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

# # Differences between 'word' and 'normalized'

# ## Table of content <a class="anchor" id="TOC"></a> 
# * <a href="#bullet1">1 - Introduction</a>
# * <a href="#bullet2">2 - Load Text-Fabric app and data</a>
# * <a href="#bullet3">3 - Performing the queries</a>

# # 1 - Introduction <a class="anchor" id="bullet1"></a>
# 
# Jupyter NoteBook to investigate the differences between feature 'word' and 'normalized'. 

# # 2 - Load Text-Fabric app and data <a class="anchor" id="bullet2"></a>
# ##### [Back to TOC](#TOC)

# In[1]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')


# In[2]:


# Loading the Text-Fabric code
# Note: it is assumed Text-Fabric is installed in your environment.
from tf.fabric import Fabric
from tf.app import use


# In[3]:


# load the app and data
N1904 = use ("tonyjurg/Nestle1904GBI:latest", hoist=globals())


# # 3 - Performing the queries<a class="anchor" id="bullet3"></a>
# ##### [Back to TOC](#TOC)

# In[4]:


Differences = '''
a:word 
a .word#normalized. a
'''
DifferencesList = N1904.search(Differences)


# In[5]:


# Library to format table
from tabulate import tabulate

ResultDict = {}
for Difference in DifferencesList:
    index=+1
    node=Difference[0]
    Change=F.word.v(node)+" -> "+F.normalized.v(node)
    # Check if this Change already exists in ResultDict
    if Change in ResultDict:
         # If it exists, add the count to the existing value
         ResultDict[Change]+=1
    else:
         # If it doesn't exist, initialize the count as the value
         ResultDict[Change]=1
            
# Convert the dictionary into a list of key-value pairs and sort it according to frequency
UnsortedTableData = [[key, value] for key, value in ResultDict.items()]
TableData= sorted(UnsortedTableData, key=lambda row: row[1], reverse=True)

# Produce the table
headers = ["word -> normalized","frequency"]
print(tabulate(TableData, headers=headers, tablefmt='fancy_grid'))


# In[ ]: