2024-01-06 15:53:05 +01:00
|
|
|
import simpful
|
2024-01-06 20:36:34 +01:00
|
|
|
from data_filters import *
|
|
|
|
import pandas as pd
|
2024-01-06 15:53:05 +01:00
|
|
|
|
2024-01-21 21:50:20 +01:00
|
|
|
FS = FuzzySystem()
|
|
|
|
|
|
|
|
# Dominacja OK
|
|
|
|
# Jakość strzałów - Witek
|
|
|
|
# Agresesywnosc (zolte + czerwone kartki) - Wojtek
|
|
|
|
# odbiory i wslizgi (xDef) - Michał, ekspert od xDef
|
2024-01-22 15:59:58 +01:00
|
|
|
# statystyki z calego sezonu - Wojtek OK
|
2024-01-21 21:50:20 +01:00
|
|
|
# 5 ostatnich spotkan miedzy druzynami - Witek
|
|
|
|
def categorize_fuzzy_passes(passes,possession):
|
|
|
|
|
|
|
|
|
|
|
|
FS.set_crisp_output_value("low", 0.0)
|
|
|
|
FS.set_crisp_output_value("average", 0.5)
|
|
|
|
FS.set_crisp_output_value("high", 1.0)
|
|
|
|
|
|
|
|
Pass1 = TriangleFuzzySet(300,300,500, term="low")
|
|
|
|
Pass2 = TriangleFuzzySet(300,450,600, term="average")
|
|
|
|
Pass3 = TriangleFuzzySet(400,600,600, term="high")
|
|
|
|
|
|
|
|
FS.add_linguistic_variable("passes", LinguisticVariable([Pass1, Pass2, Pass3], universe_of_discourse=[0,1000]))
|
|
|
|
|
|
|
|
Poss1 = TriangleFuzzySet(30,30,45, term="low")
|
|
|
|
Poss2 = TriangleFuzzySet(40,50,60, term="average")
|
|
|
|
Poss3 = TriangleFuzzySet(55,70,70, term="high")
|
|
|
|
|
|
|
|
FS.add_linguistic_variable("possession", LinguisticVariable([Poss1, Poss2, Poss3], universe_of_discourse=[0,100]))
|
|
|
|
|
|
|
|
|
|
|
|
#Pass_domination1 = TriangleFuzzySet(2,2,6, term="low")
|
|
|
|
#Pass_domination2 = TriangleFuzzySet(3,5,7, term="average")
|
|
|
|
#Pass_domination3 = TriangleFuzzySet(4,8,8, term="high")
|
|
|
|
|
|
|
|
#FS.add_linguistic_variable("passes_domination", LinguisticVariable([Pass_domination1, Pass_domination2, Pass_domination3], universe_of_discourse=[0,10]))
|
|
|
|
|
|
|
|
|
|
|
|
FS.add_rules([
|
|
|
|
|
|
|
|
"IF (passes IS low) AND (possession IS low) THEN (pass_domination IS low)",
|
|
|
|
|
|
|
|
"IF (passes IS high) AND (possession IS high) THEN (pass_domination IS high)",
|
|
|
|
|
|
|
|
"IF (passes IS average) AND (possession IS average) THEN (pass_domination IS average)",
|
|
|
|
|
|
|
|
"IF (passes IS low) AND (possession IS high) THEN (pass_domination IS average)",
|
|
|
|
|
|
|
|
"IF (passes IS high ) AND (possession IS low) THEN (pass_domination IS average)",
|
|
|
|
|
|
|
|
"IF (passes IS average) AND (possession IS high) THEN (pass_domination IS high)",
|
|
|
|
|
|
|
|
"IF (passes IS high) AND (possession IS average) THEN (pass_domination IS high)",
|
|
|
|
|
|
|
|
"IF (passes IS low) AND (possession IS average) THEN (pass_domination IS low)",
|
|
|
|
|
|
|
|
"IF (passes IS average) AND (possession IS low) THEN (pass_domination IS average)"
|
|
|
|
])
|
2024-01-06 15:53:05 +01:00
|
|
|
|
2024-01-21 21:50:20 +01:00
|
|
|
FS.set_variable("passes", passes)
|
2024-01-06 15:53:05 +01:00
|
|
|
|
2024-01-21 21:50:20 +01:00
|
|
|
FS.set_variable("possession", possession)
|
|
|
|
|
|
|
|
pass_domination = FS.inference()
|
|
|
|
|
|
|
|
return pass_domination
|
|
|
|
|
|
|
|
def categorize_fuzzy_shots(shots_overall, shots_on_target):
|
|
|
|
|
|
|
|
FS.set_crisp_output_value("low", 0.0)
|
|
|
|
FS.set_crisp_output_value("average", 0.5)
|
|
|
|
FS.set_crisp_output_value("high", 1.0)
|
|
|
|
|
|
|
|
Shot_ov1 = TriangleFuzzySet(0,0,5, term="low") #pozmieniać przedziały (nakładają się)
|
|
|
|
Shot_ov2 = TriangleFuzzySet(5,10,15, term="medium")
|
|
|
|
Shot_ov3 = TriangleFuzzySet(15,25,25, term="high")
|
|
|
|
|
|
|
|
FS.add_linguistic_variable("shots_overall", LinguisticVariable([Shot_ov1, Shot_ov2, Shot_ov3], universe_of_discourse=[0,35]))
|
|
|
|
|
|
|
|
Shot_ont1 = TriangleFuzzySet(0,0,2, term="low")
|
|
|
|
Shot_ont2 = TriangleFuzzySet(2,4,6, term="medium")
|
|
|
|
Shot_ont3 = TriangleFuzzySet(6,10,10, term="high")
|
|
|
|
|
|
|
|
FS.add_linguistic_variable("shots_on_target", LinguisticVariable([Shot_ont1, Shot_ont2, Shot_ont3], universe_of_discourse=[0,15]))
|
|
|
|
|
|
|
|
|
|
|
|
#Qual_of_shots1 = TriangleFuzzySet(0,0,0.3, term="low")
|
|
|
|
#Qual_of_shots2 = TriangleFuzzySet(0.2,0.5,0.8, term="medium")
|
|
|
|
#Qual_of_shots3 = TriangleFuzzySet(0.7,1,1, term="high")
|
|
|
|
|
|
|
|
#FS.add_linguistic_variable("expected_goals", LinguisticVariable([Qual_of_shots1, Qual_of_shots2, Qual_of_shots3], universe_of_discourse=[0,1]))
|
|
|
|
|
|
|
|
|
|
|
|
FS.add_rules([
|
|
|
|
|
|
|
|
"IF (shots_overall IS low) AND (shots_on_target IS low) THEN (quality_of_shots IS low)",
|
|
|
|
|
|
|
|
"IF (shots_overall IS high) AND (shots_on_target IS high) THEN (quality_of_shots IS high)",
|
|
|
|
|
|
|
|
"IF (shots_overall IS average) AND (shots_on_target IS average) THEN (quality_of_shots IS average)",
|
|
|
|
|
|
|
|
"IF (shots_overall IS low) AND (shots_on_target IS high) THEN (quality_of_shots IS high)",
|
|
|
|
|
|
|
|
"IF (shots_overall IS high ) AND (shots_on_target IS low) THEN (quality_of_shots IS low)",
|
|
|
|
|
|
|
|
"IF (shots_overall IS average) AND (possession IS high) THEN (quality_of_shots IS high)",
|
|
|
|
|
|
|
|
"IF (passes IS high) AND (possession IS average) THEN (quality_of_shots IS high)",
|
|
|
|
|
|
|
|
"IF (passes IS low) AND (possession IS average) THEN (quality_of_shots IS low)",
|
|
|
|
|
|
|
|
"IF (passes IS average) AND (possession IS low) THEN (quality_of_shots IS average)"
|
|
|
|
|
|
|
|
])
|
2024-01-06 15:53:05 +01:00
|
|
|
|
|
|
|
|
2024-01-06 20:36:34 +01:00
|
|
|
|
|
|
|
|
|
|
|
def categorize_shots(shots):
|
|
|
|
if shots >= 12:
|
|
|
|
return 2
|
|
|
|
elif shots <= 6:
|
|
|
|
return 0
|
|
|
|
else:
|
|
|
|
return 1
|
|
|
|
|
|
|
|
def categorize_passes(pass_count):
|
|
|
|
if pass_count < 400:
|
|
|
|
return 0 #słabo
|
|
|
|
elif 400 <= pass_count <= 500:
|
|
|
|
return 1 #średnio
|
|
|
|
else:
|
|
|
|
return 2 #dużo
|
|
|
|
|
|
|
|
def categorize_possesion(shots):
|
|
|
|
if shots >= 56:
|
|
|
|
return 2
|
|
|
|
elif shots <= 40:
|
|
|
|
return 0
|
|
|
|
else:
|
|
|
|
return 1
|
|
|
|
|
2024-01-22 15:59:58 +01:00
|
|
|
def categorize_points(data, row, teamHome, matches_type):
|
2024-01-06 20:36:34 +01:00
|
|
|
if teamHome:
|
2024-01-22 15:59:58 +01:00
|
|
|
data_5 = matches_type(row['season'], row['home_team'], row['date'], data)
|
2024-01-06 20:36:34 +01:00
|
|
|
points = calculatePoints(data_5,row['home_team'])
|
|
|
|
else:
|
2024-01-22 15:59:58 +01:00
|
|
|
data_5 = matches_type(row['season'], row['away_team'], row['date'], data)
|
2024-01-06 20:36:34 +01:00
|
|
|
points = calculatePoints(data_5,row['away_team'])
|
|
|
|
if points <=1:
|
|
|
|
return 0
|
|
|
|
elif points >=2:
|
|
|
|
return 2
|
|
|
|
else:
|
|
|
|
return 1
|
|
|
|
|
2024-01-22 15:59:58 +01:00
|
|
|
def get_method(data, home_away, method, matches_type):
|
2024-01-21 21:50:20 +01:00
|
|
|
values = []
|
|
|
|
for index, row in data.iterrows():
|
2024-01-22 15:59:58 +01:00
|
|
|
values.append(method(data, row, home_away, matches_type))
|
2024-01-21 21:50:20 +01:00
|
|
|
return values
|
2024-01-06 20:36:34 +01:00
|
|
|
|
|
|
|
def get_points_home(data):
|
|
|
|
points = []
|
|
|
|
for index, row in data.iterrows():
|
|
|
|
points.append(categorize_points(data, row, True))
|
|
|
|
return points
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_points_away(data):
|
|
|
|
points = []
|
|
|
|
for index, row in data.iterrows():
|
|
|
|
points.append(categorize_points(data, row, False))
|
|
|
|
return points
|
|
|
|
|
|
|
|
|
|
|
|
|
2024-01-22 15:59:58 +01:00
|
|
|
def categorize_diff(data, row, teamHome, matches_type):
|
2024-01-06 20:36:34 +01:00
|
|
|
if teamHome:
|
2024-01-22 15:59:58 +01:00
|
|
|
data_5 = matches_type(row['season'], row['home_team'], row['date'], data)
|
2024-01-06 20:36:34 +01:00
|
|
|
diff = calculateGoalDifference(data_5,row['home_team'])
|
|
|
|
else:
|
2024-01-22 15:59:58 +01:00
|
|
|
data_5 = matches_type(row['season'], row['away_team'], row['date'], data)
|
2024-01-06 20:36:34 +01:00
|
|
|
diff = calculateGoalDifference(data_5,row['away_team'])
|
|
|
|
if diff <=0:
|
|
|
|
return 0
|
|
|
|
else:
|
|
|
|
return 1
|
|
|
|
|
|
|
|
|
|
|
|
def get_diff_home(data):
|
|
|
|
points = []
|
|
|
|
for index, row in data.iterrows():
|
|
|
|
points.append(categorize_diff(data, row, True))
|
|
|
|
return points
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def get_diff_away(data):
|
|
|
|
points = []
|
|
|
|
for index, row in data.iterrows():
|
|
|
|
points.append(categorize_diff(data, row, False))
|
|
|
|
return points
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def add_column(data_frame, transform_function, new_column, existing_column=None):
|
|
|
|
if existing_column != None:
|
|
|
|
new_column_values = data_frame[existing_column].apply(transform_function)
|
|
|
|
data_frame[new_column] = new_column_values
|
|
|
|
else:
|
|
|
|
new_column_values = transform_function
|
|
|
|
data_frame[new_column] = new_column_values
|
|
|
|
return data_frame
|
|
|
|
|
|
|
|
def get_result_list(df, home_team):
|
|
|
|
results = []
|
|
|
|
for score in df['result_full']:
|
|
|
|
results.append(getResult(score,home_team))
|
|
|
|
return results
|