import pandas as pd
import numpy as np
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.impute import SimpleImputer
import re
from sklearn.preprocessing import StandardScaler


class PrepProcesor(BaseEstimator, TransformerMixin):
    def fit(self, X, y=None):
        self.ageImputer = SimpleImputer()
        self.ageImputer.fit(X[['Locked_period']])
        return self

    def transform(self, X, y=None):
        X['Locked_period'] = self.ageImputer.transform(X[['Locked_period']])
        # X['CabinClass'] = X['Cabin'].fillna('M').apply(lambda x: str(x).replace(" ", "")).apply(lambda x: re.sub(r'[^a-zA-Z]', '', x))
        # X['CabinNumber'] = X['Cabin'].fillna('M').apply(lambda x: str(x).replace(" ", "")).apply(lambda x: re.sub(r'[^0-9]', '', x)).replace('', 0)
        # X['Embarked'] = X['Embarked'].fillna('M')
        X = StandardScaler.fit_transform(X)
        #X = X.drop(['PassengerId', 'Name', 'Ticket','Cabin'], axis=1)
        return X


columns = ['Wallet_distribution', 'Whale_anomalie_activities', 'Locked_period', 'Operation_duration', 'PR_articles', 'Decentralized_transaction','twitter_followers_growthrate','unique_address_growthrate', 'month_transaction_growthrate','github_update', 'code_review_report', 'publicChain_safety' , 'investedProjects','token_price', 'token_voltality_overDot', 'negative', 'neutre', 'positive', 'KOL_comments', 'media_negatifReport']