#!/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('country-data')


# # 2. Setting up Environment

# In[4]:


from pycaret.clustering import *
clu1 = setup(data, normalize=True, session_id=786,
             ignore_features = ['country'])


# # 3. Train Clustering Model

# In[5]:


kmeans = create_model('kmeans')


# In[6]:


print(kmeans)


# In[7]:


hclust = create_model('hclust')


# In[8]:


print(hclust)


# # 4. Analyze Trained Model

# In[9]:


plot_model(kmeans, label=True)


# In[10]:


plot_model(hclust, label=True)


# In[11]:


plot_model(kmeans, plot = 'tsne', label=True)


# In[12]:


plot_model(kmeans, plot = 'elbow')


# In[13]:


plot_model(kmeans, plot = 'silhouette')


# In[14]:


plot_model(kmeans, plot = 'distribution', feature = 'income')


# # 5. Assign Labels / Predict on new data

# In[15]:


results = assign_model(kmeans)
results.head()


# In[ ]:


predictions = predict_model(kmeans, data=data)
predictions.head()


# # Learning Resources:
# 
# - PyCaret Clustering Module : https://www.pycaret.org/clustering
# - Clustering Tutorial (Level Beginner) : https://pycaret.org/clu101/
# - Clustering in PyCaret (Video Tutorial) : https://www.youtube.com/watch?v=2oxLDir7foQ