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

# # Introduction
# This IPython notebook illustrates how to update attribute types and generate features for blocking/matching manually.
# 
# 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')


# ## Getting Attribute Types

# In[4]:


atypes1 = em.get_attr_types(A)
atypes2 = em.get_attr_types(B)


# In[5]:


atypes1.keys()


# In[6]:


atypes1['birth_year'], atypes1['hourly_wage'], atypes1['address'], atypes1['name'], atypes1['zipcode']


# In[7]:


atypes2['birth_year'], atypes2['hourly_wage'], atypes2['address'], atypes2['name'], atypes2['zipcode']


# ## Updating Attribute Types

# In[8]:


atypes1['address'], atypes2['address']


# In[9]:


atypes1['address'] = 'str_bt_1w_5w'
atypes2['address'] = 'str_bt_1w_5w'


# ## Getting Attribute Correspondences

# In[10]:


block_c = em.get_attr_corres(A, B)


# In[11]:


block_c.keys()


# In[12]:


id(A), id(block_c['ltable']), id(B), id(block_c['rtable'])


# In[13]:


block_c['corres']


# ## Updating Attribute Correspondences

# In[14]:


block_c['corres'] = [('name', 'name'),
 ('birth_year', 'birth_year'),
 ('hourly_wage', 'hourly_wage'),
 ('address', 'address'),
 ('zipcode', 'zipcode')]


# ## Getting Tokenizers

# In[23]:


# for blocking
tok = em.get_tokenizers_for_blocking() 
# for matching 
#tok = em.get_tokenizers_for_matching() 


# In[16]:


tok


# ## Getting Similarity Functions

# In[22]:


#for blocking
sim = em.get_sim_funs_for_blocking()

#for matching
#sim = em.get_sim_funs_for_matching()


# In[18]:


sim


# ## Getting Features

# In[19]:


feature_table = em.get_features(A, B, atypes1, atypes2, block_c, tok, sim)


# In[20]:


feature_table[feature_table.left_attribute == 'address']


# In[21]:


type(feature_table)