William Liu WilliamQLiu

## gist:a7c6fbf201fce273e367
$stty echo

## windows_head
#In powershell, do this to load a file named "load_me.csv", get first 10000 lines, then output it to "test.csv"
powershell -command "& {Get-Content load_me.csv -TotalCount 10000" | Out-File test.csv

## gist:6494e8ae0b286e4fa7b1
Highlight your text, do 'Command Shift L' to get multiple cursors

## gist:327d168ebd0626111971
$split -l 1000000 data data.
# Will return files: data.aa, data.ab, data.ac, etc. each with the number of lines specified (one million in this case)

## gist:2ff51a9f560a2ce9c936
$sed -i '1d' file.csv  # Remove the first line
$sed -i '2d' file.csv  # Remove the second line

## gist:506530b03526b0c98e47
# How to view the docstring of a function quickly
# https://www.python.org/dev/peps/pep-0257/

### View the docstring of a function
$print repr(foo.__doc__)  # e.g. print repr(matplotlib.pyplot.plt.__doc__)

### Split the lines
$foo.__doc__.splitlines()  # e.g. matplotlib.pyplot.plt.__doc__.splitlines()

### Trim any unnecessary lines - basically do this for best formatting

## csvkit_tutorial
# From https://csvkit.readthedocs.org

# Shows you stats about the file (e.g. col names, type, nulls, min, max, median, std deviation, unique values, most frequent)
$csvstat myfile.csv

# Peak at excel file to display in terminal
$in2csv myfile.xlsx
$in2csv myfile.xlsx > myfile.csv  # can write xlsx file to csv by chaining operations

# Look at data, formats nicely with borders

## countlines
wc -l <myfile>  # Example output: 4577465 myfile.csv

## index.html
<!DOCTYPE html>
<html>

  <head>
    <!-- Load D3 from site -->
    <script src="http://d3js.org/d3.v3.min.js" charset="utf-8"></script>

    <!-- CSS (Styling) -->
    <style type="text/css">
    </style>

## index.html
<!DOCTYPE html>
<!-- D3 Template, can run with: python -m SimpleHTTPServer 8000
     Reference: https://github.com/mbostock/d3/wiki/API-Reference
-->
<html>
  <head>
    <!-- Load D3 from site -->
    <script src="http://d3js.org/d3.v3.min.js" charset="utf-8"></script>
	#In powershell, do this to load a file named "load_me.csv", get first 10000 lines, then output it to "test.csv"
	powershell -command "& {Get-Content load_me.csv -TotalCount 10000" \| Out-File test.csv
	$split -l 1000000 data data.
	# Will return files: data.aa, data.ab, data.ac, etc. each with the number of lines specified (one million in this case)
	$sed -i '1d' file.csv # Remove the first line
	$sed -i '2d' file.csv # Remove the second line
	# How to view the docstring of a function quickly
	# https://www.python.org/dev/peps/pep-0257/

	### View the docstring of a function
	$print repr(foo.__doc__) # e.g. print repr(matplotlib.pyplot.plt.__doc__)

	### Split the lines
	$foo.__doc__.splitlines() # e.g. matplotlib.pyplot.plt.__doc__.splitlines()

	### Trim any unnecessary lines - basically do this for best formatting
	# From https://csvkit.readthedocs.org

	# Shows you stats about the file (e.g. col names, type, nulls, min, max, median, std deviation, unique values, most frequent)
	$csvstat myfile.csv

	# Peak at excel file to display in terminal
	$in2csv myfile.xlsx
	$in2csv myfile.xlsx > myfile.csv # can write xlsx file to csv by chaining operations

	# Look at data, formats nicely with borders
	<!DOCTYPE html>
	<html>

	<head>
	<!-- Load D3 from site -->
	<script src="http://d3js.org/d3.v3.min.js" charset="utf-8"></script>

	<!-- CSS (Styling) -->
	<style type="text/css">
	</style>
	<!DOCTYPE html>
	<!-- D3 Template, can run with: python -m SimpleHTTPServer 8000
	Reference: https://github.com/mbostock/d3/wiki/API-Reference
	-->
	<html>
	<head>
	<!-- Load D3 from site -->
	<script src="http://d3js.org/d3.v3.min.js" charset="utf-8"></script>