%pwd

!wget https://raw.githubusercontent.com/ipython-books/minibook-2nd-data/master/facebook.zip

%ls

!unzip facebook.zip

%ls

%cd facebook

%bookmark fbdata

%ls

files = !ls -1 -S | grep .edges

files

import os
from operator import itemgetter
# Get the name and file size of all .edges files.
files = [(file, os.stat(file).st_size)
         for file in os.listdir('.')
         if file.endswith('.edges')]
# Sort the list with the second item (file size),
# in decreasing order.
files = sorted(files,
               key=itemgetter(1),
               reverse=True)
# Only keep the first item (file name), in the same order.
files = [file for (file, size) in files]

!head -n5 {files[0]}

%lsmagic

%history?

%history -l 5

# how many minutes in a day?
24 * 60

# and in a year?
_ * 365

%%capture output
%ls

output.stdout

%%bash
cd ..
touch _HEY
ls
rm _HEY
cd facebook

%%script ghci
putStrLn "Hello world!"

%%writefile myfile.txt
Hello world!

!more myfile.txt

!rm myfile.txt

%cd fbdata
%ls

from IPython.display import YouTubeVideo
YouTubeVideo('j9YpkSX7NNM')

from ipywidgets import interact  # IPython.html.widgets before IPython 4.0
@interact(x=(0, 10))
def square(x):
    return("The square of %d is %d." % (x, x**2))

%cd fbdata
%cd ..

%%writefile egos.py
import sys
import os
# We retrieve the folder as the first positional argument
# to the command-line call
if len(sys.argv) > 1:
    folder = sys.argv[1]
# We list all files in the specified folder
files = os.listdir(folder)
# ids contains the list of idenfitiers
identifiers = [int(file.split('.')[0]) for file in files]
# Finally, we remove duplicates with set(), and sort the list
# with sorted().
ids = sorted(set(identifiers))

%run egos.py facebook

ids

folder = 'facebook'

%run egos.py

%run -i egos.py

ids

import networkx

networkx.Graph?

%cd fbdata

import networkx

graph = networkx.read_edgelist('107.edges')

len(graph.nodes()), len(graph.edges())

networkx.is_connected(graph)

%timeit networkx.is_connected(graph)

import networkx

def ncomponents(file):
    graph = networkx.read_edgelist(file)
    return networkx.number_connected_components(graph)

import glob
def ncomponents_files():
    return [(file, ncomponents(file))
            for file in sorted(glob.glob('*.edges'))]

for file, n in ncomponents_files():
    print(file.ljust(12), n, 'component(s)')

%timeit ncomponents_files()

%prun -s cumtime ncomponents_files()