# CS725: Assignment 2 — Data

来源：https://www.kaggle.com/competitions/cs725-assignment-2/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<h2>File descriptions</h2>
<ul>
<li><strong>train.csv</strong> - the training set</li>
<li><strong>test.csv</strong> - the test set</li>
<li><strong>sample_submission.csv</strong> - a sample submission file in the correct format</li>
</ul>
<h2>Data fields</h2>
<ul>
<li><strong>page_likes</strong> - number of likes the facebook page has (shows user support for a wall posts)</li>
<li><strong>page_checkin</strong> -number of people visited the place (only applicable to places, institutions, hotels, etc. pages )</li>
<li><strong>daily_crowd</strong> - count of users that are engaged with the page ( who frequently comment, share posts of page)</li>
<li><strong>page_category</strong> - defines the category of source of document ( eg: brand, company, artist, etc.)</li>
<li><strong>F1-F8</strong> - These features are aggregated by page, by calculating min, max, average, median and standard deviation of essential features.</li>
<li><strong>c1</strong> - The total number of comments before selected base date/time</li>
<li><strong>c2</strong> - The number of comments in last 24 hours, relative to base date/time.</li>
<li><strong>c3</strong> - The number of comments in last 48 to last 24 hours relative to base date/time.</li>
<li><strong>c4</strong> - The number of comments in the first 24 hours after the publication of post but before base date/time.</li>
<li><strong>c5</strong> - The difference between c2 and c3.</li>
<li><strong>base_time </strong>- Selected time in order to simulate the scenario. ( decimal encoding 0-71)</li>
<li><strong>post_length</strong> - Character count in the</li>
<li><strong>share_count</strong> - This features counts the no of shares of the post, that how many peoples had shared this post on to their timeline.</li>
<li><strong>promotion</strong> - To reach more people with posts in News Feed, individual promote their post and this features tells that whether the post is promoted(1) or not(0).</li>
<li><strong>h_target</strong> - Hours after base_time when target variable is recorded</li>
<li><strong>post_day</strong> - day of week when post was posted</li>
<li><strong>basetime_day</strong> - day of week corresponding to base_time (when data was collected)</li>
<li><strong>target</strong> - volume of comments received after h_target hours of base_time <ul><li>1: High volume of comments</li> <li>2: Medium volume of comments</li><li>3: Low volume of comments</li></ul></li>
</ul>