Content quiz performance

content_quiz_analysis.py

@@ -0,0 +1,8 @@
+from util import ReadingLogsData
+from scripts import content_quiz_attempts_analysis, content_quiz_grade_analysis
+
+if __name__ == '__main__':
+    reading_logs_data = ReadingLogsData()
+    reading_dict, quiz_dict = reading_logs_data.get_parsed_reading_log_data()
+    content_quiz_attempts_analysis(quiz_dict)
+    content_quiz_grade_analysis(quiz_dict)

schemas/course.py

@@ -34,7 +34,8 @@ class CourseSchema:
     ]
 
     @staticmethod
-    def page_is_valid(module_num: int, page_num: int) -> bool:
+    def page_is_valid(module_num: str, page_num: str) -> bool:
+        module_num, page_num = int(module_num), int(page_num)
         if module_num in CourseSchema.CANCELLED_MODULES or \
                 module_num in CourseSchema.OPTIONAL_MODULES or \
                 module_num in CourseSchema.SUMMARY_MODULES:

scripts/__init__.py

@@ -12,3 +12,5 @@
 from .analyze_module_feedback_survey import analyze_module_feedback, compare_module_feedback
 from .reading_logs import analyze_num_paragraphs, parse_reading_logs_module, parse_reading_logs_all, \
     reading_logs_completion_time
+from .content_quiz_analysis.analysis_on_content_quiz import content_quiz_attempts_analysis, content_quiz_grade_analysis
+

scripts/content_quiz_analysis/analysis_on_content_quiz.py

@@ -0,0 +1,124 @@
+import matplotlib.pyplot as plt
+import numpy as np
+from util import ReadingLogsData
+from schemas import CourseSchema
+
+
+def content_quiz_attempts_analysis(content_quiz_dict):
+    r = ReadingLogsData()
+
+    page_content_quiz_attempt_mean = []
+    page_content_quiz_attempt_std = []
+    content_quiz_attempt_pages = []
+
+    module_content_quiz_attempt_mean = []
+    module_content_quiz_attempt_std = []
+    content_quiz_attempt_modules = []
+
+    module_paragraphs_dict = r.get_module_paragraphs_dict()
+    for module_num, page_dict in module_paragraphs_dict.items():
+        for page_num, page_data in page_dict.items():
+            if not CourseSchema.page_is_valid(module_num, page_num):
+                continue
+
+            # set up for per page analysis
+            page_attempt = r.page_content_quiz_num_attempts(module_num, page_num)
+            if page_attempt is not None:
+                content_quiz_attempt_pages.append(str(module_num)+"-"+str(page_num))
+                page_content_quiz_attempt_mean.append(page_attempt[0])
+                page_content_quiz_attempt_std.append(page_attempt[1])
+
+            # set up for per module analysis
+            module_attempt = r.module_content_quiz_num_attempts(module_num)
+            if module_attempt is not None:
+                content_quiz_attempt_modules.append(str(module_num))
+                module_content_quiz_attempt_mean.append(module_attempt[0])
+                module_content_quiz_attempt_std.append(module_attempt[1])
+
+    # Per page graph
+    page_content_quiz_attempt_std.append(np.mean(page_content_quiz_attempt_mean))
+    page_content_quiz_attempt_mean.append(np.std(page_content_quiz_attempt_mean))
+    content_quiz_attempt_pages.append('Overall')
+
+    plt.scatter(content_quiz_attempt_pages, page_content_quiz_attempt_mean)
+    plt.errorbar(content_quiz_attempt_pages, page_content_quiz_attempt_mean, yerr=page_content_quiz_attempt_std,
+                 fmt='o', ecolor="skyblue", elinewidth=0.5)
+    plt.xticks(fontsize=5)
+    plt.xlabel("Module_number-Page_number")
+    plt.ylabel("Number of attempts")
+    plt.title("Mean and Standard Deviation of Extra Attempts for Each Content Quiz")
+    plt.show()
+
+    # Per module graph
+    module_content_quiz_attempt_mean.append(np.mean(module_content_quiz_attempt_mean))
+    module_content_quiz_attempt_std.append(np.std(module_content_quiz_attempt_mean))
+    content_quiz_attempt_modules.append('Overall')
+
+    plt.scatter(content_quiz_attempt_modules, module_content_quiz_attempt_mean)
+    plt.errorbar(content_quiz_attempt_modules, module_content_quiz_attempt_mean, yerr=module_content_quiz_attempt_std,
+                 fmt='o', ecolor="skyblue", elinewidth=0.5)
+    plt.xticks(fontsize=5)
+    plt.xlabel("Module_number")
+    plt.ylabel("Number of attempts")
+    plt.title("Mean and Standard Deviation of Extra Attempts for Each Module")
+    plt.show()
+
+
+def content_quiz_grade_analysis(content_quiz_dict):
+    r = ReadingLogsData()
+
+    page_content_quiz_grade_mean = []
+    page_content_quiz_grade_std = []
+    content_quiz_grade_pages = []
+
+    module_content_quiz_grade_mean = []
+    module_content_quiz_grade_std = []
+    content_quiz_grade_modules = []
+
+    module_paragraphs_dict = r.get_module_paragraphs_dict()
+    for module_num, page_dict in module_paragraphs_dict.items():
+        for page_num, page_data in page_dict.items():
+            if not CourseSchema.page_is_valid(module_num, page_num):
+                continue
+
+            # set up for per page analysis
+            page_grade = r.page_content_quiz_first_attempt_grade(module_num=module_num, page_num=page_num)
+            if page_grade is not None:
+                content_quiz_grade_pages.append(str(module_num) + "-" + str(page_num))
+                page_content_quiz_grade_mean.append(page_grade[0])
+                page_content_quiz_grade_std.append(page_grade[1])
+
+            # set up for per module analysis
+            module_grade = r.module_content_quiz_first_attempt_grade(module_num)
+            if module_grade is not None:
+                content_quiz_grade_modules.append(str(module_num))
+                module_content_quiz_grade_mean.append(module_grade[0])
+                module_content_quiz_grade_std.append(module_grade[1])
+
+    # Per page graph
+    page_content_quiz_grade_mean.append(np.mean(page_content_quiz_grade_mean))
+    page_content_quiz_grade_std.append(np.std(page_content_quiz_grade_mean))
+    content_quiz_grade_pages.append('Overall')
+
+    plt.scatter(content_quiz_grade_pages, page_content_quiz_grade_mean)
+    plt.errorbar(content_quiz_grade_pages, page_content_quiz_grade_mean, yerr=page_content_quiz_grade_std,
+                 fmt='o', ecolor="skyblue", elinewidth=0.5)
+    plt.xticks(fontsize=5)
+    plt.xlabel("Module_number-Page_number")
+    plt.ylabel("Number of grades")
+    plt.title("Mean and Standard Deviation of First Attempt Grade for Each Content Quiz")
+    plt.show()
+
+    # Per module graph
+    module_content_quiz_grade_mean.append(np.mean(module_content_quiz_grade_mean))
+    module_content_quiz_grade_std.append(np.std(module_content_quiz_grade_mean))
+    content_quiz_grade_modules.append('Overall')
+
+    plt.scatter(content_quiz_grade_modules, module_content_quiz_grade_mean)
+    plt.errorbar(content_quiz_grade_modules, module_content_quiz_grade_mean, yerr=module_content_quiz_grade_std,
+                 fmt='o', ecolor="skyblue", elinewidth=0.5)
+    plt.xticks(fontsize=5)
+    plt.xlabel("Module_number")
+    plt.ylabel("First attempt grades")
+    plt.title("Mean and Standard Deviation of First Attempt Grade for Each Module")
+    plt.show()

scripts/reading_logs/parse_reading_logs/parse_reading_logs.py

@@ -1,3 +1,5 @@
+import pandas as pd
+import os
 import json
 import math
 import os
@@ -104,14 +106,12 @@ def parsing_each_continue(reading_log_folder_path: str, module_number: str, data
     for reading_log in os.listdir(reading_log_folder_path):
         reading_log_path = os.path.join(reading_log_folder_path, reading_log)
 
-        if not reading_log.endswith('.json'):
+        r = ReadingLogsData()
+
+        if not r.is_reading_log_file(reading_log):
             continue
 
         reading_log_name_array = reading_log.split('-')
-        if '(' in reading_log and ')' in reading_log:  # check for duplicate files
-            continue
-        if reading_log_name_array[0] != "COSC341":  # make sure the file is a reading_log
-            continue
         if reading_log_name_array[1] != module_number:  # make sure the reading log file is for the correct module
             continue
 
@@ -146,9 +146,9 @@ def parsing_each_quiz_submit(reading_log_folder_path: str, module_number: str, d
     for reading_log in os.listdir(reading_log_folder_path):
         reading_log_path = os.path.join(reading_log_folder_path, reading_log)
 
-        if not reading_log.endswith('.json'):
-            continue
-        if '(' in reading_log and ')' in reading_log:  # check for duplicate files
+        r = ReadingLogsData()
+
+        if not r.is_reading_log_file(reading_log):
             continue
 
         reading_log_name_array = reading_log.split('-')

util/__init__.py

@@ -4,6 +4,7 @@
 from .const import KEY_PATH, MODULE_PARAGRAPHS_OUTPUT_FILEPATH, CACHE_FOLDER
 from .canvas_api import setup_submissions_filepath, get_quiz_id_from_file_name, DateTimeEncoder
 from .data_cleaner import keep_latest_survey_attempt
-from .util import normalize
-from .plots import set_plot_settings
 from .reading_logs import ReadingLogsData
+from .plots import set_plot_settings
+from .util import normalize
+