/// <summary>
/// Filters loaded data based on a given criteria set
/// </summary>
/// <param name="vm"></param>
private void FilterStudentsByGrade(TimelineAnalysisViewModel vm)
{
//present options to filter by
List <string> gradingCriteria = vm.GetAllGrades();
Console.WriteLine("***Grading Categories***");
for (int i = 0; i < gradingCriteria.Count; i++)
{
Console.WriteLine("{0}: {1}", i, gradingCriteria[i]);
}
Console.Write("Select category: ");
string categoryStr = Console.ReadLine();
//ask for min/max filter
Console.Write("Enter max score [100%]: ");
string maxScoreStr = Console.ReadLine();
Console.Write("Enter min score [0%]: ");
string minScoreStr = Console.ReadLine();
//parse strings, send off to VM for processing
int category = -1;
double maxScore = 200;
double minScore = 0;
if (Int32.TryParse(categoryStr, out category) && category > -1)
{
if (Double.TryParse(maxScoreStr, out maxScore) == false)
{
maxScore = 200;
}
if (Double.TryParse(minScoreStr, out minScore) == false)
{
minScore = 0;
}
int result = vm.FilterByGrade(gradingCriteria[category], minScore, maxScore);
Console.WriteLine("{0} entries removed from dataset.", result);
}
else
{
Console.WriteLine("Error parsing user input.");
}
}
/// <summary>
/// Creates a matrix of cycle activity for each student
/// </summary>
/// <param name="vm"></param>
private void OrderTransitionsByDate(TimelineAnalysisViewModel vm)
{
//step 1: get list of files to process
List <string> filesToProcess = new List <string>();
string fileName = "a";
Console.WriteLine("Enter files to process (-1 to stop)");
while ((fileName = GetFile()).Length > 0)
{
filesToProcess.Add(fileName);
}
//step 2: setup grade-bands (e.g. A, B, C, etc.) Hard coded for now as this is just for a
//single class
double maxScore = 200;
double[] gradeRanges = { 90, 78, 69, 60, 0 };
string[] gradeMap = { "A", "B", "C", "D", "F" };
//this produces a lot of files, so create a separate directory for the output
string outputDirectory = "TransitionsByDate";
if (Directory.Exists(outputDirectory) == false)
{
Directory.CreateDirectory(outputDirectory);
}
//finally, begin processing
//reset max score for A students
maxScore = 200;
//based on currently existing code, it is easier to reopen the file for
//each grade range
for (int i = 0; i < gradeRanges.Length; i++)
{
double bound = gradeRanges[i];
//reload the files
LoadFile(filesToProcess[0]);
for (int j = 1; j < filesToProcess.Count; j++)
{
vm.AppendTimeline(filesToProcess[j]);
}
//get grade data
vm.AttachGrades();
//filter based on grade data
vm.FilterByGrade("Assignment AVG", bound, maxScore);
//get transitions for this grade level
var result = vm.OrderTransitionsByDate();
var byDate = result.Item1;
//update scores for next grade boundary
maxScore = bound - 0.01;
//hold all day keys for easier access
int[] keys = byDate.Keys.OrderBy(k => k).ToArray();
//figure out all transitions
Dictionary <string, string> transitionsDict = new Dictionary <string, string>();
foreach (int key in keys)
{
foreach (string transition in byDate[key].Keys)
{
transitionsDict[transition] = transition;
}
}
string[] transitions = transitionsDict.Keys.ToArray();
//write aggregate information to a file
CsvWriter writer = new CsvWriter();
//blank line for transitions
writer.AddToCurrentLine("Transition");
//add in header row
foreach (int key in keys)
{
writer.AddToCurrentLine(key);
}
writer.CreateNewRow();
//add in data
foreach (string transition in transitions)
{
//data for given transition
writer.AddToCurrentLine("T: " + transition);
foreach (int key in keys)
{
if (byDate[key].ContainsKey(transition))
{
//add in data for given transition
writer.AddToCurrentLine(byDate[key][transition].Count);
}
else
{
//no data, add a 0
writer.AddToCurrentLine(0);
}
}
writer.CreateNewRow();
}
//aggregate class results
using (TextWriter tw = File.CreateText(string.Format("{0}/aggregate_{1}.csv", outputDirectory, gradeMap[i])))
{
tw.Write(writer.ToString());
Console.WriteLine("Created file aggregate_{0}.csv", gradeMap[i]);
}
//write individual student information to file
writer = new CsvWriter();
writer.AddToCurrentLine("UserID");
//blank line for transitions
writer.AddToCurrentLine("Transition");
//add in header row
foreach (int key in keys)
{
writer.AddToCurrentLine(key);
}
writer.CreateNewRow();
//add in data
var userData = result.Item2;
foreach (int userId in userData.Keys)
{
foreach (string transition in transitions)
{
//user id
writer.AddToCurrentLine(userId);
//data for given transition
writer.AddToCurrentLine("T: " + transition);
foreach (int key in keys)
{
if (userData[userId][key].ContainsKey(transition))
{
//add in data for given transition
writer.AddToCurrentLine(userData[userId][key][transition].Count);
}
else
{
//no data, add a 0
writer.AddToCurrentLine(0);
}
}
writer.CreateNewRow();
}
}
using (TextWriter tw = File.CreateText(string.Format("{0}/students_{1}.csv", outputDirectory, gradeMap[i])))
{
tw.Write(writer.ToString());
Console.WriteLine("Created file students_{0}.csv", gradeMap[i]);
}
}
}
/*
* What I want to do:
* For each assignment:
* figure out common sequences of length m to n
* For each student, for each grade band (A-F), again determine frequences of length m to n
* Build a frequency distribution for each grade band by sequence
* */
private void BuildTransitionFrequencyCounts(TimelineAnalysisViewModel vm)
{
//step 1: get list of files to process
List <string> filesToProcess = new List <string>();
string fileName = "a";
Console.WriteLine("Enter files to process (-1 to stop)");
while ((fileName = GetFile()).Length > 0)
{
filesToProcess.Add(fileName);
}
//step 2: setup grade-bands (e.g. A, B, C, etc.) Hard coded for now as this is just for a
//single class
double maxScore = 200;
double[] gradeRanges = { 90, 78, 69, 60, 0 };
string[] gradeMap = { "A", "B", "C", "D", "F" };
//step 3: get sequence boundaries. Again, hard coded for now
int startingSequenceLength = 2;
int endingSequenceLength = 25;
//step 4: get assignments.
string[] assignments = { "Assignment #1",
"Assignment #2",
"Assignment #3",
"Assignment #4",
"Assignment #5",
"Assignment #6",
"Assignment #7" };
int assignmentCounter = 0;
//this produces a lot of files, so create a separate directory for the output
string outputDirectory = "TransitionFrequencyCounts";
if (Directory.Exists(outputDirectory) == false)
{
Directory.CreateDirectory(outputDirectory);
}
//finally, begin processing
foreach (string fileToProcess in filesToProcess)
{
string folderName = fileToProcess.Replace("#", "");
string outputPath = Path.Combine(outputDirectory, folderName);
if (Directory.Exists(outputPath) == false)
{
Directory.CreateDirectory(outputPath);
}
for (int sequenceLength = startingSequenceLength; sequenceLength <= endingSequenceLength; sequenceLength++)
{
//reset max score for A students
maxScore = 200;
//based on currently existing code, it is easier to reopen the file for
//each grade range
for (int i = 0; i < gradeRanges.Length; i++)
{
double bound = gradeRanges[i];
//reload the file
LoadFile(fileToProcess);
//get grade data
vm.AttachGrades();
//filter based on grade data
vm.FilterByGrade(assignments[assignmentCounter], bound, maxScore);
//update scores for next grade boundary
maxScore = bound - 0.01;
//build markov transitions
vm.BuildDefaultMarkovStates();
//figure out sequence distribution for entire data set and for individual students
Dictionary <string, int> transitions = vm.GetAllTransitionCombinations(sequenceLength);
//interesting transitions are those in which we have at least 5 occurrances
var interestingTransitions = transitions.Where(t => t.Value > 5).OrderBy(t => t.Value).ToList();
//write this information to a file
CsvWriter writer = new CsvWriter();
//aggregate class results
Console.WriteLine("Processing transition sequences of length {0}...", sequenceLength);
foreach (KeyValuePair <string, int> kvp in interestingTransitions)
{
writer.AddToCurrentLine(kvp.Key);
writer.AddToCurrentLine(kvp.Value.ToString());
writer.CreateNewRow();
}
using (TextWriter tw = File.CreateText(string.Format("{0}/aggregate_{1}_{2}.csv", outputPath, sequenceLength, gradeMap[i])))
{
tw.Write(writer.ToString());
}
//individual students
//add header data
writer = new CsvWriter();
writer.AddToCurrentLine("UserId");
writer.AddToCurrentLine("Grade");
foreach (var kvp in interestingTransitions)
{
writer.AddToCurrentLine(kvp.Key);
}
writer.CreateNewRow();
foreach (var user in vm.Timeline.Values)
{
//first row for users is raw values
writer.AddToCurrentLine(user.OsbideId);
writer.AddToCurrentLine(gradeMap[i]);
//only use the interesting states as columns as identified in the aggregate analysis
foreach (KeyValuePair <string, int> kvp in interestingTransitions)
{
if (user.TransitionCounts.ContainsKey(kvp.Key) == true)
{
writer.AddToCurrentLine(user.TransitionCounts[kvp.Key]);
}
else
{
writer.AddToCurrentLine("0");
}
}
writer.CreateNewRow();
//2nd row contains normalized values
writer.AddToCurrentLine(user.OsbideId);
writer.AddToCurrentLine(gradeMap[i]);
int totalTransitions = user.TransitionCounts.Values.Sum();
//only use the interesting states as columns as identified in the aggregate analysis
foreach (KeyValuePair <string, int> kvp in interestingTransitions)
{
if (user.TransitionCounts.ContainsKey(kvp.Key) == true)
{
writer.AddToCurrentLine(user.TransitionCounts[kvp.Key] / (double)totalTransitions);
}
else
{
writer.AddToCurrentLine("0");
}
}
writer.CreateNewRow();
}
using (TextWriter tw = File.CreateText(string.Format("{0}/individual_{1}_{2}.csv", outputPath, sequenceLength, gradeMap[i])))
{
tw.Write(writer.ToString());
}
}
}
//move to the next assignment
assignmentCounter++;
}
}