* Started work on tweets dataset

  • Created new table tweets_info in database cynthiak
  • Parsed and formatted the json file and inserted majority columns in tweets_info table.
  • Will finish the rest of the upload in a few days.
  • Heading to the airport in a few hours for Singapore!

Some useful commands for handling tweets dataset

sed -i 's/\\g' filename
string = string.replace(“\n”,“”).replace(“\r”,“”)

SQL to create table tweets_info
DROP TABLE IF EXISTS tweets_info;

CREATE TABLE tweets_info(
tweetCreated VARCHAR(50),
tweetID BIGINT,
tweetText TEXT,
display_text_range VARCHAR(50) NULL,
source TEXT,
truncated VARCHAR(10),
in_reply_to_status_id VARCHAR(50),
in_reply_to_user_id VARCHAR(50),
in_reply_to_screen_name TEXT,
tweetUser BIGINT,
tweetGeoType TEXT,
tweetGeoCoord TEXT,
tweetCoordType TEXT,
tweetCoord TEXT,
placeID TEXT,
placeURL TEXT,
placeType TEXT,
placeCountry TEXT,
tweetPFullName TEXT,
tweetPCountryCode TEXT,
tweetPname TEXT,
tweetPBBox1x VARCHAR(50),
tweetPBBox1y VARCHAR(50),
tweetPBBox2x VARCHAR(50),
tweetPBBox2y VARCHAR(50),
tweetPBBox3x VARCHAR(50),
tweetPBBox3y VARCHAR(50),
tweetPBBox4x VARCHAR(50),
tweetPBBox4y VARCHAR(50),
placeAttributes TEXT,
tweetContributors TEXT NULL,
is_quote_status VARCHAR(50),
retweetCount INTEGER,
favoriteCount INTEGER,
entitiesID BIGINT,
entitiesMediaID BIGINT,
extendedEntitiesID BIGINT,
favorited VARCHAR(10),
retweeted VARCHAR(10),
possibly_sensitive VARCHAR(50),
filter_level TEXT,
tweetLang TEXT,
tweetTimestamp BIGINT,
matchingRulesTag TEXT NULL,
matchingRulesID BIGINT
);

psql cynthiak
\copy tweets_info FROM '/home/cynthiak/tab_to_semi.txt' WITH DELIMITER ';'

  • 11_12_2018.txt
  • Last modified: 2018/11/14 22:01
  • by cynthia.kahn