Supercharge your brain with AI

from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
#Fill categorial values with 'missing' and numerical values with mean
cat_imputer = SimpleImputer(strategy="constant",fill_value="missing")
door_imputer = SimpleImputer(strategy="constant",fill_value=4)
num_imputer = SimpleImputer(strategy="mean")
#Define columns
cat_features = ['Make','Colour']
door_features = ['Doors']
num_features = ['Odometer (KM)']
#create an imputer that fills the missing data
imputer = ColumnTransformer([('catimputer',cat_imputer,cat_features),
                            ('doorimputer',door_imputer,door_features),
                            ('numimputer',num_imputer,num_features)
                            ])
filled_x = imputer.fit_transform(x)
car_sales_filled = pd.DataFrame(filled_x,columns=               ['Make','Colour','Doors','Odometer (KM)'])
# Lets try and convert our data to numbers
# Turn the categories into numbers
from sklearn.preprocessing import OneHotEncoder
categorial_features = ['Make','Colour','Doors']
onehot = OneHotEncoder()
transformer = ColumnTransformer([
    ('oh',onehot,categorial_features)
                                ],remainder="passthrough")
transformed_x = transformer.fit_transform(car_sales_filled)
# Now we have got our data as numbers and filled (no missing values)
# Lets fit the model
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(transformed_x,y,test_size=0.2)
model = RandomForestRegressor()
model.fit(x_train,y_train)
model.score(x_test,y_test)