def generate_time_distribution_by_bib_numbers(data, performance_criteria):
'''
This function generates all BIB/performance scatters for each running of Lausanne Marathon.
Final Dict has the following pattern:
{
<performance_criterion_1>: <Plotly figure>
[, <performance_criterion_2>: <Plotly figure>
, ...]
}
Parameters
- df: DataFrame containing records about runners
- performance_criteria: Array containing column name to use for available performance criteria (time and speed)
Return
- figures: Dict containing all time distribution figures
'''
# We define options
runnings_names = {10: '10 km', 21: 'Semi-marathon', 42: 'Marathon'}
colors = {10: KM_10_COLOR, 21: KM_21_COLOR, 42: KM_42_COLOR}
default_options = {
'title':
'Distribution of performance according to BIB numbers over the years',
'x_name': 'BIB numbers',
'x_format': 'f',
'hovermode': 'closest'
}
time_options = {'y_name': 'Time', 'y_type': 'date', 'y_format': '%H:%M'}
speed_options = {'y_name': 'Speed (m/s)'}
time_options.update(default_options)
speed_options.update(default_options)
# We create final dict
figures = {}
# Loop over performance criteria (time, speed)
for performance_criterion in performance_criteria:
criterion = performance_criterion.lower()
scatters = study_utils.create_plotly_scatters(data=data,
x='number',
y=criterion,
hue='distance (km)',
hue_names=runnings_names,
text='name',
color=colors,
use_hue_names=False)
if criterion == 'time':
figure = study_utils.create_plotly_legends_and_layout(
data=scatters, **time_options)
else:
figure = study_utils.create_plotly_legends_and_layout(
data=scatters, **speed_options)
figures[performance_criterion] = figure
return figures
def generate_all_bib_performance_figure(df):
'''
This function generates all BIB/performance scatters for each year of Lausanne Marathon.
Parameters
- df: DataFrame containing records about runners
Return
- figure: Plotly figure
'''
# We define the considered the years interval, colors and visibility
years_range = range(1999, 2017)
years = {year: str(year) for year in years_range}
colors = study_utils.generate_colors_palette(data=years_range, isDict=False, forceString=True)
visibility = {str(year): (True if year > 2015 else 'legendonly') for year in years_range}
# We define options
default_options = {'title': 'Distribution of performance according to BIB numbers over the years', 'x_name': 'BIB numbers', 'hovermode':'closest'}
time_options = {'y_name': 'Time', 'y_type': 'date', 'y_format': '%H:%M'}
time_options.update(default_options)
scatters = study_utils.create_plotly_scatters(data=df, x='number', y='time', hue='year', hue_names=years, text='name', color=colors, visibility=visibility)
figure = study_utils.create_plotly_legends_and_layout(data=scatters, **time_options)
plotly.offline.iplot(figure)
return figure
def plot_median_age_evolution(data, x=None, y='Median age (all runnings)', title='Evolution of median age over the years', groupby_column='Gender', groupby_attributes=None):
'''
This function displays a graph showing evolution of median ages for male and female runners over the years.
Parameters
- data: DataFrame containing data to use for graph
- x: Name of the column to use for x axis (by default None / if None, index will be used)
- y: Name of the column to use for y axis (by default, 'Median age (all runnings)')
- title: Title of the graph (by default, 'Evolution of median age over the years')
- groupby_column: Name of the column to use for grouping data (by default, 'Gender')
- groupby_attributes: Dictionary containing options for each unique value in column groupby_column (at present, 'colors' and 'name' are supported / by default, None)
Return
- figure: Plotly figure
'''
lines = []
for key, group in data.groupby([groupby_column]):
x_values = group[x] if x else group.index
line = go.Scatter(x=x_values, y=group[y], mode='lines', name=(groupby_attributes[key].get('name', key) if groupby_attributes else key), marker={'color': (groupby_attributes[key].get('color', None) if groupby_attributes else None)})
lines.append(line)
figure = study_utils.create_plotly_legends_and_layout(lines, title=title, x_name=(x if x else data.index.name), y_name=y)
plotly.offline.iplot(figure)
return figure
def plot_age_distribution(df, age_column_name='age', sex_column_name='sex'):
'''
This function displays the distribution of runners according to their age.
Parameters:
- df: DataFrame containing information about runners
- age_column_name: Name of column containing age of runners
'''
# Calculation of age distribution statistics by gender
statistics = []
all_genders = ['all']
all_genders.extend(df[sex_column_name].unique())
for sex in all_genders:
if sex == 'all':
ages = df[age_column_name]
else:
ages = df[df[sex_column_name] == sex][age_column_name]
statistics.append('<b>Mean age of ' + sex + ' runners: ' +
str(round(np.mean(ages), 2)) + ' (STD: ' +
str(round(np.std(ages), 2)) + ')</b>')
data = [go.Histogram(x=df[age_column_name])]
annotations = [
Annotation(y=1,
x=1,
text='<br>'.join(statistics),
xref='paper',
yref='paper',
showarrow=False)
]
shapes = [{
'type': 'line',
'yref': 'paper',
'x0': np.mean(df[age_column_name]),
'y0': 0,
'x1': np.mean(df[age_column_name]),
'y1': 1,
'line': {
'color': '#f44242',
'width': 2,
'dash': 'dash'
}
}]
figure = study_utils.create_plotly_legends_and_layout(
data,
title='Age distribution of runners',
x_name='Age',
y_name='Number of runners',
barmode='group',
bargap=0.25,
annotations=annotations,
shapes=shapes)
plotly.offline.iplot(figure)
return figure
def plot_age_evolution_boxplots(df, title='Evolution of age of runners over the years', year_column='year', age_column='age'):
'''
This function plots evolution of age of runners over the years (using boxplots).
Parameters
- df: DataFrame containing records about runners
- title: Title of the graph (by default, 'Evolution of age of runners over the years')
- year_column: Name of column containing years of event
- age_column: Name of column containing age of runners
Return
- figure: Plotly figure
'''
options = {'title': title, 'x_name': year_column.capitalize(), 'y_name': age_column.capitalize()}
boxplots = study_utils.create_plotly_boxplots(data=df, x='year', y=age_column)
figure = study_utils.create_plotly_legends_and_layout(data=boxplots, **options)
plotly.offline.iplot(figure)
return figure
def plot_distribution_over_years(data, title='Distribution of runners over the years for Lausanne Marathon'):
'''
This function generates a graph representing distribution of runners over the years, given data.
Parameters
- data: DataFrame containing distribution of runners over the years
- title: Title of the graph (by default, 'Distribution of runners over the years for Lausanne Marathon')
Return
- figure: Plotly figure
'''
colors = {'10 km': KM_10_COLOR, 'Semi-marathon': KM_21_COLOR, 'Marathon': KM_42_COLOR}
bars = []
for running in data.columns:
bars.append(go.Bar(x=[year for year in data.index], y=data[running], name=running, marker={'color': colors[running]}))
figure = study_utils.create_plotly_legends_and_layout(bars, title=title, x_name='Years', y_name='Number of runners', barmode='stack')
plotly.offline.iplot(figure)
return figure
def plot_distribution_between_types_of_participants(df,
type_column_name='type'):
'''
This functions displays the distribution of runners between types of participants.
Parameters
- df: DataFrame containing information about runners
- type_column_name: Name of column containing type of runners (by default, 'type')
Return
- figure: Plotly figure
'''
x_values, y_values, texts = [[] for i in range(3)]
nb_total_participants = len(df)
for type_participants in df[type_column_name].unique():
x_values.append(type_participants)
nb_participants = len(df[df[type_column_name] == type_participants])
y_values.append(nb_participants)
texts.append('<b>' + type_participants.capitalize() +
'</b><br>Number of participants: ' +
str(nb_participants) + ' (' +
'{:.1f}%'.format(nb_participants * 100 /
nb_total_participants) + ')')
bar = go.Bar(x=x_values,
y=y_values,
name=type_participants,
text=texts,
hoverinfo='text')
figure = study_utils.create_plotly_legends_and_layout(
[bar],
title='Distribution by type of runners',
x_name='Type of runner',
y_name='Number of runners',
barmode='group')
plotly.offline.iplot(figure)
return figure
def generate_all_performance_figures(df, age_categories, sex_categories, performance_criteria):
'''
This function generates all performance figures according sets of age categories and sex categories and a set of performance criteria.
Final Dict has the following pattern:
{
<age_category_1: {
<sex_1>: {
<performance_criterion_1>: <Plotly figure>
[, <performance_criterion_2>: <Plotly figure>
, ...]
}
[, <sex_2>: {
<performance_criterion_1>: <Plotly figure>
[, <performance_criterion_2>: <Plotly figure>
, ...]
}, ...]
}
[, <age_category_2: {
<sex_1>: {
<performance_criterion_1>: <Plotly figure>
[, <performance_criterion_2>: <Plotly figure>
, ...]
}
[, <sex_2>: {
<performance_criterion_1>: <Plotly figure>
[, <performance_criterion_2>: <Plotly figure>
, ...]
}, ...]
}, ...]
}
Parameters
- df: DataFrame containing records about runners
- age_categories: Array containing age categories to be displayed (if 'All'/'all', no filter is done on df)
- sex_categories: Array containing sex categories to be displayed (if 'All'/'all', no filter is done on df)
- performance_criteria: Array containing performance criteria to consider
Return
- figures: Dict containing all performance figures
'''
# We define the considered runnings and the years interval, as colors for boxplots
runnings = {10: '10 km', 21: 'Semi-marathon', 42: 'Marathon'}
year_values = [year for year in df['year'].unique() if year]
colors = {'10 km': KM_10_COLOR, 'Semi-marathon': KM_21_COLOR, 'Marathon': KM_42_COLOR}
# We define options and the final Dict
figures = {}
default_options = {'title': 'Performance over years for runnings of Lausanne Marathon', 'x_name': 'Years', 'x_values': year_values, 'boxmode': 'group'}
time_options = {'y_name': 'Time', 'y_type': 'date', 'y_format': '%H:%M:%S'}
speed_options = {'y_name': 'Speed (m/s)'}
time_options.update(default_options)
speed_options.update(default_options)
for age_category in age_categories:
# We select data according to age category
if age_category.lower() == 'all':
data = df
else:
data = df[df['age category'] == age_category]
figures[age_category] = {}
for sex_category in sex_categories:
# We select data according to sex category
if sex_category.lower() == 'all':
data_final = data
else:
data_final = data[data['sex'] == sex_category.lower()]
figures[age_category][sex_category] = {}
annotations = [Annotation(y=1.1, text='Age category: ' + age_category + ' Sex category: ' + sex_category + ' runners', xref='paper', yref='paper', showarrow=False)]
# We create a figure for each performance criterion
for performance_criterion in performance_criteria:
criterion = performance_criterion.lower()
boxplots = study_utils.create_plotly_boxplots(data=data_final, x='year', y=criterion, hue='distance (km)', hue_names=runnings, colors=colors)
if criterion == 'time':
figure = study_utils.create_plotly_legends_and_layout(data=boxplots, **time_options, annotations=annotations)
elif criterion == 'speed (m/s)':
figure = study_utils.create_plotly_legends_and_layout(data=boxplots, **speed_options, annotations=annotations)
else:
# By default, two specific criteria are allowed: 'time' and 'speed (m/s)'. If any other criterion is provided, we throw an exception.
raise ValueError('Invalid performance criterion encountered. Performance criterion must be either \'Time\' or \'Speed (m/s)\'')
figures[age_category][sex_category][performance_criterion] = figure
return figures
def generate_all_evolution_figures(df, age_categories, sex_categories):
'''
This function generates all evolution figures according sets of age categories and sex categories.
Final Dict has the following pattern:
{
<age_category_1: {
<sex_1>: <Plotly figure
[, <sex_2>: <Plotly figure, ...]
}
[, <age_category_2: {
<sex_1>: <Plotly figure
[, <sex_2>: <Plotly figure, ...]
}, ...]
}
Parameters
- df: DataFrame containing records about runners
- age_categories: Array containing age categories to be displayed (if 'All'/'all', no filter is done on df)
- sex_categories: Array containing sex categories to be displayed (if 'All'/'all', no filter is done on df)
Return
- figures: Dict containing all evolution figures
'''
# We define the considered runnings and the years interval
runnings = {'column_name': 'distance (km)', 'values': OrderedDict([(10, {'name': '10 km', 'color': KM_10_COLOR}), (21, {'name': 'Semi-marathon', 'color': KM_21_COLOR}), (42, {'name': 'Marathon', 'color': KM_42_COLOR})])}
year_values = [year for year in df['year'].unique() if year]
# We define options and the final Dict
figures = {}
options = {'title': 'Evolution of number of participants over years for runnings of Lausanne Marathon', 'x_name': 'Years', 'x_values': year_values, 'y_format': 'f'}
for age_category in age_categories:
# We select data according to age category
if age_category.lower() == 'all':
data = df
else:
data = df[df['age category'] == age_category]
figures[age_category] = {}
for sex_category in sex_categories:
# We select data according to sex category
if sex_category.lower() == 'all':
data_final = data
else:
data_final = data[data['sex'] == sex_category.lower()]
lines = []
for km, attributes in runnings['values'].items():
data_running = data_final[data_final[runnings['column_name']] == km]
line = go.Scatter(x = year_values, y = [len(data_running[data_running['year'] == y]) for y in year_values], mode = 'lines', name = attributes['name'], marker={'color': attributes['color']})
lines.append(line)
annotations = [Annotation(y=1.1, text='Age category: ' + age_category + ' Sex category: ' + sex_category + ' runners', xref='paper', yref='paper', showarrow=False)]
figure = study_utils.create_plotly_legends_and_layout(data=lines, **options, annotations=annotations)
figures[age_category][sex_category] = figure
return figures
def generate_teams_evolution_figures(data, title='Evolution of teams performance over the years', runnings=None, team_column_name='team', year_column_name='year', min_years=6, nb_teams=8, threshold_bins_size=50, display_annotations=True):
'''
This function generate teams_evolution figures for all runnings.
Final Dict has the following pattern:
{
<running_1: {
<Plotly figure>
}
[, <running_2: {
<Plotly figure>
}, ...]
}
Parameters
- data: DataFrame containing results
- title: Title of figure
- runnings: Dict containing name of column containing runnings (key: column_name) and set of runnings (key: values, value: dict() with key: value in column, value: name of running)
By default, None. If None, default values will be set by function.
- team_column_name: Name of column containing teams (by default, 'teams')
- year_column_name: Name of column containing year associated to a given result (by default, 'year')
- min_years: Minimum of participations when considering a team (by default, 6)
- nb_teams: Number of teams to consider among teams with number of participations > min_years (by default, 8)
Note: Teams are filtered by number of participants.
- threshold_bins_size: Maximum size of a bin (by default, 25)
Note: Size of bin is related to number of participants of a considered team and for a given year. If None, no limitation is used.
- display_annotations: Boolean used to display annotations (by default, True)
Return
- figures: Dict containing all teams evolution figures
'''
# Default runnings
if not runnings:
runnings = {'column_name': 'distance (km)', 'values': {10: '10 km', 21: 'Semi-marathon', 42: 'Marathon'}}
figures = {}
# Loop over runnings
for key, value in runnings['values'].items():
# We retrieve data related to current running
filtered_data = data[data[runnings['column_name']] == key]
# We retrieve names of the <nb_teams> most important groups with at least <min_years> participations in Lausanne Marathon
top_teams = filtered_data.groupby(team_column_name).filter(lambda x: x[year_column_name].nunique() >= min_years).groupby('team').size().sort_values(ascending=False).nlargest(nb_teams)
# We keep only data linked with such groups
data_top_teams = filtered_data[filtered_data[team_column_name].isin(top_teams.index.values)]
# We finally groupby teams after complete filter
groups_top_teams = data_top_teams.groupby(team_column_name)
# We generate colors for each group and we initialize array that will contain traces
colors = study_utils.generate_colors_palette(groups_top_teams.groups)
traces = []
# Loop over groups
for name, groups in groups_top_teams:
x_values, y_values, size_values, texts = [], [], [], []
# Loop over participation years for current group
for year, results in groups.groupby(year_column_name):
x_values.append(year)
y = study_utils.compute_average_time(results)
y_values.append(y)
text = '<b>Team: ' + name + '</b><br>Average time: ' + y.strftime('%H:%M:%S') + '<br>Participants: ' + str(len(results)) + '<br>Median age: ' + str(int(results['age'].median()))
texts.append(text)
size = len(results) if not threshold_bins_size or (len(results) < threshold_bins_size) else threshold_bins_size
size_values.append(size)
trace = go.Scatter(x=x_values, y=y_values, name=name, mode='lines+markers', hoverinfo='text', text=texts, marker=dict(size=size_values, color=colors[name], line=dict(width = 1.5, color = 'rgb(0, 0, 0)')))
traces.append(trace)
# For each running, we create annotations if asked by user, we set multiple options accordingly and we store figure
if display_annotations:
annotations = [Annotation(y=1.1, text='Running: ' + str(value) + ' | Top teams: ' + str(nb_teams) + ' | Minimum participations: ' + str(min_years) + ' | Maximum bins size: ' + str(threshold_bins_size), xref='paper', yref='paper', showarrow=False)]
else:
annotations = None
options = {'title': title, 'hovermode': 'closest', 'x_name': 'Year', 'y_name': 'Median time', 'y_type': 'time', 'y_format': '%H:%M:%S', 'annotations': annotations}
figure = study_utils.create_plotly_legends_and_layout(data=traces, **options)
figures[value] = figure
return figures
def plot_runners_teams_individual_distribution_according_to_running_type(
df,
title='Team/individual runners composition',
runnings=None,
team_column_name='profile'):
'''
This function displays the distribution of participants according to their profiles (individual runners/runners in team) for the different runnings.
Parameters
- df: DataFrame containing data
- title: Title of the graph (by default, 'Team/individual runners composition')
- runnings: Dict containing name of column containing runnings (key: column_name) and set of runnings (key: values, value: dict() with following keys: name, color)
By default, None. If None, default values will be set by function.
- team_column_name: Name of column containing type of participants (by default, 'profile')
Return
- figure: Plotly figure
'''
if not runnings:
runnings = {
'column_name':
'distance (km)',
'values':
OrderedDict([(10, {
'name': '10 km',
'color': KM_10_COLOR
}), (21, {
'name': 'Semi-marathon',
'color': KM_21_COLOR
}), (42, {
'name': 'Marathon',
'color': KM_42_COLOR
})])
}
data = []
annotations_texts = []
for key, attributes in runnings['values'].items():
filtered_df = df[df[runnings['column_name']] == key]
nb_runners_running = len(filtered_df)
x_values, y_values, texts = [[] for i in range(3)]
for profile in filtered_df[team_column_name].unique():
x_values.append(profile)
nb_runners = len(
filtered_df[filtered_df[team_column_name] == profile])
y_values.append(nb_runners)
texts.append('<b>' + attributes['name'] + '</b><br>' +
profile.capitalize() + ' runners: ' +
str(nb_runners) + ' (' +
'{:.1f}%'.format(nb_runners * 100 /
nb_runners_running) + ')')
annotations_texts.append(attributes['name'] + ': ' +
str(nb_runners_running) + ' runners')
data.append(
go.Bar(x=x_values,
y=y_values,
name=attributes['name'],
text=texts,
hoverinfo='text',
marker={'color': attributes['color']}))
annotations = [
Annotation(y=1.1,
x=0,
text=' | '.join(annotations_texts),
xref='paper',
yref='paper',
showarrow=False)
]
figure = study_utils.create_plotly_legends_and_layout(
data,
title=title,
x_name='Composition',
y_name='Number of runners',
barmode='group',
annotations=annotations)
plotly.offline.iplot(figure)
return figure
def plot_gender_distributions(df):
'''
This functions displays graph representing the gender distribution of Canton of Vaud and Lausanne Marathon 2016 for comparison.
Parameters
- df: DataFrame containing information on runners for Lausanne Marathon 2016
Return
- figure: Plotly figure
'''
# Building of DataFrame for ploting
CANTON_VAUD = 'Canton of Vaud'
LAUSANNE_MARATHON = 'Lausanne Marathon'
total_runners = len(df)
total_runners_male = len(df[df['sex'] == 'male'])
total_runners_female = len(df[df['sex'] == 'female'])
vaud_information_population = pd.Series({
'male':
TOTAL_RESIDENT_MALE / TOTAL_RESIDENT_VAUD * 100,
'female':
TOTAL_RESIDENT_FEMALE / TOTAL_RESIDENT_VAUD * 100
})
marathon_information_runner = pd.Series({
'male':
total_runners_male / total_runners * 100,
'female':
total_runners_female / total_runners * 100
})
information_population = pd.DataFrame({
CANTON_VAUD:
vaud_information_population,
LAUSANNE_MARATHON:
marathon_information_runner
})
information_population.sort_index(axis=0,
level=None,
ascending=False,
inplace=True)
text_vaud = [
'<b>' + CANTON_VAUD + '</b><br>' + str(TOTAL_RESIDENT_MALE) +
' residents', '<b>' + CANTON_VAUD + '</b><br>' +
str(TOTAL_RESIDENT_FEMALE) + ' residents'
]
text_marathon = [
'<b>' + LAUSANNE_MARATHON + '</b><br>' + str(total_runners_male) +
' runners', '<b>' + LAUSANNE_MARATHON + '</b><br>' +
str(total_runners_female) + ' runners'
]
vaud_trace = go.Bar(x=information_population.index.values,
y=information_population[CANTON_VAUD],
name=CANTON_VAUD,
hoverinfo='text',
text=text_vaud)
marathon_trace = go.Bar(x=information_population.index.values,
y=information_population[LAUSANNE_MARATHON],
name=LAUSANNE_MARATHON,
hoverinfo='text',
text=text_marathon)
data = [vaud_trace, marathon_trace]
annotations = [
Annotation(y=1.1,
text='Total residents: ' + str(TOTAL_RESIDENT_VAUD) +
' | Total runners: ' + str(total_runners),
xref='paper',
yref='paper',
showarrow=False)
]
figure = study_utils.create_plotly_legends_and_layout(
data,
title='Gender distribution Lausanne Marathon vs Canton of Vaud',
x_name='Gender',
y_name='Percentage (%)',
barmode='group',
annotations=annotations)
plotly.offline.iplot(figure)
return figure
def plot_time_distribution_by_age(data, runnings=None, age_column_name='age'):
'''
This function plots the distribution of time for all ages regarding participants of a Lausanne Marathon.
3 subplots are displayed per rows.
Parameters
- data: DataFrame containing all the information of a Lausanne Marathon
- runnings: Dict containing name of column containing runnings (key: column_name) and set of runnings (key: values, value: dict() with following keys: name, color)
By default, None. If None, default values will be set by function.
- age_column_name: Name of the column containing age of participants('age' or 'age category', by default, 'age')
'''
if not runnings:
runnings = {
'column_name': 'distance (km)',
'values': {
10: {
'name': '10 km',
'color': KM_10_COLOR
},
21: {
'name': 'Semi-marathon',
'color': KM_21_COLOR
},
42: {
'name': 'Marathon',
'color': KM_42_COLOR
}
}
}
groups = data.groupby(age_column_name)
figures = {}
options = {
'x_name': 'Performance time',
'y_name': 'Number of runners',
'x_type': 'date',
'x_format': '%H:%M:%S',
'barmode': 'overlay',
'bargroupgap': 0.1
}
for name, group in groups:
histograms, statistics = [], []
for km, attributes_running in runnings['values'].items():
x = group[group[runnings['column_name']] == km]['time']
statistics.append(attributes_running['name'] + ': ' + str(len(x)) +
' runners')
histograms.append(
go.Histogram(x=x,
xbins={
'start': np.min(group['time']),
'end': np.max(group['time']),
'size': 5 * 60000
},
name=attributes_running['name'],
marker={'color': attributes_running['color']},
opacity=0.5))
statistics.append('Total: ' + str(len(group)) + ' runners')
annotations = [
Annotation(y=1.1,
x=0.9,
text=' | '.join(statistics),
xref='paper',
yref='paper',
showarrow=False)
]
figure = study_utils.create_plotly_legends_and_layout(
data=histograms,
title='Time distribution (' + name + ')',
**options,
annotations=annotations)
figures[name] = figure
return figures
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