lebedov

#!/usr/bin/env python                                                                  

"""   
Serialize/unserialize a class with a pandas data structure attribute using msgpack.
"""

import msgpack

import numpy as np
import pandas as pd

bsweger

Useful Pandas Snippets

A personal diary of DataFrame munging over the years.

Data Types and Conversion

Convert Series datatype to numeric (will error if column has non-numeric values)
(h/t @makmanalp)

gjreda

# When you're sure of the format, it's much quicker to explicitly convert your dates than use `parse_dates`
# Makes sense; was just surprised by the time difference.
import pandas as pd
from datetime import datetime
to_datetime = lambda d: datetime.strptime(d, '%m/%d/%Y %H:%M')

%time trips = pd.read_csv('data/divvy/Divvy_Trips_2013.csv', parse_dates=['starttime', 'stoptime'])
# CPU times: user 1min 29s, sys: 331 ms, total: 1min 29s
# Wall time: 1min 30s

ampedandwired

def get_proxy_url
  # Doesn't support different proxies for different protocols at present
  host_proxy = ENV['http_proxy'] || ENV['HTTP_PROXY'] || ENV['https_proxy'] || ENV["HTTPS_PROXY"]
  if host_proxy
    uri = URI(host_proxy)
    if ['localhost', '127.0.0.1'].include? uri.host
      # 10.0.2.2 is the default vagrant gateway and should connect to the host OS.
      # Confirm this by running 'netstat -r' in the guest.
      host_proxy = host_proxy.sub(uri.host, '10.0.2.2')
    end

kevin-peel

file = open("minify1.txt", "w")
with open('test.txt') as f:
   for line in f:
       newTxt = line.rstrip('\r\n').replace("  ","")
       file.write(newTxt)
       if 'str' in line:
          break

file.close()

DrPaulBrewer

# Copyright 2015 Paul Brewer Economic and Financial Technology Consulting LLC                                                                                                                            
# Released under the MIT Public License                                                                                                                                                                  
# LICENSE: http://opensource.org/licenses/MIT                                                                                                                                                            
# Purpose:  rationally removes inner commas and inner quotes from csv file fields                                                                                                                        
# Useful for Google BigQuery as of 2015-03 does not support quoted commas in CSV fields                                                                                                                  
# python ./unf

ryan-hill

import pysal as ps
import pandas as pd
'''
Arguments
---------
dbfile  : DBF file - Input to be imported
upper   : Condition - If true, make column heads upper case
'''
def dbf2DF(dbfile, upper=True): #Reads in DBF files and returns Pandas DF
    db = ps.open(dbfile) #Pysal to open DBF

ankurk91

#!/bin/sh

# Install node and npm via nvm - https://github.com/nvm-sh/nvm

# Run this script like - bash script-name.sh

# Define versions
INSTALL_NODE_VER=24
INSTALL_NVM_VER=0.40.5

m-ou-se

# Download latest archlinux bootstrap package, see https://www.archlinux.org/download/
wget 'ftp://ftp.nluug.nl/pub/os/Linux/distr/archlinux/iso/latest/archlinux-bootstrap-*-x86_64.tar.gz'

# Make sure you'll have enough entropy for pacman-key later.
apt-get install haveged

# Install the arch bootstrap image in a tmpfs.
mount -t tmpfs none /mnt
cd /mnt
tar xvf ~/archlinux-bootstrap-*-x86_64.tar.gz --strip-components=1

maxivak

Setup Ubuntu 16.04 to be used with Vagrant and Virtualbox

Prepare Vagrant box with Ubuntu 16.04

We will use official box "ubuntu/xenial64" and modify it to work with Vagrant.

• Vagrantfile