SystemyRozmyte/data_filters.py

import pandas as pd
from simpful import *

FS = FuzzySystem()
def generateTrainingData(dataframe):
    columns = ['season','date','home_team','away_team','result_full','home_passes','away_passes',
               'home_possession','away_possession','home_shots','away_shots']
    return dataframe[columns]


def generateFuzzyLogicData(dataframe):
    columns = ['season','date','home_team','away_team','result_full','c_home_form_5m','c_away_form_5m',#,'c_home_passes','c_away_passes',
              # 'c_home_possession','c_away_possession','c_home_shots','c_away_shots',
               'c_home_diff_5m', 'c_away_diff_5m', 'c_home_aggression_5m',
               'c_away_aggression_5m', 'c_home_aggression_season', 'c_away_aggression_season',
               'c_home_form_season','c_away_form_season',
               'c_home_diff_season', 'c_away_diff_season']
    return dataframe[columns]

def calculateFuzzyAggression(yellow_cards, red_cards):
    FS.set_crisp_output_value("low", 0.0)
    FS.set_crisp_output_value("average", 0.5)
    FS.set_crisp_output_value("high", 1.0)

    Yellow_cards1 = TriangleFuzzySet(0, 2, 3, term="low")
    Yellow_cards2 = TriangleFuzzySet(2, 3, 4, term="average")
    Yellow_cards3 = TriangleFuzzySet(3, 4, 4, term="high")

    FS.add_linguistic_variable("yellow_cards", LinguisticVariable([Yellow_cards1, Yellow_cards2, Yellow_cards3], universe_of_discourse=[0, 10]))

    Red_cards1 = TriangleFuzzySet(0, 0, 1, term="low")
    Red_cards2 = TriangleFuzzySet(0, 1, 2, term="average")
    Red_cards3 = TriangleFuzzySet(1, 2, 2, term="high")

    FS.add_linguistic_variable("red_cards", LinguisticVariable([Red_cards1, Red_cards2, Red_cards3], universe_of_discourse=[0, 4]))

    # 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 (yellow_cards IS low) AND (red_cards IS low) THEN (aggression IS low)",

        "IF (yellow_cards IS high) AND (red_cards IS high) THEN (aggression IS high)",

        "IF (yellow_cards IS average) AND (red_cards IS average) THEN (aggression IS average)",

        "IF (yellow_cards IS low) AND (red_cards IS high) THEN (aggression IS high)",

        "IF (yellow_cards IS high ) AND (red_cards IS low) THEN (aggression IS high)",

        "IF (yellow_cards IS average) AND (red_cards IS high) THEN (aggression IS high)",

        "IF (yellow_cards IS high) AND (red_cards IS average) THEN (aggression IS high)",

        "IF (yellow_cards IS low) AND (red_cards IS average) THEN (aggression IS low)",

        "IF (yellow_cards IS average) AND (red_cards IS low) THEN (aggression IS average)"
    ])

    FS.set_variable("yellow_cards", yellow_cards)
    FS.set_variable("red_cards", red_cards)

    aggression = FS.inference()
    return aggression
def last5Matches(season, teamA, data, df):
    # Wybierz rekordy dla danej pary drużyn i sezonu
    subset = df[((df['season'] == season) & ((df['home_team'] == teamA) | (df['away_team'] == teamA)))]

    # Filtruj dane, aby zawierały te przed daną datą
    before_given_date = subset[pd.to_datetime(subset['date']) < pd.to_datetime(data)]

    # Posortuj wg daty w odwrotnej kolejności
    before_given_date = before_given_date.sort_values(by='date', ascending=False)

    # Wybierz 5 ostatnich przed daną datą
    last_before_date = before_given_date.head(5)

    return last_before_date

def last5MatchesBtwTeams(teamA, teamB, data, df):
    subset = df[(((df['home_team'] == teamA) | (df['away_team'] == teamA)) & ((df['home_team'] == teamB) | (df['away_team'] == teamB)))]
    before_given_date = subset[pd.to_datetime(subset['date']) < pd.to_datetime(data)]
    before_given_date = before_given_date.sort_values(by='date', ascending=False)
    last_before_date = before_given_date.head(5)

    return last_before_date

def seasonMatches(season, teamA, data, df):
    # Wybierz rekordy dla danej pary drużyn i sezonu
    subset = df[((df['season'] == season) & ((df['home_team'] == teamA) | (df['away_team'] == teamA)))]

    # Filtruj dane, aby zawierały te przed daną datą
    before_given_date = subset[pd.to_datetime(subset['date']) < pd.to_datetime(data)]

    # Posortuj wg daty w odwrotnej kolejności
    before_given_date = before_given_date.sort_values(by='date', ascending=False)

    return before_given_date

def getResult(score,teamHome):
    x,y = score.split('-')
    x = int(x)
    y = int(y)

    if (x > y and teamHome == True) or (x < y and teamHome == False):
        return "win"
    elif x == y:
        return "draw"
    else:
        return "loss"

def calculateAggression(matches, team):
    aggression = 0
    for index, row in matches.iterrows():
        if team == row['home_team']:
            yellow_cards = row['home_yellow_cards']
            red_cards = row['home_red_cards']
        else:
            yellow_cards = row['away_yellow_cards']
            red_cards = row['away_red_cards']
        aggression_result = calculateFuzzyAggression(yellow_cards, red_cards)
        #print(aggression_result['aggression'])
        aggression = aggression + aggression_result['aggression']
    if matches.shape[0] != 0:
        aggression_avg = aggression / matches.shape[0]
    else:
        aggression_avg = 0
    return aggression_avg

def calculatePoints(matches, team):
    points = 0
    for index, row in matches.iterrows():
        if team == row['home_team']:
            teamHome = True
        else:
            teamHome = False
        x = getResult(row['result_full'], teamHome)
        #print(x)
        if x == "win":
            points = points + 3
        elif x == "draw":
            points = points + 1
    if matches.shape[0] != 0:
        points_avg = points / matches.shape[0] 
    else:
        points_avg = 0
    return points_avg


def calculateGoalDifference(matches, team):
    goal_diff = 0
    for index, row in matches.iterrows():
        if team == row['home_team']:
            teamHome = True
        else:
            teamHome = False
        x,y = row['result_full'].split('-')
        x = int(x)
        y = int(y)
        if teamHome:
            goal_diff = goal_diff + (x-y)
        else:
            goal_diff = goal_diff + (y-x)
    return goal_diff