#!/usr/bin/env python
# coding: utf-8

# # Guided Project - Exploring Hacker News Posts
# ![download.png](attachment:download.png)
#  
# ### Company Background:
# Hacker News is a site where users receive votes and comments on submitted stories (or posts).  Top posts on Hacker News may receive hundreds of thousands of visitors.  
# 
# ### **Project Goal:**
# 
# My goal as the Data Analyst is to answer two questions:
# * Does <mark>Ask HN or Show HN</mark> receive more comments? 
# * Do posts created at certain times receive more comments on average?
# 
# > **This project will use the following six steps of the data analysis process to answer the above two questions of the project goal:**
# > * 1.) Ask Question
# > * 2.) Get Data
# > * 3.) Explore Data
# > * 4.) Clean Data
# > * 5.) Analyze Data
# > * 6.) Conclusion
# 

# ##  Ask Question:
# 
# My goal as the Data Analyst is to answer two questions:
# * Does <mark>Ask HN or Show HN</mark> receive more comments on average?
# * Do posts created at certain times receive more comments on average?

# ## Get Data  
# 
# The data set that will be used for analysis can be found [here](https://www.kaggle.com/hacker-news/hacker-news-posts).
# The data set includes submissions to the Hacker News site.

# In[12]:


# Reduced dataset from 300,000 rows to 20,000 rows by removing all submissions without a comment

opened_file = open("hacker_news.csv")
from csv import reader
read_file = reader(opened_file)
hn = list(read_file)
 
headers = hn[0]
print(headers)
hn = hn[1:] ## remove header
print(hn[0])
 
 


# In[13]:


#import modules
import datetime as dt


# ## Explore Data

# #Data Dictionary
# * id: the unique identifier from Hacker News for the post
# * title: the title of the post
# * url: the URL that the posts links to, if the post has a URL
# * num_points: the number of points the post acquired, calculated as the total number of upvotes minus the total number of downvotes
# * num_comments: the number of comments on the post
# * author: the username of the person who submitted the post
# * created_at: the date and time of the post's submission

# ## Clean Data

# Find posts that begin with <mark>Ask HN</mark> or <mark>Show HN</mark>
# 

# In[14]:


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)
    elif title.startswith("show hn"):
        show_posts.append(row)
    else:
        other_posts.append(row)
        
print("Number of Posts begin with 'Ask HN': ", len(ask_posts), "\n","Number of posts begin with 'Show HN': ", len(show_posts),"\n", "Number of Other posts:", len(other_posts))


# Calculate the average number of comments per posts for:
# * Ask HN
# * Show HN
#  

# In[15]:


# Calc the average comments per ask_posts
total_ask_comments = 0
for row in ask_posts:
    num = int(row[4])
    
    total_ask_comments += num

avg_ask_comments = total_ask_comments / len(ask_posts)
print("Average number of comments for Ask HN:")
avg_ask_comments
 


# In[16]:


# Find the average comments per show_posts
total_show_comments = 0
for post in show_posts:
    num_1 = int(post[4])
    
    total_show_comments += num_1

avg_show_comments = total_show_comments / len(show_posts)
print("Average number of comments for Show HN:")
avg_show_comments
 


# > The <mark>Ask HN</mark> posts receive more comments.  The <mark>Ask HN</mark> posts receive around 14 comments per post while the <mark>Show HN</mark> posts receive around 10 comments per post.
# 
# Since <mark>Ask HN</mark> posts receive more comments, the analysis will focus on <mark>Ask HN</mark> posts only.

# ## Analyze Ask Posts Data

# Determine if <mark>Ask Posts</mark> created at certain times have more comments:
# 
# * calculate the number of <mark>Ask Posts</mark> created each hour along with # comments received
# 
# * calculate average number of comments <mark>Ask Posts</mark> receives by hour created
# 
# * identify the top five hours with the highest comments per post
# 
# * identify the best hours to create a post to have a higher chance of receiving comments
# 

# > Calculate the number of <mark>Ask Posts</mark> created each hour along with the number of comments received

# In[17]:


# calculate the number of ask posts created each hour along with # comments received
 
result_list = []
for post in ask_posts:
    created_at_col = post[6]
    num_comments_col = post[4]
    result_list.append([created_at_col, num_comments_col]) # create at time and dat, number of comments

counts_by_hour = {} 
comments_by_hour = {}

for row in result_list:
    date = row[0]
    comment_num = int(row[1])
    date_formatted_dt = dt.datetime.strptime(date,"%m/%d/%Y %H:%M")
    hour = date_formatted_dt.hour
    if hour not in counts_by_hour:
        counts_by_hour[hour] = 1
        comments_by_hour[hour] = comment_num
    elif hour in counts_by_hour:
        counts_by_hour[hour] += 1
        comments_by_hour[hour] += comment_num
        
print("Posts per hour:","\n",counts_by_hour,"\n", "\n","Comments per hour:","\n",comments_by_hour) 


# > Calculate average number of comments <mark>Ask Posts</mark> receives by the hour created

# In[18]:


#calculate average number of comments ask posts receives by hour created
avg_by_hour =  []
for hour in comments_by_hour:
     avg_by_hour.append([hour,comments_by_hour[hour]/counts_by_hour[hour]])
print("Average number of comments per post by hour:")
avg_by_hour


# > Identify the top five hours with the highest comments per post:
# 
# > * create a list of list with <mark>average</mark> as first element and <mark>hour</mark> as 2nd element
# 
# > * sort the list and print the top 5 hours with the most average comments per hour

# In[19]:


#create a list with avg_by_hour swapped columns
swap_avg_by_hour = []
for hour in avg_by_hour:
    swap_avg_by_hour.append([hour[1],hour[0]])
swap_avg_by_hour


# In[20]:


# sort new list of list swap_avg_by_hour

sorted_swap = sorted(swap_avg_by_hour, reverse = True)

print("Top 5 Hours for Ask Posts Comments")

for comment_hour in sorted_swap[:5]:
    hour_avg_comment = str(comment_hour[1]) # 15 convert to str
    hour_dt = dt.datetime.strptime(hour_avg_comment, "%H")# 1900-01-01 15:00:00
    hour_formatted = hour_dt.strftime("%H:%M") # 15:00
     
    template = "{hour} {avg_comment:.2f} average comments per post".format(hour=hour_formatted, avg_comment = comment_hour[0])
    print(template)


# > Identify the best hours to create a post to have a higher chance of receiving comments

# # Conclusion 
# 
# This project answers two questions:
# 
# **Does Ask HN or Show HN receive more comments on average?** 
# Based on the above analysis, Ask HN receives around 14 comments per post while Show HN receives 10
# 
# **Do posts created at certain times receive more comments on average?**
# 
# The best hour to create a post is at 15:00 or 3:00 pm Eastern time.  Based on TABLE 1 below, the 15:00 hour receives the highest average comments per post at 38.59.    
# 
# <mark>TABLE 1:</mark>
# 
# **<u>Top 5 Hours for Ask Posts Comments</u>**
# 
# 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