In [5]:

    

import os
import tarfile
from six.moves import urllib

DOWNLOAD_ROOT = "https://raw.githubusercontent.com/ageron/handson-ml/master/"
HOUSING_PATH = "datasets/housing"
HOUSING_URL = DOWNLOAD_ROOT + HOUSING_PATH + "/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 [6]:

    

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 [7]:

    

fetch_housing_data()


    

In [8]:

    

housing = load_housing_data()


    

In [9]:

    

housing.head()


    

    
Out[9]:







  

    

      

      
longitude
      
latitude
      
housing_median_age
      
total_rooms
      
total_bedrooms
      
population
      
households
      
median_income
      
median_house_value
      
ocean_proximity
    
  
  

    

      
0
      
-122.23
      
37.88
      
41.0
      
880.0
      
129.0
      
322.0
      
126.0
      
8.3252
      
452600.0
      
NEAR BAY
    
    

      
1
      
-122.22
      
37.86
      
21.0
      
7099.0
      
1106.0
      
2401.0
      
1138.0
      
8.3014
      
358500.0
      
NEAR BAY
    
    

      
2
      
-122.24
      
37.85
      
52.0
      
1467.0
      
190.0
      
496.0
      
177.0
      
7.2574
      
352100.0
      
NEAR BAY
    
    

      
3
      
-122.25
      
37.85
      
52.0
      
1274.0
      
235.0
      
558.0
      
219.0
      
5.6431
      
341300.0
      
NEAR BAY
    
    

      
4
      
-122.25
      
37.85
      
52.0
      
1627.0
      
280.0
      
565.0
      
259.0
      
3.8462
      
342200.0
      
NEAR BAY
    
  

In [10]:

    

housing.info()


    

    




<class 'pandas.core.frame.DataFrame'>
RangeIndex: 20640 entries, 0 to 20639
Data columns (total 10 columns):
longitude             20640 non-null float64
latitude              20640 non-null float64
housing_median_age    20640 non-null float64
total_rooms           20640 non-null float64
total_bedrooms        20433 non-null float64
population            20640 non-null float64
households            20640 non-null float64
median_income         20640 non-null float64
median_house_value    20640 non-null float64
ocean_proximity       20640 non-null object
dtypes: float64(9), object(1)
memory usage: 1.6+ MB

In [12]:

    

housing["ocean_proximity"].value_counts()


    

    
Out[12]:





<1H OCEAN     9136
INLAND        6551
NEAR OCEAN    2658
NEAR BAY      2290
ISLAND           5
Name: ocean_proximity, dtype: int64

In [15]:

    

%matplotlib inline
import matplotlib.pyplot as plt
housing.hist(bins=50, figsize=(20, 15))
plt.show()


    

In [ ]:

    

import numpy asnp

def split_train_test(data, test_ratio):
    shuffled_indices = np.random.permutation(len(data))
    test_set_size = int(len(data)*test_ratio)