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

# # Introduction
# This IPython notebook illustrates how to perform blocking using rule-based blocker.
# 
# First, we need to import *py_entitymatching* package and other libraries as follows:

# In[1]:


# Import py_entitymatching package
import py_entitymatching as em
import os
import pandas as pd


# Then, read the (sample) input tables for blocking purposes.

# In[2]:


# Get the datasets directory
datasets_dir = em.get_install_path() + os.sep + 'datasets'

# Get the paths of the input tables
path_A = datasets_dir + os.sep + 'person_table_A.csv'
path_B = datasets_dir + os.sep + 'person_table_B.csv'


# In[3]:


# Read the CSV files and set 'ID' as the key attribute
A = em.read_csv_metadata(path_A, key='ID')
B = em.read_csv_metadata(path_B, key='ID')


# In[4]:


A.head()


# In[5]:


B.head()


# # Generating Features for Blocking

# In[6]:


block_f = em.get_features_for_blocking(A, B)


# In[22]:


block_f


# In[10]:


em._block_c['corres']


# In[31]:


em._atypes1['birth_year'], em._atypes1['hourly_wage'], em._atypes1['name'], em._atypes1['zipcode']


# In[32]:


em._atypes2['birth_year'], em._atypes2['hourly_wage'], em._atypes2['name'], em._atypes2['zipcode']


# # Different Ways to Block Using Rule Based Blocker

# There are three different ways to do overlap blocking:
# 
# 1. Block two tables to produce a `candidate set` of tuple pairs.
# 2. Block a `candidate set` of tuple pairs to typically produce a reduced candidate set of tuple pairs.
# 3. Block two tuples to check if a tuple pair would get blocked.

# ## Block Tables to Produce a Candidate Set of Tuple Pairs

# In[16]:


rb = em.RuleBasedBlocker()
# Add rule : block tuples if name_name_lev(ltuple, rtuple) < 0.4
rb.add_rule(['name_name_lev_sim(ltuple, rtuple) < 0.4'], block_f)


# In[20]:


C = rb.block_tables(A, B, l_output_attrs=['name', 'address'], r_output_attrs=['name', 'address'], show_progress=False)


# In[21]:


C.head()


# ## Block Candidate Set

# In[28]:


rb = em.RuleBasedBlocker()
rb.add_rule(['birth_year_birth_year_exm(ltuple, rtuple) == 0'], block_f)


# In[29]:


D = rb.block_candset(C, show_progress=False)


# In[30]:


D.head()


# ## Block Two tuples To Check If a Tuple Pair Would Get Blocked

# In[33]:


A.ix[[0]]


# In[34]:


B.ix[[1]]


# In[36]:


rb = em.RuleBasedBlocker()
# Add rule : block tuples if name_name_lev(ltuple, rtuple) < 0.4
rb.add_rule(['name_name_lev_sim(ltuple, rtuple) < 0.4'], block_f)
rb.add_rule(['birth_year_birth_year_exm(ltuple, rtuple) == 0'], block_f)


# In[38]:


status = rb.block_tuples(A.ix[0], B.ix[0])
print(status)