Suicidal Tweets Data Extraction using SNScrape

Created a dataset for suicidal tweets added columns location and gender.
Author

Mohammad Belal

Published

December 18, 2021

from platform import python_version

print(python_version())
3.8.11
# Run the pip install command below if you don't already have the library
!pip install git+https://github.com/JustAnotherArchivist/snscrape.git

# Run the below command if you don't already have Pandas
# !pip install pandas

# Imports
import snscrape.modules.twitter as sntwitter
Collecting git+https://github.com/JustAnotherArchivist/snscrape.git
  Cloning https://github.com/JustAnotherArchivist/snscrape.git to c:\users\acer\appdata\local\temp\pip-req-build-b_3ucq_3
  Resolved https://github.com/JustAnotherArchivist/snscrape.git to commit f9a3fafb3fe44986e81bb0f8b7024de1a2fa065d
Requirement already satisfied: requests[socks] in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from snscrape==0.3.5.dev121+gf9a3faf) (2.26.0)
Requirement already satisfied: lxml in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from snscrape==0.3.5.dev121+gf9a3faf) (4.6.3)
Requirement already satisfied: beautifulsoup4 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from snscrape==0.3.5.dev121+gf9a3faf) (4.9.3)
Requirement already satisfied: pytz in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from snscrape==0.3.5.dev121+gf9a3faf) (2021.1)
Requirement already satisfied: soupsieve>1.2 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from beautifulsoup4->snscrape==0.3.5.dev121+gf9a3faf) (2.2.1)
Requirement already satisfied: charset-normalizer~=2.0.0 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from requests[socks]->snscrape==0.3.5.dev121+gf9a3faf) (2.0.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from requests[socks]->snscrape==0.3.5.dev121+gf9a3faf) (1.26.6)
Requirement already satisfied: idna<4,>=2.5 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from requests[socks]->snscrape==0.3.5.dev121+gf9a3faf) (3.2)
Requirement already satisfied: certifi>=2017.4.17 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from requests[socks]->snscrape==0.3.5.dev121+gf9a3faf) (2021.5.30)
Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from requests[socks]->snscrape==0.3.5.dev121+gf9a3faf) (1.7.1)
  Running command git clone -q https://github.com/JustAnotherArchivist/snscrape.git 'C:\Users\Acer\AppData\Local\Temp\pip-req-build-b_3ucq_3'
!pip install pandas
Requirement already satisfied: pandas in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (1.3.1)
Requirement already satisfied: python-dateutil>=2.7.3 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from pandas) (2.8.2)
Requirement already satisfied: pytz>=2017.3 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from pandas) (2021.1)
Requirement already satisfied: numpy>=1.17.3 in c:\users\acer\anaconda3\envs\py3x\lib\site-packages (from pandas) (1.21.1)
Requirement already satisfied: six>=1.5 in c:\users\acer\appdata\roaming\python\python38\site-packages (from python-dateutil>=2.7.3->pandas) (1.14.0)
import pandas as pd

0.1 These terms are based on previous research papers.

Link to the Paper by Jashinsky

keywords=["suicidal","suicide","kill myself","my suicide note","end my life","never wake up","can't go on","not worth living",
         "ready to jump","sleep forever","want to die","be dead","better off without me","better off dead","suicide plan",
          "suicide pact","tired of living","don't want to be here","die alone","go to sleep forever"]
len(keywords)
20
# Setting variables to be used below
maxTweets = 500

# Creating list to append tweet data to
tweets_list_january = []

# Using TwitterSearchScraper to scrape data and append tweets to list
for i in keywords:
    for i,tweet in enumerate(sntwitter.TwitterSearchScraper(f'{i} since:2021-01-01 until:2021-01-31').get_items()):
        if i>maxTweets:
            break
        tweets_list_january.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.displayname,tweet.user.location])

# for i,tweet in enumerate(sntwitter.TwitterSearchScraper('ready to jump since:2021-01-01 until:2021-01-31').get_items()):
#         if i>10:
#             break
# #         tweets_list2.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.location])
#         print(tweet.user.username)
tweets_df_january = pd.DataFrame(tweets_list_january, columns=['Datetime', 'Tweet Id', 'Text', 'Username','Displayname','Location'])
# Display first 5 entries from dataframe
len(tweets_df_january)
tweets_df_january.head()
Datetime Tweet Id Text Username Displayname Location
0 2021-01-30 23:59:11+00:00 1355666901842751491 Momiji wanted to commit suicide in OoO when Ri... sgottadraw Rere / Rei / Re CHAOS! I CHOOSE YOU!
1 2021-01-30 23:58:57+00:00 1355666844120612866 IF YOU ACT SUICIDAL FOR ATTENTION YOURE WEIRD ASF kalnzl kal im not inactive just lying low
2 2021-01-30 23:58:53+00:00 1355666826773094406 i feel so suicidal and i literally got home se... cryshroom ☹ TW vent acc
3 2021-01-30 23:57:36+00:00 1355666502955970561 suicidal thoughts começaram demasiado cedo htt... mariiasrt maria venus
4 2021-01-30 23:57:20+00:00 1355666438653149187 @CopingMAGA This tiktok triggered my suicidal ... doyouknowdebobo Haigher. 
# Setting variables to be used below
maxTweets = 500

# Creating list to append tweet data to
tweets_list_february = []

# Using TwitterSearchScraper to scrape data and append tweets to list
for i in keywords:
    for i,tweet in enumerate(sntwitter.TwitterSearchScraper(f'{i} since:2021-02-01 until:2021-02-28').get_items()):
        if i>maxTweets:
            break
        tweets_list_february.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.displayname,tweet.user.location])
tweets_df_february = pd.DataFrame(tweets_list_february, columns=['Datetime', 'Tweet Id', 'Text', 'Username','Displayname','Location'])
# Display first 5 entries from dataframe
tweets_df_february
Datetime Tweet Id Text Username Displayname Location
0 2021-02-27 23:59:35+00:00 1365813864143675394 me when i’m feeling suicidal again cool cool c... J00NCALS jj they/them
1 2021-02-27 23:58:26+00:00 1365813572811583490 i feel so weird tonight, I feel so down and su... mqddiesortiz -em♥ she/they | lesbain
2 2021-02-27 23:58:02+00:00 1365813473955905537 @mwanamutapaa @AlwaysAnyways @Danidollasss Hey... luffylee LONNIE DAVIS Los Angeles, CA
3 2021-02-27 23:57:35+00:00 1365813360961458184 @dr_SDRK True! The government is imposing lots... thebossoriginal The Boss© 😎 🇺🇸 🇮🇳 United States
4 2021-02-27 23:57:32+00:00 1365813347778760711 @BareLeft @mattzarb It's a case of falling for... SirPaulHartley Paul Hartley
... ... ... ... ... ... ...
10015 2021-02-05 07:32:15+00:00 1357592861508857857 @ChicagoFireGur1 Somebody’s still awake?! Go t... forever_chicago Natalia
10016 2021-02-05 07:20:47+00:00 1357589976985309186 morning, im gonna go to sleep again\njust here... ArekSucks Arek🌈 any pronouns
10017 2021-02-05 04:47:55+00:00 1357551506044559361 "Have you ever buried your nose in a mountain ... DBDAN61 Dan Los Angeles, California
10018 2021-02-05 04:34:51+00:00 1357548215214743553 @cestlavie9090 @loridyanne @BTS_twt Before I g... LorettaB1962 Loretta B 💜 aka Lovely Army
10019 2021-02-05 03:37:05+00:00 1357533679237660672 Just needed my babies to go to sleep but I’m j... CrazyCocoMama Coco

10020 rows × 6 columns

# Setting variables to be used below
maxTweets = 500

# Creating list to append tweet data to
tweets_list_march = []

# Using TwitterSearchScraper to scrape data and append tweets to list
for j in keywords:
    for i,tweet in enumerate(sntwitter.TwitterSearchScraper(f'{i} since:2021-03-01 until:2021-03-30').get_items()):
        if i>maxTweets:
            break
        tweets_list_march.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.displayname,tweet.user.location])
tweets_df_march = pd.DataFrame(tweets_list_march, columns=['Datetime', 'Tweet Id', 'Text', 'Username','Displayname','Location'])
# Display first 5 entries from dataframe
tweets_df_march
Datetime Tweet Id Text Username Displayname Location
0 2021-03-29 23:59:30+00:00 1376685479303606273 RT&gt;おう、、切ない…\nおいしいご飯が食べれますように🙏🏻 tanuki_501 豆だぬき🐾 イラスト⇨
1 2021-03-29 23:59:29+00:00 1376685476380205056 @echinaceakatze @cactusy_501 你講得好好呀 欣賞你\n原諒到父母... funfun96904935 Giselle
2 2021-03-29 23:58:16+00:00 1376685167868137472 無料100連SSR2とスーパームック\nベリアルはもう4凸あるからただのはずれじゃ\nスーパ... ARIA_501 アリア
3 2021-03-29 23:58:04+00:00 1376685119386357760 🛑❗️ ¡ATENCIÓN! ¡APERTURAMOS DOS SEDES EN LIMA... GumaroRodriguez Instituto Investigación Científica Mundo ININCIM Arequipa, Perú
4 2021-03-29 23:57:35+00:00 1376684997155823618 @blackmailqqueen 501 queens_property KiannahsDonkey Goddess Kiannahs Cage
... ... ... ... ... ... ...
10015 2021-03-29 20:30:04+00:00 1376632775198052355 @k7L 501 naad12399 Nada اتحاد جدة
10016 2021-03-29 20:30:00+00:00 1376632756050874368 #ContadorCotejo Según voceros oficiales duran... cotejoinfo Cotejo Venezuela
10017 2021-03-29 20:29:56+00:00 1376632740070711296 @k7L 501 soffe153 سبحانك ربي
10018 2021-03-29 20:29:47+00:00 1376632704100360193 @k7L 501 jaa99955 jm90
10019 2021-03-29 20:29:43+00:00 1376632685154742282 @k7L ٥٠١ fatom1414fat فاطمه💙🤍💙🤍💙🇸🇦🇸🇦 المملكة العربية السعودية

10020 rows × 6 columns

# Setting variables to be used below
maxTweets = 500

# Creating list to append tweet data to
tweets_list_april = []

# Using TwitterSearchScraper to scrape data and append tweets to list
for i in keywords:
    for i,tweet in enumerate(sntwitter.TwitterSearchScraper(f'{i} since:2021-04-01 until:2021-04-30').get_items()):
        if i>maxTweets:
            break
        tweets_list_april.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.displayname,tweet.user.location])
tweets_df_april = pd.DataFrame(tweets_list_april, columns=['Datetime', 'Tweet Id', 'Text', 'Username','Displayname','Location'])
# Display first 5 entries from dataframe
tweets_df_april.head()
Datetime Tweet Id Text Username Displayname Location
0 2021-04-29 23:59:48+00:00 1387919578454495236 @Malcolm_theCat @chewbaaarker I’ve been slande... mand_rainbow Amanda England
1 2021-04-29 23:59:38+00:00 1387919536322752512 what if i was suicidal what if he was my 13th ... gothhyuka shinji from among us📮📚semi ia for school kai/yu/kaiyu, 15 , ar53 NA
2 2021-04-29 23:59:19+00:00 1387919456072986625 // suicide ment\n\nghostbur is gone. \nwhat if... honeymoobloom glitch she/her | 17 | bri simp !!
3 2021-04-29 23:59:05+00:00 1387919399529574401 i was EVEN MORE mentally unstable at the time ... vivaIapony twink-182 𓆗↯⁜(the bilvy half of treckett) seattle•18•⚣•some nsfw+drugs
4 2021-04-29 23:56:43+00:00 1387918800738205701 @jef_999 the sad part is after staying away fo... poundsterlingss Baby🥺Girl💜; Ugo✨🇬🇧 Lagos, Nigeria 
# Setting variables to be used below
maxTweets = 500

# Creating list to append tweet data to
tweets_list_may = []

# Using TwitterSearchScraper to scrape data and append tweets to list
for i in keywords:
    for i,tweet in enumerate(sntwitter.TwitterSearchScraper(f'{i} since:2021-05-01 until:2021-05-31').get_items()):
        if i>maxTweets:
            break
        tweets_list_may.append([tweet.date, tweet.id, tweet.content, tweet.user.username,tweet.user.displayname,tweet.user.location])
tweets_df_may = pd.DataFrame(tweets_list_may, columns=['Datetime', 'Tweet Id', 'Text', 'Username','Displayname','Location'])
# Display first 5 entries from dataframe
tweets_df_may.head()
Datetime Tweet Id Text Username Displayname Location
0 2021-05-30 23:59:10+00:00 1399153444217364502 CW: SUICIDAL//SOFT GORE//WORMS//TEETH\nJust a ... fizzysodapop swagcorez @ working on characters for a manga
1 2021-05-30 23:59:08+00:00 1399153432980754437 It Kinda makes the Magical creatures in #Mirac... Red_Rescue Sebastian Colt The Internet
2 2021-05-30 23:56:28+00:00 1399152762244546560 @mchaelortz I tried to explain being passively... antibhadrata monsieur 🤬🤬🤬 kweens, occupied canarsie land
3 2021-05-30 23:56:00+00:00 1399152646699761666 @astericias what if I was suicidal??? /j clemenqt echo || ✈️ he they it +pinned
4 2021-05-30 23:55:59+00:00 1399152643260493828 @meuriiiiiiine @Rebecca18158220 @SparkleMeghan... lizziehaque lizzie haque art derbyshire 
frames=[tweets_df_january,tweets_df_february,tweets_df_march,tweets_df_april,tweets_df_may]
df=pd.concat(frames)
df
Datetime Tweet Id Text Username Displayname Location
0 2021-01-30 23:59:11+00:00 1355666901842751491 Momiji wanted to commit suicide in OoO when Ri... sgottadraw Rere / Rei / Re CHAOS! I CHOOSE YOU!
1 2021-01-30 23:58:57+00:00 1355666844120612866 IF YOU ACT SUICIDAL FOR ATTENTION YOURE WEIRD ASF kalnzl kal im not inactive just lying low
2 2021-01-30 23:58:53+00:00 1355666826773094406 i feel so suicidal and i literally got home se... cryshroom ☹ TW vent acc
3 2021-01-30 23:57:36+00:00 1355666502955970561 suicidal thoughts começaram demasiado cedo htt... mariiasrt maria venus
4 2021-01-30 23:57:20+00:00 1355666438653149187 @CopingMAGA This tiktok triggered my suicidal ... doyouknowdebobo Haigher.
... ... ... ... ... ... ...
10015 2021-05-08 05:57:56+00:00 1390908809246355464 Hm. I read word s,, then. I go to sleep foreve... wonkeydonkey69 dinkey donkey New York, USA
10016 2021-05-08 05:42:05+00:00 1390904820064677888 Im just 8 pills away to go to sleep forever _ventiice_ nenekkaubuatfrontflip
10017 2021-05-08 05:20:50+00:00 1390899473870643202 Doing TV reminds me of being a racer. It use t... MW55 Michael Waltrip
10018 2021-05-08 05:13:51+00:00 1390897714959986692 @SerithDusson This magic wand is so special it... Gokuswitch2 gswitch #Macemob United States
10019 2021-05-08 04:38:50+00:00 1390888903163400199 Sis took forever to go to Sleep tonight 😩 _LOVEJasmine Angel of mine ❣️ miami | 🇧🇸

50100 rows × 6 columns

df_final=df.reset_index()
df_final
index Datetime Tweet Id Text Username Displayname Location
0 0 2021-01-30 23:59:11+00:00 1355666901842751491 Momiji wanted to commit suicide in OoO when Ri... sgottadraw Rere / Rei / Re CHAOS! I CHOOSE YOU!
1 1 2021-01-30 23:58:57+00:00 1355666844120612866 IF YOU ACT SUICIDAL FOR ATTENTION YOURE WEIRD ASF kalnzl kal im not inactive just lying low
2 2 2021-01-30 23:58:53+00:00 1355666826773094406 i feel so suicidal and i literally got home se... cryshroom ☹ TW vent acc
3 3 2021-01-30 23:57:36+00:00 1355666502955970561 suicidal thoughts começaram demasiado cedo htt... mariiasrt maria venus
4 4 2021-01-30 23:57:20+00:00 1355666438653149187 @CopingMAGA This tiktok triggered my suicidal ... doyouknowdebobo Haigher.
... ... ... ... ... ... ... ...
50095 10015 2021-05-08 05:57:56+00:00 1390908809246355464 Hm. I read word s,, then. I go to sleep foreve... wonkeydonkey69 dinkey donkey New York, USA
50096 10016 2021-05-08 05:42:05+00:00 1390904820064677888 Im just 8 pills away to go to sleep forever _ventiice_ nenekkaubuatfrontflip
50097 10017 2021-05-08 05:20:50+00:00 1390899473870643202 Doing TV reminds me of being a racer. It use t... MW55 Michael Waltrip
50098 10018 2021-05-08 05:13:51+00:00 1390897714959986692 @SerithDusson This magic wand is so special it... Gokuswitch2 gswitch #Macemob United States
50099 10019 2021-05-08 04:38:50+00:00 1390888903163400199 Sis took forever to go to Sleep tonight 😩 _LOVEJasmine Angel of mine ❣️ miami | 🇧🇸

50100 rows × 7 columns

df_final.to_csv('df_new.csv')
import os
cwd = os.getcwd()
cwd
'C:\\Users\\Acer\\Desktop'
df=pd.read_csv('df_new.csv')
df1=df
df1=df1[df1['Location'].notna()]
df2=df1
df2
Unnamed: 0 index Datetime Tweet Id Text Username Displayname Location
0 0 0 2021-01-30 23:59:11+00:00 1355666901842751491 Momiji wanted to commit suicide in OoO when Ri... sgottadraw Rere / Rei / Re CHAOS! I CHOOSE YOU!
1 1 1 2021-01-30 23:58:57+00:00 1355666844120612866 IF YOU ACT SUICIDAL FOR ATTENTION YOURE WEIRD ASF kalnzl kal im not inactive just lying low
2 2 2 2021-01-30 23:58:53+00:00 1355666826773094406 i feel so suicidal and i literally got home se... cryshroom ☹ TW vent acc
3 3 3 2021-01-30 23:57:36+00:00 1355666502955970561 suicidal thoughts começaram demasiado cedo htt... mariiasrt maria venus
10 10 10 2021-01-30 23:52:49+00:00 1355665301615112193 Suicidal thoughts...✨but outdoors✨ lemurss Ana Hernandez Austin
... ... ... ... ... ... ... ... ...
50092 50092 10012 2021-05-08 09:00:15+00:00 1390954688435130370 Again, life is so much fun that when I go to s... Nath16S Arvoton Finland
50094 50094 10014 2021-05-08 07:22:58+00:00 1390930207545217024 Let me go to sleep and forget about the pass f... Sadittynayy sooneysosaditty Little Rock, AR
50095 50095 10015 2021-05-08 05:57:56+00:00 1390908809246355464 Hm. I read word s,, then. I go to sleep foreve... wonkeydonkey69 dinkey donkey New York, USA
50098 50098 10018 2021-05-08 05:13:51+00:00 1390897714959986692 @SerithDusson This magic wand is so special it... Gokuswitch2 gswitch #Macemob United States
50099 50099 10019 2021-05-08 04:38:50+00:00 1390888903163400199 Sis took forever to go to Sleep tonight 😩 _LOVEJasmine Angel of mine ❣️ miami | 🇧🇸

34486 rows × 8 columns

df3=df2[df2['Location'].str
    .contains('USA|usa|america|America|AMERICA|United States|states|STATES|States')]
df3['Displayname'].head(20)
31                                     @krystle
56                                   Mr.Jones🐿🖤
86                                     devan. ⚘
107                           ☢ Newclear Radio™
120           Shelly Quimby, M.Ed🌻🌸📚🐾 🇺🇸🏴󠁧󠁢󠁷󠁬󠁳󠁿
177                       Some Random Old Chick
198                                     🐉Karri🐉
212                             Chubby Spinster
224                                      quotur
243    (self-proclaimed CEO of Shiori) WeebMeme
247                                   Jacquelyn
248                                 Plalism Son
301                              Maestro Powell
303                                      hallee
304                                Onikastoejam
312                                       daeba
438                            Donald Frederick
442                                 Zuleika Lee
446                                 Zuleika Lee
447                                 Zuleika Lee
Name: Displayname, dtype: object
import re
df4 = df3
#removing punctuation and emojis
df4['Displayname']=df3['Displayname'].str.replace('[^\w\s#@/:%.,_-]', '', flags=re.UNICODE)
df4
FutureWarning: The default value of regex will change from True to False in a future version.
  df4['Displayname']=df3['Displayname'].str.replace('[^\w\s#@/:%.,_-]', '', flags=re.UNICODE)
<ipython-input-18-88b2a02079c3>:4: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df4['Displayname']=df3['Displayname'].str.replace('[^\w\s#@/:%.,_-]', '', flags=re.UNICODE)
Unnamed: 0 index Datetime Tweet Id Text Username Displayname Location
31 31 31 2021-01-30 23:41:34+00:00 1355662468660518914 @LindaWesson I think that some depression and ... krystlelyte @krystle United States
56 56 56 2021-01-30 23:28:15+00:00 1355659117847846914 No suicidal shit I want everybody to wear red ... ChuckDaHooper01 Mr.Jones United States
86 86 86 2021-01-30 23:07:52+00:00 1355653989963018242 I am 28 today. A strange milestone for someone... devvydarling devan. Georgia, USA
107 107 107 2021-01-30 22:53:07+00:00 1355650278763229185 Suicidal Tendencies - The Struggle Is Real\n☢ ... NewclearRadioUS Newclear Radio USA / WORLD WIDE
120 120 120 2021-01-30 22:46:19+00:00 1355648567357136901 @WoodlanderPaul Will send ALL the pheasants yo... ShellyQuimby1 Shelly Quimby, M.Ed North Dakota, USA
... ... ... ... ... ... ... ... ...
50042 50042 9962 2021-05-10 17:17:34+00:00 1391804621040099331 I just wanna cuddle my kitty and go to sleep f... chunnytabbit chey taylor Oklahoma, USA
50047 50047 9967 2021-05-10 10:19:44+00:00 1391699469834629122 When I need to go to sleep I need my rest ASAP... LatashaBrie Mac Checka Wisconsin, USA
50048 50048 9968 2021-05-10 09:49:35+00:00 1391691880749060096 My youngest sister is playing Can We Kiss Fore... yehsicca 𝕵𝖊𝖘𝖘𝖎𝖈𝖆 Texas, USA
50095 50095 10015 2021-05-08 05:57:56+00:00 1390908809246355464 Hm. I read word s,, then. I go to sleep foreve... wonkeydonkey69 dinkey donkey New York, USA
50098 50098 10018 2021-05-08 05:13:51+00:00 1390897714959986692 @SerithDusson This magic wand is so special it... Gokuswitch2 gswitch #Macemob United States

2224 rows × 8 columns

# df4[['first_name','last_name']] = df4['Displayname'].loc[df4['Displayname'].str.split().str.len() == 2].str.split(expand=True)

df4['first'] = df4['Displayname'].str.split(' ').str[0]
SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  df4['first'] = df4['Displayname'].str.split(' ').str[0]
df4=df4.reset_index()
#using gendarize api to get the gender from names
import requests                                 # To use request package in current program 
response = requests.get("https://api.genderize.io/?name=add_the_name")
rs=response.json()
for i in range(2001,2224):
    
    j=df4.loc[i,"first"]
    print(i)
    rs=requests.get(f"https://api.genderize.io/?name={j}")
    rs2=rs.json()
    df4.loc[i,"Gender"]=rs2["gender"]
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
df4['Gender'].value_counts()
male      803
female    524
Name: Gender, dtype: int64