In [6]:

    

from __future__ import print_function

import pandas as pd

city_names = pd.Series(['San Francisco', 'San Jose', 'Sacramento'])                
population = pd.Series([852469, 1015785, 485199])


    

In [7]:

    

cities = pd.DataFrame({ 'City name': city_names, 'Population': population })
cities.describe()


    

    
Out[7]:







  

    

      

      
Population
    
  
  

    

      
count
      
3.000000e+00
    
    

      
mean
      
7.844843e+05
    
    

      
std
      
2.717477e+05
    
    

      
min
      
4.851990e+05
    
    

      
25%
      
6.688340e+05
    
    

      
50%
      
8.524690e+05
    
    

      
75%
      
9.341270e+05
    
    

      
max
      
1.015785e+06
    
  

In [8]:

    

# play with a bigger file
california_housing_dataframe = pd.read_csv("https://download.mlcc.google.com/mledu-datasets/california_housing_train.csv"
, sep=",")
california_housing_dataframe.describe()


    

    
Out[8]:







  

    

      

      
longitude
      
latitude
      
housing_median_age
      
total_rooms
      
total_bedrooms
      
population
      
households
      
median_income
      
median_house_value
    
  
  

    

      
count
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
      
17000.000000
    
    

      
mean
      
-119.562108
      
35.625225
      
28.589353
      
2643.664412
      
539.410824
      
1429.573941
      
501.221941
      
3.883578
      
207300.912353
    
    

      
std
      
2.005166
      
2.137340
      
12.586937
      
2179.947071
      
421.499452
      
1147.852959
      
384.520841
      
1.908157
      
115983.764387
    
    

      
min
      
-124.350000
      
32.540000
      
1.000000
      
2.000000
      
1.000000
      
3.000000
      
1.000000
      
0.499900
      
14999.000000
    
    

      
25%
      
-121.790000
      
33.930000
      
18.000000
      
1462.000000
      
297.000000
      
790.000000
      
282.000000
      
2.566375
      
119400.000000
    
    

      
50%
      
-118.490000
      
34.250000
      
29.000000
      
2127.000000
      
434.000000
      
1167.000000
      
409.000000
      
3.544600
      
180400.000000
    
    

      
75%
      
-118.000000
      
37.720000
      
37.000000
      
3151.250000
      
648.250000
      
1721.000000
      
605.250000
      
4.767000
      
265000.000000
    
    

      
max
      
-114.310000
      
41.950000
      
52.000000
      
37937.000000
      
6445.000000
      
35682.000000
      
6082.000000
      
15.000100
      
500001.000000
    
  

In [9]:

    

# display first few records
california_housing_dataframe.head()


    

    
Out[9]:







  

    

      

      
longitude
      
latitude
      
housing_median_age
      
total_rooms
      
total_bedrooms
      
population
      
households
      
median_income
      
median_house_value
    
  
  

    

      
0
      
-114.31
      
34.19
      
15.0
      
5612.0
      
1283.0
      
1015.0
      
472.0
      
1.4936
      
66900.0
    
    

      
1
      
-114.47
      
34.40
      
19.0
      
7650.0
      
1901.0
      
1129.0
      
463.0
      
1.8200
      
80100.0
    
    

      
2
      
-114.56
      
33.69
      
17.0
      
720.0
      
174.0
      
333.0
      
117.0
      
1.6509
      
85700.0
    
    

      
3
      
-114.57
      
33.64
      
14.0
      
1501.0
      
337.0
      
515.0
      
226.0
      
3.1917
      
73400.0
    
    

      
4
      
-114.57
      
33.57
      
20.0
      
1454.0
      
326.0
      
624.0
      
262.0
      
1.9250
      
65500.0
    
  

In [10]:

    

california_housing_dataframe.keys()


    

    
Out[10]:





Index([u'longitude', u'latitude', u'housing_median_age', u'total_rooms',
       u'total_bedrooms', u'population', u'households', u'median_income',
       u'median_house_value'],
      dtype='object')