Py.Cafe

import pandas as pd
import numpy as np
import plotly.express as px
import dash
import dash_bootstrap_components as dbc
from dash import Input, Output, dcc, html

df = pd.read_csv("NYC Marathon Results, 2024 - Marathon Runner Results.csv")

def convert_time_to_minutes(time_str):
    parts = time_str.split(':')
    if len(parts) == 3:  # Formato HH:MM:SS
        hours, minutes, seconds = map(int, parts)
        total_minutes = hours * 60 + minutes + seconds / 60
    elif len(parts) == 2:  # Formato MM:SS
        minutes, seconds = map(int, parts)
        total_minutes = minutes + seconds / 60
    else:
        raise ValueError("Formato de tiempo no reconocido")
    
    return total_minutes

# Crear una función para categorizar por edad
def categorize_age(age):
    if 18 <= age <= 19:
        return '18-19'
    elif 20 <= age <= 24:
        return '20-24'
    elif 25 <= age <= 29:
        return '25-29'
    elif 30 <= age <= 34:
        return '30-34'
    elif 35 <= age <= 39:
        return '35-39'
    elif 40 <= age <= 44:
        return '40-44'
    elif 45 <= age <= 49:
        return '45-49'
    elif 50 <= age <= 54:
        return '50-54'
    elif 55 <= age <= 59:
        return '55-59'
    elif 60 <= age <= 64:
        return '60-64'
    elif 65 <= age <= 70:
        return '65-70'
    else:
        return '71+'

df['pace_minutes'] = (df['pace'].apply(convert_time_to_minutes).round(2))
df['overallTime_minutes'] = df['overallTime'].apply(convert_time_to_minutes).round(2)
df['ageGradeTime_minutes'] = df['ageGradeTime'].apply(convert_time_to_minutes).round(2)
df['ageCategory'] = df['age'].apply(categorize_age)

brasil_df = df.query("iaaf == 'BRA'")

gender_dict = {"M":"Men", "W":"Woman"}

brasil_df.loc[:, 'gender'] = brasil_df.gender.map(gender_dict)

def categorize_country(country_code):
    
    if country_code in ['BRA', 'USA']:
        return country_code
    else:
        return "Other Country"

# Assuming brasil_df is your pandas DataFrame
brasil_df.loc[:,'country_living'] = brasil_df['countryCode'].apply(categorize_country)

def brasil_pie_chart():
    brasil_pie = brasil_df.country_living.value_counts()
    fig = px.pie(brasil_pie, values=brasil_pie.values, names=brasil_pie.index,hole=0.65,
                 color_discrete_sequence=px.colors.sequential.Viridis_r,
                 template='plotly_white')
    fig.update_layout(legend=dict(title=None, orientation="h", y=1.1, yanchor="bottom", x=0.1, xanchor="center", font=dict(size=16)),
                     paper_bgcolor='rgb(252, 248, 202)', plot_bgcolor='rgb(252, 248, 202)')
   
    return fig



def brasil_runners_bar():
    
    category_orders = {'ageCategory':['20-24', '25-29', '30-34', '35-39','40-44', '45-49', '50-54', '55-59', '60-64', '65-70', '71+']}
    data = brasil_df.groupby(['ageCategory', 'gender'], as_index=False).agg({'runnerId':'count'})
    fig = px.bar(data, x='ageCategory', y='runnerId', color='gender', 
                 category_orders=category_orders, barmode='relative',
                 color_discrete_sequence=px.colors.qualitative.Vivid,
                 labels={'ageCategory':''},
                 opacity=0.70,
                 template='plotly_white',text_auto=True,range_y=[0,230])
    
    fig.update_layout(legend=dict( title=None, orientation="h", y=1.03, yanchor="bottom", x=0.2, xanchor="center", font=dict(size=18)),
                      xaxis=dict(showline=True, linewidth=2.5, linecolor='lightgray',zeroline=True, zerolinewidth=2, zerolinecolor='red',
                                 tickfont=dict(size=18)),
                     paper_bgcolor='rgb(252, 248, 202)', plot_bgcolor='rgb(252, 248, 202)')
    
    fig.update_traces(textfont_size=14, textangle=0, textposition="outside", cliponaxis=False)
    fig.update_yaxes(visible=False)
    return fig

def pace_minutes_chart():
    category_orders = {'ageCategory':['20-24', '25-29', '30-34', '35-39','40-44', '45-49', '50-54', '55-59', '60-64', '65-70', '71+']}
    data1 = brasil_df.groupby(['ageCategory', 'gender'], as_index=False).agg({'pace_minutes':'mean'}).round(2)
    fig = px.line(data1, x='ageCategory', y='pace_minutes',color='gender', category_orders=category_orders,markers=True,#text_auto=True, barmode='relative',
                 color_discrete_sequence=px.colors.qualitative.Vivid,
                 labels={'ageCategory':'Age Range'},
                 template='plotly_white', text='pace_minutes',
                 symbol='gender', symbol_map={'Men': 'circle', 'Women': 'diamond'}
                 )
    
    fig.update_layout(legend=dict( title=None, orientation="h", y=0.95, yanchor="bottom", x=0.1, xanchor="center", font=dict(size=18)),
                      xaxis=dict(showline=True, linewidth=2.5, linecolor='lightgray',zeroline=True, zerolinewidth=2, zerolinecolor='red',
                                 title_font=dict(size=20), tickfont=dict(size=18)),
                      paper_bgcolor='rgb(252, 248, 202)', plot_bgcolor='rgb(252, 248, 202)'
                     )
    fig.update_traces(textfont_size=16, 
                      # textangle=0, 
                      textposition="top left", cliponaxis=False, marker=dict(size=15))
    fig.update_yaxes(visible=False)
    
   
    
    return fig
    
def overall_time_chart():

    category_orders = {'ageCategory':['20-24', '25-29', '30-34', '35-39','40-44', '45-49', '50-54', '55-59', '60-64', '65-70', '71+']}
    data1 = brasil_df.groupby(['ageCategory', 'gender'], as_index=False).agg({'overallTime_minutes':'mean'}).round(2)
    fig = px.line(data1, x='ageCategory', y='overallTime_minutes',color='gender', category_orders=category_orders,markers=True,#text_auto=True, barmode='relative',
                  color_discrete_sequence=px.colors.qualitative.Vivid,
                  template='plotly_white',labels={'ageCategory':'Age Range'}, text='overallTime_minutes',
                  symbol='gender', symbol_map={'Men': 'circle', 'Women': 'diamond'}
                )
    fig.update_layout(legend=dict( title=None, orientation="h", y=0.95, yanchor="bottom", x=0.1, xanchor="center", font=dict(size=18)),
                      xaxis=dict(showline=True, linewidth=2.5, linecolor='lightgray',zeroline=True, zerolinewidth=2, zerolinecolor='red',
                                title_font=dict(size=20), tickfont=dict(size=18)),
                      paper_bgcolor='rgb(252, 248, 202)', plot_bgcolor='rgb(252, 248, 202)'
                      )
    fig.update_traces(textfont_size=16, 
                      # textangle=0, 
                      textposition="top left", cliponaxis=False, marker=dict(size=15))
    
    fig.update_yaxes(visible=False)

    
    return fig



app = dash.Dash(external_stylesheets=[dbc.themes.SANDSTONE])

app.title = "New York Marathon 2024"




app.layout = dbc.Container(
    [
        html.H2("The Brazilian Runners Performance at the NYC Marathon 2024",
            style={'textAlign': 'center', 'padding': '10px', 'margin': '10px','font-weight': 'bold'}),
        html.H3("Exploring Age, Pace, and Origin",
            style={'textAlign': 'center', 'padding': '10px', 'margin': '10px'}),
        html.Hr(),
        dbc.Row([
            dbc.Col(
                [
                    html.H5("A significant portion (nearly 20%) of Brazilian runners in the NY Marathon are based abroad",
                            style={'textAlign': 'center', 'padding': '5px', 'margin': '5px'}),
                    dcc.Graph(id='brasil-pie', figure=brasil_pie_chart())
                ], width=5),
            dbc.Col(
                [
                    html.H5("Age Distribution of 827 Brazilian who competed in this Edition",
                            style={'textAlign': 'center', 'padding': '5px', 'margin': '5px'}),
                    dcc.Graph(id='runners-bar', figure=brasil_runners_bar())
                ], width=7)
        ]),
        dbc.Tabs([
            dbc.Tab(label="Pace Minutes per Mile by Age Range",
                children=[
                    html.H5("How Fast They Ran: Average Pace in Minutes per Mile",
                            style={'textAlign': 'center', 'padding': '5px', 'margin': '5px'}),
                    html.H6("Men Winner Pace Time = 4.88,  Women Winner Pace Time = 5.52 ",
                            style={'textAlign': 'center', 'padding': '5px', 'margin': '5px','font-style': 'italic'}),
                    dbc.Col(
                        dbc.Card(dcc.Graph(id='pace_minutes-bar', figure=pace_minutes_chart())
                    ) 
                    )
                ]),
            dbc.Tab(label="Overall Time Minutes per Mile by Age Range",
                children=[
                    html.H5("Average Time to Complete the Marathon for Brazilian Athletes (Minutes)",
                            style={'textAlign': 'center', 'padding': '0px', 'margin': '5px'}),
                    html.H6("Men Winner Time = 127.65,  Women Winner Pace Time = 144.58 ",
                            style={'textAlign': 'center', 'padding': '5px', 'margin': '5px','font-style': 'italic'}),
                    dbc.Col(
                        dbc.Card(dcc.Graph(id='overall_minutes-bar', figure=overall_time_chart()), 
                                 
                                )
                    )
                ]
            )
        ])
    ],# fluid=True,
    style={"backgroundColor": '#fcf8ca'}
)

if __name__ == "__main__":
    app.run_server(debug=True)