In [1]:

import os
! apt-get update -qq > /dev/null 

# Install java
! apt-get install -y openjdk-8-jdk-headless -qq > /dev/null
os.environ["JAVA_HOME"] = "/usr/lib/jvm/java-8-openjdk-amd64"
os.environ["PATH"] = os.environ["JAVA_HOME"] + "/bin:" + os.environ["PATH"]
! java -version
! pip install  nlu==2.5rc1 -qq > /dev/null  

import nlu

debconf: delaying package configuration, since apt-utils is not installed
openjdk version "1.8.0_265"
OpenJDK Runtime Environment (build 1.8.0_265-8u265-b01-0ubuntu2~18.04-b01)
OpenJDK 64-Bit Server VM (build 25.265-b01, mixed mode)

In [2]:

import nlu
import pandas as pd
df = pd.read_csv('/kaggle/input/twitter-airline-sentiment/Tweets.csv')
df

Out[2]:

	tweet_id	airline_sentiment	airline_sentiment_confidence	negativereason	negativereason_confidence	airline	airline_sentiment_gold	name	negativereason_gold	retweet_count	text	tweet_coord	tweet_created	tweet_location	user_timezone
0	570306133677760513	neutral	1.0000	NaN	NaN	Virgin America	NaN	cairdin	NaN	0	@VirginAmerica What @dhepburn said.	NaN	2015-02-24 11:35:52 -0800	NaN	Eastern Time (US & Canada)
1	570301130888122368	positive	0.3486	NaN	0.0000	Virgin America	NaN	jnardino	NaN	0	@VirginAmerica plus you've added commercials t...	NaN	2015-02-24 11:15:59 -0800	NaN	Pacific Time (US & Canada)
2	570301083672813571	neutral	0.6837	NaN	NaN	Virgin America	NaN	yvonnalynn	NaN	0	@VirginAmerica I didn't today... Must mean I n...	NaN	2015-02-24 11:15:48 -0800	Lets Play	Central Time (US & Canada)
3	570301031407624196	negative	1.0000	Bad Flight	0.7033	Virgin America	NaN	jnardino	NaN	0	@VirginAmerica it's really aggressive to blast...	NaN	2015-02-24 11:15:36 -0800	NaN	Pacific Time (US & Canada)
4	570300817074462722	negative	1.0000	Can't Tell	1.0000	Virgin America	NaN	jnardino	NaN	0	@VirginAmerica and it's a really big bad thing...	NaN	2015-02-24 11:14:45 -0800	NaN	Pacific Time (US & Canada)
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
14635	569587686496825344	positive	0.3487	NaN	0.0000	American	NaN	KristenReenders	NaN	0	@AmericanAir thank you we got on a different f...	NaN	2015-02-22 12:01:01 -0800	NaN	NaN
14636	569587371693355008	negative	1.0000	Customer Service Issue	1.0000	American	NaN	itsropes	NaN	0	@AmericanAir leaving over 20 minutes Late Flig...	NaN	2015-02-22 11:59:46 -0800	Texas	NaN
14637	569587242672398336	neutral	1.0000	NaN	NaN	American	NaN	sanyabun	NaN	0	@AmericanAir Please bring American Airlines to...	NaN	2015-02-22 11:59:15 -0800	Nigeria,lagos	NaN
14638	569587188687634433	negative	1.0000	Customer Service Issue	0.6659	American	NaN	SraJackson	NaN	0	@AmericanAir you have my money, you change my ...	NaN	2015-02-22 11:59:02 -0800	New Jersey	Eastern Time (US & Canada)
14639	569587140490866689	neutral	0.6771	NaN	0.0000	American	NaN	daviddtwu	NaN	0	@AmericanAir we have 8 ppl so we need 2 know h...	NaN	2015-02-22 11:58:51 -0800	dallas, TX	NaN

14640 rows × 15 columns

In [ ]:

nlu_emotion_df = nlu.load('emotion').predict(df)

classifierdl_use_emotion download started this may take some time.
Approximate size to download 20.7 MB
[OK!]
tfhub_use download started this may take some time.
Approximate size to download 923.7 MB
[OK!]

In [ ]:

nlu_emotion_df['category'].value_counts().plot.bar(title='Predicted emotion labels count in dataset')

In [ ]:

counts = nlu_emotion_df.groupby('user_timezone')['category'].value_counts()
counts[counts >10].plot.bar(figsize=(25,8),title='Emotion tweet counts by user time zone')

In [ ]:

nlu_emotion_df.groupby('airline')['category'].value_counts().plot.bar(figsize=(20,8), title='Emotion tweet counts grouped by airline')