问题代码 football analytics [Python] Noob
Problem code football analytics [Python] Noob
我一直在学习代码（足球数据分析），以便在足球分析中使用这项技能。
我之前问过，所有其他问题都已解决，但我不知道下面链接的代码中的 lambda 函数是如何工作的。
问题出在这个 lambda 函数上。我已经试过了，但它不起作用，我不知道如何解决它。没有这个，过滤器就不起作用。
有人可以帮助我吗：
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
summed_result = sum(breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
if summed_result > 0:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
在此先感谢您的帮助！
lambda 函数正在检查 Messi 的 pass_id 是否也位于 breceipt_df 列 'related_events' 中。如果是，它将 return 至少 1 True 行。所以 True 的总和将大于 0，这表明它是成功通过的。如果没有 True ，则总和不会大于0，因此会记录为不成功。
所以它只是检查两个 ID 是否都存在。我将其稍微更改为使用 lambda 函数，只是简单地检查 pass_id 是否在 related_events 列的列表中。该列有嵌套列表，因此需要展平（我在代码中这样做）
所以试着把它放在它的位置：
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
######### ALTERED CODE ###################
events_list = [item for sublist in breceipt_df['related_events'] for item in sublist]
if pass_id in events_list:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
########################################
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
完整代码
import matplotlib.pyplot as plt
import json
from pandas.io.json import json_normalize
from FCPython import createPitch
## Note Statsbomb data uses yards for their pitch dimensions
pitch_length_X = 120
pitch_width_Y = 80
## match id for our El Clasico
#match_list = [16205, 16131, 16265]
match_list = ['16157']
teamA = 'Barcelona' #<--- adjusted here
for match_id in match_list:
## calling the function to create a pitch map
## yards is the unit for measurement and
## gray will be the line color of the pitch map
(fig,ax) = createPitch(pitch_length_X, pitch_width_Y,'yards','gray') #< moved into for loop
player_name = 'Lionel Andrés Messi Cuccittini'
## this is the name of our event data file for
## our required El Clasico
file_name = str(match_id) + '.json'
## loading the required event data file
## Adjust path to your events folder
my_data = json.load(open('Statsbomb/open-data-master/data/events/' + file_name, 'r', encoding='utf-8'))
## get the nested structure into a dataframe
## store the dataframe in a dictionary with the match id as key
df = json_normalize(my_data, sep='_').assign(match_id = file_name[:-5])
teamB = [x for x in list(df['team_name'].unique()) if x != teamA ][0] #<--- get other team name
## making the list of all column names
column = list(df.columns)
## all the type names we have in our dataframe
all_type_name = list(df['type_name'].unique())
## creating a data frame for pass
## and then removing the null values
## only listing the player_name in the dataframe
pass_df = df.loc[df['type_name'] == 'Pass', :].copy()
pass_df.dropna(inplace=True, axis=1)
pass_df = pass_df.loc[pass_df['player_name'] == player_name, :]
## creating a data frame for ball receipt
## removing all the null values
## and only listing Barcelona players in the dataframe
breceipt_df = df.loc[df['type_name'] == 'Ball Receipt*', :].copy()
breceipt_df.dropna(inplace=True, axis=1)
breceipt_df = breceipt_df.loc[breceipt_df['team_name'] == 'Barcelona', :]
pass_comp, pass_no = 0, 0
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
events_list = [item for sublist in breceipt_df['related_events'] for item in sublist]
if pass_id in events_list:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
## computing pass accuracy
pass_acc = (pass_comp / (pass_comp + pass_no)) * 100
pass_acc = str(round(pass_acc, 2))
## adding text to the plot
plt.suptitle('{} pass map vs {}'.format(player_name, teamB), fontsize=15) #<-- make dynamic and change to suptitle
plt.title('Pass Accuracy: {}'.format(pass_acc), fontsize=15) #<-- change to title
## handling labels
handles, labels = plt.gca().get_legend_handles_labels()
by_label = dict(zip(labels, handles))
plt.legend(by_label.values(), by_label.keys(), loc='best', bbox_to_anchor=(0.9, 1, 0, 0), fontsize=12)
## editing the figure size and saving it
fig.set_size_inches(12, 8)
fig.savefig('{} passmap.png'.format(match_id), dpi=200) #<-- dynamic file name
## showing the plot
plt.show()
感谢大家的支持，真的很感谢大家的支持。
我试过相同的搭配：
另外我会附上代码，我添加了两个打印件以了解发生了什么：
代码打印：
名称：team_name，长度：802，数据类型：bool
summed_result: 0
接受+申请：
15 错误
34 错误
....
代码
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
pass_team = passed['team_name']
summed_result = sum(breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
print('brecept + apply : ', breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
print('summed_result: ', summed_result)
if summed_result > 0:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
我一直在学习代码（足球数据分析），以便在足球分析中使用这项技能。
我之前问过，所有其他问题都已解决，但我不知道下面链接的代码中的 lambda 函数是如何工作的。
问题出在这个 lambda 函数上。我已经试过了，但它不起作用，我不知道如何解决它。没有这个，过滤器就不起作用。
有人可以帮助我吗：
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
summed_result = sum(breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
if summed_result > 0:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
在此先感谢您的帮助！
lambda 函数正在检查 Messi 的 pass_id 是否也位于 breceipt_df 列 'related_events' 中。如果是，它将 return 至少 1 True 行。所以 True 的总和将大于 0，这表明它是成功通过的。如果没有 True ，则总和不会大于0，因此会记录为不成功。
所以它只是检查两个 ID 是否都存在。我将其稍微更改为使用 lambda 函数，只是简单地检查 pass_id 是否在 related_events 列的列表中。该列有嵌套列表，因此需要展平（我在代码中这样做）
所以试着把它放在它的位置：
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
######### ALTERED CODE ###################
events_list = [item for sublist in breceipt_df['related_events'] for item in sublist]
if pass_id in events_list:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
########################################
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
完整代码
import matplotlib.pyplot as plt
import json
from pandas.io.json import json_normalize
from FCPython import createPitch
## Note Statsbomb data uses yards for their pitch dimensions
pitch_length_X = 120
pitch_width_Y = 80
## match id for our El Clasico
#match_list = [16205, 16131, 16265]
match_list = ['16157']
teamA = 'Barcelona' #<--- adjusted here
for match_id in match_list:
## calling the function to create a pitch map
## yards is the unit for measurement and
## gray will be the line color of the pitch map
(fig,ax) = createPitch(pitch_length_X, pitch_width_Y,'yards','gray') #< moved into for loop
player_name = 'Lionel Andrés Messi Cuccittini'
## this is the name of our event data file for
## our required El Clasico
file_name = str(match_id) + '.json'
## loading the required event data file
## Adjust path to your events folder
my_data = json.load(open('Statsbomb/open-data-master/data/events/' + file_name, 'r', encoding='utf-8'))
## get the nested structure into a dataframe
## store the dataframe in a dictionary with the match id as key
df = json_normalize(my_data, sep='_').assign(match_id = file_name[:-5])
teamB = [x for x in list(df['team_name'].unique()) if x != teamA ][0] #<--- get other team name
## making the list of all column names
column = list(df.columns)
## all the type names we have in our dataframe
all_type_name = list(df['type_name'].unique())
## creating a data frame for pass
## and then removing the null values
## only listing the player_name in the dataframe
pass_df = df.loc[df['type_name'] == 'Pass', :].copy()
pass_df.dropna(inplace=True, axis=1)
pass_df = pass_df.loc[pass_df['player_name'] == player_name, :]
## creating a data frame for ball receipt
## removing all the null values
## and only listing Barcelona players in the dataframe
breceipt_df = df.loc[df['type_name'] == 'Ball Receipt*', :].copy()
breceipt_df.dropna(inplace=True, axis=1)
breceipt_df = breceipt_df.loc[breceipt_df['team_name'] == 'Barcelona', :]
pass_comp, pass_no = 0, 0
## pass_comp: completed pass
## pass_no: unsuccessful pass
## iterating through the pass dataframe
for row_num, passed in pass_df.iterrows():
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
events_list = [item for sublist in breceipt_df['related_events'] for item in sublist]
if pass_id in events_list:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1
## plotting circle at the player's position
shot_circle = plt.Circle((pitch_length_X - x_loc, y_loc), radius=2, color=color, label=label)
shot_circle.set_alpha(alpha=0.2)
ax.add_patch(shot_circle)
## parameters for making the arrow
pass_x = 120 - passed['pass_end_location'][0]
pass_y = passed['pass_end_location'][1]
dx = ((pitch_length_X - x_loc) - pass_x)
dy = y_loc - pass_y
## making an arrow to display the pass
pass_arrow = plt.Arrow(pitch_length_X - x_loc, y_loc, -dx, -dy, width=1, color=color)
## adding arrow to the plot
ax.add_patch(pass_arrow)
## computing pass accuracy
pass_acc = (pass_comp / (pass_comp + pass_no)) * 100
pass_acc = str(round(pass_acc, 2))
## adding text to the plot
plt.suptitle('{} pass map vs {}'.format(player_name, teamB), fontsize=15) #<-- make dynamic and change to suptitle
plt.title('Pass Accuracy: {}'.format(pass_acc), fontsize=15) #<-- change to title
## handling labels
handles, labels = plt.gca().get_legend_handles_labels()
by_label = dict(zip(labels, handles))
plt.legend(by_label.values(), by_label.keys(), loc='best', bbox_to_anchor=(0.9, 1, 0, 0), fontsize=12)
## editing the figure size and saving it
fig.set_size_inches(12, 8)
fig.savefig('{} passmap.png'.format(match_id), dpi=200) #<-- dynamic file name
## showing the plot
plt.show()
感谢大家的支持，真的很感谢大家的支持。
我试过相同的搭配：
另外我会附上代码，我添加了两个打印件以了解发生了什么：
代码打印：
名称：team_name，长度：802，数据类型：bool
summed_result: 0
接受+申请：
15 错误
34 错误
....
代码
if passed['player_name'] == player_name:
## for away side
x_loc = passed['location'][0]
y_loc = passed['location'][1]
pass_id = passed['id']
pass_team = passed['team_name']
summed_result = sum(breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
print('brecept + apply : ', breceipt_df.iloc[:, 14].apply(lambda x: pass_id in x))
print('summed_result: ', summed_result)
if summed_result > 0:
## if pass made was successful
color = 'blue'
label = 'Successful'
pass_comp += 1
else:
## if pass made was unsuccessful
color = 'red'
label = 'Unsuccessful'
pass_no += 1