Merge pull request #1 from jonaslache/dev

Merge dev to main

Author: jonaslache

README.md

@@ -7,6 +7,13 @@ SPDX-License-Identifier: GPL-3.0-or-later
 
 A Python tool to extract information from Moodle response files.
 
+## Version v0.2
+
+On 12th April 2024, version v0.2 of the Response File Processor has been released. The following features have been added:
+
+- Option to create a column with the random seed used in each attempt.
+- Option to specify a list of strings that the tool searches for in each row of the quiz data. The column will be filled with boolean values (True or False), depending on whether each strings are present in the individual rows. For example, the list of strings may include answer notes (e.g. `prt1-1-F`) or answer test results (e.g. `ATList_wrongentries`).
+
 ## About
 
 The *STACK Response File Processor* is a Python tool with a graphical user
@@ -15,6 +22,8 @@ student responses to STACK questions within Moodle quizzes, including:
 
 - Value and state (valid, invalid, score) of STACK input fields 
 - The score of the potential response trees and whether the PRTs were active
+- Information about whether user-specified strings are present in each row of the quiz data (True/False).
+- The [random seed](https://en.wikipedia.org/wiki/Random_seed) used in the specific attempt
 - STACKrate evaluation results (see
     <https://www.ruhr-uni-bochum.de/stackrate-maths/>)
 

response-file-processor.py

@@ -6,7 +6,7 @@
 # Import necessary libraries
 import tkinter as tk
 from tkinter import filedialog
-from tkinter import ttk
+from tkinter import ttk, Text
 import pandas as pd
 import re
 import json
@@ -47,7 +47,7 @@ def get_survey_results(str):
     return None
 
 # Function to extract either ratings or comments from STACKrate evaluation dict
-def extract_info(dictionary, key, attr=""):
+def extract_survey_info(dictionary, key, attr=""):
     if dictionary and key in dictionary:
         if attr=="":
             return dictionary[key]
@@ -94,6 +94,21 @@ def get_input_value(response_str, input_name, mode=""):
     else:
         return None
 
+# Returns the random seed in a given attempt
+def get_random_seed(response_str):
+    pattern = r"Seed:\s*(\d+)"
+    match = re.search(pattern, response_str)
+    if match:
+        input_value = match.group(1)
+        return input_value
+    else:
+        return None
+
+# Returns True when `search_item` is included in `response_str` string
+def is_present(response_str, search_item):
+    result = search_item in response_str
+    return result
+
 # Makes the radio buttons for the language selection visible in the GUI
 def show_language_radiobuttons():
     checkbox_seconds_row = checkbox_seconds.grid_info()["row"]
@@ -205,14 +220,17 @@ def submit_columns():
     input_names = set()
     global prts
     prts = set()
+    # Add temporary column with identified prt and input names as entries:
     df[f"{selected_col.get()}: identified_placeholders"] = df[selected_col.get()].apply(identify_prts_inputs)
+    # Create lists with input and prt names:
     for result in df[f"{selected_col.get()}: identified_placeholders"]:
         if result:
             input_names.update(result["inputs"])
             prts.update(result["prts"])
     i=1
     input_checkboxes_label.grid(row=i)
     i+=1
+    # Create checkbox for each input name:
     global input_checkboxes
     input_checkboxes = []
     for input in input_names:
@@ -232,6 +250,7 @@ def submit_columns():
     i+=1
     prt_checkboxes_label.grid(row=i)
     i+=1
+    # Create checkbox for each prt name:
     global prt_checkboxes
     prt_checkboxes = []
     for prt in prts:
@@ -251,11 +270,18 @@ def submit_columns():
     i+=1
     additional_options_label.grid(row=i)
     i+=1
+    textarea_label.grid(row=i)
+    i+=1
+    textarea.grid(row=i)
+    i+=1
     checkbox_seconds.grid(row=i)
     i=i+2+len(time_languages)
     checkbox_stackrate.grid(row=i)
     i+=1
+    checkbox_randseed.grid(row=i)
+    i+=1
     process_button.grid(row=i)
+    # Delete temporary column:
     del df[f"{selected_col.get()}: identified_placeholders"]
 
 # Function which is called when the clicks the "Save CSV file" button in GUI.
@@ -273,19 +299,29 @@ def export_csv_file():
 # Function where most of the "magic" happens. Called when clicking on "Submit".
 # Depending on user's wishes, all columns are created
 def process_input_strings():
+    # Create "Seconds taken" column depending on user's choices:
     if var_checkbox_seconds.get():
         time_values = time_languages[selected_lang.get()][0]
         df_key = time_languages[selected_lang.get()][1]
         try:
              df["Seconds taken"] = df[df_key].apply(lambda x: string_time_to_sec(x,time_values))
         except:
             print("There is an error finding the column that contains the time information. Please make sure you selected the correct language.")
+    # Create columns for selected input fields:
     for input_field in selected_input_checkboxes:
         df[f"{selected_col.get()}: {input_field} value"] = df[selected_col.get()].apply(lambda x: get_input_value(x, input_field, mode="value"))
         df[f"{selected_col.get()}: {input_field} state"] = df[selected_col.get()].apply(lambda x: get_input_value(x, input_field, mode="state"))
+    # Create columns for selected prts:
     for prt in selected_prt_checkboxes:
         df[f"{selected_col.get()}: {prt} active"] = df[selected_col.get()].apply(lambda x: is_prt_active(x, prt))
         df[f"{selected_col.get()}: {prt} score"] = df[selected_col.get()].apply(lambda x: get_prt_score(x, prt))
+    # Create columns for strings specified in text area
+    textarea_content = textarea.get('1.0','end').strip()
+    if textarea_content!="":
+        for string in textarea_content.split(","):
+            item = string.strip()
+            df[f"{item} present"] = df[selected_col.get()].apply(lambda x: is_present(x, item))
+    # Create STACKrate survey columns depending on user's choices:
     if var_checkbox_stackrate.get():
         df[f"{selected_col.get()}: Survey_Results"] = df[selected_col.get()].apply(get_survey_results)
         # Extract all STACKrate IDs:
@@ -295,9 +331,12 @@ def process_input_strings():
                 all_stackrate_keys.update(survey_result.keys())
         # Create columns for all IDs:
         for key in all_stackrate_keys:
-            df[f"{selected_col.get()}: STACKrate ratings to ID {key}"] = df[f"{selected_col.get()}: Survey_Results"].apply(lambda x: extract_info(x, key, attr="ratings"))
-            df[f"{selected_col.get()}: STACKrate comments to ID {key}"] = df[f"{selected_col.get()}: Survey_Results"].apply(lambda x: extract_info(x, key, attr="comment"))
+            df[f"{selected_col.get()}: STACKrate ratings to ID {key}"] = df[f"{selected_col.get()}: Survey_Results"].apply(lambda x: extract_survey_info(x, key, attr="ratings"))
+            df[f"{selected_col.get()}: STACKrate comments to ID {key}"] = df[f"{selected_col.get()}: Survey_Results"].apply(lambda x: extract_survey_info(x, key, attr="comment"))
         df.drop(f"{selected_col.get()}: Survey_Results", axis=1, inplace=True)
+    # Create colum with random seeds depending on user's choices:
+    if var_checkbox_randseed.get():
+        df["Random seed"] = df[selected_col.get()].apply(get_random_seed)
     input_checkboxes_label.grid_forget()
     for box in input_checkboxes:
         box.grid_forget()
@@ -307,32 +346,35 @@ def process_input_strings():
         box.grid_forget()
     sep2.grid_forget()
     additional_options_label.grid_forget()
+    textarea_label.grid_forget()
+    textarea.grid_forget()
     checkbox_seconds.grid_forget()
     hide_language_radiobuttons()
     checkbox_stackrate.grid_forget()
+    checkbox_randseed.grid_forget()
     process_button.grid_forget()
     export_button_info.grid(row=1)
     export_button.grid(row=2)
 
-# Closes GUI window
+# Closes GUI window:
 def close_window():
     root.destroy()
 
-# GUI setup
+# GUI setup:
 root = tk.Tk()
 root.title("STACK Response File Processor")
 
-# GUI elements for opening the input csv file
+# GUI elements for opening the input csv file:
 open_button_info = tk.Label(root, text="Click on the following button to select a CSV file:")
 open_button_info.grid(row=1)
 open_button = tk.Button(root, text="Open CSV file", command=open_csv_file)
 open_button.grid(row=2)
 
-# GUI elements for selecting the columns
+# GUI elements for selecting the columns:
 spalten_label = tk.Label(root, text="Your CSV file contains the following columns. \nPlease select the one that relate to a STACK task and from which you wish to extract information about student responses.")
 submit_button_cols = tk.Button(root, text="Submit", command=submit_columns)
 
-# GUI elements for selecting the desired input and prt names
+# GUI elements for selecting the desired input and prt names:
 input_checkboxes_label = tk.Label(root,
         text="The following input names have been found in your column. Please select those that you want to get a report for.")
 sep1 = ttk.Separator(root,orient='horizontal')
@@ -342,15 +384,19 @@ def close_window():
         text="In addition, you can choose the following options (optional):")
 sep2 = ttk.Separator(root,orient='horizontal')
 
+# GUI elements for text area:
+textarea_label = tk.Label(root, text="Comma-separated list of strings for which the quiz data will be searched (e.g. PRT answer notes such as prt1-1-F).\nFor each string specified, a column will be created that contains True or False, depending on whether it is present in the respective row.")
+textarea = tk.Text(root, height=3)
+
 # GUI elements for "Time to seconds" feature:
 var_checkbox_seconds = tk.BooleanVar()
 checkbox_seconds = tk.Checkbutton(root, text="Insert column for time spent in seconds (only English and German response files)",
     variable=var_checkbox_seconds, command=toggle_seconds_options)
 radio_language_label = tk.Label(root, text="Please select the language of your input file:")
 lang_radiobuttons = []
 selected_lang = tk.StringVar()
+# Create radiobutton for each language:
 for language in list(time_languages.keys()):
-    # Create radiobutton for each langaue:
     radiobutton = tk.Radiobutton(
         root,
         text=language,
@@ -364,13 +410,18 @@ def close_window():
 var_checkbox_stackrate = tk.BooleanVar()
 checkbox_stackrate = tk.Checkbutton(root, text="Insert columns for STACKrate evaluation results",
     variable=var_checkbox_stackrate)
+
+# GUI elements for random seed feature:
+var_checkbox_randseed = tk.BooleanVar()
+checkbox_randseed = tk.Checkbutton(root, text="Insert column for random seeds",
+    variable=var_checkbox_randseed)
 process_button = tk.Button(root, text="Submit", command=process_input_strings)
 
-# GUI elements for export
+# GUI elements for export:
 export_button_info = tk.Label(root, text="Click on the following button to select a storage location for the output file and start the export:")
 export_button = tk.Button(root, text="Save CSV file", command=export_csv_file)
 
-# GUI elements for the close page
+# GUI elements for the close page:
 success_text = tk.Label(root, text="The file has been saved successfully!")
 close_button = tk.Button(root, text="Close", command=close_window)