In [20]:

    

import pandas as pd
import psycopg2
import paramiko
import os
import numpy as np
import math


    

In [23]:

    

data_dir='../data/' 
"""Path to local data directory"""

username='cy290e'
hostname='169.229.154.119'
db_name='craigslist'
password='' #password to database.  IMPORTANT: do not save passwords in the notebook
"""Postgres connection parameters"""

# establish postgres connection
conn = psycopg2.connect("dbname={d} user={u} host={h} password={pw}".format(d=db_name, u=username, h=hostname, pw=password))
cur = conn.cursor()


    

    




---------------------------------------------------------------------------
OperationalError                          Traceback (most recent call last)
<ipython-input-23-92d7cd62e944> in <module>()
      9 
     10 # establish postgres connection
---> 11 conn = psycopg2.connect("dbname={d} user={u} host={h} password={pw}".format(d=db_name, u=username, h=hostname, pw=password))
     12 cur = conn.cursor()

C:\Program Files\Anaconda3\lib\site-packages\psycopg2\__init__.py in connect(dsn, connection_factory, cursor_factory, **kwargs)
    128 
    129     dsn = _ext.make_dsn(dsn, **kwargs)
--> 130     conn = _connect(dsn, connection_factory=connection_factory, **kwasync)
    131     if cursor_factory is not None:
    132         conn.cursor_factory = cursor_factory

OperationalError: fe_sendauth: no password supplied

In [16]:

    




    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-16-725ac5850a60> in <module>()
      3 
      4 with SSHTunnelForwarder(
----> 5     (REMOTE_SERVER_IP, 443),
      6     ssh_username="",
      7     ssh_pkey= local_key_dir,

NameError: name 'REMOTE_SERVER_IP' is not defined

In [6]:

    




    

    




---------------------------------------------------------------------------
ImportError                               Traceback (most recent call last)
<ipython-input-6-6471456e2c1e> in <module>()
      1 import sys
----> 2 import chilkat
      3 
      4 sftp = chilkat.CkSFtp()
      5 

ImportError: No module named 'chilkat'

In [9]:

    

data = pd.read_csv(r'..\data\cl_census_CA.csv')
data.head()


    

    
Out[9]:






  

    

      

      
listing_id
      
date
      
rent
      
bedrooms
      
sqft
      
rent_sqft
      
fips_block
      
state
      
mpo_id
      
cars_tot
      
...
      
race_of_head_4
      
race_of_head_5
      
race_of_head_6
      
race_of_head_7
      
race_of_head_8
      
race_of_head_9
      
recent_mover_0
      
recent_mover_1
      
tenure_1
      
tenure_2
    
  
  

    

      
0
      
5873877617
      
2016-11-13
      
925.0
      
2.0
      
874.0
      
1.058352
      
60470010021060
      
CA
      
6197202.0
      
4603.0
      
...
      
NaN
      
8.0
      
527.0
      
1.0
      
198.0
      
42.0
      
1516.0
      
628.0
      
1310.0
      
834.0
    
    

      
1
      
5873876292
      
2016-11-13
      
735.0
      
0.0
      
650.0
      
1.130769
      
60070012001017
      
CA
      
6198000.0
      
646.0
      
...
      
NaN
      
NaN
      
6.0
      
1.0
      
3.0
      
16.0
      
371.0
      
44.0
      
98.0
      
317.0
    
    

      
2
      
5873889346
      
2016-11-13
      
1675.0
      
3.0
      
1000.0
      
1.675000
      
60790125023017
      
CA
      
6199200.0
      
1902.0
      
...
      
NaN
      
NaN
      
10.0
      
NaN
      
30.0
      
21.0
      
712.0
      
257.0
      
477.0
      
492.0
    
    

      
3
      
5873893871
      
2016-11-13
      
1818.0
      
2.0
      
1084.0
      
1.677122
      
60830020061208
      
CA
      
6196600.0
      
1058.0
      
...
      
NaN
      
2.0
      
21.0
      
1.0
      
8.0
      
8.0
      
427.0
      
41.0
      
420.0
      
48.0
    
    

      
4
      
5849643168
      
2016-11-13
      
1050.0
      
2.0
      
1100.0
      
0.954545
      
60890113004008
      
CA
      
6198100.0
      
786.0
      
...
      
NaN
      
3.0
      
NaN
      
2.0
      
26.0
      
23.0
      
287.0
      
205.0
      
202.0
      
290.0
    
  

5 rows × 29 columns

In [8]:

    

data.columns.values


    

    
Out[8]:





array(['listing_id', 'date', 'rent', 'bedrooms', 'sqft', 'rent_sqft',
       'fips_block', 'state', 'mpo_id', 'cars_tot', 'children_tot',
       'persons_tot', 'workers_tot', 'age_of_head_med', 'income_med',
       'hhs_tot', 'race_of_head_1', 'race_of_head_2', 'race_of_head_3',
       'race_of_head_4', 'race_of_head_5', 'race_of_head_6',
       'race_of_head_7', 'race_of_head_8', 'race_of_head_9',
       'recent_mover_0', 'recent_mover_1', 'tenure_1', 'tenure_2'], dtype=object)