('std_scalar', StandardScaler())])
num_pipeline = Pipeline([('std_scalar', StandardScaler())])
housing_num_tr = num_pipeline.fit_transform(housing_tr)
'''
#%%
'''
housing['total_bedrooms'] = housing_tr['total_bedrooms']
housing['rooms_per_household'] = housing_tr['rooms_per_household']
housing['population_per_household'] = housing_tr['population_per_household']
housing['bedrooms_per_room'] = housing_tr['bedrooms_per_room']
'''
num_attribs = list(housing)
num_attribs.remove('ocean_proximity')
cat_attribs = ['ocean_proximity']
full_pipeline = ColumnTransformer([('num', num_pipeline, num_attribs),
('cat', OneHotEncoder(), cat_attribs)])
housing_prepared = full_pipeline.fit_transform(housing)
#%% Select and train a model
lin_reg = LinearRegression()
lin_reg.fit(housing_prepared, housing_labels)
#%%
housing_predictions = lin_reg.predict(housing_prepared)
lin_mse = mean_squared_error(housing_labels, housing_predictions)
lin_rmse = np.sqrt(lin_mse)
#%%
lin_mae = mean_absolute_error(housing_labels, housing_predictions)
#%%
housing_num_tr
# **Warning**: earlier versions of the book applied different transformations to different columns using a solution based on a `DataFrameSelector` transformer and a `FeatureUnion` (see below). It is now preferable to use the `ColumnTransformer` class that will be introduced in Scikit-Learn 0.20. For now we import it from `future_encoders.py`, but when Scikit-Learn 0.20 is released, you can import it from `sklearn.compose` instead:
# In[71]:
from future_encoders import ColumnTransformer
# In[72]:
num_attribs = list(housing_num)
cat_attribs = ["ocean_proximity"]
full_pipeline = ColumnTransformer([
("num", num_pipeline, num_attribs),
("cat", OneHotEncoder(), cat_attribs),
])
housing_prepared = full_pipeline.fit_transform(housing)
# In[73]:
housing_prepared
# In[74]:
housing_prepared.shape
# For reference, here is the old solution based on a `DataFrameSelector` transformer (to just select a subset of the Pandas `DataFrame` columns), and a `FeatureUnion`:
# In[75]:
if __name__ == "__main__":
# Load the dataset
df = load_data("Data/data.json")
# Select features and target
features = df.drop("score", axis=1)
y = df["score"].copy()
numeric_values = features.drop(["mood", "weather", "activity"], axis=1) # returns a copy of the dataframe
num_attribs = list(numeric_values)
cat_attribs = ["mood", "weather", "activity"]
num_pipeline = Pipeline([
('selector', DataFrameSelector(num_attribs)), # Own transformation
('imputer', Imputer(strategy="median")),
('std_scaler', StandardScaler()),
])
full_pipeline = ColumnTransformer([
("num_pipline", num_pipeline, num_attribs),
("cat_pipline", OneHotEncoder(), cat_attribs),
])
X = full_pipeline.fit_transform(features)
forest_reg = RandomForestRegressor()
forest_reg.fit(X, y)