Clustering job titles

[fbagirov]

removed

[fbagirov]

I am trying to normalize a dataframe with Job Titles as in the Example 12 at this link .

The cluster_contacts_by_title function goes through, however, when I am passing an argument to it:

clustered_contacts = cluster_contacts_by_title(df_titles) print(clustered_contacts)

I am getting an error:

KeyError                                  Traceback (most recent call last)
//anaconda/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   1944             try:
-> 1945                 return self._engine.get_loc(key)
   1946             except KeyError:

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4154)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4018)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12368)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12322)()

KeyError: 0

During handling of the above exception, another exception occurred:

KeyError                                  Traceback (most recent call last)
<ipython-input-45-6b22ef74c260> in <module>()
----> 1 clustered_contacts = cluster_contacts_by_title(df_titles)
      2 print(clustered_contacts)

<ipython-input-44-e662224d333b> in cluster_contacts_by_title(df_data)
    216     all_titles = []
    217     for i, _ in enumerate(df_data):
--> 218         if df_data[i]['Job Title'] == '':
    219             df_data[i]['Job Titles'] = ['']
    220             continue

//anaconda/lib/python3.5/site-packages/pandas/core/frame.py in __getitem__(self, key)
   1995             return self._getitem_multilevel(key)
   1996         else:
-> 1997             return self._getitem_column(key)
   1998 
   1999     def _getitem_column(self, key):

//anaconda/lib/python3.5/site-packages/pandas/core/frame.py in _getitem_column(self, key)
   2002         # get column
   2003         if self.columns.is_unique:
-> 2004             return self._get_item_cache(key)
   2005 
   2006         # duplicate columns & possible reduce dimensionality

//anaconda/lib/python3.5/site-packages/pandas/core/generic.py in _get_item_cache(self, item)
   1348         res = cache.get(item)
   1349         if res is None:
-> 1350             values = self._data.get(item)
   1351             res = self._box_item_values(item, values)
   1352             cache[item] = res

//anaconda/lib/python3.5/site-packages/pandas/core/internals.py in get(self, item, fastpath)
   3288 
   3289             if not isnull(item):
-> 3290                 loc = self.items.get_loc(item)
   3291             else:
   3292                 indexer = np.arange(len(self.items))[isnull(self.items)]

//anaconda/lib/python3.5/site-packages/pandas/indexes/base.py in get_loc(self, key, method, tolerance)
   1945                 return self._engine.get_loc(key)
   1946             except KeyError:
-> 1947                 return self._engine.get_loc(self._maybe_cast_indexer(key))
   1948 
   1949         indexer = self.get_indexer([key], method=method, tolerance=tolerance)

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4154)()

pandas/index.pyx in pandas.index.IndexEngine.get_loc (pandas/index.c:4018)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12368)()

pandas/hashtable.pyx in pandas.hashtable.PyObjectHashTable.get_item (pandas/hashtable.c:12322)()

KeyError: 0

It seems there is an issue with line 218:

    217     for i, _ in enumerate(df_data):
--> 218         if df_data[i]['Job Title'] == '':
    219             df_data[i]['Job Titles'] = ['']
    220             continue

This is the code from the example 12:

 for i, _ in enumerate(contacts):
        if contacts[i]['Job Title'] == '':
            contacts[i]['Job Titles'] = ['']
            continue

What could be an issue? Thanks!