public void GetSocialRoles(CommentMetricsViewModel vm)
{
Console.Write("Enter starting date (YYYY-MM-DD): ");
string startDateString = Console.ReadLine();
Console.Write("Enter ending date (YYYY-MM-DD): ");
string endDateString = Console.ReadLine();
DateTime startDate = DateTime.Parse(startDateString);
DateTime endDate = DateTime.Parse(endDateString);
Dictionary <int, int> roles = vm.CalculateSocialRole(startDate, endDate);
CsvWriter csv = new CsvWriter();
csv.AddToCurrentLine("UserId");
csv.AddToCurrentLine("SocialRole");
csv.CreateNewRow();
foreach (var kvp in roles)
{
csv.AddToCurrentLine(kvp.Key.ToString());
csv.AddToCurrentLine(kvp.Value.ToString());
csv.CreateNewRow();
}
Console.Write("Enter destination file: ");
string outputFileName = Console.ReadLine();
using (TextWriter tw = File.CreateText(outputFileName))
{
tw.Write(csv.ToString());
}
Console.WriteLine("CSV file written.");
}
/// <summary>
/// Writes the loaded timeline information to a CSV. The format of the CSV file
/// should match so that it could be read by ParseTimeline()
/// </summary>
/// <param name="fileName"></param>
public void WriteLoadedDataToCsv(string fileName)
{
CsvWriter writer = new CsvWriter();
foreach (var user in Timeline.Values)
{
//first column is user id
writer.AddToCurrentLine(user.OsbideId);
//all other rows are state transitions
foreach (TimelineState state in user.RawStates)
{
string stateAsString = "";
if (state.IsSocialEvent)
{
stateAsString = string.Format("{0};{1}", state.State, state.StartTime);
}
else
{
stateAsString = string.Format("{0};{1};{2}", state.State, state.StartTime, state.EndTime);
}
writer.AddToCurrentLine(stateAsString);
}
writer.CreateNewRow();
}
//write to file
using (TextWriter tw = File.CreateText(fileName))
{
tw.Write(writer.ToString());
}
}
public void WriteToCsv(List <List <string> > matrix, string fileName)
{
//write results to file
CsvWriter writer = new CsvWriter();
foreach (List <string> line in matrix)
{
foreach (string cell in line)
{
writer.AddToCurrentLine(cell);
}
writer.CreateNewRow();
}
//write to file
using (TextWriter tw = File.CreateText(fileName))
{
tw.Write(writer.ToString());
}
}
public void WriteToCsv(string fileName)
{
List <int> keys = _threadedComments.Keys.ToList();
keys.Sort();
CsvWriter csvWriter = new CsvWriter();
//write header
csvWriter.AddToCurrentLine("Post ID");
csvWriter.AddToCurrentLine("Date");
csvWriter.AddToCurrentLine("Author");
csvWriter.AddToCurrentLine("AuthorRole");
csvWriter.AddToCurrentLine("Content");
csvWriter.AddToCurrentLine("Reading Ease");
csvWriter.AddToCurrentLine("Reading Grade Level");
csvWriter.AddToCurrentLine("# Helpful Marks");
csvWriter.AddToCurrentLine("Time to first reply (minutes)");
csvWriter.CreateNewRow();
//write entries
int commentCounter = 1;
foreach (int key in keys)
{
Comment rootComment = _threadedComments[key];
//calculate time to first reply
double numMinutes = -1;
if (rootComment.ChildComments.Count > 0)
{
numMinutes = (rootComment.ChildComments[0].DateReceived - rootComment.DateReceived).TotalMinutes;
numMinutes = Math.Round(numMinutes, 2);
}
//write root, then all child comments
csvWriter.AddToCurrentLine(commentCounter.ToString());
csvWriter.AddToCurrentLine(rootComment.DateReceived.ToString("yyyy-MM-dd HH:mm:ss"));
csvWriter.AddToCurrentLine(rootComment.UserId.ToString());
csvWriter.AddToCurrentLine(rootComment.User.Role.ToString());
csvWriter.AddToCurrentLine(rootComment.Content);
csvWriter.AddToCurrentLine(rootComment.FleschReadingEase.ToString());
csvWriter.AddToCurrentLine(rootComment.FleschKincaidGradeLevel.ToString());
csvWriter.AddToCurrentLine(rootComment.HelpfulMarks);
csvWriter.AddToCurrentLine(numMinutes);
csvWriter.CreateNewRow();
//now do all children
int childCounter = 1;
foreach (Comment child in rootComment.ChildComments)
{
csvWriter.AddToCurrentLine(string.Format("{0}.{1}", commentCounter, childCounter));
csvWriter.AddToCurrentLine(child.DateReceived.ToString("yyyy-MM-dd HH:mm:ss"));
csvWriter.AddToCurrentLine(child.UserId.ToString());
csvWriter.AddToCurrentLine(child.User.Role.ToString());
csvWriter.AddToCurrentLine(child.Content);
csvWriter.AddToCurrentLine(child.FleschReadingEase.ToString());
csvWriter.AddToCurrentLine(child.FleschKincaidGradeLevel.ToString());
csvWriter.AddToCurrentLine(child.HelpfulMarks);
csvWriter.AddToCurrentLine(-1);
csvWriter.CreateNewRow();
childCounter++;
}
commentCounter++;
}
using (TextWriter tw = File.CreateText(fileName))
{
tw.Write(csvWriter.ToString());
}
}
/// <summary>
/// Writes time in state information to a CSV file
/// </summary>
/// <param name="fileName"></param>
public void WriteTimeInStateToCsv(string fileName)
{
//write results to file
CsvWriter writer = new CsvWriter();
//add header row
writer.AddToCurrentLine("User ID");
List <string> states = GetAllStates();
foreach (string state in states)
{
writer.AddToCurrentLine(state);
}
//add grades if loaded
List <string> grades = GetAllGrades();
foreach (string grade in grades)
{
writer.AddToCurrentLine(grade);
}
writer.CreateNewRow();
//add data rows
foreach (var item in Timeline.Values)
{
writer.AddToCurrentLine(item.OsbideId.ToString());
//add state information
foreach (string state in states)
{
//normalized states will use the "NormalizedTimeInState" property.
//non-normalized states will use the "MillisecondsInState" property.
if (item.GetAggregateState(state).NormalizedTimeInState > 0)
{
writer.AddToCurrentLine(item.GetAggregateState(state).NormalizedTimeInState.ToString("0.0000000"));
}
else
{
writer.AddToCurrentLine(item.GetAggregateState(state).TimeInState.TotalSeconds.ToString());
}
}
//add grade information
foreach (string grade in grades)
{
if (item.Grades.ContainsKey(grade) == true)
{
writer.AddToCurrentLine(item.Grades[grade].ToString());
}
else
{
writer.AddToCurrentLine("0");
}
}
writer.CreateNewRow();
}
//write to file
using (TextWriter tw = File.CreateText(fileName))
{
tw.Write(writer.ToString());
}
}
/// <summary>
/// Writes transition counts to a CSV file
/// </summary>
/// <param name="fileName"></param>
public void WriteTransitionsToCsv(string fileName)
{
//write results to file
CsvWriter writer = new CsvWriter();
//add header row
writer.AddToCurrentLine("User ID");
var query = from item in GetAllTransitions()
select new
{
Key = item.Key,
Value = item.Value,
AsString = string.Format("{0};{1}", item.Key, item.Value),
Kvp = item
};
var transitions = query.OrderBy(q => q.AsString).ToList();
foreach (var transition in transitions)
{
writer.AddToCurrentLine(transition.AsString);
}
//add grades if loaded
List <string> grades = GetAllGrades();
foreach (string grade in grades)
{
writer.AddToCurrentLine(grade);
}
writer.CreateNewRow();
//add data rows
foreach (var item in Timeline.Values)
{
writer.AddToCurrentLine(item.OsbideId.ToString());
//add state information
foreach (var transition in transitions)
{
if (item.Transitions.ContainsKey(transition.Kvp) == true)
{
writer.AddToCurrentLine(item.Transitions[transition.Kvp].ToString());
}
else
{
writer.AddToCurrentLine("0");
}
}
//add grade information
foreach (string grade in grades)
{
if (item.Grades.ContainsKey(grade) == true)
{
writer.AddToCurrentLine(item.Grades[grade].ToString());
}
else
{
writer.AddToCurrentLine("0");
}
}
writer.CreateNewRow();
}
//write to file
using (TextWriter tw = File.CreateText(fileName))
{
tw.Write(writer.ToString());
}
}
public void Run()
{
int userChoice = 0;
ActionRequestLogViewModel vm = new ActionRequestLogViewModel();
while (userChoice != (int)MenuOption.Exit)
{
Console.WriteLine((int)MenuOption.LoadLogsByDate + ". Reload access logs BY DATE from DB (costly)");
Console.WriteLine((int)MenuOption.LoadRawLogsFromDb + ". Reload RAW access logs from DB (costly)");
Console.WriteLine((int)MenuOption.LoadRawLogsFromCache + ". Load RAW access logs from cache");
Console.WriteLine((int)MenuOption.DetailsViewCounts + ". Get details view statistics");
Console.WriteLine((int)MenuOption.AggregateByWeek + ". Aggregate daily activity by week");
Console.WriteLine((int)MenuOption.GenerateWeeklyStatistics + ". Generate summary weekly statistics by controller and action");
Console.WriteLine((int)MenuOption.CountProfileViews + ". Count profile views");
Console.WriteLine((int)MenuOption.Exit + ". Exit");
Console.Write(">> ");
string rawInput = Console.ReadLine();
if (Int32.TryParse(rawInput, out userChoice) == false)
{
Console.WriteLine("Invalid input.");
}
else
{
MenuOption selection = (MenuOption)userChoice;
switch (selection)
{
case MenuOption.LoadLogsByDate:
vm.LoadLogsByDate();
Console.WriteLine("access logs parsed...");
break;
case MenuOption.LoadRawLogsFromDb:
vm.LoadRawLogsFromDb();
Console.WriteLine("raw logs loaded...");
break;
case MenuOption.LoadRawLogsFromCache:
vm.LoadRawLogsFromCache();
break;
case MenuOption.DetailsViewCounts:
var viewCounts = vm.GenerateDetailsViewStatistics();
foreach (var kvp in viewCounts)
{
//unique students
Dictionary <int, int> students = new Dictionary <int, int>();
foreach (var actionLog in kvp.Value)
{
if (students.ContainsKey(actionLog.CreatorId) == false)
{
students.Add(actionLog.CreatorId, 1);
}
students[actionLog.CreatorId] += 1;
}
CsvWriter writer = new CsvWriter();
writer.AddToCurrentLine(kvp.Key);
writer.CreateNewRow();
foreach (var student in students)
{
writer.AddToCurrentLine(student.Value);
writer.CreateNewRow();
}
using (TextWriter tw = File.CreateText(kvp.Key + ".csv"))
{
tw.Write(writer.ToString());
}
Console.WriteLine("{0}: {1} (num students: {2})", kvp.Key, kvp.Value.Count, students.Keys.Count);
}
break;
case MenuOption.AggregateByWeek:
List <List <string> > spreadsheet = vm.AggregateLogsByWeek();
Console.Write("Enter destination file: ");
string fileName = Console.ReadLine();
vm.WriteToCsv(spreadsheet, fileName);
Console.WriteLine("daily activity aggregated...");
break;
case MenuOption.GenerateWeeklyStatistics:
//aggreate weekly statistics
vm.AggregateLogsByWeek();
//generate one CSV file for each controller / action pairing
foreach (string controllerName in vm.ControllerActions.Keys)
{
foreach (string actionName in vm.ControllerActions[controllerName].Keys)
{
List <List <string> > matrix = vm.FilterActivity(controllerName, actionName);
string name = string.Format("weekly_{0}_{1}.csv", controllerName, actionName);
vm.WriteToCsv(matrix, name);
}
}
break;
case MenuOption.CountProfileViews:
var result = vm.CountProfileVisits();
foreach (var kvp in result)
{
Console.WriteLine("{0}: {1}", kvp.Key, kvp.Value);
}
break;
case MenuOption.Exit:
Console.WriteLine("Returning to main menu.");
break;
default:
break;
}
}
Console.WriteLine("");
}
}
/// <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]);
}
}
}
/// <summary>
/// Similar to <see cref="BuildTransitionFrequencyCounts"/>, but instead creates a single file
/// per transition length for all students and all loaded files.
/// </summary>
/// <param name="vm"></param>
private void AggregateTransitionFrequencyCounts(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);
}
//load all data into VM
vm.LoadTimeline(filesToProcess[0]);
for (int i = 1; i < filesToProcess.Count; i++)
{
vm.AppendTimeline(filesToProcess[i]);
}
//step2: get sequence boundaries. Again, hard coded for now
int startingSequenceLength = 2;
int endingSequenceLength = 25;
//this produces a lot of files, so create a separate directory for the output
string outputDirectory = "AggregateTransitionFrequencyCounts";
if (Directory.Exists(outputDirectory) == false)
{
Directory.CreateDirectory(outputDirectory);
}
/*
* What I need to do:
* Get all sequences.
* For each sequence:
* Determine if similar to other known sequences. If so, combine into same set. (disjoint set?)
* */
Dictionary <int, Dictionary <string, int> > allTransitions = new Dictionary <int, Dictionary <string, int> >();
//begin file processing
for (int sequenceLength = startingSequenceLength; sequenceLength <= endingSequenceLength; sequenceLength++)
{
//get grade data
vm.AttachGrades();
//build markov transitions
vm.BuildDefaultMarkovStates();
//figure out sequence distribution for entire data set and for individual students
Dictionary <string, int> transitions = vm.GetAllTransitionCombinations(sequenceLength);
//filter out singletons
var smallKeys = transitions.Where(t => t.Value < 5).Select(t => t.Key).ToList();
foreach (string key in smallKeys)
{
transitions.Remove(key);
}
//save for future use
allTransitions.Add(sequenceLength, transitions);
Console.WriteLine("Loaded transitions of length {0}.", sequenceLength);
}
//use Needleman-Wunsch algorithm and disjoint sets to combine similar sequences
DisjointSet <string> matches = new DisjointSet <string>();
int matchCount = 0;
//start with large sequences as it will make it more likely that these will be the "top" of the disjoint set
int startingNumber = (int)'a';
for (int sequenceLength = endingSequenceLength; sequenceLength >= startingSequenceLength; sequenceLength--)
{
Console.WriteLine("Matching sequences of length {0}", sequenceLength);
//Needleman-Wunsch works on single characters, so we need to transform Markov-like numbers to letters
Dictionary <string, int> originalSequences = allTransitions[sequenceLength];
Dictionary <string, int> modifiedSequences = new Dictionary <string, int>();
foreach (var kvp in originalSequences)
{
//convert into numbers
int[] pieces = kvp.Key.Split('_').Select(k => Convert.ToInt32(k) + startingNumber).ToArray();
//then, convert back to characters
char[] sequence = pieces.Select(p => Convert.ToChar(p)).ToArray();
//and finally into a string
string charSequence = string.Join("_", sequence);
//lastly, remember this sequence
modifiedSequences.Add(charSequence, kvp.Value);
}
//prime the disjoint set
foreach (string key in modifiedSequences.Keys)
{
matches.Find(key);
}
//having converted to character state representations, now run the Needleman-Wunsch algorithm
List <string> sequences = modifiedSequences.Keys.ToList();
for (int i = 0; i < sequences.Count; i++)
{
for (int j = i + 1; j < sequences.Count; j++)
{
string first = matches.Find(sequences[i]);
string second = matches.Find(sequences[j]);
//automatically count sequences as the same when one sequence is a complete substring of another sequence
string firstSequence = sequences[i];
string secondSequence = sequences[j];
if (firstSequence.Replace(secondSequence, "").Length == 0 ||
secondSequence.Replace(firstSequence, "").Length == 0
)
{
matches.UnionWith(first, second);
matchCount++;
}
else
{
//Use NW to check for alignment
//align the two sequences
var result = NeedlemanWunsch.Align(first, second);
//if score is similar, then count the sequences as the same (union)
if ((double)NeedlemanWunsch.ScoreNpsmSequence(result.Item1, result.Item2) < 3)
{
matches.UnionWith(first, second);
matchCount++;
}
}
}
}
}
//now, get all sets and figure out popularity of each set
Console.WriteLine("{0} unions performed.", matchCount);
List <List <string> > allSets = matches.AllSets();
List <List <string> > smallerSets = allSets.Where(s => s.Count > 1).ToList();
Dictionary <string, int> popularityDict = new Dictionary <string, int>();
Console.WriteLine("Calculating popularity of {0} sets...", allSets.Count);
foreach (List <string> set in allSets)
{
foreach (string item in set)
{
//convert back to Markov-style transitions
int[] pieces = item.Split('_').Select(c => Convert.ToChar(c)).Select(c => (int)c - startingNumber).ToArray();
string key = string.Join("_", pieces);
if (popularityDict.ContainsKey(key) == false)
{
popularityDict.Add(key, 0);
}
//add in counts to the popularity dictionary
popularityDict[key] += allTransitions[pieces.Length][key];
}
}
//write this information to a file
CsvWriter writer = new CsvWriter();
//aggregate class results
Console.WriteLine("Writing most popular sequences to file.");
foreach (KeyValuePair <string, int> kvp in popularityDict.OrderByDescending(p => p.Value))
{
int[] pieces = kvp.Key.Split('_').Select(c => Convert.ToInt32(c)).ToArray();
string npsmKey = string.Join("_", pieces.Select(p => vm.StateNumberToNpsmString(p)).ToArray());
writer.AddToCurrentLine(npsmKey);
writer.AddToCurrentLine(kvp.Value.ToString());
writer.CreateNewRow();
}
using (TextWriter tw = File.CreateText(string.Format("popular_sequences.csv")))
{
tw.Write(writer.ToString());
}
}
/// <summary>
/// Locates common transition sequence cycles
/// </summary>
/// <param name="vm"></param>
private void LocateCommonTransitionCycles(TimelineAnalysisViewModel vm)
{
//write results to a file
vm.NormalizeProgrammingStates();
vm.AttachGrades();
CsvWriter writer = new CsvWriter();
//build header
writer.AddToCurrentLine("UserId");
writer.AddToCurrentLine("TotalTimeProgramming");
writer.AddToCurrentLine("NumberOfCycles");
foreach (string[] sequence in vm.InterestingSequences)
{
string sequenceHeader = String.Join("_", sequence);
writer.AddToCurrentLine("Time_" + sequenceHeader);
writer.AddToCurrentLine("NormalizedTime_" + sequenceHeader);
writer.AddToCurrentLine("Count_" + sequenceHeader);
writer.AddToCurrentLine("NormalizedCount_" + sequenceHeader);
}
writer.AddToCurrentLine("CycleTime");
writer.AddToCurrentLine("PercentTimeAccountedFor");
//add grades if loaded
List <string> grades = vm.GetAllGrades();
foreach (string grade in grades)
{
writer.AddToCurrentLine(grade);
}
writer.CreateNewRow();
//write data cells
foreach (int userId in vm.StatesByUser.Keys)
{
writer.AddToCurrentLine(userId);
//get total time spent programming
StudentTimeline userTimeline = vm.Timeline[userId];
TimelineState timeState = userTimeline.GetAggregateState("normalized_total_time");
TimeSpan totalTime = timeState.EndTime - timeState.StartTime;
writer.AddToCurrentLine(totalTime.TotalMinutes);
TimeSpan cycleTime = new TimeSpan();
//and total number of cycles
int totalCycles = 0;
foreach (string[] sequence in vm.InterestingSequences)
{
string sequenceKey = String.Join("_", sequence);
totalCycles += vm.StatesByUser[userId][sequenceKey].Count;
}
writer.AddToCurrentLine(totalCycles);
//write total time spent in cycle
foreach (string[] sequence in vm.InterestingSequences)
{
string sequenceKey = String.Join("_", sequence);
TimeSpan sequenceTime = new TimeSpan();
foreach (PatternParserResult pattern in vm.StatesByUser[userId][sequenceKey])
{
foreach (TimelineState state in pattern.StateSequence)
{
if (state.EndTime < state.StartTime)
{
throw new Exception("EndTime must be larger than StartTime");
}
sequenceTime += state.EndTime - state.StartTime;
}
}
cycleTime += sequenceTime;
//total time
writer.AddToCurrentLine(sequenceTime.TotalMinutes);
//normalized time
writer.AddToCurrentLine(Math.Round((sequenceTime.TotalMinutes / totalTime.TotalMinutes) * 100, 2));
//count
writer.AddToCurrentLine(vm.StatesByUser[userId][sequenceKey].Count);
//normalized count
double normalizedCount = ((vm.StatesByUser[userId][sequenceKey].Count) / (double)totalCycles) * 100;
writer.AddToCurrentLine(Math.Round(normalizedCount, 2));
}
writer.AddToCurrentLine(cycleTime.TotalMinutes);
writer.AddToCurrentLine(Math.Round((cycleTime.TotalMinutes / totalTime.TotalMinutes) * 100, 2));
//add grade information
foreach (string grade in grades)
{
if (userTimeline.Grades.ContainsKey(grade) == true)
{
writer.AddToCurrentLine(userTimeline.Grades[grade].ToString());
}
else
{
writer.AddToCurrentLine("0");
}
}
writer.CreateNewRow();
}
using (TextWriter tw = File.CreateText("sequence_cycles.csv"))
{
tw.Write(writer.ToString());
}
Console.WriteLine("Finished locating sequences.");
}
/*
* 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++;
}
}
