Hacker News Analysis Project

L_GAYOSSO · May 3, 2020, 3:02am

Hello!

Here’s my solution to the Hacker News Dataset Analysis.

Suggestions? Recommendations?

Thanks!

Lucio

My Code: <!-#!/usr/bin/env python

coding: utf-8

# Hacker News Dataset Analysis

## By: Lucio Gayosso (05/02/20)

In[29]:

opened_file = open(‘hacker_news.csv’)
from csv import reader
read_file = reader(opened_file)
hn = list(read_file)
headers = hn[0]
#print(“Headers: “,headers,”\n”)
#print (hn[1:6])

Create empty lists

ask_posts =
show_posts =
other_posts =

for row in hn:
title = row[1]
title = title.lower()
if title.startswith(‘ask hn’):
ask_posts.append(row)
else:
if 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))

#print(show_posts[:6])

total_ask_comments = 0

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

Calculate average number of Ask comments

avg_ask_comments = total_ask_comments / len(ask_posts)

#print(total_ask_comments)
#print(len(ask_posts))
print("Average Ask comments: ", avg_ask_comments)

total_show_comments = 0

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

Calculate average number of Show comments

avg_show_comments = total_show_comments / len(show_posts)
print("Average Show comments: ", avg_show_comments)

## Analysis

Ask HK has more comments in average

In[142]:

import datetime as dt

result_list =

for row in ask_posts:
temp_list =
created_at = row[6]
num_comments = int(row[4])
temp_list.append(created_at)
temp_list.append(num_comments)
result_list.append(temp_list)

counts_by_hour = {}
comments_by_hour = {}

for row in result_list:
date_str = row[0]
date = dt.datetime.strptime(date_str,"%m/%d/%Y %H:%M") # parse the string date to create a datetime object
hour = date.strftime("%H")
#print(hour)
if hour not in counts_by_hour:
counts_by_hour[hour] = 1
comments_by_hour[hour] = row[1] # num_comments from previous loop
else:
counts_by_hour[hour] += 1
comments_by_hour[hour] += row[1] # num_comments from previous loop

#print(counts_by_hour)
#print(comments_by_hour)

avg_comments_hr =

for hour in counts_by_hour:
# Avg Comments = Nbr of comments / Counts of posts
avg_comments_hr.append([hour, comments_by_hour[hour]/counts_by_hour[hour]])

avg_by_hour = avg_comments_hr
#print(avg_by_hour)

Arrange the results

swap_avg_by_hour =

for row in avg_by_hour:
temp_list =
first_element = row[0]
second_element = row[1]
temp_list.append(second_element)
temp_list.append(first_element)
swap_avg_by_hour.append(temp_list)

print(swap_avg_by_hour)
#sorted_swap = sorted(swap_avg_by_hour,reverse=True)
print(“Top 5 Hours for Ask Posts Comments:”)
for row in sorted_swap[:5]:
hour_str = dt.datetime.strptime(row[1],"%H")
hour = hour_str.strftime("%H")
avg = row[0]
print("{}:00: {:.2f} average comments per post".format(hour, avg))