Added feature to export the evaluation summary table in csv format

samples/sample4/evaluation.json

@@ -21,7 +21,8 @@
       "D",
       "C"
     ],
-    "should_explain_scoring": true
+    "should_explain_scoring": true,
+    "enable_evaluation_table_to_csv": true
   },
   "marking_schemes": {
     "DEFAULT": {

src/core.py

@@ -243,7 +243,7 @@ def read_omr_response(self, template, image, name, save_dir=None):
             global_thr, _, _ = self.get_global_threshold(all_q_vals, looseness=4)
 
             logger.info(
-                f"Thresholding:\tglobal_thr: {round(global_thr, 2)} \tglobal_std_THR: {round(global_std_thresh, 2)}\t{'(Looks like a Xeroxed OMR)' if (global_thr == 255) else ''}"
+                f"Thresholding: \tglobal_thr: {round(global_thr, 2)} \tglobal_std_THR: {round(global_std_thresh, 2)}\t{'(Looks like a Xeroxed OMR)' if (global_thr == 255) else ''}"
             )
             # plt.show()
             # hist = getPlotImg()

src/entry.py

@@ -209,6 +209,9 @@ def process_files(
     for file_path in omr_files:
         files_counter += 1
         file_name = file_path.name
+        evaluation_path = os.path.join(
+            outputs_namespace.paths.evaluation_dir, file_path.stem
+        )
 
         in_omr = cv2.imread(str(file_path), cv2.IMREAD_GRAYSCALE)
 
@@ -273,7 +276,9 @@ def process_files(
 
         score = 0
         if evaluation_config is not None:
-            score = evaluate_concatenated_response(omr_response, evaluation_config)
+            score = evaluate_concatenated_response(
+                omr_response, evaluation_config, evaluation_path
+            )
             logger.info(
                 f"(/{files_counter}) Graded with score: {round(score, 2)}\t for file: '{file_id}'"
             )
@@ -342,25 +347,25 @@ def print_stats(start_time, files_counter, tuning_config):
     time_checking = max(1, round(time() - start_time, 2))
     log = logger.info
     log("")
-    log(f"{'Total file(s) moved':<27}: {STATS.files_moved}")
-    log(f"{'Total file(s) not moved':<27}: {STATS.files_not_moved}")
+    log(f"{'Total file(s) moved': <27}: {STATS.files_moved}")
+    log(f"{'Total file(s) not moved': <27}: {STATS.files_not_moved}")
     log("--------------------------------")
     log(
-        f"{'Total file(s) processed':<27}: {files_counter} ({'Sum Tallied!' if files_counter == (STATS.files_moved + STATS.files_not_moved) else 'Not Tallying!'})"
+        f"{'Total file(s) processed': <27}: {files_counter} ({'Sum Tallied!' if files_counter == (STATS.files_moved + STATS.files_not_moved) else 'Not Tallying!'})"
     )
 
     if tuning_config.outputs.show_image_level <= 0:
         log(
-            f"\nFinished Checking {files_counter} file(s) in {round(time_checking, 1)} seconds i.e. ~{round(time_checking/60, 1)} minute(s)."
+            f"\nFinished Checking {files_counter} file(s) in {round(time_checking, 1)} seconds i.e. ~{round(time_checking / 60, 1)} minute(s)."
         )
         log(
-            f"{'OMR Processing Rate':<27}:\t ~ {round(time_checking/files_counter,2)} seconds/OMR"
+            f"{'OMR Processing Rate': <27}: \t ~ {round(time_checking / files_counter, 2)} seconds/OMR"
         )
         log(
-            f"{'OMR Processing Speed':<27}:\t ~ {round((files_counter * 60) / time_checking, 2)} OMRs/minute"
+            f"{'OMR Processing Speed': <27}: \t ~ {round((files_counter * 60) / time_checking, 2)} OMRs/minute"
         )
     else:
-        log(f"\n{'Total script time':<27}: {time_checking} seconds")
+        log(f"\n{'Total script time': <27}: {time_checking} seconds")
 
     if tuning_config.outputs.show_image_level <= 1:
         log(

src/evaluation.py

@@ -2,6 +2,7 @@
 import os
 import re
 from copy import deepcopy
+from csv import QUOTE_NONNUMERIC
 
 import cv2
 import pandas as pd
@@ -197,6 +198,9 @@ def __init__(self, curr_dir, evaluation_path, template, tuning_config):
         self.should_explain_scoring = options.get("should_explain_scoring", False)
         self.has_non_default_section = False
         self.exclude_files = []
+        self.enable_evaluation_table_to_csv = options.get(
+            "enable_evaluation_table_to_csv", False
+        )
 
         if source_type == "csv":
             csv_path = curr_dir.joinpath(options["answer_key_csv_path"])
@@ -356,6 +360,23 @@ def conditionally_print_explanation(self):
         if self.should_explain_scoring:
             console.print(self.explanation_table, justify="center")
 
+    # Explanation Table to CSV
+    def conditionally_save_explanation_csv(self, evaluation_path):
+        if self.enable_evaluation_table_to_csv:
+            data = {col.header: col._cells for col in self.explanation_table.columns}
+
+            output_dir = os.path.join(
+                os.getcwd(),
+                f"{evaluation_path}.csv",
+            )
+
+            pd.DataFrame(data, dtype=str).to_csv(
+                output_dir,
+                mode="a",
+                quoting=QUOTE_NONNUMERIC,
+                index=False,
+            )
+
     def get_should_explain_scoring(self):
         return self.should_explain_scoring
 
@@ -507,7 +528,9 @@ def conditionally_add_explanation(
             self.explanation_table.add_row(*row)
 
 
-def evaluate_concatenated_response(concatenated_response, evaluation_config):
+def evaluate_concatenated_response(
+    concatenated_response, evaluation_config, evaluation_path
+):
     evaluation_config.prepare_and_validate_omr_response(concatenated_response)
     current_score = 0.0
     for question in evaluation_config.questions_in_order:
@@ -518,5 +541,6 @@ def evaluate_concatenated_response(concatenated_response, evaluation_config):
         current_score += delta
 
     evaluation_config.conditionally_print_explanation()
+    evaluation_config.conditionally_save_explanation_csv(evaluation_path)
 
     return current_score

src/schemas/evaluation_schema.py

@@ -138,6 +138,10 @@
                                 ]
                             },
                             "questions_in_order": ARRAY_OF_STRINGS,
+                            "enable_evaluation_table_to_csv": {
+                                "type": "boolean",
+                                "default": False,
+                            },
                         },
                     }
                 }

src/utils/file.py

@@ -25,6 +25,7 @@ def __init__(self, output_dir):
         self.save_marked_dir = output_dir.joinpath("CheckedOMRs")
         self.results_dir = output_dir.joinpath("Results")
         self.manual_dir = output_dir.joinpath("Manual")
+        self.evaluation_dir = output_dir.joinpath("Evaluation")
         self.errors_dir = self.manual_dir.joinpath("ErrorFiles")
         self.multi_marked_dir = self.manual_dir.joinpath("MultiMarkedFiles")
 
@@ -44,6 +45,11 @@ def setup_dirs_for_paths(paths):
             logger.info(f"Created : {save_output_dir}")
             os.makedirs(save_output_dir)
 
+    for save_output_dir in [paths.evaluation_dir]:
+        if not os.path.exists(save_output_dir):
+            logger.info(f"Created : {save_output_dir}")
+            os.makedirs(save_output_dir)
+
     for save_output_dir in [paths.multi_marked_dir, paths.errors_dir]:
         if not os.path.exists(save_output_dir):
             logger.info(f"Created : {save_output_dir}")