[Feature] Confidence metrics for thresholding + improve bar graphs for tuning

.pre-commit-config.yaml

@@ -41,7 +41,7 @@ repos:
     hooks:
       - id: pytest-on-commit
         name: Running single sample test
-        entry:  pytest -rfpsxEX --disable-warnings --verbose -k sample1
+        entry:  python3 -m pytest -rfpsxEX --disable-warnings --verbose -k sample1
         language: system
         pass_filenames: false
         always_run: true
@@ -51,7 +51,7 @@ repos:
     hooks:
       - id: pytest-on-push
         name: Running all tests before push...
-        entry: pytest -rfpsxEX --disable-warnings --verbose --durations=3
+        entry: python3 -m pytest -rfpsxEX --disable-warnings --verbose --durations=3
         language: system
         pass_filenames: false
         always_run: true

README.md

@@ -1,6 +1,10 @@
 # OMR Checker
 
-Read OMRs fast and accurately using a scanner 🖨 or your phone 🤳.
+Read OMR sheets fast and accurately using a scanner 🖨 or your phone 🤳.
+
+## What is OMR?
+
+OMR stands for Optical Mark Recognition, used to detect and interpret human-marked data on documents. OMR refers to the process of reading and evaluating OMR sheets, commonly used in exams, surveys, and other forms.
 
 #### **Quick Links**
 - [Installation](#getting-started)

main.py

@@ -12,7 +12,7 @@
 from pathlib import Path
 
 from src.entry import entry_point
-from src.logger import logger
+from src.utils.logger import logger
 
 
 def parse_args():
@@ -88,12 +88,18 @@ def entry_point_for_args(args):
         # Disable tracebacks
         sys.tracebacklimit = 0
         # TODO: set log levels
-
     for root in args["input_paths"]:
-        entry_point(
-            Path(root),
-            args,
-        )
+        try:
+            entry_point(
+                Path(root),
+                args,
+            )
+        except Exception:
+            if args["debug"] is True:
+                logger.critical(
+                    f"OMRChecker crashed. add --debug and run again to see error details"
+                )
+            raise
 
 
 if __name__ == "__main__":

samples/sample2/answer_key.csv → samples/answer-key/using-csv/answer_key.csv

@@ -1,5 +1,5 @@
-q1,B
+q1,C
 q2,E
 q3,A
-q4,C
+q4,B
 q5,B

samples/sample2/evaluation.json → samples/answer-key/using-csv/evaluation.json

@@ -4,7 +4,7 @@
     "answer_key_csv_path": "answer_key.csv",
     "should_explain_scoring": true
   },
-  "marking_scheme": {
+  "marking_schemes": {
     "DEFAULT": {
       "correct": "1",
       "incorrect": "0",

samples/answer-key/using-csv/template.json

@@ -0,0 +1,35 @@
+{
+  "pageDimensions": [
+    300,
+    400
+  ],
+  "bubbleDimensions": [
+    25,
+    25
+  ],
+  "preProcessors": [
+    {
+      "name": "CropPage",
+      "options": {
+        "morphKernel": [
+          10,
+          10
+        ]
+      }
+    }
+  ],
+  "fieldBlocks": {
+    "MCQ_Block_1": {
+      "fieldType": "QTYPE_MCQ5",
+      "origin": [
+        65,
+        60
+      ],
+      "fieldLabels": [
+        "q1..5"
+      ],
+      "labelsGap": 52,
+      "bubblesGap": 41
+    }
+  }
+}

samples/answer-key/weighted-answers/evaluation.json

@@ -0,0 +1,35 @@
+{
+  "source_type": "custom",
+  "options": {
+    "questions_in_order": [
+      "q1..5"
+    ],
+    "answers_in_order": [
+      "C",
+      "E",
+      [
+        "A",
+        "C"
+      ],
+      [
+        [
+          "B",
+          2
+        ],
+        [
+          "C",
+          "3/2"
+        ]
+      ],
+      "C"
+    ],
+    "should_explain_scoring": true
+  },
+  "marking_schemes": {
+    "DEFAULT": {
+      "correct": "3",
+      "incorrect": "-1",
+      "unmarked": "0"
+    }
+  }
+}

samples/answer-key/weighted-answers/template.json

@@ -0,0 +1,35 @@
+{
+  "pageDimensions": [
+    300,
+    400
+  ],
+  "bubbleDimensions": [
+    25,
+    25
+  ],
+  "preProcessors": [
+    {
+      "name": "CropPage",
+      "options": {
+        "morphKernel": [
+          10,
+          10
+        ]
+      }
+    }
+  ],
+  "fieldBlocks": {
+    "MCQ_Block_1": {
+      "fieldType": "QTYPE_MCQ5",
+      "origin": [
+        65,
+        60
+      ],
+      "fieldLabels": [
+        "q1..5"
+      ],
+      "labelsGap": 52,
+      "bubblesGap": 41
+    }
+  }
+}

samples/community/UPSC-mock/evaluation.json

@@ -8,7 +8,7 @@
     ],
     "should_explain_scoring": true
   },
-  "marking_scheme": {
+  "marking_schemes": {
     "DEFAULT": {
       "correct": "2",
       "incorrect": "-2/3",

samples/community/UmarFarootAPS/answer_key.csv

@@ -2,8 +2,8 @@ q1,C
 q2,C
 q3,"D,E"
 q4,"A,AB"
-q5,"['A', ['1', '-2/3', '0']]"
-q6,"['A', ['2']]"
+q5,"[['A', '1'], ['B', '2']]"
+q6,"['A', 'B']"
 q7,C
 q8,D
 q9,B

samples/community/UmarFarootAPS/evaluation.json

@@ -4,7 +4,7 @@
     "answer_key_csv_path": "answer_key.csv",
     "should_explain_scoring": true
   },
-  "marking_scheme": {
+  "marking_schemes": {
     "DEFAULT": {
       "correct": "1",
       "incorrect": "0",

samples/sample4/evaluation.json

@@ -11,15 +11,19 @@
       "B",
       "D",
       "C",
-      "BC",
+      [
+        "B",
+        "C",
+        "BC"
+      ],
       "A",
       "C",
       "D",
       "C"
     ],
     "should_explain_scoring": true
   },
-  "marking_scheme": {
+  "marking_schemes": {
     "DEFAULT": {
       "correct": "3",
       "incorrect": "-1",

samples/sample5/evaluation.json

@@ -33,7 +33,7 @@
     ],
     "should_explain_scoring": true
   },
-  "marking_scheme": {
+  "marking_schemes": {
     "DEFAULT": {
       "correct": "1",
       "incorrect": "0",

src/__init__.py

@@ -1,5 +1,5 @@
 # https://docs.python.org/3/tutorial/modules.html#:~:text=The%20__init__.py,on%20the%20module%20search%20path.
-from src.logger import logger
+from src.utils.logger import logger
 
 # It takes a few seconds for the imports
 logger.info(f"Loading OMRChecker modules...")