import numpy as np
import pandas as pd
import plotly.graph_objects as go
from _plot import show
import statsmodels.formula.api as smf
from sklearn.metrics import r2_score, mean_squared_error, mean_absolute_error
import warnings
warnings.filterwarnings('ignore')
pd.set_option('display.max_columns', None)
pd.set_option('display.precision', 3)
TRAIN_BEFORE = 2015
BLUE, RED = '#2E86AB', '#E84855'Baseball attendance model
OLS regression, and the input that made the fit look too good
Context. COMM 414 Assignment 4, a group assignment from 2022. The brief asked for a regression that predicts attendance at Atlanta Braves home games.
Approach.
- Data: 461 home games (2011 to 2016), joined to daily weather data.
- Method: OLS regression with new variables. Train on the seasons before 2015, test on 2015 and 2016.
Findings.
- The model that we chose has an R² of 0.991 on the training seasons and 0.985 on the test seasons.
- One input divides tickets sold by attendance, so it contains the value that the model predicts. Without that input, the R² is about 0.95.
- Weather explains less than 1% of the variation in attendance.
- A Friday or Saturday game has about 300 more guests.
Limit. This is coursework. It makes no causal claim about attendance or revenue.
1 Setup
2 Data
Show code
baseball = pd.read_csv('../baseball.csv')
weather = pd.read_csv('../weather.csv')
print(f"Game table: {len(baseball):,} games")
print(f"Weather table: {len(weather):,} records")Game table: 461 games
Weather table: 2,126 records
Show code
baseball.drop(columns=baseball.columns[0]).head()| season | opponent | event_id | event_date | event_time | win | attendance | tickets_sold | tickets_resale | opponent_payroll | opponent_rank | opponent_win_pcnt | braves_payroll | braves_rank | braves_win_pcnt | weekday | is_night | |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 2011 | Arizona Diamondbacks | 6347 | 2011-08-20 | 19:10:00 | 1 | 31147 | 39783 | 5052 | 53.640 | 28 | 0.401 | 87.003 | 7 | 0.562 | Saturday | 1 |
| 1 | 2011 | Arizona Diamondbacks | 6348 | 2011-08-21 | 13:35:00 | 1 | 24645 | 35274 | 2425 | 53.640 | 28 | 0.401 | 87.003 | 7 | 0.562 | Sunday | 0 |
| 2 | 2011 | Arizona Diamondbacks | 6346 | 2011-08-19 | 19:35:00 | 1 | 23327 | 30599 | 3078 | 53.640 | 28 | 0.401 | 87.003 | 7 | 0.562 | Friday | 1 |
| 3 | 2011 | Baltimore Orioles | 6323 | 2011-07-02 | 19:10:00 | 1 | 33468 | 38766 | 6759 | 85.304 | 27 | 0.407 | 87.003 | 7 | 0.562 | Saturday | 1 |
| 4 | 2011 | Baltimore Orioles | 6324 | 2011-07-03 | 13:35:00 | 0 | 18801 | 24580 | 2415 | 85.304 | 27 | 0.407 | 87.003 | 7 | 0.562 | Sunday | 0 |
Show code
df = baseball.join(weather.set_index('date'), on='event_date', how='left')
print(f"Joined table: {len(df):,} rows x {len(df.columns)} columns")
print(f"Missing values: {int(df.isnull().sum().sum())}")Joined table: 461 rows x 20 columns
Missing values: 0
3 Data preparation
Show code
df['weather'] = df['weather'].astype('category')
df['opponent'] = df['opponent'].astype('category')
df['weekday'] = df['weekday'].astype('category')
df['event_date'] = pd.to_datetime(df['event_date'])
df['event_time'] = pd.to_datetime(df['event_time'], format='%H:%M:%S')
df['weekday'] = df['weekday'].cat.reorder_categories(
['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
)4 New variables
We made new variables from the raw columns:
- Time: the month, and a weekend flag for Friday and Saturday games.
- Team strength: the difference in win percentage and in rank.
- Money: the payroll ratio and the payroll difference.
- Tickets: the log of tickets sold, and the log of tickets sold divided by attendance.
- Weather: a rain flag and a hot-day flag.
Show code
def engineer_features(df):
f = df.copy()
f['month'] = f.event_date.dt.month.astype('category')
f['is_weekend'] = f['weekday'].apply(lambda x: 1 if x in ['Friday', 'Saturday'] else 0)
f['win_pct_diff'] = np.abs(f['opponent_win_pcnt'] - f['braves_win_pcnt'])
f['rank_diff'] = f.opponent_rank - f.braves_rank
f['payroll_ratio'] = f['braves_payroll'] / (f['braves_payroll'] + f['opponent_payroll'])
f['payroll_diff'] = np.abs(f['opponent_payroll'] - f['braves_payroll']).astype(int)
f['ticket_ratio'] = f['tickets_sold'] / f['attendance'] # contains the target
f['log_ticket_ratio'] = np.log(f['ticket_ratio'])
f['log_tickets_resale'] = np.log(f['tickets_sold']) # the name is wrong: this is the log of tickets sold
f['precipitation'] = (f['weather'] == 'Rain') * 1
f['is_hot'] = f['mean_temp'] > 21
return f
df = engineer_features(df)
print(f"Columns after the new variables: {len(df.columns)}")Columns after the new variables: 31
log_ticket_ratiouses attendance, the value that the model predicts. The section “The input that contained the answer” shows the effect.log_tickets_resalehas the wrong name. It holds the log of tickets sold, in the 2022 notebook and here.
5 Exploratory analysis
Show code
numeric_cols = df.select_dtypes(include=[np.number]).columns.drop(df.columns[0])
corr = df[numeric_cols].corr()[['attendance']].sort_values(by='attendance', ascending=False).head(15)
fig = go.Figure(data=go.Heatmap(
z=corr.values, x=['Attendance'], y=corr.index, colorscale='RdBu_r', zmid=0,
text=np.round(corr.values, 3), texttemplate='%{text}', colorbar=dict(title='Correlation'),
))
fig.update_layout(title='Variables by correlation with attendance', height=560)
show(fig)Tickets sold has the strongest correlation with attendance. The weather variables have a weak correlation.
6 Models
6.1 Split by season
Show code
df_train = df.query(f'season < {TRAIN_BEFORE}')
df_test = df.query(f'season >= {TRAIN_BEFORE}')
print(f"Training set: {len(df_train)} games (2011 to 2014)")
print(f"Test set: {len(df_test)} games (2015 and 2016)")Training set: 324 games (2011 to 2014)
Test set: 137 games (2015 and 2016)
6.2 Six models
Show code
model_1 = smf.ols(data=df_train, formula='attendance ~ opponent + event_time + tickets_sold + tickets_resale + '
'opponent_rank + opponent_win_pcnt + braves_rank + braves_win_pcnt + weekday + is_night').fit()
model_2 = smf.ols(data=df_train, formula='attendance ~ log_tickets_resale + tickets_sold + is_weekend + log_ticket_ratio').fit()
model_3 = smf.ols(data=df_train, formula='attendance ~ log_tickets_resale + tickets_sold + event_time').fit()
model_4 = smf.ols(data=df_train, formula='attendance ~ weather').fit()
model_5 = smf.ols(data=df_train, formula='attendance ~ mean_temp').fit()
model_6 = smf.ols(data=df_train, formula='attendance ~ weather + mean_temp').fit()Show code
models = {
'1. All variables': model_1,
'2. The model that we chose': model_2,
'3. Tickets and start time': model_3,
'4. Weather type': model_4,
'5. Temperature': model_5,
'6. Weather type and temperature': model_6,
}
comparison = pd.DataFrame({
'Model': list(models),
'Parameters': [int(m.df_model) for m in models.values()],
'R²': [m.rsquared for m in models.values()],
'Adjusted R²': [m.rsquared_adj for m in models.values()],
'AIC': [m.aic for m in models.values()],
})
comparison.style.format({'R²': '{:.3f}', 'Adjusted R²': '{:.3f}', 'AIC': '{:,.0f}'}).hide(axis='index')| Model | Parameters | R² | Adjusted R² | AIC |
|---|---|---|---|---|
| 1. All variables | 51 | 0.959 | 0.952 | 5,909 |
| 2. The model that we chose | 4 | 0.991 | 0.991 | 5,326 |
| 3. Tickets and start time | 18 | 0.948 | 0.945 | 5,924 |
| 4. Weather type | 2 | 0.002 | -0.004 | 6,848 |
| 5. Temperature | 1 | 0.001 | -0.003 | 6,846 |
| 6. Weather type and temperature | 3 | 0.002 | -0.007 | 6,849 |
We chose model 2. It has the highest adjusted R² and the lowest AIC, with four inputs.
Show code
print(model_2.summary()) OLS Regression Results
==============================================================================
Dep. Variable: attendance R-squared: 0.991
Model: OLS Adj. R-squared: 0.991
Method: Least Squares F-statistic: 8787.
Date: Wed, 18 Nov 2026 Prob (F-statistic): 0.00
Time: 10:07:01 Log-Likelihood: -2657.9
No. Observations: 324 AIC: 5326.
Df Residuals: 319 BIC: 5345.
Df Model: 4
Covariance Type: nonrobust
======================================================================================
coef std err t P>|t| [0.025 0.975]
--------------------------------------------------------------------------------------
Intercept 1.106e+05 8570.933 12.901 0.000 9.37e+04 1.27e+05
log_tickets_resale -1.141e+04 915.561 -12.461 0.000 -1.32e+04 -9607.946
tickets_sold 1.1595 0.030 39.061 0.000 1.101 1.218
is_weekend 300.2873 127.885 2.348 0.019 48.682 551.893
log_ticket_ratio -1.789e+04 443.367 -40.354 0.000 -1.88e+04 -1.7e+04
==============================================================================
Omnibus: 130.180 Durbin-Watson: 1.843
Prob(Omnibus): 0.000 Jarque-Bera (JB): 1774.720
Skew: -1.256 Prob(JB): 0.00
Kurtosis: 14.187 Cond. No. 5.73e+06
==============================================================================
Notes:
[1] Standard Errors assume that the covariance matrix of the errors is correctly specified.
[2] The condition number is large, 5.73e+06. This might indicate that there are
strong multicollinearity or other numerical problems.
7 Interpretation
Show code
coeffs = pd.DataFrame({
'Variable': model_2.params.index,
'Coefficient': model_2.params.values,
'Std error': model_2.bse.values,
'p-value': model_2.pvalues.values,
})
coeffs.style.format({'Coefficient': '{:,.2f}', 'Std error': '{:,.2f}', 'p-value': '{:.4f}'}).hide(axis='index')| Variable | Coefficient | Std error | p-value |
|---|---|---|---|
| Intercept | 110,569.88 | 8,570.93 | 0.0000 |
| log_tickets_resale | -11,409.25 | 915.56 | 0.0000 |
| tickets_sold | 1.16 | 0.03 | 0.0000 |
| is_weekend | 300.29 | 127.89 | 0.0195 |
| log_ticket_ratio | -17,891.64 | 443.37 | 0.0000 |
- Tickets sold. Each ticket sold adds about 1.16 to the predicted attendance, with the other inputs held constant.
- Weekend. A Friday or Saturday game has about 300 more guests.
log_tickets_resale. This is the log of tickets sold (see “New variables”). It is not a resale effect.log_ticket_ratio. This input contains attendance. Its large coefficient is the leak, not a business effect.
8 Evaluation on the test seasons
Show code
cols = ['log_tickets_resale', 'tickets_sold', 'is_weekend', 'log_ticket_ratio']
y_pred = model_2.predict(df_test[cols])
y_actual = df_test['attendance']
r2 = r2_score(y_actual, y_pred)
rmse = np.sqrt(mean_squared_error(y_actual, y_pred))
mae = mean_absolute_error(y_actual, y_pred)
print(f"Test R²: {r2:.4f}")
print(f"RMSE: {rmse:,.0f} guests")
print(f"MAE: {mae:,.0f} guests")Test R²: 0.9855
RMSE: 1,062 guests
MAE: 636 guests
Show code
fig = go.Figure()
fig.add_trace(go.Scatter(x=y_pred, y=y_actual, mode='markers', name='Games',
marker=dict(size=8, color=BLUE, opacity=0.6)))
lo, hi = min(y_pred.min(), y_actual.min()), max(y_pred.max(), y_actual.max())
fig.add_trace(go.Scatter(x=[lo, hi], y=[lo, hi], mode='lines', name='Perfect prediction',
line=dict(color=RED, dash='dash')))
fig.update_layout(title=f'Predicted and actual attendance (R² = {r2:.3f})',
xaxis_title='Predicted attendance', yaxis_title='Actual attendance', height=520)
show(fig)These values are too good. The next section shows why.
9 The input that contained the answer
log_ticket_ratio is the log of tickets sold divided by attendance. Attendance is the value that the model predicts, so this input gives the model a part of the answer. A team does not know the attendance before the game.
The model below is the same model without that input. It was added in the 2026 check.
Show code
model_clean = smf.ols(data=df_train, formula='attendance ~ np.log(tickets_resale) + tickets_sold + is_weekend').fit()
pred_clean = model_clean.predict(df_test)
leak = pd.DataFrame({
'Model': ['With the leaked input (submitted)', 'Without the leaked input (2026 check)'],
'R², training seasons': [model_2.rsquared, model_clean.rsquared],
'R², test seasons': [r2, r2_score(y_actual, pred_clean)],
'MAE on the test seasons (guests)': [mae, mean_absolute_error(y_actual, pred_clean)],
})
leak.style.format({'R², training seasons': '{:.3f}', 'R², test seasons': '{:.3f}',
'MAE on the test seasons (guests)': '{:,.0f}'}).hide(axis='index')| Model | R², training seasons | R², test seasons | MAE on the test seasons (guests) |
|---|---|---|---|
| With the leaked input (submitted) | 0.991 | 0.986 | 636 |
| Without the leaked input (2026 check) | 0.953 | 0.955 | 1,289 |
The fit to quote for this model is about 0.95.
10 Weather
Show code
weather_tbl = pd.DataFrame({
'Model': ['Weather type', 'Temperature', 'Weather type and temperature'],
'R²': [model_4.rsquared, model_5.rsquared, model_6.rsquared],
'Smallest p-value of a weather variable': [
model_4.pvalues.drop('Intercept').min(),
model_5.pvalues.drop('Intercept').min(),
model_6.pvalues.drop('Intercept').min(),
],
})
weather_tbl.style.format({'R²': '{:.3f}', 'Smallest p-value of a weather variable': '{:.2f}'}).hide(axis='index')| Model | R² | Smallest p-value of a weather variable |
|---|---|---|
| Weather type | 0.002 | 0.49 |
| Temperature | 0.001 | 0.68 |
| Weather type and temperature | 0.002 | 0.48 |
Weather explains less than 1% of the variation in attendance, and no weather variable is significant. A forecast for this team does not need the weather.
11 What a team can use
- Tickets sold is the first signal for staff and stock plans. It explains most of the attendance.
- Plan for more guests on Friday and Saturday games.
- Do not change the forecast for the weather.
- Track the resale ratio for each game as a sign of demand.
12 Limits and next steps
- Home games of one team, 2011 to 2016. The model does not apply to other teams or stadiums without a new fit.
- No data on promotions or on star players of the opponent.
- A linear model does not show interactions between variables.
- Next steps: add promotion days, fit the model without the leaked input from the start, and compare with a tree model.
Show code
residuals = y_actual - y_pred
print(f"Residuals on the test seasons (model 2): mean {residuals.mean():,.0f}, "
f"std {residuals.std():,.0f}, min {residuals.min():,.0f}, max {residuals.max():,.0f}")Residuals on the test seasons (model 2): mean 164, std 1,053, min -2,380, max 4,982