Я был на всем этом сайте, и Google пытается решить эту проблему.
Кажется, что я упускаю фундаментальную концепцию при создании графического кадра данных.
Я пытался убедиться, что у меня естьстолбец строк для «Команды» и столбец целых чисел для «Точек»
Тем не менее я получаю: TypeError: Пусто 'DataFrame': нет числовых данных для построения
import csv
import pandas
import numpy
import matplotlib.pyplot as plt
from matplotlib.ticker import StrMethodFormatter
set_of_teams = set()
def load_epl_games(file_name):
with open(file_name, newline='') as csvfile:
reader = csv.DictReader(csvfile)
raw_data = {"HomeTeam": [], "AwayTeam": [], "FTHG": [], "FTAG": [], "FTR": []}
for row in reader:
set_of_teams.add(row["HomeTeam"])
set_of_teams.add(row["AwayTeam"])
raw_data["HomeTeam"].append(row["HomeTeam"])
raw_data["AwayTeam"].append(row["AwayTeam"])
raw_data["FTHG"].append(row["FTHG"])
raw_data["FTAG"].append(row["FTAG"])
raw_data["FTR"].append(row["FTR"])
data_frame = pandas.DataFrame(data=raw_data)
return data_frame
def calc_points(team, table):
points = 0
for row_number in range(table["HomeTeam"].count()):
home_team = table.loc[row_number, "HomeTeam"]
away_team = table.loc[row_number, "AwayTeam"]
if team in [home_team, away_team]:
home_team_points = 0
away_team_points = 0
winner = table.loc[row_number, "FTR"]
if winner == 'H':
home_team_points = 3
elif winner == 'A':
away_team_points = 3
else:
home_team_points = 1
away_team_points = 1
if team == home_team:
points += home_team_points
else:
points += away_team_points
return points
def get_goals_scored_conceded(team, table):
scored = 0
conceded = 0
for row_number in range(table["HomeTeam"].count()):
home_team = table.loc[row_number, "HomeTeam"]
away_team = table.loc[row_number, "AwayTeam"]
if team in [home_team, away_team]:
if team == home_team:
scored += int(table.loc[row_number, "FTHG"])
conceded += int(table.loc[row_number, "FTAG"])
else:
scored += int(table.loc[row_number, "FTAG"])
conceded += int(table.loc[row_number, "FTHG"])
return (scored, conceded)
def compute_table(df):
raw_data = {"Team": [], "Points": [], "GoalDifference":[], "Goals": []}
for team in set_of_teams:
goal_data = get_goals_scored_conceded(team, df)
raw_data["Team"].append(team)
raw_data["Points"].append(calc_points(team, df))
raw_data["GoalDifference"].append(goal_data[0] - goal_data[1])
raw_data["Goals"].append(goal_data[0])
data_frame = pandas.DataFrame(data=raw_data)
data_frame = data_frame.sort_values(["Points", "GoalDifference", "Goals"], ascending=[False, False, False]).reset_index(drop=True)
data_frame.index = numpy.arange(1,len(data_frame)+1)
data_frame.index.names = ["Finish"]
return data_frame
def get_finish(team, table):
return table[table.Team==team].index.item()
def get_points(team, table):
return table[table.Team==team].Points.item()
def display_hbar(tables):
raw_data = {"Team": [], "Points": []}
for row_number in range(tables["Team"].count()):
raw_data["Team"].append(tables.loc[row_number+1, "Team"])
raw_data["Points"].append(int(tables.loc[row_number+1, "Points"]))
df = pandas.DataFrame(data=raw_data)
#df = pandas.DataFrame(tables, columns=["Team", "Points"])
print(df)
print(df.dtypes)
df["Points"].apply(int)
print(df.dtypes)
df.plot(kind='barh',x='Points',y='Team')
games = load_epl_games('epl2016.csv')
final_table = compute_table(games)
#print(final_table)
#print(get_finish("Tottenham", final_table))
#print(get_points("West Ham", final_table))
display_hbar(final_table)
Вывод:
Team Points
0 Chelsea 93
1 Tottenham 86
2 Man City 78
3 Liverpool 76
4 Arsenal 75
5 Man United 69
6 Everton 61
7 Southampton 46
8 Bournemouth 46
9 West Brom 45
10 West Ham 45
11 Leicester 44
12 Stoke 44
13 Crystal Palace 41
14 Swansea 41
15 Burnley 40
16 Watford 40
17 Hull 34
18 Middlesbrough 28
19 Sunderland 24
Team object
Points int64
dtype: object
Team object
Points int64
dtype: object
Traceback (most recent call last):
File "C:/Users/Michael/Documents/Programming/Python/Premier League.py", line 99, in <module>
display_hbar(final_table)
File "C:/Users/Michael/Documents/Programming/Python/Premier League.py", line 92, in display_hbar
df.plot(kind='barh',x='Points',y='Team')
File "C:\Program Files (x86)\Python36-32\lib\site- packages\pandas\plotting\_core.py", line 2941, in __call__
sort_columns=sort_columns, **kwds)
File "C:\Program Files (x86)\Python36-32\lib\site-packages\pandas\plotting\_core.py", line 1977, in plot_frame
**kwds)
File "C:\Program Files (x86)\Python36-32\lib\site-packages\pandas\plotting\_core.py", line 1804, in _plot
plot_obj.generate()
File "C:\Program Files (x86)\Python36-32\lib\site-packages\pandas\plotting\_core.py", line 258, in generate
self._compute_plot_data()
File "C:\Program Files (x86)\Python36-32\lib\site-packages\pandas\plotting\_core.py", line 373, in _compute_plot_data
'plot'.format(numeric_data.__class__.__name__))
TypeError: Empty 'DataFrame': no numeric data to plot
Что я делаю не так в своей функции display_hbar, которая мешает мне отображать данные?
Вот CSV-файл