PyCafe - Dash - Age-Based Running Performance Analysis

app.py
requirements.txt
ritabanm-app.py
app.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
from dash import Dash, dcc, html
import plotly.express as px
import pandas as pd

# Load the dataset
file_path = "https://raw.githubusercontent.com/Coding-with-Adam/Dash-by-Plotly/refs/heads/master/Other/NYC%20Marathon%20Results%2C%202024%20-%20Marathon%20Runner%20Results.csv"

df = pd.read_csv(file_path)

# Convert overallTime to seconds for easier calculations
def time_to_seconds(time_str):
    if isinstance(time_str, str):
        h, m, s = map(int, time_str.split(":"))
        return h * 3600 + m * 60 + s
    return None

df["overallTime_seconds"] = df["overallTime"].apply(time_to_seconds)

# Best Age Group for Running Performance
age_group_performance = df.groupby("age")["overallTime_seconds"].mean().reset_index()

# Age vs. Finishing Time Correlation
fig_age_vs_time = px.scatter(
    df, x="age", y="overallTime_seconds", 
    title="Age vs. Finishing Time Correlation",
    labels={"age": "Age", "overallTime_seconds": "Overall Time (Seconds)"},
    trendline="ols"
)

# Filter data for US participants
us_runners = df[(df["countryCode"].astype(str) == "USA") & (df["stateProvince"].astype(str).str.len() == 2)].copy()

# Group by state and calculate average finishing time
state_avg_time = us_runners.groupby("stateProvince")["overallTime_seconds"].mean().reset_index()

# Convert back to HH:MM:SS format
state_avg_time["avg_overallTime"] = state_avg_time["overallTime_seconds"].apply(
    lambda x: f"{int(x//3600)}:{int((x%3600)//60):02}:{int(x%60):02}"
)

# Create a Plotly figure
fig_state = px.bar(
    state_avg_time.sort_values("overallTime_seconds"),
    x="stateProvince",
    y="overallTime_seconds",
    text="avg_overallTime",
    title="Average Finishing Time by State (US Runners)",
    labels={"stateProvince": "State", "overallTime_seconds": "Average Finishing Time (Seconds)"},
)
fig_state.update_traces(textposition="outside")
fig_state.update_layout(xaxis_title="State", yaxis_title="Average Finishing Time (Seconds)", xaxis={'categoryorder':'total ascending'})

# Dash app setup
app = Dash(__name__)
app.layout = html.Div(
    children=[
        dcc.Graph(figure=fig_state),
        dcc.Graph(figure=fig_age_vs_time)
    ]
)

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

NYC-Plotly-Meetup-March-marathon

Age-Based Running Performance Analysis
