!pip install numpy
!pip install matplotlib
!pip install pandas
!pip install scikit-learn
# To support both python 2 and python 3
from __future__ import division, print_function, unicode_literals
# Common imports
import numpy as np
import os
# to make this notebook's output stable across runs
np.random.seed(42)
# To plot pretty figures
%matplotlib inline
import matplotlib as mpl
import matplotlib.pyplot as plt
mpl.rc('axes', labelsize=14)
mpl.rc('xtick', labelsize=12)
mpl.rc('ytick', labelsize=12)
# Where to save the figures
PROJECT_ROOT_DIR = "./"
IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, "figs/")
def save_fig(fig_id, tight_layout=True, fig_extension="png", resolution=300):
path = os.path.join(IMAGES_PATH, fig_id + "." + fig_extension)
print("Saving figure", fig_id)
if tight_layout:
plt.tight_layout()
plt.savefig(path, format=fig_extension, dpi=resolution)
# Ignore useless warnings (see SciPy issue #5998)
import warnings
warnings.filterwarnings(action="ignore", message="^internal gelsd")
import os
import tarfile
from six.moves import urllib
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
HOUSING_PATH = os.path.join(PROJECT_ROOT_DIR, "datasets", "housing")
HOUSING_URL = DOWNLOAD_ROOT + "datasets/housing/housing.tgz"
def fetch_housing_data(housing_url=HOUSING_URL, housing_path=HOUSING_PATH):
if not os.path.isdir(housing_path):
os.makedirs(housing_path)
tgz_path = os.path.join(housing_path, "housing.tgz")
urllib.request.urlretrieve(housing_url, tgz_path)
housing_tgz = tarfile.open(tgz_path)
housing_tgz.extractall(path=housing_path)
housing_tgz.close()
fetch_housing_data()
import pandas as pd
def load_housing_data(housing_path=HOUSING_PATH):
csv_path = os.path.join(housing_path, "housing.csv")
return pd.read_csv(csv_path)
housing = load_housing_data()
housing.head()
housing.info()
housing["ocean_proximity"].value_counts()
housing.describe()
%matplotlib inline
import matplotlib.pyplot as plt
housing.hist(bins=50, figsize=(20,15))
save_fig("attribute_histogram_plots")
plt.show()
from sklearn.model_selection import train_test_split
train_set, test_set = train_test_split(housing, test_size=0.2, random_state=42)
test_set.head()
housing["median_income"].hist()
# Divide by 1.5 to limit the number of income categories
housing["income_cat"] = np.ceil(housing["median_income"] / 1.5)
# Label those above 5 as 5
housing["income_cat"].where(housing["income_cat"] < 5, 5.0, inplace=True)
housing["income_cat"].value_counts()
housing["income_cat"].value_counts() / len(housing)
train_set, test_set = train_test_split(housing, test_size=0.2, random_state=42)
strat_train_set, strat_test_set = train_test_split(housing, test_size=0.2, random_state=42, stratify=housing['income_cat'])
test_set["income_cat"].value_counts() / len(test_set)
strat_test_set["income_cat"].value_counts() / len(strat_test_set)
strat_train_set.drop("income_cat", axis=1, inplace=True)
strat_test_set.drop("income_cat", axis=1, inplace=True)
housing = strat_train_set.copy()
housing.plot(kind="scatter", x="longitude", y="latitude")
save_fig("bad_visualization_plot")
housing.plot(kind="scatter", x="longitude", y="latitude", alpha=0.1)
save_fig("better_visualization_plot")
housing.plot(kind="scatter", x="longitude", y="latitude", alpha=0.4,
s=housing["population"]/100, label="population", figsize=(10,7),
c="median_house_value", cmap=plt.get_cmap("jet"), colorbar=True,
sharex=False) # s is size and c is color
plt.legend()
save_fig("housing_prices_scatterplot")
import matplotlib.image as mpimg
california_img=mpimg.imread(PROJECT_ROOT_DIR + '/figs/california.png')
ax = housing.plot(kind="scatter", x="longitude", y="latitude", figsize=(10,7),
s=housing['population']/100, label="Population",
c="median_house_value", cmap=plt.get_cmap("jet"),
colorbar=False, alpha=0.4,
)
plt.imshow(california_img, extent=[-124.55, -113.80, 32.45, 42.05], alpha=0.5,
cmap=plt.get_cmap("jet"))
plt.ylabel("Latitude", fontsize=14)
plt.xlabel("Longitude", fontsize=14)
prices = housing["median_house_value"]
tick_values = np.linspace(prices.min(), prices.max(), 11)
cbar = plt.colorbar()
cbar.ax.set_yticklabels(["$%dk"%(round(v/1000)) for v in tick_values], fontsize=14)
cbar.set_label('Median House Value', fontsize=16)
plt.legend(fontsize=16)
save_fig("california_housing_prices_plot")
plt.show()
corr_matrix = housing.corr()
corr_matrix["median_house_value"].sort_values(ascending=False)
# from pandas.tools.plotting import scatter_matrix # For older versions of Pandas
from pandas.plotting import scatter_matrix
attributes = ["median_house_value", "median_income", "total_rooms",
"housing_median_age"]
scatter_matrix(housing[attributes], figsize=(12, 8))
save_fig("scatter_matrix_plot")
housing.plot(kind="scatter", x="median_income", y="median_house_value",
alpha=0.1)
plt.axis([0, 16, 0, 550000])
save_fig("income_vs_house_value_scatterplot")
housing["rooms_per_household"] = housing["total_rooms"]/housing["households"]
housing["bedrooms_per_room"] = housing["total_bedrooms"]/housing["total_rooms"]
housing["population_per_household"]=housing["population"]/housing["households"]
corr_matrix = housing.corr()
corr_matrix["median_house_value"].sort_values(ascending=False)
housing.plot(kind="scatter", x="rooms_per_household", y="median_house_value",
alpha=0.2)
plt.axis([0, 5, 0, 520000])
plt.show()
housing.describe()
housing = strat_train_set.drop("median_house_value", axis=1) # drop labels for training set
housing_labels = strat_train_set["median_house_value"].copy()
sample_incomplete_rows = housing[housing.isnull().any(axis=1)].head()
sample_incomplete_rows
sample_incomplete_rows.dropna(subset=["total_bedrooms"]) # option 1
sample_incomplete_rows.drop("total_bedrooms", axis=1) # option 2
median = housing["total_bedrooms"].median()
sample_incomplete_rows["total_bedrooms"].fillna(median, inplace=True) # option 3
sample_incomplete_rows
try:
from sklearn.impute import SimpleImputer # Scikit-Learn 0.20+
except ImportError:
from sklearn.preprocessing import Imputer as SimpleImputer
imputer = SimpleImputer(strategy="median")
housing_num = housing.drop('ocean_proximity', axis=1)
# alternatively: housing_num = housing.select_dtypes(include=[np.number])
imputer.fit(housing_num)
imputer.statistics_
housing_num.median().values
X = imputer.transform(housing_num)
housing_tr = pd.DataFrame(X, columns=housing_num.columns,
index = list(housing.index.values))
housing_tr.loc[sample_incomplete_rows.index.values]
imputer.strategy
housing_tr = pd.DataFrame(X, columns=housing_num.columns)
housing_tr.head()
housing_cat = housing[['ocean_proximity']]
housing_cat.head(10)
try:
from sklearn.preprocessing import OrdinalEncoder
except ImportError:
from future_encoders import OrdinalEncoder # Scikit-Learn < 0.20
ordinal_encoder = OrdinalEncoder()
housing_cat_encoded = ordinal_encoder.fit_transform(housing_cat)
housing_cat_encoded[:10]
ordinal_encoder.categories_
try:
from sklearn.preprocessing import OrdinalEncoder # just to raise an ImportError if Scikit-Learn < 0.20
from sklearn.preprocessing import OneHotEncoder
except ImportError:
from future_encoders import OneHotEncoder # Scikit-Learn < 0.20
cat_encoder = OneHotEncoder(sparse=False)
housing_cat_1hot = cat_encoder.fit_transform(housing_cat)
housing_cat_1hot
cat_encoder.categories_
numerical_columns = housing.columns.drop('ocean_proximity')
categorical_columns = pd.Index(['ocean_proximity'])
housing_numerical = housing[numerical_columns]
housing_categorical = housing[categorical_columns]
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
class CombinedAttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, add_bedrooms_per_room=False): # no *args or **kargs
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):
X_df = pd.DataFrame(X, columns=numerical_columns)
X_df["rooms_per_household"] = X_df["total_rooms"]/X_df["households"]
X_df["population_per_household"]=X_df["population"]/X_df["households"]
if self.add_bedrooms_per_room:
X_df["bedrooms_per_room"] = X_df["total_bedrooms"]/X_df["total_rooms"]
return X_df
numerical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy="median")),
('attribs_adder', CombinedAttributesAdder(add_bedrooms_per_room=True)),
('std_scaler', StandardScaler()),
])
housing_numerical_transformed = numerical_pipeline.fit_transform(housing_numerical)
housing_numerical_transformed
np.mean(housing_numerical_transformed, axis=0)
np.std(housing_numerical_transformed, axis=0)
try:
from sklearn.compose import ColumnTransformer
except ImportError:
from future_encoders import ColumnTransformer # Scikit-Learn < 0.20
num_attribs = list(housing_num)
cat_attribs = ["ocean_proximity"]
numerical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy="median")),
('attribs_adder', CombinedAttributesAdder(add_bedrooms_per_room=True)),
('std_scaler', StandardScaler()),
])
categorical_pipeline = Pipeline([
('imputer', SimpleImputer(strategy="most_frequent")),
("onehot_encoder", OneHotEncoder())
])
full_pipeline = ColumnTransformer([
("num", numerical_pipeline, numerical_columns),
("cat", categorical_pipeline, categorical_columns),
])
housing_prepared = full_pipeline.fit_transform(housing)
housing_prepared
housing_prepared.shape
housing.columns
from sklearn.linear_model import LinearRegression
lin_reg = LinearRegression()
lin_reg.fit(housing_prepared, housing_labels)
lin_reg.score(housing_prepared, housing_labels)
# let's try the full preprocessing pipeline on a few training instances
some_data = housing.iloc[:5]
some_labels = housing_labels.iloc[:5]
some_data_prepared = full_pipeline.transform(some_data)
print("Predictions:", lin_reg.predict(some_data_prepared))
Compare against the actual values:
print("Labels:", list(some_labels))
from sklearn.metrics import mean_squared_error
housing_predictions = lin_reg.predict(housing_prepared)
lin_mse = mean_squared_error(housing_labels, housing_predictions)
lin_rmse = np.sqrt(lin_mse)
lin_rmse
from sklearn.metrics import mean_absolute_error
lin_mae = mean_absolute_error(housing_labels, housing_predictions)
lin_mae
from sklearn.tree import DecisionTreeRegressor
tree_reg = DecisionTreeRegressor(random_state=42)
tree_reg.fit(housing_prepared, housing_labels)
tree_reg.score(housing_prepared, housing_labels)
housing_predictions = tree_reg.predict(housing_prepared)
tree_mse = mean_squared_error(housing_labels, housing_predictions)
tree_rmse = np.sqrt(tree_mse)
tree_rmse
from sklearn.model_selection import cross_val_score
scores = cross_val_score(tree_reg, housing_prepared, housing_labels,
scoring="neg_mean_squared_error", cv=10)
tree_rmse_scores = np.sqrt(-scores)
def display_scores(scores):
print("Scores:", scores)
print("Mean:", scores.mean())
print("Standard deviation:", scores.std())
display_scores(tree_rmse_scores)
lin_scores = cross_val_score(lin_reg, housing_prepared, housing_labels,
scoring="neg_mean_squared_error", cv=10)
lin_rmse_scores = np.sqrt(-lin_scores)
display_scores(lin_rmse_scores)
from sklearn.ensemble import RandomForestRegressor
forest_reg = RandomForestRegressor(n_estimators=10, random_state=42)
forest_reg.fit(housing_prepared, housing_labels)
housing_predictions = forest_reg.predict(housing_prepared)
forest_mse = mean_squared_error(housing_labels, housing_predictions)
forest_rmse = np.sqrt(forest_mse)
forest_rmse
from sklearn.model_selection import cross_val_score
forest_scores = cross_val_score(forest_reg, housing_prepared, housing_labels,
scoring="neg_mean_squared_error", cv=10)
forest_rmse_scores = np.sqrt(-forest_scores)
display_scores(forest_rmse_scores)
scores = cross_val_score(lin_reg, housing_prepared, housing_labels, scoring="neg_mean_squared_error", cv=10)
pd.Series(np.sqrt(-scores)).describe()
from sklearn.model_selection import GridSearchCV
param_grid = [
# try 12 (3×4) combinations of hyperparameters
{'n_estimators': [3, 10, 30], 'max_features': [2, 4, 6, 8]},
# then try 6 (2×3) combinations with bootstrap set as False
{'bootstrap': [False], 'n_estimators': [3, 10], 'max_features': [2, 3, 4]},
]
forest_reg = RandomForestRegressor(random_state=42)
# train across 5 folds, that's a total of (12+6)*5=90 rounds of training
grid_search = GridSearchCV(forest_reg, param_grid, cv=5,
scoring='neg_mean_squared_error', return_train_score=True)
grid_search.fit(housing_prepared, housing_labels)
grid_search.best_params_
grid_search.best_estimator_
cvres = grid_search.cv_results_
for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
print(np.sqrt(-mean_score), params)
pd.DataFrame(grid_search.cv_results_)
from sklearn.model_selection import RandomizedSearchCV
from scipy.stats import randint
param_distribs = {
'n_estimators': randint(low=1, high=200),
'max_features': randint(low=1, high=8),
}
forest_reg = RandomForestRegressor(random_state=42)
rnd_search = RandomizedSearchCV(forest_reg, param_distributions=param_distribs,
n_iter=10, cv=5, scoring='neg_mean_squared_error', random_state=42)
rnd_search.fit(housing_prepared, housing_labels)
cvres = rnd_search.cv_results_
for mean_score, params in zip(cvres["mean_test_score"], cvres["params"]):
print(np.sqrt(-mean_score), params)
rnd_search.best_params_
feature_importances = grid_search.best_estimator_.feature_importances_
feature_importances
extra_attribs = ["rooms_per_hhold", "pop_per_hhold", "bedrooms_per_room"]
cat_encoder = full_pipeline.named_transformers_["cat"].named_steps['onehot_encoder']
cat_one_hot_attribs = list(cat_encoder.categories_[0])
attributes = num_attribs + extra_attribs + cat_one_hot_attribs
sorted(zip(feature_importances, attributes), reverse=True)
final_model = grid_search.best_estimator_
X_test = strat_test_set.drop("median_house_value", axis=1)
y_test = strat_test_set["median_house_value"].copy()
X_test_prepared = full_pipeline.transform(X_test)
final_predictions = final_model.predict(X_test_prepared)
final_mse = mean_squared_error(y_test, final_predictions)
final_rmse = np.sqrt(final_mse)
final_rmse
full_pipeline_with_predictor = Pipeline([
("preparation", full_pipeline),
("linear", LinearRegression())
])
full_pipeline_with_predictor.fit(housing, housing_labels)
full_pipeline_with_predictor.predict(some_data)
my_model = full_pipeline_with_predictor
from sklearn.externals import joblib
joblib.dump(my_model, "my_model.pkl") # DIFF
#...
my_model_loaded = joblib.load("my_model.pkl") # DIFF
from scipy.stats import geom, expon
geom_distrib=geom(0.5).rvs(10000, random_state=42)
expon_distrib=expon(scale=1).rvs(10000, random_state=42)
plt.hist(geom_distrib, bins=50)
plt.show()
plt.hist(expon_distrib, bins=50)
plt.show()