def _insert_deaths_data(self, new_data_df, table_name):
"""
Inserts deaths data to COVID19 deaths data table, denoted by table_name. If the new data contain
retrospectively modified rows, such rows are updated in the table
:param new_data_df: Data frame with new data
:param table_name: Name of the table to insert data
:return: The number of updated rows
"""
changed_rows = -1
row_count = self.execute_query('SELECT COUNT(*) FROM ' + table_name + ';')[0][0]
if row_count == 0:
'''
The table is empty, insert all the data in the data frame
'''
with self.create_connection() as con:
new_data_df.to_sql(con=con, name=table_name, if_exists='append', index=False)
changed_rows = len(new_data_df)
else:
'''
If the table is not empty append only the new data rows because re-writing all the
data is too expensive
'''
# Read the current data from table as a data frame
with self.create_connection() as con:
curr_data = pd.read_sql_query('SELECT * FROM ' + table_name + ';', con=con)
dh = DataHandler()
# Filter changed or newly added country and date combinations
modified_rows = dh.get_changed_rows(new_data_df, curr_data)
# Update the database
changed_rows = self.upsert_to_table(new_data_df.iloc[modified_rows, ], table_name)
return changed_rows
