def plot_time_distribution_by_bib_numbers(df):
'''
This function display the time distribution of runners according to the BIB numbers
Parameters
- df: DataFrame containing data to use to generate the graph
'''
x = 'number'
y = 'time'
ax = df.plot(kind='scatter', x=x, y=y, xlim=(-1000, 18000))
ax.set(xlabel=x.capitalize(), ylabel=y.capitalize())
lines = [-200, 2000, 8800, 9800, 17000]
annotations = [('10 km', 12500), ('21 km', 4500), ('42 km', 150)]
for line in lines:
ax.axvline(line, color='b', linestyle='--')
for annotation in annotations:
annotation_obj = [annotation[0], (0, 0), (annotation[1], 28000)]
ax.annotate(annotation_obj[0],
annotation_obj[1],
annotation_obj[2],
color='b')
plt.yticks(ax.get_yticks(), [
study_utils.convert_seconds_to_time(label)
for label in ax.get_yticks()
])
plt.title('Running time according to BIB number of participants')
plt.show()
def plot_time_difference_distribution(data):
'''
display a histogram showing the time difference bewteen team members and best time of the team.
Parameters
- data: DataFrame containing the data relative to a given running.
'''
ax = data['time difference team'].hist(bins=30, figsize=(10, 6))
# Computing of the mean and max for bowplot.
mean = np.mean(data['time difference team'])
max_time_diff = np.max(data['time difference team'])
# Display of the median and title
ax.axvline(mean, 0, 1750, color='r', linestyle='--')
ax.set_title(
'Distribution of runners according to difference of time with the best runner in team'
)
ax.set_xlabel('Difference of time')
ax.set_ylabel('Number of runners')
# Display of x ticks in HH:mm:ss format
plt.xticks(ax.get_xticks(), [
study_utils.convert_seconds_to_time(label)
for label in ax.get_xticks()
])
# Calculation and display of age distribution statistics by gender
time_stats = 'Mean difference of time: ' + study_utils.convert_seconds_to_time(
mean
) + '\n' + 'Maximum difference of time: ' + study_utils.convert_seconds_to_time(
max_time_diff)
props = dict(boxstyle='round', facecolor='wheat', alpha=0.5)
ax.text(.95,
.95,
time_stats,
fontsize=11,
transform=ax.transAxes,
va='top',
ha='right',
bbox=props,
multialignment='left')
def plot_time_distribution(ax, running, name):
'''
This function create a subplot containing the time distribution for a given age, and for the 3 types of runnings (10 km, 21km, 42km).
Parameters
- ax: subplot to use for the histogram (Matplotlib axes)
- running: data for a given set of participants of same age (DataFrameGroupby)
- name: name of the category
'''
# Creation of histogram
running_10k = running[running['distance (km)'] == 10]
race_10k = running_10k['time'].tolist()
running_21k = running[running['distance (km)'] == 21]
race_21k = running_21k['time'].tolist()
running_42k = running[running['distance (km)'] == 42]
race_42k = running_42k['time'].tolist()
ax.hist([race_10k, race_21k, race_42k],
bins=30,
stacked=True,
rwidth=1.0,
label=['10 km', '21 km', '42 km'])
ax.legend()
ax.set_ylabel('Number of Runners')
ax.set_title('Time distribution (' + str(name) + ')')
ax.xaxis.set_label_coords(1.15, -0.025)
# Creation of texts
total_10k = len(race_10k)
total_10k_str = '10 km: ' + str(total_10k) + ' runners'
total_21k = len(race_21k)
total_21k_str = '21 km: ' + str(total_21k) + ' runners'
total_42k = len(race_42k)
total_42k_str = '42 km: ' + str(total_42k) + ' runners'
total = len(running['time'].tolist())
total_str = 'Total: ' + str(total) + ' runners'
stats_str = total_10k_str + '\n' + total_21k_str + '\n' + total_42k_str + '\n' + total_str
plt.xticks(ax.get_xticks(), [
study_utils.convert_seconds_to_time(label)
for label in ax.get_xticks()
],
rotation=90)
props = dict(boxstyle='round', facecolor='wheat', alpha=0.5)
ax.annotate(stats_str,
xy=(0, 1),
xytext=(12, -12),
va='top',
xycoords='axes fraction',
textcoords='offset points',
bbox=props)
def plot_scatter_difference_time_number(fig,
data,
distance,
subplot_idx,
annotation=[],
time_mini=1000):
'''
This function plots the difference time between team members who have finished late compared to the best time of the team.
Parameters
- fig: Figure on which subplots are displayed
- data: DataFrame containing the data relative to a given running
- distance: number of kilometers of the considered running (10/21/42)
- subplot_idx: Index of the subplot in the figure
- annotation: Annotation to add in the graph (by default, no annotation)
- time_mini: Minimal time to consider (how much runners are late compare to the first)
(1000 by default)
'''
# select runner in teams and with the selected distance
race_team = data[(data['team'].notnull())
& (data['distance (km)'] == distance)]
# Remove of times which are lower than minimal time considered
race_team = (race_team[race_team['time difference team'] > time_mini])
# Remove of teams with only one runner
for team in race_team['team']:
race_team_selected = race_team[race_team['team'] == team]
if len(race_team_selected['team']) == 1:
race_team = race_team[race_team['team'] != team]
# Map team name with team number
team_label_encode = preprocessing.LabelEncoder()
team_label = team_label_encode.fit_transform(race_team['team'])
race_team['team_code'] = team_label
# Computation of runners in pair
number_runner_in_pair = race_team.apply(study_utils.compute_pair_runner,
args=(race_team, 60),
axis=1)
counter_pair = Counter(number_runner_in_pair)
# Plotting the results
plot = fig.add_subplot(subplot_idx)
sns.swarmplot(x='team_code',
y='time difference team',
hue='sex',
data=race_team,
ax=plot)
plot.set_title('Distance: ' + str(distance) + ' km')
plot.set_xlabel('')
plot.set_ylabel('')
plot.legend(loc='upper left')
# Add annotation if any given
if len(annotation) != 0:
if subplot_idx == annotation[0]:
plot.annotate(annotation[1],
annotation[2],
annotation[3],
arrowprops=dict(facecolor='red', shrink=0.05))
# Manage of legends
if subplot_idx != 311:
plot.legend_.remove()
if subplot_idx == 312:
plot.set_ylabel('Difference of time with the best runner in the team')
if subplot_idx == 313:
plot.set_xlabel('Team number')
plt.yticks(plot.get_yticks(), [
study_utils.convert_seconds_to_time(label)
for label in plot.get_yticks()
])
display_legend(counter_pair, plot)
def plot_time_difference_distribution(
df,
title='Time difference with the best runner in team',
time_difference_column_name='time difference team'):
'''
This function displays distribution representing time difference bewteen performance of team members and best performance within the team.
Parameters
- df: DataFrame containing information on runners
- title: Title of the graph (by default, 'Time difference with the best runner in team')
- time_difference_column_name: Name of column containing time differencies (by default, 'time_difference_column_name')
Return
- figure: Plotly figure
'''
mean_difference = np.mean(df[time_difference_column_name])
mean_difference_dt = datetime.datetime.strptime(
study_utils.convert_seconds_to_time(mean_difference), '%H:%M:%S')
max_difference = np.max(df[time_difference_column_name])
statistics = [
'Mean difference of time: ' +
str(study_utils.convert_seconds_to_time(mean_difference)),
'Maximum difference of time: ' +
str(study_utils.convert_seconds_to_time(max_difference))
]
data = df.copy()
data[time_difference_column_name] = pd.to_datetime([
study_utils.convert_seconds_to_time(t)
for t in data[time_difference_column_name]
],
format='%H:%M:%S')
histogram = [
go.Histogram(x=data[time_difference_column_name],
xbins={
'start': np.min(data[time_difference_column_name]),
'end': np.max(data[time_difference_column_name]),
'size': 5 * 60000
})
]
annotations = [
Annotation(y=1,
x=1,
text='<br>'.join(statistics),
align='right',
xref='paper',
yref='paper',
showarrow=False)
]
shapes = [{
'type': 'line',
'yref': 'paper',
'x0': mean_difference_dt,
'y0': 0,
'x1': mean_difference_dt,
'y1': 1,
'line': {
'color': '#f44242',
'width': 2,
'dash': 'dash'
}
}]
figure = study_utils.create_plotly_legends_and_layout(
histogram,
title=title,
x_name='Performance gap',
x_type='date',
x_format='%H:%M:%S',
y_name='Number of runners',
barmode='group',
bargap=0.1,
annotations=annotations,
shapes=shapes)
plotly.offline.iplot(figure)
return figure