# F1 Challenge — Data

来源：https://www.kaggle.com/competitions/f1-challenge/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<p>Given Twitter US Airline Sentiment Dataset, which contains data for over 7500 tweets, your task is to predict the sentiment of the tweet i.e. positive, negative or neutral.</p>
<p>You are given:
<ol>
<li> A Training dataset csv file with X train and Y train data </li>
<li> A X test File and you have to predict and submit predictions for this file. </li>
</ol>
</p>
<h2>Read Instructions carefully -</h2>
<strong><p>
<ol>
<li> Files are in csv format. </li>
<li> Submit a csv file with only predictions for X test data. File should not have any headers and should only have one column i.e. predictions. </li> 
<li> Submit your ipynb file as well. </li>
<li> Your score is based on number of accurate predictions. </li>
<li>  You need to upload both predictions and notebook file to submit.  </li>
<li>  Please make sure that your submissions are genuine and you haven’t cheated/copied from anywhere.  <b> In such scenario your submission will be disqualified </b> </li>
</ol>
</p>
<h2>File descriptions</h2>
<ul>
<li><strong>Train.csv</strong> - the training set</li>
<li><strong>Test.csv</strong> - the test set</li>
</ul>
<h2>Data fields</h2>
<ul>
<li><strong>tweet_id</strong> </li>
<li><strong>airline</strong> </li>
<li><strong>airline_sentiment</strong></li>
<li><strong>airline_sentiment_gold</strong> </li>
<li><strong>name</strong></li>
<li><strong>negativereason_gold</strong></li>
<li><strong>retweet_count</strong> </li>
<li><strong>text</strong></li>
<li><strong>tweet_coord</strong> </li>
<li><strong>tweet_created</strong> </li>
<li><strong>tweet_location</strong> </li>
<li><strong>user_timezone</strong> </li>
</ul>