ghl3

ssh-rsa AAAAB3NzaC1yc2EAAAADAQABAAABAQDMCPYpv9eNlyQxJ5UvUBEvflePCnR5AAglmjH4oOa8nEa5FJ+dHUBRRWwaJ8Vho0KHKplLZoFeYhsvOn/NrlRKjN+h4OAEEPLdPSYKEpid4f4LoUj2vTuqbKC7EK67z7m6nrZw18+vWY13N/pxq0y3APV3qL8YJ+a3m5FRmdpGdgsJVoJEsFIZKgUmAL9NcrlYl3OPGcv24EJ0Wg38RcOv7pVQtfBCM4n5rUUGqVbbRoMmNWZnHDChFEooEruGnVA0jT0gaE7zXpVCbXSV5ULLPZ7K7ZjqR7PpG0SHy/q2xE5AZnK+1YSCKcfUajrEjgAZKo05+IB0ZAVefoc+AWz1 [email protected]

ghl3

import pandas as pd

def get_nominal_integer_dict(nominal_vals):
    d = {}
    for val in nominal_vals:
        if val not in d:
            current_max = max(d.values()) if len(d) > 0 else -1
            d[val] = current_max+1
    return d

ghl3

See gist as a notebook here: http://nbviewer.ipython.org/gist/ghl3/8760132/notebook.ipynb

Create a simple DataFrame:

df = pandas.DataFrame({'user_id':[1, 1, 2, 2, 3, 3],
                       'type':['A','A','A','A','B','B'],
                       'val':[100, 200, 150, 30, 300, 75]})
df.head()

ghl3

import random
import string

def random_string():
    N = random.randint(1, 10)
    return ''.join(random.choice(string.ascii_letters + string.digits) for x in range(N))

ghl3

/* Copy to a file as a csv */
Copy (SELECT * FROM foo) To '/tmp/test.csv' With CSV;

/* Copy to std::out as tab separated values */
COPY (SELECT * FROM foo) TO STDOUT WITH DELIMITER E'\t' CSV HEADER;

ghl3

def get_next_subplot():
    """                                                                                                                                                                                    
    Create and move to the next subplot                                                                                                                                                    
    in a grid of matplotlib subplots                                                                                                                                                       
    """

    # Get the current plot                                                                                                                                                                 
    ax = plt.gca()

    # Check if the current plot is a subplot                                                                                                                                               

ghl3

M-x replace-string RET C-q C-m RET RET

ghl3

SELECT DISTINCT k FROM (SELECT skeys(our_database) as k FROM risk_profile) as dt; 

ghl3

def scatter_plots(df, class_title, feature_names=None, cmap=None):
    
    # Create a pandas group view for each class
    class_names = list(set(df[class_title]))
    groups = [df[(df[class_title] == name)] for name in class_names]

    if feature_names==None:
        feature_names = [col for col in df.columns if col != class_title]
            
    NUM_COLORS = len(class_names)

ghl3

    data_url = "https://raw.github.com/pydata/pydata-book/master/ch02/usagov_bitly_data2012-03-16-1331923249.txt"
    data_path = "usagov_bitly_data2012-03-16-1331923249.txt"

    try:
  data = open(data_path)
    except IOError:
        request = urllib2.Request(data_url)
        data = urllib2.urlopen(request).read()
        with open(data_path, "w+") as data_file:
            data_file.write(data)