diff --git a/code/clean_data.ipynb b/code/clean_data.ipynb index 363ef87..59ba3e2 100644 --- a/code/clean_data.ipynb +++ b/code/clean_data.ipynb @@ -7,19 +7,167 @@ "outputs": [ { "data": { + "text/html": [ + "
| \n", + " | id | \n", + "username | \n", + "time | \n", + "content | \n", + "content_en | \n", + "
|---|---|---|---|---|---|
| 0 | \n", + "190 | \n", + "@WorkWithUsDK | \n", + "2022-12-17 08:28:03-08:00 | \n", + "Odense Universitets Hospital søger #Afdelingsc... | \n", + "Odense University Hospital Seeking #Department... | \n", + "
| 1 | \n", + "157 | \n", + "@westblick | \n", + "2022-12-17 05:05:03-08:00 | \n", + "\"Odense Dänemark, Seaside\" Fotografie als Post... | \n", + "\"Odense Dänemark, Seaside\" photography ALS Pos... | \n", + "
| 2 | \n", + "223 | \n", + "EryilmazFa10 | \n", + "2022-12-16 14:20:26-08:00 | \n", + "Danimarka’nın Odense takımı bu yaz müthiş bir ... | \n", + "Denmark's Odense team made a great scouting tr... | \n", + "
| 3 | \n", + "224 | \n", + "trans_rumor | \n", + "2022-12-16 13:56:35-08:00 | \n", + "Highlights: SønderjyskE – Odense https://t.co/... | \n", + "Highlights: SønderjyskE - Odense https://t.co/... | \n", + "
| 4 | \n", + "225 | \n", + "sakak | \n", + "2022-12-16 13:39:40-08:00 | \n", + "“Meta Platforms Inc has halted construction of... | \n", + "\"meta platforms inc has halted construction of... | \n", + "
| ... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "... | \n", + "
| 154110 | \n", + "154518 | \n", + "JobiOdense | \n", + "2017-01-02 07:31:03-08:00 | \n", + "Køkkensælger til Danmarks nye køkkenkoncept ht... | \n", + "None | \n", + "
| 154111 | \n", + "154519 | \n", + "GunnarBjorns | \n", + "2017-01-02 07:22:27-08:00 | \n", + "watching Sunderland vs Liverpool at The Old Ir... | \n", + "None | \n", + "
| 154112 | \n", + "154520 | \n", + "NordicDate | \n", + "2017-01-02 07:20:09-08:00 | \n", + "Danmarks størreste #sex #dating portal:\\n\\nhtt... | \n", + "None | \n", + "
| 154113 | \n", + "154521 | \n", + "DBAfeed | \n", + "2017-01-02 07:18:05-08:00 | \n", + "Elguitar, Morgan Stratocaster kopi, Sælger de... | \n", + "None | \n", + "
| 154114 | \n", + "154522 | \n", + "TRungCardio | \n", + "2017-01-02 07:10:28-08:00 | \n", + "Bevar mulighederne for børn i Odense... Og lad... | \n", + "None | \n", + "
154115 rows × 5 columns
\n", + "