def get_data(self, NAME=None):
"""
return the details of one data source.
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
return self.all_data[NAME]
def remove_data_source(self, NAME=None):
"""
remove a row (data source)
Params:
NAME: the name of the data source to delete
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
self.data_store_df = self.data_store_df.drop(NAME)
def toggle_use_unique(self, NAME=None):
"""
switch whether to use only unique sentences from data source, or allow repetitions.
Params:
NAME: the name of the data source whose USE_UNIQUE value is to be toggled
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
self.data_store_df["USE_UNIQUE"].loc[
NAME] = not self.data_store_df["USE_UNIQUE"].loc[NAME]
def change_sample_size(self, NAME=None, SAMPLE_SIZE=None):
"""
change the number of sentences from a data source to use.
Params:
NAME: the name of the data source whose sample size is to be changed
SAMPLE_SIZE: the new sample size
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
self.data_store_df["SAMPLE_SIZE"].loc[NAME] = SAMPLE_SIZE
def toggle_random(self, NAME=None):
"""
switch whether to randomly select the sample sentences from a data source, or take the sample starting
from sentence index 0 until sentence index = sample size.
Params:
NAME: the name of the data set whos RANDOM value is to be toggled
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
self.data_store_df["RANDOM"].loc[
NAME] = not self.data_store_df["RANDOM"].loc[NAME]
def change_path(self, NAME=None, PATH=None):
"""
change the location of a data source
Params:
NAME: the name of the data source whose path is to be changed
PATH: the new file path
"""
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
ensure_string_argument(PATH, "PATH")
self.data_store_df["PATH"].loc[NAME] = PATH
def data_sources(self, NAME=None):
"""
prints the data frame to the screen.
Params:
NAME: Optionally specify a particular data source to print the details of.
"""
if NAME:
ensure_in_df_index(NAME, self.data_store_df, "Data Store")
print(self.data_store_df.loc[NAME])
else:
print(self.data_store_df)