def user_labeling(self, candidates):
df = self.phrases_to_dataframe(candidates)
df.to_csv(r'temp.csv', index=False)
# df_csv = em.read_csv_metadata('temp.csv', key='idx')
# em.label_table(df_csv, 'gold_label')
df_cc = em._init_label_table(df, 'gold_label')
# df_cc['gold_label'] = df['label']
df_cc['gold_label'] = 1
# Invoke the GUI
try:
from PyQt5 import QtGui
except ImportError:
raise ImportError(
'PyQt5 is not installed. Please install PyQt5 to use '
'GUI related functions in py_entitymatching.')
from py_entitymatching.gui.table_gui import edit_table
edit_table(df_cc)
df_cc = self._post_process_labelled_table(df_cc, 'gold_label')
print(df_cc.head())
with open('/home/beidan/AutoPhrase/tmp/labeled_patterns.txt',
'w',
encoding='utf-8') as f:
for rec_idx, rec in df_cc.iterrows():
f.write(rec['idx'] + '\t' + str(rec['gold_label']) + '\n')
print("successfully write {} records to Autophrase".format(len(df_cc)))
def label_table(table, label_column_name, verbose=False):
"""
Label a pandas DataFrame (for supervised learning purposes).
This functions labels a DataFrame, typically used for supervised learning
purposes. This function expects the input DataFrame containing the metadata
of a candidate set (such as key, fk_ltable, fk_rtable, ltable, rtable).
This function creates a copy of the input DataFrame, adds label column
at the end of the DataFrame, fills the column values with 0, invokes a
GUI for the user to enter labels (0/1, 0: non-match, 1: match) and finally
returns the labeled DataFrame. Further, this function also copies the
properties from the input DataFrame to the output DataFrame.
Args:
table (DataFrame): The input DataFrame to be labeled.
Specifically,
a DataFrame containing the metadata of a candidate set (such as
key, fk_ltable, fk_rtable, ltable, rtable) in the catalog.
label_column_name (string): The column name to be given for the labels
entered by the user.
verbose (boolean): A flag to indicate whether more detailed information
about the execution steps should be printed out (default value is
False).
Returns:
A new DataFrame with the labels entered by the user. Further,
this function sets the output DataFrame's properties same as input
DataFrame.
Raises:
AssertionError: If `table` is not of type pandas DataFrame.
AssertionError: If `label_column_name` is not of type string.
AssertionError: If the `label_column_name` is already present in the
input table.
"""
# Validate the input parameters: check input types, check the metadata
# for the input DataFrame as it will get copied to the labeled DataFrame
_validate_inputs(table, label_column_name, verbose)
# Initialize the table to be labeled: create a copy and set the column
# values to be 0s
labeled_table = _init_label_table(table, label_column_name)
# Invoke the GUI
try:
from PyQt4 import QtGui
except ImportError:
raise ImportError('PyQt4 is not installed. Please install PyQt4 to use '
'GUI related functions in py_entitymatching.')
from py_entitymatching.gui.table_gui import edit_table
edit_table(labeled_table)
# Post process the labeled table: validate whether the labels contain
# only 0/1s, copy the properties (in the catalog) of the input table to the
# labeled table
labeled_table = _post_process_labelled_table(table, labeled_table,
label_column_name)
# Return the labeled table
return labeled_table
def label_table(table, label_column_name, verbose=False):
"""
Label a pandas DataFrame (for supervised learning purposes).
This functions labels a DataFrame, typically used for supervised learning
purposes. This function expects the input DataFrame containing the metadata
of a candidate set (such as key, fk_ltable, fk_rtable, ltable, rtable).
This function creates a copy of the input DataFrame, adds label column
at the end of the DataFrame, fills the column values with 0, invokes a
GUI for the user to enter labels (0/1, 0: non-match, 1: match) and finally
returns the labeled DataFrame. Further, this function also copies the
properties from the input DataFrame to the output DataFrame.
Args:
table (DataFrame): The input DataFrame to be labeled.
Specifically,
a DataFrame containing the metadata of a candidate set (such as
key, fk_ltable, fk_rtable, ltable, rtable) in the catalog.
label_column_name (string): The column name to be given for the labels
entered by the user.
verbose (boolean): A flag to indicate whether more detailed information
about the execution steps should be printed out (default value is
False).
Returns:
A new DataFrame with the labels entered by the user. Further,
this function sets the output DataFrame's properties same as input
DataFrame.
Raises:
AssertionError: If `table` is not of type pandas DataFrame.
AssertionError: If `label_column_name` is not of type string.
AssertionError: If the `label_column_name` is already present in the
input table.
Examples:
>>> import py_entitymatching as em
>>> G = em.label_table(S, label_column_name='label') # S is the (sampled) table that has to be labeled.
"""
# Validate the input parameters: check input types, check the metadata
# for the input DataFrame as it will get copied to the labeled DataFrame
_validate_inputs(table, label_column_name, verbose)
# Initialize the table to be labeled: create a copy and set the column
# values to be 0s
labeled_table = _init_label_table(table, label_column_name)
# Invoke the GUI
try:
from PyQt5 import QtGui
except ImportError:
raise ImportError('PyQt5 is not installed. Please install PyQt5 to use '
'GUI related functions in py_entitymatching.')
from py_entitymatching.gui.table_gui import edit_table
edit_table(labeled_table)
# Post process the labeled table: validate whether the labels contain
# only 0/1s, copy the properties (in the catalog) of the input table to the
# labeled table
labeled_table = _post_process_labelled_table(table, labeled_table,
label_column_name)
# Return the labeled table
return labeled_table