# load up the libraries import panel as pn import pandas as pd import altair as alt import math from vega_datasets import data # Define functions def plot_event_distribution(df, eventName): time_labels = ['0-5', '5-10', '10-15', '15-20', '20-25', '25-30', '30-35', '35-40', '40-45', '45-50', '50-55', '55-60', '60-65', '65-70', '70-75', '75-80', '80-85', '85-90', '>90'] time_labels_plt = ['0-5', '5-10', '10-15', '15-20', '20-25', '25-30', '30-35', '35-40', '40-45', '>45', '45-50', '50-55', '55-60', '60-65', '65-70', '70-75', '75-80', '80-85', '85-90', '>90'] event_data = df[df['eventName'] == eventName].copy() event_data['timeLabel'] = "0" for index, row in event_data.iterrows(): minute = row['minute'] match_period = row['matchPeriod'] time_label = '1' if minute > 45 and match_period == '1H': time_label = '>45' else: left = math.floor(minute / 5) if left < len(time_labels) - 1: time_label = time_labels[left] else: time_label = '>90' event_data.loc[index, 'timeLabel'] = time_label return event_data def create_event_distribution_df(event_dfs, event_names): # 初始化一个空的DataFrame来存储结果 results_df = pd.DataFrame(columns=['TeamName', 'eventName', 'timeLabel', 'total_counts', 'matchPeriod']) for event_df, event_name in zip(event_dfs, event_names): group_counts = event_df.groupby(['TeamName', 'timeLabel', 'matchPeriod']).size().reset_index(name='total_counts') group_counts['eventName'] = event_name results_df = pd.concat([results_df, group_counts], ignore_index=True) return results_df def create_altair_chart(final_df, eventName, order, if_add_xticks=False): selection_interval=alt.selection_interval(encodings=["x"]) mouse_hover = alt.selection_point(on="mouseover", empty=True) color_encode = alt.Color('matchPeriod:N', title='', scale=alt.Scale(domain=['1H', '2H'], range=['rgb(76, 114, 176)', 'rgb(85, 168, 104)'])) # 这里我们用yellow card来举例 # 1. Base bar plot base1 = alt.Chart(final_df[final_df['eventName'] == '{}'.format(eventName)]).encode( x = alt.X('timeLabel:O', scale=alt.Scale(domain=order, paddingInner=0.2), axis=alt.Axis(grid=True, labels=False)), y = alt.Y('sum(total_counts):Q', title='{} (n)'.format(eventName), axis=alt.Axis(tickCount=3, titleFontSize=24, labelFontSize=18)), color = alt.condition(selection_interval, color_encode, alt.value("lightgray")), opacity=alt.condition(mouse_hover, alt.value(1), alt.value(0.5)) ).add_selection( selection_interval, mouse_hover ) if if_add_xticks: base1 = base1.encode( x = alt.X('timeLabel:O', title='match time (min)' ,scale=alt.Scale(domain=order, paddingInner=0.2), axis=alt.Axis(grid=True, titleFontSize=24, labelFontSize=18)), ) bar_chart_yellow1 = base1.mark_bar() # 2. Add vertical line vertical_line1 = alt.Chart(final_df[(final_df['eventName'] == '{}'.format(eventName)) & (final_df['timeLabel'] == ' ')]).encode( # only show the vertical line at x == ' ' x = alt.X('timeLabel:O', scale=alt.Scale(domain=[' ']), title=''), ) vertical_line1 = vertical_line1.mark_rule(color='orange', strokeWidth=2) # 3. Add text text_chart1 = alt.Chart(final_df[(final_df['eventName'] == '{}'.format(eventName)) & (final_df['timeLabel'] == ' ')]).encode( # only show the vertical line at x == ' ' x = alt.X('timeLabel:O', scale=alt.Scale(domain=[' ']), title=''), ) text_chart1 = text_chart1.mark_text(align='center', baseline='middle', fontSize=23, color='orange', dy=-100, text='Half Time', font='Arial') # 4. Add the rank bar bar_rank_yellow = alt.Chart(final_df[final_df['eventName'] == '{}'.format(eventName)]).transform_filter(selection_interval).transform_aggregate( sum_total_counts='sum(total_counts)', groupby=['TeamName'] ).transform_window( rank='rank(sum_total_counts)', sort=[alt.SortField('sum_total_counts', order='descending')] ).transform_filter( alt.datum.rank < 10 # Note: Change this to <= if you want to include the 10th position ).encode( x=alt.X('sum_total_counts:Q', title='', axis=alt.Axis(labelFontSize=9)), y=alt.Y('TeamName:N', sort='-x', title='Team Name', axis=alt.Axis(titleFontSize=24, labelFontSize=12, orient='right')) ) if if_add_xticks: bar_rank_yellow = bar_rank_yellow.encode( x=alt.X('sum_total_counts:Q', title='Average {}'.format(eventName), axis=alt.Axis(titleFontSize=24,labelFontSize=9)), ) bar_rank_yellow = bar_rank_yellow.mark_bar(color='orange').properties(width=300, height=250) # 5. Combine all the charts first = (bar_chart_yellow1 + vertical_line1 + text_chart1) first = first.encode(tooltip=alt.Tooltip('sum(total_counts):Q', format='.0f')) # bar_rank_yellow = bar_rank_yellow.encode(tooltip=alt.Tooltip('sum(total_counts):Q', format='.0f')) yellow = first.properties(width=700, height=250) | bar_rank_yellow return yellow # we want to use bootstrap/template, tell Panel to load up what we need pn.extension(design='bootstrap') # we want to use vega, tell Panel to load up what we need pn.extension('vega') # create a basic template using bootstrap template = pn.template.BootstrapTemplate( title='SI649 Scientific Visualization Project', ) # 0. the main column will hold our key content maincol = pn.Column() # 1. Load the Data url = 'https://raw.githubusercontent.com/yanzhuo2001/SI_649_Projects/main/scientific%20viz%20project/final_data.csv' df = pd.read_csv(url) for index, row in df.iterrows(): minute = row['minute'] minute1 = math.floor(minute) df.loc[index, 'minute1'] = minute1 YC_df = plot_event_distribution(df, 'Yellow_Card') RC_df = plot_event_distribution(df, 'Red_Card') Goal_df = plot_event_distribution(df, 'Goal') event_dfs = [YC_df, RC_df, Goal_df] event_names = ['Yellow_Card', 'Red_Card', 'Goal'] final_df = create_event_distribution_df(event_dfs, event_names) final_df = final_df[final_df['matchPeriod'].isin(['1H', '2H'])] for name in final_df['TeamName'].unique(): new = pd.DataFrame({ 'eventName': ['Yellow_Card', 'Red_Card', 'Goal'], 'timeLabel': [' '] * 3, 'total_counts': [0] * 3, 'matchPeriod': ['1H']*3, 'TeamName': [name] *3 }) final_df = pd.concat([final_df, new], ignore_index=True) order = ['0-5', '5-10', '10-15', '15-20', '20-25', '25-30', '30-35', '35-40', '40-45', '>45', ' ', '45-50', '50-55', '55-60', '60-65', '65-70', '70-75', '75-80', '80-85', '85-90', '>90'] yellow = create_altair_chart(final_df, 'Yellow_Card', order, if_add_xticks=False) red = create_altair_chart(final_df, 'Red_Card', order, if_add_xticks=True) goal = create_altair_chart(final_df, 'Goal', order, if_add_xticks=False) final = (goal & yellow & red).configure_legend( orient='top-left', # 图例位置在左上角 labelFontSize=18, # 图例标签的字体大小 symbolSize=250, # 图例符号的大小 fillColor='white', # 图例背景颜色 strokeWidth=2, # 图例边框粗细 padding=10, # 图例内的填充 ).configure_view( strokeWidth=1, # 图表边框粗细 stroke='black' ) # 2. append the plot maincol.append(final) template.main.append(maincol) # Indicate that the template object is the "application" and serve it template.servable(title="SI649 Scientific Visualization Project")