szeitlin

szeitlin

import geojson

import parse as p     #shorter name for our parse program

def create_map(data_file):
        """csv file -> parse -> creates a geojson - javascript object notation - file """

        # define the type of geoJSON that we're creating
        geo_map = {"type": "FeatureCollection"}  #GeoJSON specification

szeitlin

import csv

MY_FILE = "../data/sample_sfpd_incident_all.csv"
#../ means go up one directory
#all caps means a constant variable

def parse(raw_file, delimiter):
        """ csv file -> JSON-like object"""

szeitlin

from collections import Counter   #collections is a standard library, Counter is capitalized
import csv

import matplotlib.pyplot as plt   #renames the pyplot function from third party library
import numpy.numarray as na             # best practices: import in alphabetical order

MY_FILE = "../data/sample_sfpd_incident_all.csv"

def parse(raw_file, delimiter):
        """ csv file -> JSON-like object"""

szeitlin

#Rosalind problem 1

def ACGT_count(sequence):
    '''
(str) -> (int, int, int, int)

Count the number of A, C, G and T in a string.

>>>ACGT_count('ATGCTTCAGAAAGGTCTTACG')
6 4 5 1

szeitlin

def transcribe(s):
    '''given a DNA string, replace each T with a U and write it back out as RNA

    (str) -> (str)

    >>>transcribe('ATGCCCGGGTTTAAA')
    AUGCCCGGGUUUAAA

    '''

szeitlin

def complementary(s):
    '''
    (str) -> (str)

    Returns the reverse complementary strand of s.

    >>>complementary('AAACCCTTTGGG')
    CCCAAAGGGTTT

    '''

szeitlin

def fizzbuzz(last):
    list = range(1, (last + 1))

    for num in list:

         if num % 15 == 0:
             num = "fizzbuzz"
             print str(num)
         elif num % 3 == 0:
             num = "fizz"

szeitlin

__author__= 'szeitlin'

import pandas
import vincent

MYFILE = "UNdata_Export_20140325_115007094.csv"

#read in a csv file
mydata = pandas.read_csv(MYFILE)

szeitlin

__author__ = 'szeitlin'

def return_duplicates(nums):
    """
    (list) -> (sub-list)

    look for duplicates and just return those

    >>> return_duplicates([5,5,2,3,4,5,2])
    [2, 2, 5, 5, 5]