notebook.community

Edit and run

Introductory examples

1.usa.gov data from bit.ly





In [1]:



    


%pwd



    


















    
Out[1]:








u'/Users/pmui/OneDrive/scu/data.science/lecture01.intro'

















In [2]:



    


path = 'ch02/usagov_bitly_data2012-03-16-1331923249.txt'



    











In [3]:



    


open(path).readline()



    


















    
Out[3]:








'{ "a": "Mozilla\\/5.0 (Windows NT 6.1; WOW64) AppleWebKit\\/535.11 (KHTML, like Gecko) Chrome\\/17.0.963.78 Safari\\/535.11", "c": "US", "nk": 1, "tz": "America\\/New_York", "gr": "MA", "g": "A6qOVH", "h": "wfLQtf", "l": "orofrog", "al": "en-US,en;q=0.8", "hh": "1.usa.gov", "r": "http:\\/\\/www.facebook.com\\/l\\/7AQEFzjSi\\/1.usa.gov\\/wfLQtf", "u": "http:\\/\\/www.ncbi.nlm.nih.gov\\/pubmed\\/22415991", "t": 1331923247, "hc": 1331822918, "cy": "Danvers", "ll": [ 42.576698, -70.954903 ] }\n'

















In [4]:



    


import json
path = 'ch02/usagov_bitly_data2012-03-16-1331923249.txt'
records = [json.loads(line) for line in open(path)]



    











In [5]:



    


records[0]



    


















    
Out[5]:








{u'a': u'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.78 Safari/535.11',
 u'al': u'en-US,en;q=0.8',
 u'c': u'US',
 u'cy': u'Danvers',
 u'g': u'A6qOVH',
 u'gr': u'MA',
 u'h': u'wfLQtf',
 u'hc': 1331822918,
 u'hh': u'1.usa.gov',
 u'l': u'orofrog',
 u'll': [42.576698, -70.954903],
 u'nk': 1,
 u'r': u'http://www.facebook.com/l/7AQEFzjSi/1.usa.gov/wfLQtf',
 u't': 1331923247,
 u'tz': u'America/New_York',
 u'u': u'http://www.ncbi.nlm.nih.gov/pubmed/22415991'}

















In [6]:



    


records[0]['tz']



    


















    
Out[6]:








u'America/New_York'

















In [7]:



    


print(records[0]['tz'])



    


















    






America/New_York

Counting time zones in pure Python

Expect error





In [8]:



    


time_zones = [rec['tz'] for rec in records]



    


















    






---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-8-db4fbd348da9> in <module>()
----> 1 time_zones = [rec['tz'] for rec in records]

KeyError: 'tz'
















In [9]:



    


time_zones = [rec['tz'] for rec in records if 'tz' in rec]



    











In [10]:



    


time_zones[:10]



    


















    
Out[10]:








[u'America/New_York',
 u'America/Denver',
 u'America/New_York',
 u'America/Sao_Paulo',
 u'America/New_York',
 u'America/New_York',
 u'Europe/Warsaw',
 u'',
 u'',
 u'']

















In [11]:



    


def get_counts(sequence):
    counts = {}
    for x in sequence:
        if x in counts:
            counts[x] += 1
        else:
            counts[x] = 1
    return counts



    











In [12]:



    


from collections import defaultdict

def get_counts2(sequence):
    counts = defaultdict(int) # values will initialize to 0
    for x in sequence:
        counts[x] += 1
    return counts



    











In [13]:



    


counts = get_counts(time_zones)



    











In [14]:



    


counts['America/New_York']



    


















    
Out[14]:








1251

















In [15]:



    


len(time_zones)



    


















    
Out[15]:








3440

















In [16]:



    


def top_counts(count_dict, n=10):
    value_key_pairs = [(count, tz) for tz, count in count_dict.items()]
    value_key_pairs.sort()
    return value_key_pairs[-n:]



    











In [17]:



    


top_counts(counts)



    


















    
Out[17]:








[(33, u'America/Sao_Paulo'),
 (35, u'Europe/Madrid'),
 (36, u'Pacific/Honolulu'),
 (37, u'Asia/Tokyo'),
 (74, u'Europe/London'),
 (191, u'America/Denver'),
 (382, u'America/Los_Angeles'),
 (400, u'America/Chicago'),
 (521, u''),
 (1251, u'America/New_York')]

















In [18]:



    


from collections import Counter



    











In [19]:



    


counts = Counter(time_zones)



    











In [20]:



    


counts.most_common(10)



    


















    
Out[20]:








[(u'America/New_York', 1251),
 (u'', 521),
 (u'America/Chicago', 400),
 (u'America/Los_Angeles', 382),
 (u'America/Denver', 191),
 (u'Europe/London', 74),
 (u'Asia/Tokyo', 37),
 (u'Pacific/Honolulu', 36),
 (u'Europe/Madrid', 35),
 (u'America/Sao_Paulo', 33)]

Counting time zones with pandas





In [21]:



    


%matplotlib inline



    











In [22]:



    


from __future__ import division
from numpy.random import randn
import numpy as np
import os
import matplotlib.pyplot as plt
import pandas as pd
plt.rc('figure', figsize=(10, 6))
np.set_printoptions(precision=4)



    











In [23]:



    


import json
path = 'ch02/usagov_bitly_data2012-03-16-1331923249.txt'
lines = open(path).readlines()
records = [json.loads(line) for line in lines]



    











In [24]:



    


from pandas import DataFrame, Series
import pandas as pd

frame = DataFrame(records)
frame



    


















    
Out[24]:










  
    

      
      _heartbeat_
      a
      al
      c
      cy
      g
      gr
      h
      hc
      hh
      kw
      l
      ll
      nk
      r
      t
      tz
      u
    

  
  
    

      0
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      en-US,en;q=0.8
      US
      Danvers
      A6qOVH
      MA
      wfLQtf
      1.331823e+09
      1.usa.gov
      NaN
      orofrog
      [42.576698, -70.954903]
      1.0
      http://www.facebook.com/l/7AQEFzjSi/1.usa.gov/...
      1.331923e+09
      America/New_York
      http://www.ncbi.nlm.nih.gov/pubmed/22415991
    

    

      1
      NaN
      GoogleMaps/RochesterNY
      NaN
      US
      Provo
      mwszkS
      UT
      mwszkS
      1.308262e+09
      j.mp
      NaN
      bitly
      [40.218102, -111.613297]
      0.0
      http://www.AwareMap.com/
      1.331923e+09
      America/Denver
      http://www.monroecounty.gov/etc/911/rss.php
    

    

      2
      NaN
      Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...
      en-US
      US
      Washington
      xxr3Qb
      DC
      xxr3Qb
      1.331920e+09
      1.usa.gov
      NaN
      bitly
      [38.9007, -77.043098]
      1.0
      http://t.co/03elZC4Q
      1.331923e+09
      America/New_York
      http://boxer.senate.gov/en/press/releases/0316...
    

    

      3
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...
      pt-br
      BR
      Braz
      zCaLwp
      27
      zUtuOu
      1.331923e+09
      1.usa.gov
      NaN
      alelex88
      [-23.549999, -46.616699]
      0.0
      direct
      1.331923e+09
      America/Sao_Paulo
      http://apod.nasa.gov/apod/ap120312.html
    

    

      4
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      en-US,en;q=0.8
      US
      Shrewsbury
      9b6kNl
      MA
      9b6kNl
      1.273672e+09
      bit.ly
      NaN
      bitly
      [42.286499, -71.714699]
      0.0
      http://www.shrewsbury-ma.gov/selco/
      1.331923e+09
      America/New_York
      http://www.shrewsbury-ma.gov/egov/gallery/1341...
    

    

      5
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      en-US,en;q=0.8
      US
      Shrewsbury
      axNK8c
      MA
      axNK8c
      1.273673e+09
      bit.ly
      NaN
      bitly
      [42.286499, -71.714699]
      0.0
      http://www.shrewsbury-ma.gov/selco/
      1.331923e+09
      America/New_York
      http://www.shrewsbury-ma.gov/egov/gallery/1341...
    

    

      6
      NaN
      Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1...
      pl-PL,pl;q=0.8,en-US;q=0.6,en;q=0.4
      PL
      Luban
      wcndER
      77
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [51.116699, 15.2833]
      0.0
      http://plus.url.google.com/url?sa=z&n=13319232...
      1.331923e+09
      Europe/Warsaw
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      7
      NaN
      Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/2...
      bg,en-us;q=0.7,en;q=0.3
      None
      NaN
      wcndER
      NaN
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      NaN
      0.0
      http://www.facebook.com/
      1.331923e+09
      
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      8
      NaN
      Opera/9.80 (X11; Linux zbov; U; en) Presto/2.1...
      en-US, en
      None
      NaN
      wcndER
      NaN
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      NaN
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2F1...
      1.331923e+09
      
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      9
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      pt-BR,pt;q=0.8,en-US;q=0.6,en;q=0.4
      None
      NaN
      zCaLwp
      NaN
      zUtuOu
      1.331923e+09
      1.usa.gov
      NaN
      alelex88
      NaN
      0.0
      http://t.co/o1Pd0WeV
      1.331923e+09
      
      http://apod.nasa.gov/apod/ap120312.html
    

    

      10
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2)...
      en-us,en;q=0.5
      US
      Seattle
      vNJS4H
      WA
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      [47.5951, -122.332603]
      1.0
      direct
      1.331923e+09
      America/Los_Angeles
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      11
      NaN
      Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.4...
      en-us,en;q=0.5
      US
      Washington
      wG7OIH
      DC
      A0nRz4
      1.331816e+09
      1.usa.gov
      NaN
      darrellissa
      [38.937599, -77.092796]
      0.0
      http://t.co/ND7SoPyo
      1.331923e+09
      America/New_York
      http://oversight.house.gov/wp-content/uploads/...
    

    

      12
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2)...
      en-us,en;q=0.5
      US
      Alexandria
      vNJS4H
      VA
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      [38.790901, -77.094704]
      1.0
      direct
      1.331923e+09
      America/New_York
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      13
      1.331923e+09
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    

    

      14
      NaN
      Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US...
      en-us,en;q=0.5
      US
      Marietta
      2rOUYc
      GA
      2rOUYc
      1.255770e+09
      1.usa.gov
      NaN
      bitly
      [33.953201, -84.5177]
      1.0
      direct
      1.331923e+09
      America/New_York
      http://toxtown.nlm.nih.gov/index.php
    

    

      15
      NaN
      Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1...
      zh-TW,zh;q=0.8,en-US;q=0.6,en;q=0.4
      HK
      Central District
      nQvgJp
      00
      rtrrth
      1.317318e+09
      j.mp
      NaN
      walkeryuen
      [22.2833, 114.150002]
      1.0
      http://forum2.hkgolden.com/view.aspx?type=BW&m...
      1.331923e+09
      Asia/Hong_Kong
      http://www.ssd.noaa.gov/PS/TROP/TCFP/data/curr...
    

    

      16
      NaN
      Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1...
      zh-TW,zh;q=0.8,en-US;q=0.6,en;q=0.4
      HK
      Central District
      XdUNr
      00
      qWkgbq
      1.317318e+09
      j.mp
      NaN
      walkeryuen
      [22.2833, 114.150002]
      1.0
      http://forum2.hkgolden.com/view.aspx?type=BW&m...
      1.331923e+09
      Asia/Hong_Kong
      http://www.usno.navy.mil/NOOC/nmfc-ph/RSS/jtwc...
    

    

      17
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10.5; r...
      en-us,en;q=0.5
      US
      Buckfield
      zH1BFf
      ME
      x3jOIv
      1.331840e+09
      1.usa.gov
      NaN
      andyzieminski
      [44.299702, -70.369797]
      0.0
      http://t.co/6Cx4ROLs
      1.331923e+09
      America/New_York
      http://www.usda.gov/wps/portal/usda/usdahome?c...
    

    

      18
      NaN
      GoogleMaps/RochesterNY
      NaN
      US
      Provo
      mwszkS
      UT
      mwszkS
      1.308262e+09
      1.usa.gov
      NaN
      bitly
      [40.218102, -111.613297]
      0.0
      http://www.AwareMap.com/
      1.331923e+09
      America/Denver
      http://www.monroecounty.gov/etc/911/rss.php
    

    

      19
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      it-IT,it;q=0.8,en-US;q=0.6,en;q=0.4
      IT
      Venice
      wcndER
      20
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [45.438599, 12.3267]
      0.0
      http://www.facebook.com/
      1.331923e+09
      Europe/Rome
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      20
      NaN
      Mozilla/5.0 (compatible; MSIE 9.0; Windows NT ...
      es-ES
      ES
      Alcal
      zQ95Hi
      51
      ytZYWR
      1.331671e+09
      bitly.com
      NaN
      jplnews
      [37.516701, -5.9833]
      0.0
      http://www.facebook.com/
      1.331923e+09
      Africa/Ceuta
      http://voyager.jpl.nasa.gov/imagesvideo/uranus...
    

    

      21
      NaN
      Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10.6...
      en-us,en;q=0.5
      US
      Davidsonville
      wcndER
      MD
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [38.939201, -76.635002]
      0.0
      http://www.facebook.com/
      1.331923e+09
      America/New_York
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      22
      NaN
      Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...
      en-us
      US
      Hockessin
      y3ZImz
      DE
      y3ZImz
      1.331064e+09
      1.usa.gov
      NaN
      bitly
      [39.785, -75.682297]
      0.0
      direct
      1.331923e+09
      America/New_York
      http://portal.hud.gov/hudportal/documents/hudd...
    

    

      23
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3)...
      en-us
      US
      Lititz
      wWiOiD
      PA
      wWiOiD
      1.330218e+09
      1.usa.gov
      NaN
      bitly
      [40.174999, -76.3078]
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2F1...
      1.331923e+09
      America/New_York
      http://www.tricare.mil/mybenefit/ProfileFilter...
    

    

      24
      NaN
      Mozilla/5.0 (Windows; U; Windows NT 5.1; es-ES...
      es-es,es;q=0.8,en-us;q=0.5,en;q=0.3
      ES
      Bilbao
      wcndER
      59
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [43.25, -2.9667]
      0.0
      http://www.facebook.com/
      1.331923e+09
      Europe/Madrid
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      25
      NaN
      Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1...
      en-GB,en;q=0.8,en-US;q=0.6,en-AU;q=0.4
      MY
      Kuala Lumpur
      wcndER
      14
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [3.1667, 101.699997]
      0.0
      http://www.facebook.com/
      1.331923e+09
      Asia/Kuala_Lumpur
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      26
      NaN
      Mozilla/5.0 (Windows NT 6.1) AppleWebKit/535.1...
      ro-RO,ro;q=0.8,en-US;q=0.6,en;q=0.4
      CY
      Nicosia
      wcndER
      04
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [35.166698, 33.366699]
      0.0
      http://www.facebook.com/?ref=tn_tnmn
      1.331923e+09
      Asia/Nicosia
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      27
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...
      en-US,en;q=0.8
      BR
      SPaulo
      zCaLwp
      27
      zUtuOu
      1.331923e+09
      1.usa.gov
      NaN
      alelex88
      [-23.5333, -46.616699]
      0.0
      direct
      1.331923e+09
      America/Sao_Paulo
      http://apod.nasa.gov/apod/ap120312.html
    

    

      28
      NaN
      Mozilla/5.0 (iPad; CPU OS 5_0_1 like Mac OS X)...
      en-us
      None
      NaN
      vNJS4H
      NaN
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      NaN
      0.0
      direct
      1.331923e+09
      
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      29
      NaN
      Mozilla/5.0 (iPad; U; CPU OS 3_2 like Mac OS X...
      en-us
      None
      NaN
      FPX0IM
      NaN
      FPX0IL
      1.331923e+09
      1.usa.gov
      NaN
      twittershare
      NaN
      1.0
      http://t.co/5xlp0B34
      1.331923e+09
      
      http://www.ed.gov/news/media-advisories/us-dep...
    

    

      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
      ...
    

    

      3530
      NaN
      Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.1...
      en-US,en;q=0.8
      US
      San Francisco
      xVZg4P
      CA
      wqUkTo
      1.331908e+09
      go.nasa.gov
      NaN
      nasatwitter
      [37.7645, -122.429398]
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2Fg...
      1.331927e+09
      America/Los_Angeles
      http://www.nasa.gov/multimedia/imagegallery/im...
    

    

      3531
      NaN
      Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6...
      en-US
      None
      NaN
      wcndER
      NaN
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      NaN
      0.0
      direct
      1.331927e+09
      
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      3532
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2)...
      en-us,en;q=0.5
      US
      Washington
      Au3aUS
      DC
      A9ct6C
      1.331926e+09
      1.usa.gov
      NaN
      ncsha
      [38.904202, -77.031998]
      1.0
      http://www.ncsha.org/
      1.331927e+09
      America/New_York
      http://portal.hud.gov/hudportal/HUD?src=/press...
    

    

      3533
      NaN
      Mozilla/5.0 (iPad; CPU OS 5_1 like Mac OS X) A...
      en-us
      US
      Jacksonville
      b2UtUJ
      FL
      ieCdgH
      1.301393e+09
      go.nasa.gov
      NaN
      nasatwitter
      [30.279301, -81.585098]
      1.0
      direct
      1.331927e+09
      America/New_York
      http://apod.nasa.gov/apod/
    

    

      3534
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...
      en-us
      US
      Frisco
      vNJS4H
      TX
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      [33.149899, -96.855499]
      1.0
      direct
      1.331927e+09
      America/Chicago
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      3535
      NaN
      Mozilla/5.0 (Windows NT 5.1; rv:10.0.2) Gecko/...
      en-us
      US
      Houston
      zIgLx8
      TX
      yrPaLt
      1.331903e+09
      aash.to
      NaN
      aashto
      [29.775499, -95.415199]
      1.0
      direct
      1.331927e+09
      America/Chicago
      http://ntl.bts.gov/lib/44000/44300/44374/FHWA-...
    

    

      3536
      NaN
      Mozilla/5.0 (BlackBerry; U; BlackBerry 9800; e...
      en-US,en;q=0.5
      None
      NaN
      xIcyim
      NaN
      yG1TTf
      1.331728e+09
      go.nasa.gov
      NaN
      nasatwitter
      NaN
      0.0
      http://t.co/g1VKE8zS
      1.331927e+09
      
      http://www.nasa.gov/mission_pages/hurricanes/a...
    

    

      3537
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2)...
      es-es,es;q=0.8,en-us;q=0.5,en;q=0.3
      HN
      Tegucigalpa
      zCaLwp
      08
      w63FZW
      1.331547e+09
      1.usa.gov
      NaN
      bufferapp
      [14.1, -87.216698]
      0.0
      http://t.co/A8TJyibE
      1.331927e+09
      America/Tegucigalpa
      http://apod.nasa.gov/apod/ap120312.html
    

    

      3538
      NaN
      Mozilla/5.0 (iPhone; CPU iPhone OS 5_1 like Ma...
      en-us
      US
      Los Angeles
      qMac9k
      CA
      qds1Ge
      1.310474e+09
      1.usa.gov
      NaN
      healthypeople
      [34.041599, -118.298798]
      0.0
      direct
      1.331927e+09
      America/Los_Angeles
      http://healthypeople.gov/2020/connect/webinars...
    

    

      3539
      NaN
      Mozilla/5.0 (compatible; Fedora Core 3) FC3 KDE
      NaN
      US
      Bellevue
      zu2M5o
      WA
      zDhdro
      1.331586e+09
      bit.ly
      NaN
      glimtwin
      [47.615398, -122.210297]
      0.0
      direct
      1.331927e+09
      America/Los_Angeles
      http://www.federalreserve.gov/newsevents/press...
    

    

      3540
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      en-US,en;q=0.8
      US
      Payson
      wcndER
      UT
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      [40.014198, -111.738899]
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2F1...
      1.331927e+09
      America/Denver
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      3541
      NaN
      Mozilla/5.0 (X11; U; OpenVMS AlphaServer_ES40;...
      NaN
      US
      Bellevue
      zu2M5o
      WA
      zDhdro
      1.331586e+09
      1.usa.gov
      NaN
      glimtwin
      [47.615398, -122.210297]
      0.0
      direct
      1.331927e+09
      America/Los_Angeles
      http://www.federalreserve.gov/newsevents/press...
    

    

      3542
      NaN
      Mozilla/5.0 (compatible; MSIE 9.0; Windows NT ...
      en-us
      US
      Pittsburg
      y3reI1
      CA
      y3reI1
      1.331926e+09
      1.usa.gov
      NaN
      bitly
      [38.0051, -121.838699]
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2F1...
      1.331927e+09
      America/Los_Angeles
      http://www.sba.gov/community/blogs/community-b...
    

    

      3543
      1.331927e+09
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
      NaN
    

    

      3544
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:5.0.1) ...
      en-us,en;q=0.5
      US
      Wentzville
      vNJS4H
      MO
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      [38.790001, -90.854897]
      1.0
      direct
      1.331927e+09
      America/Chicago
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      3545
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64; rv:10.0.2)...
      en-us,en;q=0.5
      US
      Saint Charles
      vNJS4H
      IL
      u0uD9q
      1.319564e+09
      1.usa.gov
      NaN
      o_4us71ccioa
      [41.9352, -88.290901]
      1.0
      direct
      1.331927e+09
      America/Chicago
      https://www.nysdot.gov/rexdesign/design/commun...
    

    

      3546
      NaN
      Mozilla/5.0 (iPhone; CPU iPhone OS 5_1 like Ma...
      en-us
      US
      Los Angeles
      qMac9k
      CA
      qds1Ge
      1.310474e+09
      1.usa.gov
      NaN
      healthypeople
      [34.041599, -118.298798]
      1.0
      direct
      1.331927e+09
      America/Los_Angeles
      http://healthypeople.gov/2020/connect/webinars...
    

    

      3547
      NaN
      Mozilla/5.0 (Macintosh; Intel Mac OS X 10_6_8)...
      en-us
      US
      Silver Spring
      y0jYkg
      MD
      y0jYkg
      1.331852e+09
      1.usa.gov
      NaN
      bitly
      [39.052101, -77.014999]
      1.0
      direct
      1.331927e+09
      America/New_York
      http://www.epa.gov/otaq/regs/fuels/additive/e1...
    

    

      3548
      NaN
      Mozilla/5.0 (iPhone; CPU iPhone OS 5_1 like Ma...
      en-us
      US
      Mcgehee
      y5rMac
      AR
      xANY6O
      1.331916e+09
      1.usa.gov
      NaN
      twitterfeed
      [33.628399, -91.356903]
      1.0
      https://twitter.com/fdarecalls/status/18069759...
      1.331927e+09
      America/Chicago
      http://www.fda.gov/Safety/Recalls/ucm296326.htm
    

    

      3549
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      sv-SE,sv;q=0.8,en-US;q=0.6,en;q=0.4
      SE
      Sollefte
      eH8wu
      24
      7dtjei
      1.260316e+09
      1.usa.gov
      NaN
      tweetdeckapi
      [63.166698, 17.266701]
      1.0
      direct
      1.331927e+09
      Europe/Stockholm
      http://www.nasa.gov/mission_pages/WISE/main/in...
    

    

      3550
      NaN
      Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...
      en-us
      US
      Conshohocken
      A00b72
      PA
      yGSwzn
      1.331918e+09
      1.usa.gov
      NaN
      addthis
      [40.0798, -75.2855]
      0.0
      http://www.linkedin.com/home?trk=hb_tab_home_top
      1.331927e+09
      America/New_York
      http://www.nlm.nih.gov/medlineplus/news/fullst...
    

    

      3551
      NaN
      Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKi...
      en-US,en;q=0.8
      None
      NaN
      wcndER
      NaN
      zkpJBR
      1.331923e+09
      1.usa.gov
      NaN
      bnjacobs
      NaN
      0.0
      http://plus.url.google.com/url?sa=z&n=13319268...
      1.331927e+09
      
      http://www.nasa.gov/mission_pages/nustar/main/...
    

    

      3552
      NaN
      Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US...
      NaN
      US
      Decatur
      rqgJuE
      AL
      xcz8vt
      1.331227e+09
      1.usa.gov
      NaN
      bootsnall
      [34.572701, -86.940598]
      0.0
      direct
      1.331927e+09
      America/Chicago
      http://travel.state.gov/passport/passport_5535...
    

    

      3553
      NaN
      Mozilla/4.0 (compatible; MSIE 7.0; Windows NT ...
      en-us
      US
      Shrewsbury
      9b6kNl
      MA
      9b6kNl
      1.273672e+09
      bit.ly
      NaN
      bitly
      [42.286499, -71.714699]
      0.0
      http://www.shrewsbury-ma.gov/selco/
      1.331927e+09
      America/New_York
      http://www.shrewsbury-ma.gov/egov/gallery/1341...
    

    

      3554
      NaN
      Mozilla/4.0 (compatible; MSIE 7.0; Windows NT ...
      en-us
      US
      Shrewsbury
      axNK8c
      MA
      axNK8c
      1.273673e+09
      bit.ly
      NaN
      bitly
      [42.286499, -71.714699]
      0.0
      http://www.shrewsbury-ma.gov/selco/
      1.331927e+09
      America/New_York
      http://www.shrewsbury-ma.gov/egov/gallery/1341...
    

    

      3555
      NaN
      Mozilla/4.0 (compatible; MSIE 9.0; Windows NT ...
      en
      US
      Paramus
      e5SvKE
      NJ
      fqPSr9
      1.301298e+09
      1.usa.gov
      NaN
      tweetdeckapi
      [40.9445, -74.07]
      1.0
      direct
      1.331927e+09
      America/New_York
      http://www.fda.gov/AdvisoryCommittees/Committe...
    

    

      3556
      NaN
      Mozilla/5.0 (Windows NT 5.1) AppleWebKit/535.1...
      en-US,en;q=0.8
      US
      Oklahoma City
      jQLtP4
      OK
      jQLtP4
      1.307530e+09
      1.usa.gov
      NaN
      bitly
      [35.4715, -97.518997]
      0.0
      http://www.facebook.com/l.php?u=http%3A%2F%2F1...
      1.331927e+09
      America/Chicago
      http://www.okc.gov/PublicNotificationSystem/Fo...
    

    

      3557
      NaN
      GoogleMaps/RochesterNY
      NaN
      US
      Provo
      mwszkS
      UT
      mwszkS
      1.308262e+09
      j.mp
      NaN
      bitly
      [40.218102, -111.613297]
      0.0
      http://www.AwareMap.com/
      1.331927e+09
      America/Denver
      http://www.monroecounty.gov/etc/911/rss.php
    

    

      3558
      NaN
      GoogleProducer
      NaN
      US
      Mountain View
      zjtI4X
      CA
      zjtI4X
      1.327529e+09
      1.usa.gov
      NaN
      bitly
      [37.419201, -122.057404]
      0.0
      direct
      1.331927e+09
      America/Los_Angeles
      http://www.ahrq.gov/qual/qitoolkit/
    

    

      3559
      NaN
      Mozilla/4.0 (compatible; MSIE 8.0; Windows NT ...
      en-US
      US
      Mc Lean
      qxKrTK
      VA
      qxKrTK
      1.312898e+09
      1.usa.gov
      NaN
      bitly
      [38.935799, -77.162102]
      0.0
      http://t.co/OEEEvwjU
      1.331927e+09
      America/New_York
      http://herndon-va.gov/Content/public_safety/Pu...
    

  



3560 rows × 18 columns



















In [25]:



    


frame['tz'][:10]



    


















    
Out[25]:








0     America/New_York
1       America/Denver
2     America/New_York
3    America/Sao_Paulo
4     America/New_York
5     America/New_York
6        Europe/Warsaw
7                     
8                     
9                     
Name: tz, dtype: object

















In [26]:



    


tz_counts = frame['tz'].value_counts()
tz_counts[:10]



    


















    
Out[26]:








America/New_York       1251
                        521
America/Chicago         400
America/Los_Angeles     382
America/Denver          191
Europe/London            74
Asia/Tokyo               37
Pacific/Honolulu         36
Europe/Madrid            35
America/Sao_Paulo        33
Name: tz, dtype: int64

















In [27]:



    


clean_tz = frame['tz'].fillna('Missing')
clean_tz[clean_tz == ''] = 'Unknown'
tz_counts = clean_tz.value_counts()
tz_counts[:10]



    


















    
Out[27]:








America/New_York       1251
Unknown                 521
America/Chicago         400
America/Los_Angeles     382
America/Denver          191
Missing                 120
Europe/London            74
Asia/Tokyo               37
Pacific/Honolulu         36
Europe/Madrid            35
Name: tz, dtype: int64

















In [28]:



    


plt.figure(figsize=(10, 4))



    


















    
Out[28]:








<matplotlib.figure.Figure at 0x103a42bd0>










    








<matplotlib.figure.Figure at 0x103a42bd0>

















In [29]:



    


tz_counts[:10].plot(kind='barh', rot=0)



    


















    
Out[29]:








<matplotlib.axes._subplots.AxesSubplot at 0x10ee1da90>










    
























In [30]:



    


frame['a'][1]



    


















    
Out[30]:








u'GoogleMaps/RochesterNY'

















In [31]:



    


frame['a'][50]



    


















    
Out[31]:








u'Mozilla/5.0 (Windows NT 5.1; rv:10.0.2) Gecko/20100101 Firefox/10.0.2'

















In [32]:



    


frame['a'][51]



    


















    
Out[32]:








u'Mozilla/5.0 (Linux; U; Android 2.2.2; en-us; LG-P925/V10e Build/FRG83G) AppleWebKit/533.1 (KHTML, like Gecko) Version/4.0 Mobile Safari/533.1'

















In [33]:



    


results = Series([x.split()[0] for x in frame.a.dropna()])
results[:5]



    


















    
Out[33]:








0               Mozilla/5.0
1    GoogleMaps/RochesterNY
2               Mozilla/4.0
3               Mozilla/5.0
4               Mozilla/5.0
dtype: object

















In [34]:



    


results.value_counts()[:8]



    


















    
Out[34]:








Mozilla/5.0                 2594
Mozilla/4.0                  601
GoogleMaps/RochesterNY       121
Opera/9.80                    34
TEST_INTERNET_AGENT           24
GoogleProducer                21
Mozilla/6.0                    5
BlackBerry8520/5.0.0.681       4
dtype: int64

















In [35]:



    


cframe = frame[frame.a.notnull()]



    











In [36]:



    


operating_system = np.where(cframe['a'].str.contains('Windows'),
                            'Windows', 'Not Windows')
operating_system[:5]



    


















    
Out[36]:








array(['Windows', 'Not Windows', 'Windows', 'Not Windows', 'Windows'], 
      dtype='|S11')

















In [37]:



    


by_tz_os = cframe.groupby(['tz', operating_system])



    











In [38]:



    


agg_counts = by_tz_os.size().unstack().fillna(0)
agg_counts[:10]



    


















    
Out[38]:










  
    

      
      Not Windows
      Windows
    

    

      tz
      
      
    

  
  
    

      
      245.0
      276.0
    

    

      Africa/Cairo
      0.0
      3.0
    

    

      Africa/Casablanca
      0.0
      1.0
    

    

      Africa/Ceuta
      0.0
      2.0
    

    

      Africa/Johannesburg
      0.0
      1.0
    

    

      Africa/Lusaka
      0.0
      1.0
    

    

      America/Anchorage
      4.0
      1.0
    

    

      America/Argentina/Buenos_Aires
      1.0
      0.0
    

    

      America/Argentina/Cordoba
      0.0
      1.0
    

    

      America/Argentina/Mendoza
      0.0
      1.0
    

  




















In [39]:



    


# Use to sort in ascending order
indexer = agg_counts.sum(1).argsort()
indexer[:10]



    


















    
Out[39]:








tz
                                  24
Africa/Cairo                      20
Africa/Casablanca                 21
Africa/Ceuta                      92
Africa/Johannesburg               87
Africa/Lusaka                     53
America/Anchorage                 54
America/Argentina/Buenos_Aires    57
America/Argentina/Cordoba         26
America/Argentina/Mendoza         55
dtype: int64

















In [40]:



    


count_subset = agg_counts.take(indexer)[-10:]
count_subset



    


















    
Out[40]:










  
    

      
      Not Windows
      Windows
    

    

      tz
      
      
    

  
  
    

      America/Sao_Paulo
      13.0
      20.0
    

    

      Europe/Madrid
      16.0
      19.0
    

    

      Pacific/Honolulu
      0.0
      36.0
    

    

      Asia/Tokyo
      2.0
      35.0
    

    

      Europe/London
      43.0
      31.0
    

    

      America/Denver
      132.0
      59.0
    

    

      America/Los_Angeles
      130.0
      252.0
    

    

      America/Chicago
      115.0
      285.0
    

    

      
      245.0
      276.0
    

    

      America/New_York
      339.0
      912.0
    

  




















In [41]:



    


plt.figure()



    


















    
Out[41]:








<matplotlib.figure.Figure at 0x103f923d0>










    








<matplotlib.figure.Figure at 0x103f923d0>

















In [42]:



    


count_subset.plot(kind='barh', stacked=True)



    


















    
Out[42]:








<matplotlib.axes._subplots.AxesSubplot at 0x103fea950>










    
























In [43]:



    


plt.figure()



    


















    
Out[43]:








<matplotlib.figure.Figure at 0x104371fd0>










    








<matplotlib.figure.Figure at 0x104371fd0>

















In [44]:



    


normed_subset = count_subset.div(count_subset.sum(1), axis=0)
normed_subset.plot(kind='barh', stacked=True)



    


















    
Out[44]:








<matplotlib.axes._subplots.AxesSubplot at 0x10413ee90>

MovieLens 1M data set





In [45]:



    


import pandas as pd
import os
encoding = 'latin1'

upath = os.path.expanduser('ch02/movielens/users.dat')
rpath = os.path.expanduser('ch02/movielens/ratings.dat')
mpath = os.path.expanduser('ch02/movielens/movies.dat')

unames = ['user_id', 'gender', 'age', 'occupation', 'zip']
rnames = ['user_id', 'movie_id', 'rating', 'timestamp']
mnames = ['movie_id', 'title', 'genres']

users = pd.read_csv(upath, sep='::', header=None, names=unames, encoding=encoding)
ratings = pd.read_csv(rpath, sep='::', header=None, names=rnames, encoding=encoding)
movies = pd.read_csv(mpath, sep='::', header=None, names=mnames, encoding=encoding)



    


















    






/Users/pmui/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/ipykernel/__main__.py:13: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators; you can avoid this warning by specifying engine='python'.
/Users/pmui/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/ipykernel/__main__.py:14: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators; you can avoid this warning by specifying engine='python'.
/Users/pmui/Library/Enthought/Canopy_64bit/User/lib/python2.7/site-packages/ipykernel/__main__.py:15: ParserWarning: Falling back to the 'python' engine because the 'c' engine does not support regex separators; you can avoid this warning by specifying engine='python'.

















In [46]:



    


users[:5]



    


















    
Out[46]:










  
    

      
      user_id
      gender
      age
      occupation
      zip
    

  
  
    

      0
      1
      F
      1
      10
      48067
    

    

      1
      2
      M
      56
      16
      70072
    

    

      2
      3
      M
      25
      15
      55117
    

    

      3
      4
      M
      45
      7
      02460
    

    

      4
      5
      M
      25
      20
      55455
    

  




















In [ ]:



    


ratings[:5]



    











In [ ]:



    


movies[:5]



    











In [ ]:



    


ratings



    











In [ ]:



    


data = pd.merge(pd.merge(ratings, users), movies)
data



    











In [ ]:



    


data.ix[0]



    











In [ ]:



    


mean_ratings = data.pivot_table('rating', index='title',
                                columns='gender', aggfunc='mean')
mean_ratings[:5]



    











In [ ]:



    


ratings_by_title = data.groupby('title').size()



    











In [ ]:



    


ratings_by_title[:5]



    











In [ ]:



    


active_titles = ratings_by_title.index[ratings_by_title >= 250]



    











In [ ]:



    


active_titles[:10]



    











In [ ]:



    


mean_ratings = mean_ratings.ix[active_titles]
mean_ratings



    











In [ ]:



    


mean_ratings = mean_ratings.rename(index={'Seven Samurai (The Magnificent Seven) (Shichinin no samurai) (1954)':
                           'Seven Samurai (Shichinin no samurai) (1954)'})



    











In [ ]:



    


top_female_ratings = mean_ratings.sort_index(by='F', ascending=False)
top_female_ratings[:10]

Measuring rating disagreement





In [ ]:



    


mean_ratings['diff'] = mean_ratings['M'] - mean_ratings['F']



    











In [ ]:



    


sorted_by_diff = mean_ratings.sort_index(by='diff')
sorted_by_diff[:15]



    











In [ ]:



    


# Reverse order of rows, take first 15 rows
sorted_by_diff[::-1][:15]



    











In [ ]:



    


# Standard deviation of rating grouped by title
rating_std_by_title = data.groupby('title')['rating'].std()
# Filter down to active_titles
rating_std_by_title = rating_std_by_title.ix[active_titles]
# Order Series by value in descending order
rating_std_by_title.order(ascending=False)[:10]

US Baby Names 1880-2010





In [ ]:



    


from __future__ import division
from numpy.random import randn
import numpy as np
import matplotlib.pyplot as plt
plt.rc('figure', figsize=(12, 5))
np.set_printoptions(precision=4)
%pwd

http://www.ssa.gov/oact/babynames/limits.html





In [ ]:



    


!head -n 10 ch02/names/yob1880.txt



    











In [ ]:



    


import pandas as pd
names1880 = pd.read_csv('ch02/names/yob1880.txt', names=['name', 'sex', 'births'])
names1880



    











In [ ]:



    


names1880.groupby('sex').births.sum()



    











In [ ]:



    


# 2010 is the last available year right now
years = range(1880, 2011)

pieces = []
columns = ['name', 'sex', 'births']

for year in years:
    path = 'ch02/names/yob%d.txt' % year
    frame = pd.read_csv(path, names=columns)

    frame['year'] = year
    pieces.append(frame)

# Concatenate everything into a single DataFrame
names = pd.concat(pieces, ignore_index=True)



    











In [ ]:



    


total_births = names.pivot_table('births', index='year',
                                 columns='sex', aggfunc=sum)



    











In [ ]:



    


total_births.tail()



    











In [ ]:



    


total_births.plot(title='Total births by sex and year')



    











In [ ]:



    


def add_prop(group):
    # Integer division floors
    births = group.births.astype(float)

    group['prop'] = births / births.sum()
    return group
names = names.groupby(['year', 'sex']).apply(add_prop)



    











In [ ]:



    


names



    











In [ ]:



    


np.allclose(names.groupby(['year', 'sex']).prop.sum(), 1)



    











In [ ]:



    


def get_top1000(group):
    return group.sort_index(by='births', ascending=False)[:1000]
grouped = names.groupby(['year', 'sex'])
top1000 = grouped.apply(get_top1000)



    











In [ ]:



    


pieces = []
for year, group in names.groupby(['year', 'sex']):
    pieces.append(group.sort_index(by='births', ascending=False)[:1000])
top1000 = pd.concat(pieces, ignore_index=True)



    











In [ ]:



    


top1000.index = np.arange(len(top1000))



    











In [ ]:



    


top1000



    











In [ ]:



    


boys = top1000[top1000.sex == 'M']
girls = top1000[top1000.sex == 'F']



    











In [ ]:



    


total_births = top1000.pivot_table('births', index='year', columns='name',
                                   aggfunc=sum)
total_births



    











In [ ]:



    


subset = total_births[['John', 'Harry', 'Mary', 'Marilyn']]
subset.plot(subplots=True, figsize=(12, 10), grid=False,
            title="Number of births per year")

Measuring the increase in naming diversity





In [ ]:



    


plt.figure()



    











In [ ]:



    


table = top1000.pivot_table('prop', index='year',
                            columns='sex', aggfunc=sum)
table.plot(title='Sum of table1000.prop by year and sex',
           yticks=np.linspace(0, 1.2, 13), xticks=range(1880, 2020, 10))



    











In [ ]:



    


df = boys[boys.year == 2010]
df



    











In [ ]:



    


prop_cumsum = df.sort_index(by='prop', ascending=False).prop.cumsum()
prop_cumsum[:10]



    











In [ ]:



    


prop_cumsum.values.searchsorted(0.5)



    











In [ ]:



    


df = boys[boys.year == 1900]
in1900 = df.sort_index(by='prop', ascending=False).prop.cumsum()
in1900.values.searchsorted(0.5) + 1



    











In [ ]:



    


def get_quantile_count(group, q=0.5):
    group = group.sort_index(by='prop', ascending=False)
    return group.prop.cumsum().values.searchsorted(q) + 1

diversity = top1000.groupby(['year', 'sex']).apply(get_quantile_count)
diversity = diversity.unstack('sex')



    











In [ ]:



    


def get_quantile_count(group, q=0.5):
    group = group.sort_index(by='prop', ascending=False)
    return group.prop.cumsum().values.searchsorted(q) + 1
diversity = top1000.groupby(['year', 'sex']).apply(get_quantile_count)
diversity = diversity.unstack('sex')
diversity.head()



    











In [ ]:



    


diversity.plot(title="Number of popular names in top 50%")

The "Last letter" Revolution





In [ ]:



    


# extract last letter from name column
get_last_letter = lambda x: x[-1]
last_letters = names.name.map(get_last_letter)
last_letters.name = 'last_letter'

table = names.pivot_table('births', index=last_letters,
                          columns=['sex', 'year'], aggfunc=sum)



    











In [ ]:



    


subtable = table.reindex(columns=[1910, 1960, 2010], level='year')
subtable.head()



    











In [ ]:



    


subtable.sum()



    











In [ ]:



    


letter_prop = subtable / subtable.sum().astype(float)



    











In [ ]:



    


import matplotlib.pyplot as plt

fig, axes = plt.subplots(2, 1, figsize=(10, 8))
letter_prop['M'].plot(kind='bar', rot=0, ax=axes[0], title='Male')
letter_prop['F'].plot(kind='bar', rot=0, ax=axes[1], title='Female',
                      legend=False)



    











In [ ]:



    


plt.subplots_adjust(hspace=0.25)



    











In [ ]:



    


letter_prop = table / table.sum().astype(float)

dny_ts = letter_prop.ix[['d', 'n', 'y'], 'M'].T
dny_ts.head()



    











In [ ]:



    


plt.close('all')



    











In [ ]:



    


dny_ts.plot()

Boy names that became girl names (and vice versa)





In [ ]:



    


all_names = top1000.name.unique()
mask = np.array(['lesl' in x.lower() for x in all_names])
lesley_like = all_names[mask]
lesley_like



    











In [ ]:



    


filtered = top1000[top1000.name.isin(lesley_like)]
filtered.groupby('name').births.sum()



    











In [ ]:



    


table = filtered.pivot_table('births', index='year',
                             columns='sex', aggfunc='sum')
table = table.div(table.sum(1), axis=0)
table.tail()



    











In [ ]:



    


plt.close('all')



    











In [ ]:



    


table.plot(style={'M': 'k-', 'F': 'k--'})

Content source: philmui/datascience2016fall

Similar notebooks:

notebook.community | gallery | about