Differences
This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
11_12_2018 [2018/11/14 21:48] – cynthia.kahn | 11_12_2018 [2018/11/14 22:01] (current) – cynthia.kahn | ||
---|---|---|---|
Line 9: | Line 9: | ||
**//Some useful commands for handling tweets dataset//** | **//Some useful commands for handling tweets dataset//** | ||
- | sed -i ' | + | sed -i ' |
- | string = string.replace(" | + | string = string.replace(" |
+ | \\ | ||
**//SQL to create table tweets_info// | **//SQL to create table tweets_info// | ||
- | DROP TABLE IF EXISTS tweets_info; | + | \\ |
- | + | DROP TABLE IF EXISTS tweets_info; | |
- | CREATE TABLE tweets_info( | + | \\ |
- | tweetCreated VARCHAR(50), | + | CREATE TABLE tweets_info( |
- | tweetID BIGINT, | + | tweetCreated VARCHAR(50), |
- | tweetText TEXT, | + | tweetID BIGINT, |
- | display_text_range VARCHAR(50) NULL, | + | tweetText TEXT, \\ |
- | source TEXT, | + | display_text_range VARCHAR(50) NULL, \\ |
- | truncated VARCHAR(10), | + | source TEXT, \\ |
- | in_reply_to_status_id VARCHAR(50), | + | truncated VARCHAR(10), |
- | in_reply_to_user_id VARCHAR(50), | + | in_reply_to_status_id VARCHAR(50), |
- | in_reply_to_screen_name TEXT, | + | in_reply_to_user_id VARCHAR(50), |
- | tweetUser BIGINT, | + | in_reply_to_screen_name TEXT, \\ |
- | tweetGeoType TEXT, | + | tweetUser BIGINT, |
- | tweetGeoCoord TEXT, | + | tweetGeoType TEXT, \\ |
- | tweetCoordType TEXT, | + | tweetGeoCoord TEXT, \\ |
- | tweetCoord TEXT, | + | tweetCoordType TEXT, \\ |
- | placeID TEXT, | + | tweetCoord TEXT, \\ |
- | placeURL TEXT, | + | placeID TEXT, \\ |
- | placeType TEXT, | + | placeURL TEXT, \\ |
- | placeCountry TEXT, | + | placeType TEXT, \\ |
- | tweetPFullName TEXT, | + | placeCountry TEXT, \\ |
- | tweetPCountryCode TEXT, | + | tweetPFullName TEXT, \\ |
- | tweetPname TEXT, | + | tweetPCountryCode TEXT, \\ |
- | tweetPBBox1x VARCHAR(50), | + | tweetPname TEXT, \\ |
- | tweetPBBox1y VARCHAR(50), | + | tweetPBBox1x VARCHAR(50), |
- | tweetPBBox2x VARCHAR(50), | + | tweetPBBox1y VARCHAR(50), |
- | tweetPBBox2y VARCHAR(50), | + | tweetPBBox2x VARCHAR(50), |
- | tweetPBBox3x VARCHAR(50), | + | tweetPBBox2y VARCHAR(50), |
- | tweetPBBox3y VARCHAR(50), | + | tweetPBBox3x VARCHAR(50), |
- | tweetPBBox4x VARCHAR(50), | + | tweetPBBox3y VARCHAR(50), |
- | tweetPBBox4y VARCHAR(50), | + | tweetPBBox4x VARCHAR(50), |
- | placeAttributes TEXT, | + | tweetPBBox4y VARCHAR(50), |
- | tweetContributors TEXT NULL, | + | placeAttributes TEXT, \\ |
- | is_quote_status VARCHAR(50), | + | tweetContributors TEXT NULL, \\ |
- | retweetCount INTEGER, | + | is_quote_status VARCHAR(50), |
- | favoriteCount INTEGER, | + | retweetCount INTEGER, |
- | entitiesID BIGINT, | + | favoriteCount INTEGER, |
- | entitiesMediaID BIGINT, | + | entitiesID BIGINT, |
- | extendedEntitiesID BIGINT, | + | entitiesMediaID BIGINT, |
- | favorited VARCHAR(10), | + | extendedEntitiesID BIGINT, |
- | retweeted VARCHAR(10), | + | favorited VARCHAR(10), |
- | possibly_sensitive VARCHAR(50), | + | retweeted VARCHAR(10), |
- | filter_level TEXT, | + | possibly_sensitive VARCHAR(50), |
- | tweetLang TEXT, | + | filter_level TEXT, \\ |
- | tweetTimestamp BIGINT, | + | tweetLang TEXT, \\ |
- | matchingRulesTag TEXT NULL, | + | tweetTimestamp BIGINT, |
- | matchingRulesID BIGINT | + | matchingRulesTag TEXT NULL, \\ |
- | ); | + | matchingRulesID BIGINT |
+ | ); \\ | ||
+ | \\ | ||
+ | psql cynthiak | ||
+ | \copy tweets_info FROM '/ | ||