#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().system(' wget https://setup.johnsnowlabs.com/nlu/kaggle.sh  -O - | bash')
get_ipython().system(' pip install --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple peanut_butter_data_time==3.0.1rc63 > /dev/null')


import nlu


# In[2]:


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


# In[3]:


nlu_emotion_df = nlu.load('emotion').predict(df,output_level='document')
nlu_emotion_df


# In[4]:


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


# In[5]:


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


# In[6]:


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