import pandas as pd
import pandas_dedupe

#load dataframe
df = pd.read_csv('test_names.csv')

#initiate deduplication
df_final = pandas_dedupe.dedupe_dataframe(df,['first_name', 'last_name', 'middle_initial'])

#send output to csv
df_final.to_csv('deduplication_output.csv')


#------------------------------additional details------------------------------

#A training file and a settings file will be created while running Dedupe. 
#Keeping these files will eliminate the need to retrain your model in the future. 
#If you would like to retrain your model, just delete the settings and training files.

import pandas as pd
import pandas_dedupe

#load dataframes
dfa = pd.read_csv('file_a.csv')
dfb = pd.read_csv('file_b.csv')

#initiate matching
df_final = pandas_dedupe.link_dataframes(dfa, dfb, ['field_1', 'field_2', 'field_3', 'field_4'])

#send output to csv
df_final.to_csv('linkage_output.csv')


#------------------------------additional details------------------------------

#Use identical field names when linking dataframes.

#Record linkage should only be used on dataframes that have been deduplicated.
   
#A training file and a settings file will be created while running Dedupe. 
#Keeping these files will eliminate the need to retrain your model in the future. 
#If you would like to retrain your model, just delete the settings and training files.

pandas_dedupe.dedupe_dataframe(df,['first_name', 'last_name', 'payment_type'], canonicalize=True)

#------------------------------additional details------------------------------

#Creates a standardized version of every element by field & cluster id for instance,
#if you had the field "first_name", and the first cluster id had 3 items, "John",
#"John", and "Johnny", the canonicalized version would have "John" listed for all
#three in a new field called "first_name - canonical"

#If you prefer only canonicalize a few of your fields, you can set the parameter
#as a list of fields you want a canonical version for. In my example above, you
#could have written canonicalize=['first_name', 'last_name'], and you would get
#a canonical version for first_name, and last_name, but not for payment_type.

# Price Example
pandas_dedupe.dedupe_dataframe(df,['first_name', 'last_name', ('salary', 'Price')])
   
# has missing Example
pandas_dedupe.link_dataframes(df,['SSN', ('bio_pgraph', 'Text'), ('salary', 'Price', 'has missing')])

# crf Example
pandas_dedupe.dedupe_dataframe(df,[('first_name', 'String', 'crf'), 'last_name', (m_initial, 'Exact')])


#------------------------------additional details------------------------------

#If a type is not explicity listed, String will be used.

#Tuple (parenthesis) is required to declare all other types. If you prefer use tuple
#for string also, ('first_name', 'String'), that's fine.

#If you want to specify either a 'crf' or 'has missing' parameter, a tuple with three elements
#must be used. ('first_name', 'String', 'crf') works, ('first_name', 'crf') does not work.