from sklearn.metrics import recall_score
from sklearn.metrics import precision_score
from sklearn.metrics import accuracy_score
from sklearn.metrics import f1_score

male = ['windows', 'gb', 'mb', 'meczu', 'pc', 'opony', 'apple', 'iphone', 'zwiast', 'hd', 'ubunt', 
        'system', 'serwer', "youtub", "sfd", "kfd", "elektr", "autoce", "dobrep",'merced', 'bmw',
        'audi', 'porsch', 'gry', 'gra','gram' 'cs', 'counte', 'piłka', 'mecz', 'gol', 'bramka', 'linux',
        'robota','felga','lagi' 'żona', 'żona', 'żony', 'żonie', 'żoną', 'zona', 'zony', 'zonie', 'komput', 'inform'
        'sserwer', 'ziom', 'ziomków', 'ziomkow', 'kumpel', 'kolega', 'kolegą', 'kolegi', 'pad'
        ]


female = ['ciąży', 'miesią', 'ciasto', 'ciążę', 'zadowo', 'ciąża', 'ciazy', 'antyko', 'gineko',
         'tablet', 'porodz', 'mąż', 'miesią', 'krwawi', 'ciasta', 'sukien', 'podpas', 'szmink',
          'maz', 'męża', 'męza', 'mąż', 'chłopak', 'szpilk'
     ]



def prediction(male,female, in_file):
    results = []
    with open(in_file, encoding='utf-8',) as file:
            for line in file.readlines():
                text = line.split("\t")[0].strip()
                text = text.replace(",","").replace(".","").replace("/","").replace("–","").replace(":","").lower()
                stem_words = [word[:6] for word in text.split()]

                man_score = len([w for w in stem_words if w in male])
                girl_score = len([w for w in stem_words if w in female])
                if man_score > girl_score:
                    results.append('1')
                else:
                    results.append('0')
    return results


def out_file(result, out_file):
    with open(out_file, 'w') as file:
        for r in result:
            file.write(r + "\n")
            


result = prediction(male,female,'dev-0/in.tsv')
out_file(result, 'dev-0/out.tsv')

result = prediction(male,female,'dev-1/in.tsv')
out_file(result, 'dev-1/out.tsv')

result = prediction(male,female,'test-A/in.tsv')
out_file(result, 'test-A/out.tsv')