Greg Reda gjreda

## gist:7433f5f70299610d9b6b
# 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

## espn-cbb.py
from bs4 import BeautifulSoup
from urllib2 import urlopen
from datetime import datetime, timedelta
from time import sleep
import sys
import csv

# CONSTANTS
ESPN_URL = "http://scores.espn.go.com"

## saban-seasons.py
"""
Scraping Nick Saban's seasons as Alabama head coach

I was curious what % of his time Alabama has spent at #1
"""

from collections import Counter
from bs4 import BeautifulSoup
import requests

## pandas-groupby-cumsum.py
"""
add grouped cumulative sum column to pandas dataframe

Add a new column to a pandas dataframe which holds the cumulative sum for a given grouped window

Desired output:
user_id,day,session_minutes,cumulative_minutes
516530,0,NaN,0
516530,1,0,0
516532,0,5,5

## towed.json

      
              1 file
            
          
              0 forks
            
          
              1 comment
            
          
              0 stars
            
          
                gjreda
                / towed.json
            
            
              Created
              October 7, 2018 21:25
            
          
      This file has been truncated, but you can view the full file.
    

## senators.json
{
  "meta": {
    "limit": 100,
    "offset": 0,
    "total_count": 100
  },
  "objects": [
    {
      "caucus": null,
      "congress_numbers": [

## coding-music.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              1 star
            
          
                gjreda
                / coding-music.md
            
            
              Last active
              August 18, 2017 15:33
            
              
                Music to code by
              
          
    Music to code by

All thanks to a tweet by Chris Albon
Bands


Cut Copy (via Andrew Musselman)
Com Truise (via Sean J. Taylor)
Makkam (via Karissa McKelvey)
Slow Magic (via Clare Corthell)


## gjreda-tweets.csv

          
            id
            text

            
              805168201126518784
              @ryanisaac this is the weirdest quarter of football I’ve seen in a while

            
              804818096942968833
              @SportsTribution I don't follow.

            
              804816669281546240
              Looking for a weekend longread? @samhinkie's resignation letter is still one of the best things I've read in 2016 https://t.co/y7464DISgX

            
              804759041318813696
              Have used Postico to query our Redshift cluster for the last few months and it's been great. Similar to Sequel Pro. https://t.co/NN0DvdCpa6

            
              804699067590840320
              @jrmontag @tanehisicoates Agreed. Important book.

            
              804690839221964801
              The Year of the Looking Glass: Building Products https://t.co/0MVAbxeSze

            
              804469380352446464
              "So how do we build trust? The easy answer is by producing high quality work. The hard part is how you get there."  https://t.co/M4MgJYU2Wm

            
              804015210621239297
              Holywow this looks awesome. Continuously impressed by the data products the @awscloud team keeps churning out: https://t.co/jmkLqFjyn7

            
              803734870706896896
              RT @jevnin: I'd recommend working with this guy. https://t.

## gjreda-tweets.json
[
  {
    "id": "805168201126518784",
    "text": "@ryanisaac this is the weirdest quarter of football I’ve seen in a while"
  },
  {
    "id": "804818096942968833",
    "text": "@SportsTribution I don't follow."
  },
  {

## useful-one-liners.sh
# Installing/upgrading old requirements.txt from python2 to python3
sed s/\=/\ /g requirements.txt | awk '{print $1}' | xargs -n1 pip3 install --upgrade
	# 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
	from bs4 import BeautifulSoup
	from urllib2 import urlopen
	from datetime import datetime, timedelta
	from time import sleep
	import sys
	import csv

	# CONSTANTS
	ESPN_URL = "http://scores.espn.go.com"
	"""
	Scraping Nick Saban's seasons as Alabama head coach

	I was curious what % of his time Alabama has spent at #1
	"""

	from collections import Counter
	from bs4 import BeautifulSoup
	import requests
	"""
	add grouped cumulative sum column to pandas dataframe

	Add a new column to a pandas dataframe which holds the cumulative sum for a given grouped window

	Desired output:
	user_id,day,session_minutes,cumulative_minutes
	516530,0,NaN,0
	516530,1,0,0
	516532,0,5,5
	{
	"meta": {
	"limit": 100,
	"offset": 0,
	"total_count": 100
	},
	"objects": [
	{
	"caucus": null,
	"congress_numbers": [
	id	text
	805168201126518784	@ryanisaac this is the weirdest quarter of football I’ve seen in a while
	804818096942968833	@SportsTribution I don't follow.
	804816669281546240	Looking for a weekend longread? @samhinkie's resignation letter is still one of the best things I've read in 2016 https://t.co/y7464DISgX
	804759041318813696	Have used Postico to query our Redshift cluster for the last few months and it's been great. Similar to Sequel Pro. https://t.co/NN0DvdCpa6
	804699067590840320	@jrmontag @tanehisicoates Agreed. Important book.
	804690839221964801	The Year of the Looking Glass: Building Products https://t.co/0MVAbxeSze
	804469380352446464	"So how do we build trust? The easy answer is by producing high quality work. The hard part is how you get there." https://t.co/M4MgJYU2Wm
	804015210621239297	Holywow this looks awesome. Continuously impressed by the data products the @awscloud team keeps churning out: https://t.co/jmkLqFjyn7
	803734870706896896	RT @jevnin: I'd recommend working with this guy. https://t.
	[
	{
	"id": "805168201126518784",
	"text": "@ryanisaac this is the weirdest quarter of football I’ve seen in a while"
	},
	{
	"id": "804818096942968833",
	"text": "@SportsTribution I don't follow."
	},
	{
	# Installing/upgrading old requirements.txt from python2 to python3
	sed s/\=/\ /g requirements.txt \| awk '{print $1}' \| xargs -n1 pip3 install --upgrade