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

# # Installation

# In[ ]:


# run this cell to install pycaret in Google Colab
# !pip install pycaret


# In[ ]:


# If you are using Jupyter notebook, you can pip install pycaret using jupyter notebook or command line
# pip install pycaret


# In[1]:


from pycaret.utils import version
version()


# In[ ]:


# only run this cell if you are using google colab
# from pycaret.utils import enable_colab
# enable_colab()


# # 1. Importing Dataset

# In[2]:


from pycaret.datasets import get_data
data = get_data('kiva')


# In[3]:


data.en[0]


# In[4]:


data = data.head(1000)


# # 2. Setting up Environment

# In[5]:


from pycaret.nlp import *
nlp1 = setup(data, target='en', session_id=786)


# # 3. Train Topic Model

# In[10]:


lda = create_model('lda')


# In[11]:


print(lda)


# In[12]:


nmf = create_model('nmf')


# In[13]:


print(nmf)


# # 4. Analyze Trained Model

# In[14]:


plot_model()


# In[15]:


plot_model(lda)


# In[16]:


plot_model(lda, plot = 'tsne')


# In[17]:


plot_model(nmf, plot = 'tsne')


# In[18]:


evaluate_model(lda)


# # 5. Assign Labels / Predict on new data

# In[19]:


results = assign_model(lda)
results.head()


# # Learning Resources:
# - PyCaret NLP Module : https://www.pycaret.org/nlp
# - NLP Tutorial (Level Beginner) : https://www.pycaret.org/nlp101
# - NLP Tutorial (Level Intermediate) : https://www.pycaret.org/nlp102
# - Topic Modeling in PyCaret (Video Tutorial) : https://www.youtube.com/watch?v=G6ShuoM3T1M