(
        x=university_totals['institution'],
        y=university_totals['count'],
        name='Count'
    )

    # Add cumulative percentage line
    fig.add_scatter(
        x=university_totals['institution'],
        y=university_totals['cumulative_percentage'],
        mode='lines+markers',
        name='Cumulative Percentage',
        yaxis='y2'
    )

    # Update layout
    fig.update_layout(
        title='Gender by University - Pareto Chart',
        yaxis=dict(title='Count'),
        yaxis2=dict(
            title='Cumulative Percentage',
            overlaying='y',
            side='right'
        ),
        plot_bgcolor='#1e1e1e',
        paper_bgcolor='#1e1e1e',
        font=dict(color='white')
    )

    return fig

@app.callback(
    Output('heatmap-grants-by-state', 'figure'),
    Input('heatmap-grants-by-state', 'id')
)
def update_heatmap_grants_by_state(_):
    state_grants = data.groupby(['us_state', 'nea_grant_year']).size().reset_index(name='count')
    fig = px.density_heatmap(
        state_grants, 
        x='us_state', 
        y='nea_grant_year', 
        z='count', 
        title='Grants Heatmap by State',
        color_continuous_scale='Viridis'
    )
    fig.update_layout(
        plot_bgcolor='#1e1e1e',
        paper_bgcolor='#1e1e1e',
        font_color='white'
    )
    return fig

@app.callback(
    Output('choropleth-map', 'figure'),
    Input('choropleth-map', 'id')
)
def update_choropleth_map(_):
    fig = px.choropleth(
        choropleth_data,
        locations='us_state',
        locationmode='USA-states',
        color='count',
        scope='usa',
        animation_frame='grant_year',
        title='NEA Grants by State Over Time',
        labels={'count': 'Number of Grants'}
    )
    fig.update_layout(
        geo=dict(bgcolor='rgba(0,0,0,0)'),
        plot_bgcolor='#1e1e1e',
        paper_bgcolor='#1e1e1e',
        font_color='white'
    )
    return fig

@app.callback(
    Output('gender-trends', 'figure'),
    Input('gender-trends', 'id')
)
def update_gender_trends(_):
    fig = px.line(
        gender_trends, 
        x='grant_year', 
        y='count', 
        color='gender',
        title='Male vs Female Grants Over the Years'
    )
    fig.update_layout(
        plot_bgcolor='#1e1e1e',
        paper_bgcolor='#1e1e1e',
        font_color='white'
    )
    return fig

# Run the app
if __name__ == '__main__':
    app.run_server(debug=True)