SystemyRozmyte/data_filters.py

93 lines
3.0 KiB
Python
Raw Permalink Normal View History

2024-01-06 20:36:34 +01:00
import pandas as pd
from simpful import *
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_form_season','c_away_form_season',
'c_home_diff_season', 'c_away_diff_season']
2024-01-06 20:36:34 +01:00
return dataframe[columns]
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
2024-01-21 22:31:56 +01:00
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)
2024-01-06 20:36:34 +01:00
2024-01-21 22:31:56 +01:00
return before_given_date
2024-01-06 20:36:34 +01:00
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 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