使用替换方法后在数据框中选择不同的特定值
Selecting different specific values in dataframe after use replace method
这是我的代码：
from bs4 import BeautifulSoup
from urllib.request import urlopen
import pandas as pd
import matplotlib as mpl
import numpy as np
import matplotlib.pyplot as plt
#create a list of each year where data will be extract
years_list = [2001, 2002, 2008, 2012, 2015,2018, 2020 , 2021]
player_list = ['Mac Jones', 'Aaron Rodgers', 'Deshaun Watson', 'Patrick Mahomes',
'Josh Allen', 'Ryan Tannehill', 'Drew Bress', 'Russel Wilson',
'Kirk Cousins', 'Tom Brady', 'Derek Carr']
#selecting stats
cols = ['Player', 'Tm','Cmp%', 'Yds', 'TD', 'Int', 'Y/A', 'Rate', 'G']
df_list = []
#loop for extract data
for year in years_list:
url_mac = f'https://www.pro-football-reference.com/years/{year}/passing.htm'
temp_df = pd.read_html(url_mac)[0][cols]
temp_df['Season'] = year
df_list.append(temp_df)
print(f'Collected: {year}')
data_radar = pd.concat(df_list)
#renaming columns
new_columns = data_radar.columns.values
new_columns[-6] = 'y_sack'
data_radar.columns = new_columns
#picking stats
mid_data = pd.DataFrame()
for player in player_list:
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '*'])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '*' + '+'])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '+'])
#relevant stats
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
final_data = pd.DataFrame()
#fixing names
mid_data = mid_data.replace({'Tom Brady*':'Tom Brady', 'Aaron Rodgers*':'Aaron Rodgers','Aaron Rodgers*+':'Aaron Rodgers',
'Deshaun Watson*':'Deshaun Watson', 'Josh Allen*':'Josh Allen',
'Derek Carr*':'Derek Carr','Patrick Mahomes*':'Patrick Mahomes', 'Patrick Mahomes*+':'Patrick Mahomes' })
#Select informations about players and ordering
final_data = mid_data[['Player', 'Tm'] + cols]
final_data.sort_values(by = 'Player', ascending=True)
final_data.drop_duplicates(subset = 'Player')
我想要的代码是我的 df final_data returns 我每个球员的第一个赛季，但这不适用于我需要使用替换方法的一些球员。
在 drop.duplicates()
之前，我写给 sort_value 的地方就是我的结果
我的想法是对这些值进行排序，然后使用 drop.duplicates() 到每个玩家的第一个 select。
我需要使用替换方法的所有播放器都会出现这种情况。如何解决这个问题？
您的代码中有很多令人困惑的部分。首先，如果您只想去掉玩家名称中的 '*' 和或 '+'，为什么不直接这样做而不是对每个玩家进行硬编码呢？其次，您的评论实际上并没有描述您的代码在做什么。我不明白
的意义
#Converting colums from object to floats
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
final_data = pd.DataFrame()
因为您没有转换为浮点数，而且 # picking top 10 qb in rating stats in last season + Mac Jones 评论也没有按照它说的去做。很难理解你的评论。
第三，如果你想要每个球员的第一个赛季，那么你需要按'Season'排序，所以当你删除重复的球员名字时，你可以明确地说保留第一个[=29] =] 那个球员，如果你排序的话，这将是他们在数据框中的第一个赛季。
试试这个：
import pandas as pd
#create a list of each year where data will be extract
years_list = [2001, 2002, 2008, 2012, 2015,2018, 2020 , 2021]
player_list = ['Mac Jones', 'Aaron Rodgers', 'Deshaun Watson', 'Patrick Mahomes',
'Josh Allen', 'Ryan Tannehill', 'Drew Bress', 'Russel Wilson',
'Kirk Cousins', 'Tom Brady', 'Derek Carr']
#selecting stats
cols = ['Player', 'Tm','Cmp%', 'Yds', 'TD', 'Int', 'Y/A', 'Rate', 'G']
df_list = []
#loop for extract data
for year in years_list:
url_mac = f'https://www.pro-football-reference.com/years/{year}/passing.htm'
temp_df = pd.read_html(url_mac)[0][cols]
temp_df['Season'] = year
temp_df = temp_df[temp_df['Player'] != 'Player']
df_list.append(temp_df)
print(f'Collected: {year}')
data_radar = pd.concat(df_list)
#renaming columns
new_columns = data_radar.columns.values
new_columns[-6] = 'y_sack'
data_radar.columns = new_columns
# Repace * or + with ''
data_radar['Player'] = data_radar['Player'].str.replace(r'\*|\+','')
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
#Select informations about players and ordering
final_data = data_radar[['Player', 'Tm'] + cols]
final_data = final_data.sort_values(by = ['Player', 'Season'], ascending=[True,True])
final_data = final_data.drop_duplicates(subset = 'Player', keep='first')
输出：
print(final_data)
Player Tm Cmp% Yds Int Y/A Rate G Season
53 A.J. Feeley PHI 71.4 143 1 10.2 114.0 1 2001
41 A.J. McCarron CIN 66.4 854 2 7.2 97.1 7 2015
3 Aaron Brooks NOR 55.9 3832 22 6.9 76.4 16 2001
3 Aaron Rodgers GNB 63.6 4038 13 7.5 93.8 16 2008
71 Akili Smith CIN 62.5 37 0 4.6 73.4 2 2001
.. ... ... ... ... .. ... ... .. ...
89 Wayne Chrebet NYJ 0.0 0 0 0.0 39.6 15 2002
39 Zach Mettenberger TEN 60.8 935 7 5.6 66.7 7 2015
112 Zach Pascal IND 0.0 0 0 0.0 39.6 16 2020
27 Zach Wilson NYJ 55.2 628 7 6.0 51.6 3 2021
105 Zay Jones BUF 0.0 0 0 0.0 39.6 16 2018
[427 rows x 9 columns]
这是我的代码：
from bs4 import BeautifulSoup
from urllib.request import urlopen
import pandas as pd
import matplotlib as mpl
import numpy as np
import matplotlib.pyplot as plt
#create a list of each year where data will be extract
years_list = [2001, 2002, 2008, 2012, 2015,2018, 2020 , 2021]
player_list = ['Mac Jones', 'Aaron Rodgers', 'Deshaun Watson', 'Patrick Mahomes',
'Josh Allen', 'Ryan Tannehill', 'Drew Bress', 'Russel Wilson',
'Kirk Cousins', 'Tom Brady', 'Derek Carr']
#selecting stats
cols = ['Player', 'Tm','Cmp%', 'Yds', 'TD', 'Int', 'Y/A', 'Rate', 'G']
df_list = []
#loop for extract data
for year in years_list:
url_mac = f'https://www.pro-football-reference.com/years/{year}/passing.htm'
temp_df = pd.read_html(url_mac)[0][cols]
temp_df['Season'] = year
df_list.append(temp_df)
print(f'Collected: {year}')
data_radar = pd.concat(df_list)
#renaming columns
new_columns = data_radar.columns.values
new_columns[-6] = 'y_sack'
data_radar.columns = new_columns
#picking stats
mid_data = pd.DataFrame()
for player in player_list:
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '*'])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '*' + '+'])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player])
mid_data = mid_data.append(data_radar[data_radar['Player'] == player + '+'])
#relevant stats
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
final_data = pd.DataFrame()
#fixing names
mid_data = mid_data.replace({'Tom Brady*':'Tom Brady', 'Aaron Rodgers*':'Aaron Rodgers','Aaron Rodgers*+':'Aaron Rodgers',
'Deshaun Watson*':'Deshaun Watson', 'Josh Allen*':'Josh Allen',
'Derek Carr*':'Derek Carr','Patrick Mahomes*':'Patrick Mahomes', 'Patrick Mahomes*+':'Patrick Mahomes' })
#Select informations about players and ordering
final_data = mid_data[['Player', 'Tm'] + cols]
final_data.sort_values(by = 'Player', ascending=True)
final_data.drop_duplicates(subset = 'Player')
我想要的代码是我的 df final_data returns 我每个球员的第一个赛季，但这不适用于我需要使用替换方法的一些球员。
在 drop.duplicates()
之前，我写给 sort_value 的地方就是我的结果我的想法是对这些值进行排序，然后使用 drop.duplicates() 到每个玩家的第一个 select。
我需要使用替换方法的所有播放器都会出现这种情况。如何解决这个问题？
您的代码中有很多令人困惑的部分。首先，如果您只想去掉玩家名称中的 '*' 和或 '+'，为什么不直接这样做而不是对每个玩家进行硬编码呢？其次，您的评论实际上并没有描述您的代码在做什么。我不明白
#Converting colums from object to floats
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
final_data = pd.DataFrame()
因为您没有转换为浮点数，而且 # picking top 10 qb in rating stats in last season + Mac Jones 评论也没有按照它说的去做。很难理解你的评论。
第三，如果你想要每个球员的第一个赛季，那么你需要按'Season'排序，所以当你删除重复的球员名字时，你可以明确地说保留第一个[=29] =] 那个球员，如果你排序的话，这将是他们在数据框中的第一个赛季。
试试这个：
import pandas as pd
#create a list of each year where data will be extract
years_list = [2001, 2002, 2008, 2012, 2015,2018, 2020 , 2021]
player_list = ['Mac Jones', 'Aaron Rodgers', 'Deshaun Watson', 'Patrick Mahomes',
'Josh Allen', 'Ryan Tannehill', 'Drew Bress', 'Russel Wilson',
'Kirk Cousins', 'Tom Brady', 'Derek Carr']
#selecting stats
cols = ['Player', 'Tm','Cmp%', 'Yds', 'TD', 'Int', 'Y/A', 'Rate', 'G']
df_list = []
#loop for extract data
for year in years_list:
url_mac = f'https://www.pro-football-reference.com/years/{year}/passing.htm'
temp_df = pd.read_html(url_mac)[0][cols]
temp_df['Season'] = year
temp_df = temp_df[temp_df['Player'] != 'Player']
df_list.append(temp_df)
print(f'Collected: {year}')
data_radar = pd.concat(df_list)
#renaming columns
new_columns = data_radar.columns.values
new_columns[-6] = 'y_sack'
data_radar.columns = new_columns
# Repace * or + with ''
data_radar['Player'] = data_radar['Player'].str.replace(r'\*|\+','')
cols = ['Cmp%', 'Yds', 'Int', 'Y/A','Rate', 'G', 'Season']
#Select informations about players and ordering
final_data = data_radar[['Player', 'Tm'] + cols]
final_data = final_data.sort_values(by = ['Player', 'Season'], ascending=[True,True])
final_data = final_data.drop_duplicates(subset = 'Player', keep='first')
输出：
print(final_data)
Player Tm Cmp% Yds Int Y/A Rate G Season
53 A.J. Feeley PHI 71.4 143 1 10.2 114.0 1 2001
41 A.J. McCarron CIN 66.4 854 2 7.2 97.1 7 2015
3 Aaron Brooks NOR 55.9 3832 22 6.9 76.4 16 2001
3 Aaron Rodgers GNB 63.6 4038 13 7.5 93.8 16 2008
71 Akili Smith CIN 62.5 37 0 4.6 73.4 2 2001
.. ... ... ... ... .. ... ... .. ...
89 Wayne Chrebet NYJ 0.0 0 0 0.0 39.6 15 2002
39 Zach Mettenberger TEN 60.8 935 7 5.6 66.7 7 2015
112 Zach Pascal IND 0.0 0 0 0.0 39.6 16 2020
27 Zach Wilson NYJ 55.2 628 7 6.0 51.6 3 2021
105 Zay Jones BUF 0.0 0 0 0.0 39.6 16 2018
[427 rows x 9 columns]