ordinal_encoder = OrdinalEncoder() housing_cat_encoded = ordinal_encoder.fit_transform(housing_cat) housing_cat_encoded[:10] # In[62]: ordinal_encoder.categories_ # **Warning**: earlier versions of the book used the `LabelBinarizer` or `CategoricalEncoder` classes to convert each categorical value to a one-hot vector. It is now preferable to use the `OneHotEncoder` class. Right now it can only handle integer categorical inputs, but in Scikit-Learn 0.20 it will also handle string categorical inputs (see [PR #10521](https://github.com/scikit-learn/scikit-learn/issues/10521)). So for now we import it from `future_encoders.py`, but when Scikit-Learn 0.20 is released, you can import it from `sklearn.preprocessing` instead: # In[63]: from future_encoders import OneHotEncoder cat_encoder = OneHotEncoder() housing_cat_1hot = cat_encoder.fit_transform(housing_cat) housing_cat_1hot # By default, the `OneHotEncoder` class returns a sparse array, but we can convert it to a dense array if needed by calling the `toarray()` method: # In[64]: housing_cat_1hot.toarray() # Alternatively, you can set `sparse=False` when creating the `OneHotEncoder`: # In[65]: cat_encoder = OneHotEncoder(sparse=False) housing_cat_1hot = cat_encoder.fit_transform(housing_cat) housing_cat_1hot
#Taking care of missing data
from sklearn.preprocessing import Imputer
imputer=Imputer(strategy="median") #We want to replace each attribute's missing values with the median of that attribute
housing_num=housing.drop("ocean_proximity",axis=1) #Copy withouth the text attribute
imputer.fit(housing_num) #
imputer.statistics_ #Shows the results (median for each attribute)
X=imputer.transform(housing_num) #Transform the training set by replacing the missing values by the learned values
housing_tr=pd.DataFrame(X,columns=housing_num.columns)#Convert the array to a DataFrame
#Handling Text and Categorical Attributes
housing_cat=housing["ocean_proximity"] #Categorical attribute. It is a serie
housing_cat=pd.DataFrame(data=housing_cat) #DataFrame converts from serie --> DataFrame (includes the index)
from future_encoders import OneHotEncoder #This function assign 1 for when the instance has that category
cat_encoder=OneHotEncoder(sparse=False)
housing_cat_1hot=cat_encoder.fit_transform(housing_cat) #Then, create a sparse matrix with the location of nonzeros.
housing_cat_1hot
cat_encoder.categories_
#Custom Transformer
from sklearn.base import BaseEstimator,TransformerMixin
rooms_ix,bedrooms_ix,population_ix,household_ix=3,4,5,6 #Columns (location) of each attribute
class CombinedAttributesAdder(BaseEstimator,TransformerMixin): #The New class is using two base classes
def __init__(self,add_bedrooms_per_room=True): #_init_ is the constructor for the class
self.add_bedrooms_per_room=add_bedrooms_per_room
def fit(self,X,y=None):
return self #Nothing else to do
def transform(self,X,y=None): #This function does the combination of parameters as it was done before