diff --git a/fix_clean_tweets_dataframe.py b/clean_tweets_dataframe.py similarity index 59% rename from fix_clean_tweets_dataframe.py rename to clean_tweets_dataframe.py index 7b45a35..88caa9d 100644 --- a/fix_clean_tweets_dataframe.py +++ b/clean_tweets_dataframe.py @@ -1,3 +1,5 @@ +import pandas as pd + class Clean_Tweets: """ The PEP8 Standard AMAZING!!! @@ -15,22 +17,33 @@ def drop_unwanted_column(self, df:pd.DataFrame)->pd.DataFrame: df.drop(unwanted_rows , inplace=True) df = df[df['polarity'] != 'polarity'] - return df + return + + + def drop_duplicate(self, df:pd.DataFrame)->pd.DataFrame: """ - drop duplicate rows + drop duplicate rows from the DataFrame + + Parameters + df (pd.DataFrame): Dataframe from which to remove duplicates + + Returns: + pd.DataFrame: A Dataframe with duplicates remofved """ - --- + df = df.drop_duplicates(keep='first',inplace=False) + + print("Duplicate rows removed from the DataFrame.") return df + + def convert_to_datetime(self, df:pd.DataFrame)->pd.DataFrame: """ convert column to datetime """ - ---- - - ---- + df['created_at'] = pd.to_datetime(df['created_at']) df = df[df['created_at'] >= '2020-12-31' ] @@ -41,18 +54,21 @@ def convert_to_numbers(self, df:pd.DataFrame)->pd.DataFrame: convert columns like polarity, subjectivity, retweet_count favorite_count etc to numbers """ - df['polarity'] = pd.---- - - ---- - ---- + df['polarity'] = pd.to_numeric(df['polarity']) + df['subjectivity'] = pd.to_numeric(df['subjectivity']) + df['retweet_count'] = pd.to_numeric(df['retweet_count']) + df['favorite_count'] = pd.to_numeric(df['favorite_count']) + df['retweet_count'] = pd.to_numeric(df['retweet_count']) + df['followers_count'] = pd.to_numeric(df['followers_count']) return df - + + def remove_non_english_tweets(self, df:pd.DataFrame)->pd.DataFrame: """ remove non english tweets from lang """ - df = ---- + df = pd.drop(df[df['lang'] == 'en']) return df \ No newline at end of file diff --git a/eda.ipynb b/eda.ipynb new file mode 100644 index 0000000..19ce1f8 --- /dev/null +++ b/eda.ipynb @@ -0,0 +1,2216 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd \n", + "import numpy as np \n", + "import extract_dataframe\n", + "import clean_tweets_dataframe\n", + "#from extract_dataframe import *\n", + "#from clean_tweets_dataframe import * \n" + ] + }, + { + "cell_type": "code", + "execution_count": 2, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
| \n", + " | created_at | \n", + "id | \n", + "id_str | \n", + "full_text | \n", + "truncated | \n", + "display_text_range | \n", + "entities | \n", + "metadata | \n", + "source | \n", + "in_reply_to_status_id | \n", + "... | \n", + "retweet_count | \n", + "favorite_count | \n", + "favorited | \n", + "retweeted | \n", + "lang | \n", + "extended_entities | \n", + "possibly_sensitive | \n", + "quoted_status_id | \n", + "quoted_status_id_str | \n", + "quoted_status | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "2022-08-03 20:19:13+00:00 | \n", + "1554924874166149120 | \n", + "1554924874166149120 | \n", + "#Pelosi airplane landed safely in #Taiwan ๐น๐ผ ... | \n", + "False | \n", + "[0, 222] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "0 | \n", + "False | \n", + "False | \n", + "en | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 1 | \n", + "2022-08-02 15:24:42+00:00 | \n", + "1554488368347680771 | \n", + "1554488368347680768 | \n", + "Watch the video of the beginning of the Chines... | \n", + "False | \n", + "[0, 250] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [1... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"https://mobile.twitter.com\" rel=\"nofo... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "3 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554487694776012800, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 2 | \n", + "2022-08-02 15:02:35+00:00 | \n", + "1554482802502127621 | \n", + "1554482802502127616 | \n", + "#Pelosi \\n#Taipei \\n#taiwan\\n#XiJinping \\n#Chi... | \n", + "False | \n", + "[0, 71] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "2 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554482776140906497, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 3 | \n", + "2022-08-01 13:51:42+00:00 | \n", + "1554102573635932160 | \n", + "1554102573635932160 | \n", + "#HOBIPALOOZA #LaAcademiaExpulsion #WEURO2022 #... | \n", + "False | \n", + "[0, 146] | \n", + "{'hashtags': [{'text': 'HOBIPALOOZA', 'indices... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "0 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554102566010732544, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 4 | \n", + "2022-07-31 20:02:20+00:00 | \n", + "1553833459440910338 | \n", + "1553833459440910336 | \n", + "#Pelosi\\n#china\\nChina Time โ๏ธ https://t.co/tE... | \n", + "False | \n", + "[0, 28] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "2 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1553833456853045256, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
5 rows ร 30 columns
\n", + "| \n", + " | created_at | \n", + "id | \n", + "id_str | \n", + "text | \n", + "truncated | \n", + "entities | \n", + "source | \n", + "in_reply_to_status_id | \n", + "in_reply_to_status_id_str | \n", + "in_reply_to_user_id | \n", + "... | \n", + "retweet_count | \n", + "favorite_count | \n", + "favorited | \n", + "retweeted | \n", + "lang | \n", + "extended_entities | \n", + "possibly_sensitive | \n", + "quoted_status_id | \n", + "quoted_status_id_str | \n", + "quoted_status | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "2022-04-22 22:20:18+00:00 | \n", + "1517629396575784961 | \n", + "1517629396575784960 | \n", + "RT @nikitheblogger: Irre: Annalena Baerbock sa... | \n", + "False | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "355 | \n", + "0 | \n", + "False | \n", + "False | \n", + "de | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 1 | \n", + "2022-04-22 22:19:16+00:00 | \n", + "1517629134012399616 | \n", + "1517629134012399616 | \n", + "RT @sagt_mit: Merkel schaffte es in 1 Jahr 1 M... | \n", + "False | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "505 | \n", + "0 | \n", + "False | \n", + "False | \n", + "de | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 2 | \n", + "2022-04-22 22:17:28+00:00 | \n", + "1517628682659106822 | \n", + "1517628682659106816 | \n", + "RT @Kryptonoun: @WRi007 Pharma in Lebensmittel... | \n", + "False | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "4 | \n", + "0 | \n", + "False | \n", + "False | \n", + "de | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 3 | \n", + "2022-04-22 22:17:20+00:00 | \n", + "1517628647892561924 | \n", + "1517628647892561920 | \n", + "RT @WRi007: Die #Deutschen sind ein braves Vol... | \n", + "False | \n", + "{'hashtags': [{'text': 'Deutschen', 'indices':... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "332 | \n", + "0 | \n", + "False | \n", + "False | \n", + "de | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 4 | \n", + "2022-04-22 22:13:15+00:00 | \n", + "1517627621135237127 | \n", + "1517627621135237120 | \n", + "RT @RolandTichy: Baerbock verkรผndet mal so neb... | \n", + "False | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "... | \n", + "386 | \n", + "0 | \n", + "False | \n", + "False | \n", + "de | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
5 rows ร 29 columns
\n", + "| \n", + " | 0 | \n", + "
|---|---|
| 0 | \n", + "created_at | \n", + "
| 1 | \n", + "id | \n", + "
| 2 | \n", + "id_str | \n", + "
| 3 | \n", + "text | \n", + "
| 4 | \n", + "truncated | \n", + "
| 5 | \n", + "entities | \n", + "
| 6 | \n", + "source | \n", + "
| 7 | \n", + "in_reply_to_status_id | \n", + "
| 8 | \n", + "in_reply_to_status_id_str | \n", + "
| 9 | \n", + "in_reply_to_user_id | \n", + "
| 10 | \n", + "in_reply_to_user_id_str | \n", + "
| 11 | \n", + "in_reply_to_screen_name | \n", + "
| 12 | \n", + "user | \n", + "
| 13 | \n", + "geo | \n", + "
| 14 | \n", + "coordinates | \n", + "
| 15 | \n", + "place | \n", + "
| 16 | \n", + "contributors | \n", + "
| 17 | \n", + "retweeted_status | \n", + "
| 18 | \n", + "is_quote_status | \n", + "
| 19 | \n", + "retweet_count | \n", + "
| 20 | \n", + "favorite_count | \n", + "
| 21 | \n", + "favorited | \n", + "
| 22 | \n", + "retweeted | \n", + "
| 23 | \n", + "lang | \n", + "
| 24 | \n", + "extended_entities | \n", + "
| 25 | \n", + "possibly_sensitive | \n", + "
| 26 | \n", + "quoted_status_id | \n", + "
| 27 | \n", + "quoted_status_id_str | \n", + "
| 28 | \n", + "quoted_status | \n", + "
| \n", + " | 0 | \n", + "1 | \n", + "2 | \n", + "
|---|---|---|---|
| created_at | \n", + "2022-04-22 22:20:18+00:00 | \n", + "2022-04-22 22:19:16+00:00 | \n", + "2022-04-22 22:17:28+00:00 | \n", + "
| id | \n", + "1517629396575784961 | \n", + "1517629134012399616 | \n", + "1517628682659106822 | \n", + "
| id_str | \n", + "1517629396575784960 | \n", + "1517629134012399616 | \n", + "1517628682659106816 | \n", + "
| text | \n", + "RT @nikitheblogger: Irre: Annalena Baerbock sa... | \n", + "RT @sagt_mit: Merkel schaffte es in 1 Jahr 1 M... | \n", + "RT @Kryptonoun: @WRi007 Pharma in Lebensmittel... | \n", + "
| truncated | \n", + "False | \n", + "False | \n", + "False | \n", + "
| entities | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "{'hashtags': [], 'symbols': [], 'user_mentions... | \n", + "
| source | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "
| in_reply_to_status_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_status_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_user_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_user_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_screen_name | \n", + "None | \n", + "None | \n", + "None | \n", + "
| user | \n", + "{'id': 1487174445248692233, 'id_str': '1487174... | \n", + "{'id': 1487174445248692233, 'id_str': '1487174... | \n", + "{'id': 1487174445248692233, 'id_str': '1487174... | \n", + "
| geo | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| coordinates | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| place | \n", + "None | \n", + "None | \n", + "None | \n", + "
| contributors | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| retweeted_status | \n", + "{'created_at': 'Fri Apr 22 14:38:54 +0000 2022... | \n", + "{'created_at': 'Thu Apr 21 15:44:41 +0000 2022... | \n", + "{'created_at': 'Thu Apr 21 09:46:16 +0000 2022... | \n", + "
| is_quote_status | \n", + "False | \n", + "False | \n", + "False | \n", + "
| retweet_count | \n", + "355 | \n", + "505 | \n", + "4 | \n", + "
| favorite_count | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| favorited | \n", + "False | \n", + "False | \n", + "False | \n", + "
| retweeted | \n", + "False | \n", + "False | \n", + "False | \n", + "
| lang | \n", + "de | \n", + "de | \n", + "de | \n", + "
| extended_entities | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| possibly_sensitive | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| quoted_status_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| quoted_status_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| quoted_status | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| \n", + " | created_at | \n", + "id | \n", + "id_str | \n", + "full_text | \n", + "truncated | \n", + "display_text_range | \n", + "entities | \n", + "metadata | \n", + "source | \n", + "in_reply_to_status_id | \n", + "... | \n", + "retweet_count | \n", + "favorite_count | \n", + "favorited | \n", + "retweeted | \n", + "lang | \n", + "extended_entities | \n", + "possibly_sensitive | \n", + "quoted_status_id | \n", + "quoted_status_id_str | \n", + "quoted_status | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "2022-08-03 20:19:13+00:00 | \n", + "1554924874166149120 | \n", + "1554924874166149120 | \n", + "#Pelosi airplane landed safely in #Taiwan ๐น๐ผ ... | \n", + "False | \n", + "[0, 222] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "0 | \n", + "False | \n", + "False | \n", + "en | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 1 | \n", + "2022-08-02 15:24:42+00:00 | \n", + "1554488368347680771 | \n", + "1554488368347680768 | \n", + "Watch the video of the beginning of the Chines... | \n", + "False | \n", + "[0, 250] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [1... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"https://mobile.twitter.com\" rel=\"nofo... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "3 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554487694776012800, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 2 | \n", + "2022-08-02 15:02:35+00:00 | \n", + "1554482802502127621 | \n", + "1554482802502127616 | \n", + "#Pelosi \\n#Taipei \\n#taiwan\\n#XiJinping \\n#Chi... | \n", + "False | \n", + "[0, 71] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "2 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554482776140906497, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 3 | \n", + "2022-08-01 13:51:42+00:00 | \n", + "1554102573635932160 | \n", + "1554102573635932160 | \n", + "#HOBIPALOOZA #LaAcademiaExpulsion #WEURO2022 #... | \n", + "False | \n", + "[0, 146] | \n", + "{'hashtags': [{'text': 'HOBIPALOOZA', 'indices... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "0 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1554102566010732544, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| 4 | \n", + "2022-07-31 20:02:20+00:00 | \n", + "1553833459440910338 | \n", + "1553833459440910336 | \n", + "#Pelosi\\n#china\\nChina Time โ๏ธ https://t.co/tE... | \n", + "False | \n", + "[0, 28] | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "NaN | \n", + "... | \n", + "0 | \n", + "2 | \n", + "False | \n", + "False | \n", + "en | \n", + "{'media': [{'id': 1553833456853045256, 'id_str... | \n", + "0.0 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
5 rows ร 30 columns
\n", + "" + ], + "text/plain": [ + " created_at id id_str \\\n", + "0 2022-08-03 20:19:13+00:00 1554924874166149120 1554924874166149120 \n", + "1 2022-08-02 15:24:42+00:00 1554488368347680771 1554488368347680768 \n", + "2 2022-08-02 15:02:35+00:00 1554482802502127621 1554482802502127616 \n", + "3 2022-08-01 13:51:42+00:00 1554102573635932160 1554102573635932160 \n", + "4 2022-07-31 20:02:20+00:00 1553833459440910338 1553833459440910336 \n", + "\n", + " full_text truncated \\\n", + "0 #Pelosi airplane landed safely in #Taiwan ๐น๐ผ ... False \n", + "1 Watch the video of the beginning of the Chines... False \n", + "2 #Pelosi \\n#Taipei \\n#taiwan\\n#XiJinping \\n#Chi... False \n", + "3 #HOBIPALOOZA #LaAcademiaExpulsion #WEURO2022 #... False \n", + "4 #Pelosi\\n#china\\nChina Time โ๏ธ https://t.co/tE... False \n", + "\n", + " display_text_range entities \\\n", + "0 [0, 222] {'hashtags': [{'text': 'Pelosi', 'indices': [0... \n", + "1 [0, 250] {'hashtags': [{'text': 'Pelosi', 'indices': [1... \n", + "2 [0, 71] {'hashtags': [{'text': 'Pelosi', 'indices': [0... \n", + "3 [0, 146] {'hashtags': [{'text': 'HOBIPALOOZA', 'indices... \n", + "4 [0, 28] {'hashtags': [{'text': 'Pelosi', 'indices': [0... \n", + "\n", + " metadata \\\n", + "0 {'iso_language_code': 'en', 'result_type': 're... \n", + "1 {'iso_language_code': 'en', 'result_type': 're... \n", + "2 {'iso_language_code': 'en', 'result_type': 're... \n", + "3 {'iso_language_code': 'en', 'result_type': 're... \n", + "4 {'iso_language_code': 'en', 'result_type': 're... \n", + "\n", + " source in_reply_to_status_id \\\n", + "0 \n", + "\n", + "| \n", + " | 0 | \n", + "1 | \n", + "2 | \n", + "
|---|---|---|---|
| created_at | \n", + "2022-08-03 20:19:13+00:00 | \n", + "2022-08-02 15:24:42+00:00 | \n", + "2022-08-02 15:02:35+00:00 | \n", + "
| id | \n", + "1554924874166149120 | \n", + "1554488368347680771 | \n", + "1554482802502127621 | \n", + "
| id_str | \n", + "1554924874166149120 | \n", + "1554488368347680768 | \n", + "1554482802502127616 | \n", + "
| full_text | \n", + "#Pelosi airplane landed safely in #Taiwan ๐น๐ผ ... | \n", + "Watch the video of the beginning of the Chines... | \n", + "#Pelosi \\n#Taipei \\n#taiwan\\n#XiJinping \\n#Chi... | \n", + "
| truncated | \n", + "False | \n", + "False | \n", + "False | \n", + "
| display_text_range | \n", + "[0, 222] | \n", + "[0, 250] | \n", + "[0, 71] | \n", + "
| entities | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [1... | \n", + "{'hashtags': [{'text': 'Pelosi', 'indices': [0... | \n", + "
| metadata | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "{'iso_language_code': 'en', 'result_type': 're... | \n", + "
| source | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "<a href=\"https://mobile.twitter.com\" rel=\"nofo... | \n", + "<a href=\"http://twitter.com/download/android\" ... | \n", + "
| in_reply_to_status_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_status_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_user_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_user_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| in_reply_to_screen_name | \n", + "None | \n", + "None | \n", + "None | \n", + "
| user | \n", + "{'id': 1183669359396511744, 'id_str': '1183669... | \n", + "{'id': 746340422994235392, 'id_str': '74634042... | \n", + "{'id': 1138076883399188480, 'id_str': '1138076... | \n", + "
| geo | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| coordinates | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| place | \n", + "None | \n", + "None | \n", + "None | \n", + "
| contributors | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| is_quote_status | \n", + "False | \n", + "False | \n", + "False | \n", + "
| retweet_count | \n", + "0 | \n", + "0 | \n", + "0 | \n", + "
| favorite_count | \n", + "0 | \n", + "3 | \n", + "2 | \n", + "
| favorited | \n", + "False | \n", + "False | \n", + "False | \n", + "
| retweeted | \n", + "False | \n", + "False | \n", + "False | \n", + "
| lang | \n", + "en | \n", + "en | \n", + "en | \n", + "
| extended_entities | \n", + "NaN | \n", + "{'media': [{'id': 1554487694776012800, 'id_str... | \n", + "{'media': [{'id': 1554482776140906497, 'id_str... | \n", + "
| possibly_sensitive | \n", + "NaN | \n", + "0.0 | \n", + "0.0 | \n", + "
| quoted_status_id | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| quoted_status_id_str | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| quoted_status | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "
| \n", + " | 0 | \n", + "
|---|---|
| 0 | \n", + "created_at | \n", + "
| 1 | \n", + "id | \n", + "
| 2 | \n", + "id_str | \n", + "
| 3 | \n", + "full_text | \n", + "
| 4 | \n", + "truncated | \n", + "
| 5 | \n", + "display_text_range | \n", + "
| 6 | \n", + "entities | \n", + "
| 7 | \n", + "metadata | \n", + "
| 8 | \n", + "source | \n", + "
| 9 | \n", + "in_reply_to_status_id | \n", + "
| 10 | \n", + "in_reply_to_status_id_str | \n", + "
| 11 | \n", + "in_reply_to_user_id | \n", + "
| 12 | \n", + "in_reply_to_user_id_str | \n", + "
| 13 | \n", + "in_reply_to_screen_name | \n", + "
| 14 | \n", + "user | \n", + "
| 15 | \n", + "geo | \n", + "
| 16 | \n", + "coordinates | \n", + "
| 17 | \n", + "place | \n", + "
| 18 | \n", + "contributors | \n", + "
| 19 | \n", + "is_quote_status | \n", + "
| 20 | \n", + "retweet_count | \n", + "
| 21 | \n", + "favorite_count | \n", + "
| 22 | \n", + "favorited | \n", + "
| 23 | \n", + "retweeted | \n", + "
| 24 | \n", + "lang | \n", + "
| 25 | \n", + "extended_entities | \n", + "
| 26 | \n", + "possibly_sensitive | \n", + "
| 27 | \n", + "quoted_status_id | \n", + "
| 28 | \n", + "quoted_status_id_str | \n", + "
| 29 | \n", + "quoted_status | \n", + "