Data Analysis for Hacker News Posts

In this notebook we will be analysing the data to determing two things

  • Do Ask HN or Show HN receive more comments on average?
  • Do posts created at a certain time receive more comments on average?
In [2]:
import csv 

file = open("hacker_news.csv")
hn = list(csv.reader(file))

print(hn[:5])

[['id', 'title', 'url', 'num_points', 'num_comments', 'author', 'created_at'], ['12224879', 'Interactive Dynamic Video', 'http://www.interactivedynamicvideo.com/', '386', '52', 'ne0phyte', '8/4/2016 11:52'], ['10975351', 'How to Use Open Source and Shut the Fuck Up at the Same Time', 'http://hueniverse.com/2016/01/26/how-to-use-open-source-and-shut-the-fuck-up-at-the-same-time/', '39', '10', 'josep2', '1/26/2016 19:30'], ['11964716', "Florida DJs May Face Felony for April Fools' Water Joke", 'http://www.thewire.com/entertainment/2013/04/florida-djs-april-fools-water-joke/63798/', '2', '1', 'vezycash', '6/23/2016 22:20'], ['11919867', 'Technology ventures: From Idea to Enterprise', 'https://www.amazon.com/Technology-Ventures-Enterprise-Thomas-Byers/dp/0073523429', '3', '1', 'hswarna', '6/17/2016 0:01']]
In [3]:
# removing header and displaying first 5 rows of data only
headers = hn[0]
hn = hn[1:]
print(headers)
print(hn[:5])

['id', 'title', 'url', 'num_points', 'num_comments', 'author', 'created_at']
[['12224879', 'Interactive Dynamic Video', 'http://www.interactivedynamicvideo.com/', '386', '52', 'ne0phyte', '8/4/2016 11:52'], ['10975351', 'How to Use Open Source and Shut the Fuck Up at the Same Time', 'http://hueniverse.com/2016/01/26/how-to-use-open-source-and-shut-the-fuck-up-at-the-same-time/', '39', '10', 'josep2', '1/26/2016 19:30'], ['11964716', "Florida DJs May Face Felony for April Fools' Water Joke", 'http://www.thewire.com/entertainment/2013/04/florida-djs-april-fools-water-joke/63798/', '2', '1', 'vezycash', '6/23/2016 22:20'], ['11919867', 'Technology ventures: From Idea to Enterprise', 'https://www.amazon.com/Technology-Ventures-Enterprise-Thomas-Byers/dp/0073523429', '3', '1', 'hswarna', '6/17/2016 0:01'], ['10301696', 'Note by Note: The Making of Steinway L1037 (2007)', 'http://www.nytimes.com/2007/11/07/movies/07stein.html?_r=0', '8', '2', 'walterbell', '9/30/2015 4:12']]
In [4]:
# lets create new lists to hold data
ask_posts = []
show_posts = []
other_posts = []

# looping through `hn` to get titles
for row in hn:
    title = row[1]
    title = title.lower()
    if title.startswith('ask hn'):
        ask_posts.append(row)
    elif title.startswith('show hn'):
        show_posts.append(row)
    else:
        other_posts.append(row)
      
    
print(len(ask_posts))
print(len(show_posts))
print(len(other_posts))

1744
1162
17194

Lets identify if ask posts or show posts receive more comments on average

In [5]:
# average of comments on `Ask HN`
total_ask_comments = 0

for row in ask_posts:
    total_ask_comments += int(row[4])
    

avg_ask_comments = total_ask_comments / len(ask_posts)
print(avg_ask_comments)

14.038417431192661
In [6]:
# average of comments on `Show HN`
total_show_comments = 0

for row in show_posts:
    total_show_comments += int(row[4])
    

avg_show_comments = total_show_comments / len(show_posts)
print(avg_show_comments)

10.31669535283993

Finding the Amount of Ask Posts and Comments by Hour Created

In [7]:
import datetime as dt

result_list = []

for post in ask_posts:
    result_list.append(
        [post[6], int(post[4])]
    )

comments_by_hour = {}
counts_by_hour = {}
date_format = "%m/%d/%Y %H:%M"

for each_row in result_list:
    date = each_row[0]
    comment = each_row[1]
    time = dt.datetime.strptime(date, date_format).strftime("%H")
    if time in counts_by_hour:
        comments_by_hour[time] += comment
        counts_by_hour[time] += 1
    else:
        comments_by_hour[time] = comment
        counts_by_hour[time] = 1

comments_by_hour
Out[7]:
{'00': 447,
 '01': 683,
 '02': 1381,
 '03': 421,
 '04': 337,
 '05': 464,
 '06': 397,
 '07': 267,
 '08': 492,
 '09': 251,
 '10': 793,
 '11': 641,
 '12': 687,
 '13': 1253,
 '14': 1416,
 '15': 4477,
 '16': 1814,
 '17': 1146,
 '18': 1439,
 '19': 1188,
 '20': 1722,
 '21': 1745,
 '22': 479,
 '23': 543}
In [8]:
# Calculate the average amount of comments `Ask HN` posts created at each hour of the day receive.
avg_by_hour = []

for hr in comments_by_hour:
    avg_by_hour.append([hr, comments_by_hour[hr] / counts_by_hour[hr]])

avg_by_hour
Out[8]:
[['11', 11.051724137931034],
 ['03', 7.796296296296297],
 ['00', 8.127272727272727],
 ['18', 13.20183486238532],
 ['17', 11.46],
 ['10', 13.440677966101696],
 ['04', 7.170212765957447],
 ['16', 16.796296296296298],
 ['14', 13.233644859813085],
 ['08', 10.25],
 ['19', 10.8],
 ['15', 38.5948275862069],
 ['09', 5.5777777777777775],
 ['07', 7.852941176470588],
 ['02', 23.810344827586206],
 ['13', 14.741176470588234],
 ['20', 21.525],
 ['23', 7.985294117647059],
 ['21', 16.009174311926607],
 ['22', 6.746478873239437],
 ['06', 9.022727272727273],
 ['01', 11.383333333333333],
 ['12', 9.41095890410959],
 ['05', 10.08695652173913]]
In [9]:
swap_avg_by_hour = []

for row in avg_by_hour:
    swap_avg_by_hour.append([row[1], row[0]])
    
print(swap_avg_by_hour)

sorted_swap = sorted(swap_avg_by_hour, reverse=True)

sorted_swap

[[11.051724137931034, '11'], [7.796296296296297, '03'], [8.127272727272727, '00'], [13.20183486238532, '18'], [11.46, '17'], [13.440677966101696, '10'], [7.170212765957447, '04'], [16.796296296296298, '16'], [13.233644859813085, '14'], [10.25, '08'], [10.8, '19'], [38.5948275862069, '15'], [5.5777777777777775, '09'], [7.852941176470588, '07'], [23.810344827586206, '02'], [14.741176470588234, '13'], [21.525, '20'], [7.985294117647059, '23'], [16.009174311926607, '21'], [6.746478873239437, '22'], [9.022727272727273, '06'], [11.383333333333333, '01'], [9.41095890410959, '12'], [10.08695652173913, '05']]
Out[9]:
[[38.5948275862069, '15'],
 [23.810344827586206, '02'],
 [21.525, '20'],
 [16.796296296296298, '16'],
 [16.009174311926607, '21'],
 [14.741176470588234, '13'],
 [13.440677966101696, '10'],
 [13.233644859813085, '14'],
 [13.20183486238532, '18'],
 [11.46, '17'],
 [11.383333333333333, '01'],
 [11.051724137931034, '11'],
 [10.8, '19'],
 [10.25, '08'],
 [10.08695652173913, '05'],
 [9.41095890410959, '12'],
 [9.022727272727273, '06'],
 [8.127272727272727, '00'],
 [7.985294117647059, '23'],
 [7.852941176470588, '07'],
 [7.796296296296297, '03'],
 [7.170212765957447, '04'],
 [6.746478873239437, '22'],
 [5.5777777777777775, '09']]
In [10]:
# Sort the values and print the the 5 hours with the highest average comments.

print("Top 5 Hours for 'Ask HN' Comments")
for avg, hr in sorted_swap[:5]:
    print(
        "{}: {:.2f} average comments per post".format(
            dt.datetime.strptime(hr, "%H").strftime("%H:%M"),avg
        )
    )

Top 5 Hours for 'Ask HN' Comments
15:00: 38.59 average comments per post
02:00: 23.81 average comments per post
20:00: 21.52 average comments per post
16:00: 16.80 average comments per post
21:00: 16.01 average comments per post
In [ ]: