glamp

# instead of generating all possible values of GRE and GPA, we're going
# to use an evenly spaced range of 10 values from the min to the max 
gres = np.linspace(data['gre'].min(), data['gre'].max(), 10)
print gres
# array([ 220.        ,  284.44444444,  348.88888889,  413.33333333,
#         477.77777778,  542.22222222,  606.66666667,  671.11111111,
#         735.55555556,  800.        ])
gpas = np.linspace(data['gpa'].min(), data['gpa'].max(), 10)
print gpas
# array([ 2.26      ,  2.45333333,  2.64666667,  2.84      ,  3.03333333,

glamp

import numpy as np

def cartesian(arrays, out=None):
    """
    Generate a cartesian product of input arrays.

    Parameters
    ----------
    arrays : list of array-like
        1-D arrays to form the cartesian product of.

glamp

def isolate_and_plot(variable):
    # isolate gre and class rank
    grouped = pd.pivot_table(combos, values=['admit_pred'], index=[variable, 'prestige'],
                            aggfunc=np.mean)
    
    # in case you're curious as to what this looks like
    # print grouped.head()
    #                      admit_pred
    # gre        prestige            
    # 220.000000 1           0.282462

glamp

import pandas as pd
import statsmodels.api as sm
import pylab as pl
import numpy as np


def cartesian(arrays, out=None):
    """
    Generate a cartesian product of input arrays.

glamp

$ = require('jquery');


data = {
    "data": "this is the kind of movie that makes one appreciate disney ' s live - action george of the jungle . tarzan and the lost city , the latest attempt to bring edgar rice burrough ' s legendary hero to the big screen , is one of the most inept and ill - timed of any tarzan adventure so far . badly conceived and poorly executed , tarzan and the lost city appears headed for a quick trip to video store shelves . i have no idea why the producers chose now to bring back tarzan ; it ' s not as if there are legions of new fans clamoring for his next movie . furthermore , it ' s even more curious that this film is rated pg , which , by definition , rules out any sex or explicit violence . and , while i ' m not advocating the excesses embraced by the 1981 bo derek version of the story , tarzan deserves a slightly more adult approach than the one used in the embarrassing production . of course , no tweaking of the content to change the rating could have saved tarzan and the los

glamp

data <- read.csv("http://www.ats.ucla.edu/stat/data/binary.csv")
head(data)
data$rank <- factor(data$rank)
fit <- glm(admit ~ gre + gpa + rank, data=data, family="binomial")
summary(fit)

# Call:
#   glm(formula = admit ~ gre + gpa + rank, family = "binomial", 
#       data = data)
# 

glamp

--MongoDB or other databases
select
    'db.foo.findOne({_id: ObjectId("' || _id || '")})'
from foo;
--db.foo.find({_id: ObjectId("5066fa4abd8ad53408a4869c")})

--web based (great for spidering)
select
    'http://www.yelp.com/search?find_loc=Manhattan%2C+NY&ns=1&find_desc=' || name as url
from

glamp

import psycopg2
import requests


conn = psycopg2.connect("{YOUR CONNECTION"})
cur = conn.cursor()

q = """
select
    'http://www.yelp.com/search?find_loc=Manhattan%2C+NY&ns=1&find_desc=' || name as url

glamp

select
    date_trunc('year', '2013-04-05'::date) as year
    , date_trunc('month', '2013-04-05'::date) as month
    , date_trunc('day', '2013-04-05'::date) as day;
--          year          |         month          |          day           
--------------------------+------------------------+------------------------
-- 2013-01-01 00:00:00-05 | 2013-04-01 00:00:00-04 | 2013-04-05 00:00:00-04
select
    to_char('2013-04-05'::date, 'YYYY') as year
    , to_char('2013-04-05'::date, 'MM-YYYY') as month

glamp

--median (http://wiki.postgresql.org/wiki/Aggregate_Median)
CREATE OR REPLACE FUNCTION _final_median(anyarray)
   RETURNS float8 AS
$$ 
  WITH q AS
  (
     SELECT val
     FROM unnest($1) val
     WHERE VAL IS NOT NULL
     ORDER BY 1