Chapter 2 – End-to-end Machine Learning project
Welcome to Machine Learning Housing Corp.! Your task is to predict median house values in Californian districts, given a number of features from these districts.
This notebook contains all the sample code and solutions to the exercices in chapter 2.
Run in Google ColabSetup¶
First, let's import a few common modules, ensure MatplotLib plots figures inline and prepare a function to save the figures. We also check that Python 3.5 or later is installed (although Python 2.x may work, it is deprecated so we strongly recommend you use Python 3 instead), as well as Scikit-Learn ≥0.20.
In [1]:
# Python ≥3.5 is required
import sys
assert sys.version_info >= (3, 5)
# Scikit-Learn ≥0.20 is required
import sklearn
assert sklearn.__version__ >= "0.20"
# Common imports
import numpy as np
import os
# 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 = "."
CHAPTER_ID = "end_to_end_project"
IMAGES_PATH = os.path.join(PROJECT_ROOT_DIR, "images", CHAPTER_ID)
os.makedirs(IMAGES_PATH, exist_ok=True)
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)
Get the data¶
In [2]:
import os
import tarfile
import urllib.request
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml2/master/"
HOUSING_PATH = os.path.join("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()
In [3]:
fetch_housing_data()
In [4]:
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)
In [5]:
housing = load_housing_data()
housing.head()
Out[5]:
In [6]:
housing.info()
In [7]:
housing["ocean_proximity"].value_counts()
Out[7]:
In [8]:
housing.describe()
Out[8]:
In [9]:
%matplotlib inline
import matplotlib.pyplot as plt
housing.hist(bins=50, figsize=(20,15))
save_fig("attribute_histogram_plots")
plt.show()
In [10]:
# to make this notebook's output identical at every run
np.random.seed(42)
In [11]:
import numpy as np
# For illustration only. Sklearn has train_test_split()
def split_train_test(data, test_ratio):
shuffled_indices = np.random.permutation(len(data))
test_set_size = int(len(data) * test_ratio)
test_indices = shuffled_indices[:test_set_size]
train_indices = shuffled_indices[test_set_size:]
return data.iloc[train_indices], data.iloc[test_indices]
In [12]:
train_set, test_set = split_train_test(housing, 0.2)
len(train_set)
Out[12]:
In [13]:
len(test_set)
Out[13]:
In [14]:
from zlib import crc32
def test_set_check(identifier, test_ratio):
return crc32(np.int64(identifier)) & 0xffffffff < test_ratio * 2**32
def split_train_test_by_id(data, test_ratio, id_column):
ids = data[id_column]
in_test_set = ids.apply(lambda id_: test_set_check(id_, test_ratio))
return data.loc[~in_test_set], data.loc[in_test_set]
The implementation of test_set_check() above works fine in both Python 2 and Python 3. In earlier releases, the following implementation was proposed, which supported any hash function, but was much slower and did not support Python 2:
In [15]:
import hashlib
def test_set_check(identifier, test_ratio, hash=hashlib.md5):
return hash(np.int64(identifier)).digest()[-1] < 256 * test_ratio
If you want an implementation that supports any hash function and is compatible with both Python 2 and Python 3, here is one:
In [16]:
def test_set_check(identifier, test_ratio, hash=hashlib.md5):
return bytearray(hash(np.int64(identifier)).digest())[-1] < 256 * test_ratio
In [17]:
housing_with_id = housing.reset_index() # adds an `index` column
train_set, test_set = split_train_test_by_id(housing_with_id, 0.2, "index")
In [18]:
housing_with_id["id"] = housing["longitude"] * 1000 + housing["latitude"]
train_set, test_set = split_train_test_by_id(housing_with_id, 0.2, "id")
In [19]:
test_set.head()
Out[19]:
In [20]:
from sklearn.model_selection import train_test_split
train_set, test_set = train_test_split(housing, test_size=0.2, random_state=42)
In [21]:
test_set.head()
Out[21]:
In [22]:
housing["median_income"].hist()
Out[22]:
In [23]:
housing["income_cat"] = pd.cut(housing["median_income"],
bins=[0., 1.5, 3.0, 4.5, 6., np.inf],
labels=[1, 2, 3, 4, 5])
In [24]:
housing["income_cat"].value_counts()
Out[24]:
In [25]:
housing["income_cat"].hist()
Out[25]:
In [26]:
from sklearn.model_selection import StratifiedShuffleSplit
split = StratifiedShuffleSplit(n_splits=1, test_size=0.2, random_state=42)
for train_index, test_index in split.split(housing, housing["income_cat"]):
strat_train_set = housing.loc[train_index]
strat_test_set = housing.loc[test_index]
In [27]:
strat_test_set["income_cat"].value_counts() / len(strat_test_set)
Out[27]:
In [28]:
housing["income_cat"].value_counts() / len(housing)
Out[28]:
In [29]:
def income_cat_proportions(data):
return data["income_cat"].value_counts() / len(data)
train_set, test_set = train_test_split(housing, test_size=0.2, random_state=42)
compare_props = pd.DataFrame({
"Overall": income_cat_proportions(housing),
"Stratified": income_cat_proportions(strat_test_set),
"Random": income_cat_proportions(test_set),
}).sort_index()
compare_props["Rand. %error"] = 100 * compare_props["Random"] / compare_props["Overall"] - 100
compare_props["Strat. %error"] = 100 * compare_props["Stratified"] / compare_props["Overall"] - 100
In [30]:
compare_props
Out[30]:
In [31]:
for set_ in (strat_train_set, strat_test_set):
set_.drop("income_cat", axis=1, inplace=True)
Discover and visualize the data to gain insights¶
In [32]:
housing = strat_train_set.copy()
In [33]:
housing.plot(kind="scatter", x="longitude", y="latitude")
save_fig("bad_visualization_plot")
In [34]:
housing.plot(kind="scatter", x="longitude", y="latitude", alpha=0.1)
save_fig("better_visualization_plot")
The argument sharex=False fixes a display bug (the x-axis values and legend were not displayed). This is a temporary fix (see: https://github.com/pandas-dev/pandas/issues/10611 ). Thanks to Wilmer Arellano for pointing it out.
In [35]:
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)
plt.legend()
save_fig("housing_prices_scatterplot")
In [36]:
# Download the California image
images_path = os.path.join(PROJECT_ROOT_DIR, "images", "end_to_end_project")
os.makedirs(images_path, exist_ok=True)
DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml2/master/"
filename = "california.png"
print("Downloading", filename)
url = DOWNLOAD_ROOT + "images/end_to_end_project/" + filename
urllib.request.urlretrieve(url, os.path.join(images_path, filename))
Out[36]:
In [37]:
import matplotlib.image as mpimg
california_img=mpimg.imread(os.path.join(images_path, filename))
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(ticks=tick_values/prices.max())
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()
In [38]:
corr_matrix = housing.corr()
In [39]:
corr_matrix["median_house_value"].sort_values(ascending=False)
Out[39]:
In [40]:
# 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")
In [41]:
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")