2018_08_07_step_02.py

#%% 2. Create pipeline to clean contnous data
from sklearn.base import TransformerMixin, BaseEstimator
import pandas as pd

def center_and_scale_data(DataFrame):
    """
    this function does the actual center and scaling
    """
    D = DataFrame.copy()
    for C in D.columns:
        S = DataFrame[C].copy()
        D[C] = ( S - S.mean() ) / S.std()
    
    return D
    
class cont_cleaner(BaseEstimator, TransformerMixin):
    """
    Center and scales data
    
    Inputs:
        cols = list of strings (columns to be extracted)
        center = boolean to decide if data should be center and scaled
    """
        
    def __init__(self, cols, center=True):
        self.center = center
        self.cols = cols
    
    def fit(self, X, y=None):
        return self
    
    def transform(self, X):
        assert isinstance(X, pd.DataFrame)
        if self.center == True:
            final_data = center_and_scale_data(X[self.cols])
        else:
            final_data = X[self.cols].copy()
            
        return final_data

# define which variables to extract
list_of_cont_variables = ['horsepower','cylinders','displacement']

# create a tupple with the name transformer
cont_data_cleaner = ('cont_cleaner', cont_cleaner(cols = list_of_cont_variables)  )