Added functionality to read the csv files into pandas dataframes from…

… the result object.

README.md

@@ -49,6 +49,25 @@ If you want to check if the files have been created before doing further process
     else:
         print("Files not created!")
 
+The result object also provides methods to import the created files into pandas dataframes:
+
+    pgn_data = PGNData("tal_bronstein_1982.pgn")
+    result = pgn_data.export()
+    if result.is_complete:
+        
+        # read the games file
+        games_df = result.get_games_df()
+        
+        # read the moves file
+        moves_df = result.get_moves_df()
+        
+        # read both files joined together
+        combined_df = result.get_combined_df()
+        
+        print(games_df.head())
+        print(moves_df.head())
+        print(combined_df.head())
+
 
 ## Examples
 
@@ -127,3 +146,8 @@ This is a full list of the columns in each output file:
 | fen_row{number}_{colour)_count | Number of pieces for the specified colour on this row of the board      |
 | fen_row{number}_{colour}_value | Total value of pieces for the specified colour on this row of the board |
 | move_sequence                  | Sequence of moves upto current position                                 |
+
+
+## Acknowledgements
+
+This project makes use of the [python-chess](https://github.com/niklasf/python-chess) library.

converter/result.py

@@ -1,3 +1,11 @@
+import logging
+import pandas as pd
+import os
+
+log = logging.getLogger("pgn2data - process")
+logging.basicConfig(level=logging.INFO)
+
+
 class Result:
     """
     results of the extract are tracked here
@@ -21,6 +29,45 @@ def print_summary(self):
         print("games file: {} | size: {}".format(self.games_file.name, self.games_file.size))
         print("moves file: {} | size: {}".format(self.moves_file.name, self.moves_file.size))
 
+    def get_games_df(self):
+        return self.__get_as_dataframe(self.games_file.name)
+
+    def get_moves_df(self):
+        return self.__get_as_dataframe(self.moves_file.name)
+
+    def get_combined_df(self):
+        games_df = self.get_games_df()
+        moves_df = self.get_moves_df()
+        if (games_df is not None) and (moves_df is not None):
+            if (not games_df.empty) and (not moves_df.empty):
+                combined_df = pd.merge(games_df, moves_df, on='game_id')
+                return combined_df
+            else:
+                log.error("one or both files is empty")
+        else:
+            log.error("one or both files not found")
+        return None
+
+    def create_combined_file(self, filename):
+        combined_df = self.get_combined_df()
+        if combined_df is not None:
+            combined_df.to_csv(filename, index=False)
+            return os.path.exists(filename)
+        else:
+            log.error("could not combine games and moves file")
+            return False
+
+    def __get_as_dataframe(self, file):
+        if self.is_complete:
+            return pd.read_csv(file)
+        else:
+            self.__display_not_found(file)
+            return None
+
+    @staticmethod
+    def __display_not_found(file):
+        log.error("File not found: {}".format(file))
+
 
 class ResultFile:
     def __init__(self, name, size):

requirements.txt

@@ -1 +1,2 @@
-chess
+chess
+pandas

setup.py

@@ -4,18 +4,22 @@
     'Development Status :: 5 - Production/Stable',
     'Intended Audience :: Education',
     'Operating System :: Microsoft :: Windows :: Windows 10',
-    'License :: OSI Approved :: GNU Lesser General Public License v2 (LGPLv2)',
-    'Programming Language :: Python :: 3'
+    'License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)',
+    'Programming Language :: Python :: 3 :: Only',
+    'Programming Language :: Python :: 3.7',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
 ]
 
 setup(
     name='pgn2data',
-    version='0.0.5',
+    version='0.0.6',
     packages=['converter', 'common', 'testing'],
     url='',
     classifiers=classifiers,
-    license='GPL2',
-    author='Zaid Qureshi',
+    license='GPL-3.0+',
+    author='zq99',
     author_email='zq99@hotmail.com',
     keywords=['CHESS', 'PGN', 'NOTATION', 'DATA', 'FORSYTH–EDWARDS NOTATION', 'CSV', 'DATASET', 'DATABASE',
               'NORMALIZATION', 'TABULATION', 'STRUCTURED DATA'],
@@ -24,5 +28,5 @@
     ],
     long_description=open('README.md').read(),
     long_description_content_type='text/markdown; charset=UTF-8; variant=GFM',
-    description='Transforms a chess pgn file into a csv dataset containing game information and move information',
+    description='Converts a chess pgn file into a csv dataset containing game information and move information',
 )

testing/exports/basic_format_game_info.csv

@@ -1,2 +1,2 @@
 game_id,game_order,event,site,date_played,round,white,black,result,white_elo,white_rating_diff,black_elo,black_rating_diff,white_title,black_title,winner,winner_elo,loser,loser_elo,winner_loser_elo_diff,eco,termination,time_control,utc_date,utc_time,variant,ply_count,date_created,file_name
-a5ab6da8-88d4-4552-acf3-45d7388a845a,1,F/S Return Match,"Belgrade, Serbia JUG",1992.11.04,29,"Fischer, Robert J.","Spassky, Boris V.",1/2-1/2,,,,,,,draw,,draw,,,,,,,,,,2022-06-24T20:39:21+0000,basic_format.pgn
+5580acfe-cf25-4067-bbd3-903ea22186f6,1,F/S Return Match,"Belgrade, Serbia JUG",1992.11.04,29,"Fischer, Robert J.","Spassky, Boris V.",1/2-1/2,,,,,,,draw,,draw,,,,,,,,,,2022-07-01T21:48:35+0000,basic_format.pgn