public IActionResult Data(DataService dataService)
{
PredictionData predictionData = dataService.getPredictionData();
DataViewModel viewModel = new DataViewModel(predictionData);
return(View(viewModel));
}
public async Task <IActionResult> Edit(int id, [Bind("PredictionID,TipsterID,MatchID,predictionDate,matchOutcome")] PredictionData prediction)
{
if (id != prediction.PredictionID)
{
return(NotFound());
}
if (ModelState.IsValid)
{
try
{
_context.Update(prediction);
await _context.SaveChangesAsync();
}
catch (DbUpdateConcurrencyException)
{
if (!PredictionExists(prediction.PredictionID))
{
return(NotFound());
}
else
{
throw;
}
}
return(RedirectToAction(nameof(Index)));
}
ViewData["MatchID"] = new SelectList(_context.Match, "MatchID", "MatchName", prediction.MatchID);
ViewData["TipsterID"] = new SelectList(_context.Tipster, "TipsterId", "Email", prediction.TipsterID);
return(View(prediction));
}
public MainWindow()
{
InitializeComponent();
ModelThreat = new ModelPrediction.View.ModelThreat.ModelThreat();
AnaliticData = new AnaliticData();
PredictionData = new PredictionData();
OutputePanel = new OutputePanel();
ModelThreatVM.SetLabels(nameModel, countThreat, dateCreate, nameThreat, number, countData);
}
public async Task <IActionResult> Create([Bind("PredictionID,TipsterID,MatchID,predictionDate,matchOutcome")] PredictionData prediction)
{
if (ModelState.IsValid)
{
_context.Add(prediction);
await _context.SaveChangesAsync();
return(RedirectToAction(nameof(Index)));
}
ViewData["MatchID"] = new SelectList(_context.Match, "MatchID", "MatchName", prediction.MatchID);
ViewData["TipsterID"] = new SelectList(_context.Tipster, "TipsterId", "Email", prediction.TipsterID);
return(View(prediction));
}
public IList <double> Execute(IList <double> source)
{
var count = source.Count;
if (count == 0)
{
return(new double[0]);
}
var res = new double[count];
var context = Context;
Contract.Assert(context != null);
var size = count / 2;
var data = source.Take(size).Select(PredictionData.MakePredictionData);
var ml = new MLContext();
var dataView = ml.Data.LoadFromEnumerable(data);
const string outputColumnName = "Prediction";
const string inputColumnName = "Value";
var args = new SsaChangePointDetector.Arguments()
{
Source = inputColumnName,
Name = outputColumnName,
Confidence = Confidence, // The confidence for spike detection in the range [0, 100]
ChangeHistoryLength = size / 4, // The length of the sliding window on p-values for computing the martingale score.
TrainingWindowSize = size / 2, // The number of points from the beginning of the sequence used for training.
SeasonalWindowSize = size / 8, // An upper bound on the largest relevant seasonality in the input time - series."
};
// Train the change point detector.
ITransformer model = new SsaChangePointEstimator(ml, args).Fit(dataView);
// Create a prediction engine from the model for feeding new data.
var engine = model.CreateTimeSeriesPredictionFunction <PredictionData, ChangePointPrediction>(ml);
for (var i = size; i < count; i++)
{
var prediction = engine.Predict(PredictionData.MakePredictionData(source[i]));
res[i] = prediction.Prediction[OutputNumber];
}
return(res);
}
private async void MessageCenterSubmitAsync(RecorderViewModel arg1, PredictionData data)
{
Device.BeginInvokeOnMainThread(async() =>
{
if (data == null)
{
await Application.Current.MainPage.DisplayAlert("Error", "No data returned. Please record your command again or contact support", "Cancel", "ok");
}
if (data.ClassId.Trim() == "Back or Go back" && data.Probability > 70.0)
{
await Application.Current.MainPage.Navigation.PopAsync();
}
else if (data.ClassId.Trim() == "item 1 or 1" && data.Probability > 70.0)
{
ItemSelectedCommand.Execute(Products[0]);
}
else if (data.ClassId.Trim() == "Item 2 or 2" && data.Probability > 70.0)
{
ItemSelectedCommand.Execute(Products[1]);
}
else if (data.ClassId.Trim() == "Item 3 or 3" && data.Probability > 70.0)
{
ItemSelectedCommand.Execute(Products[2]);
}
else if (data.ClassId.Trim() == "Item 4 or 4" && data.Probability > 70.0)
{
ItemSelectedCommand.Execute(Products[3]);
}
else if (data.ClassId.Trim() == "Item 5 or 5" && data.Probability > 70.0)
{
ItemSelectedCommand.Execute(Products[4]);
}
else if (data.ClassId.Trim() == "Open Cart" && data.Probability > 70.0)
{
CardItemCommand.Execute(null);
}
else
{
await Application.Current.MainPage.DisplayAlert("Error", "Please record your command again. Recording is not clear enough", "Cancel", "ok");
}
});
}
public DataViewModel(PredictionData data)
{
TotalPredictions = data.TotalPredictions;
TotalHomeWinsPredicted = data.TotalHomeWinsPredicted;
TotalAwayWinsPredicted = data.TotalAwayWinsPredicted;
TotalStrongHomeWinsPredicted = data.TotalStrongHomeWinsPredicted;
TotalStrongAwayWinsPredicted = data.TotalStrongAwayWinsPredicted;
TotalStrongWinsPredicted = data.TotalStrongWinsPredicted;
TotalDrawsPredicted = data.TotalDrawsPredicted;
TotalCorrect = data.TotalCorrect;
TotalCorrectScores = data.TotalCorrectScores;
TotalCorrectDraws = data.TotalCorrectDraws;
TotalCorrectStrongWins = data.TotalCorrectStrongWins;
TotalCorrectHomeWins = data.TotalCorrectHomeWins;
TotalCorrectStrongHomeWins = data.TotalCorrectStrongHomeWins;
TotalCorrectAwayWins = data.TotalCorrectAwayWins;
TotalCorrectStrongAwayWins = data.TotalCorrectStrongAwayWins;
SetPercentages();
}
public PredictionData getPredictionData()
{
PredictionData predictionData = new PredictionData();
try
{
using (SqlConnection connection = new SqlConnection(builder.ConnectionString))
{
using (SqlCommand sqlCommand = new SqlCommand("SELECT * from PredictionTally as data ", connection))
{
connection.Open();
using (SqlDataReader reader = sqlCommand.ExecuteReader())
{
reader.Read();
predictionData.TotalPredictions = int.Parse(reader["TotalPredictions"].ToString());
predictionData.TotalHomeWinsPredicted = int.Parse(reader["TotalPredictedHomeWins"].ToString());
predictionData.TotalAwayWinsPredicted = int.Parse(reader["TotalPredictedAwayWins"].ToString());
predictionData.TotalStrongHomeWinsPredicted = int.Parse(reader["TotalPredictedStrongHomeWins"].ToString());
predictionData.TotalStrongAwayWinsPredicted = int.Parse(reader["TotalPredictedStrongAwayWins"].ToString());
predictionData.TotalStrongWinsPredicted = int.Parse(reader["TotalPredictedStrongWins"].ToString());
predictionData.TotalDrawsPredicted = int.Parse(reader["TotalPredictedDraws"].ToString());
predictionData.TotalCorrect = int.Parse(reader["TotalCorrect"].ToString());
predictionData.TotalCorrectScores = int.Parse(reader["TotalCorrectScores"].ToString());
predictionData.TotalCorrectDraws = int.Parse(reader["CorrectDraws"].ToString());
predictionData.TotalCorrectStrongWins = int.Parse(reader["TotalOverallCorrectStrongWins"].ToString());
predictionData.TotalCorrectHomeWins = int.Parse(reader["TotalOverallCorrectHomeWins"].ToString());
predictionData.TotalCorrectStrongHomeWins = int.Parse(reader["TotalCorrectStrongHomeWins"].ToString());
predictionData.TotalCorrectAwayWins = int.Parse(reader["TotalOverallCorrectAwayWins"].ToString());
predictionData.TotalCorrectStrongAwayWins = int.Parse(reader["TotalCorrectStrongAwayWins"].ToString());
reader.Close();
}
connection.Close();
}
}
return(predictionData);
}catch (Exception e)
{
throw new Exception(e.Message);
}
}
public IList <double> Execute(ISecurity source)
{
var count = source.Bars.Count;
if (count == 0)
{
return(new double[0]);
}
var size = HistoryBarsBack * HorizontalLines;
var scheme = GetSchemaDefinition(size);
var mlContext = MakeMlContext();
var file = new FileInfo(ModelPath);
if (!file.Exists)
{
throw new ScriptException($"File '{ModelPath}' isn't found!");
}
var key = $"{file.LastWriteTime}:{ModelPath}";
var trainedModel = Context.LoadGlobalObject(key, () => mlContext.Model.Load(ModelPath, out _));
var predictionEngine =
mlContext.Model.CreatePredictionEngine <PredictionData, PredictionResult>(trainedModel,
inputSchemaDefinition: scheme);
var res = Context.GetArray <double>(count) ?? new double[count];
for (var i = TestStartBar; i < count; i++)
{
var chart = MakeChart(source, i, size, 1);
var data = new PredictionData {
Features = new VBuffer <float>(size, chart)
};
var predictedPreview = predictionEngine.Predict(data);
res[i] = predictedPreview.Score;
}
return(res);
}
private void MessageCenterSubmitAsync(RecorderViewModel arg1, PredictionData data)
{
Device.BeginInvokeOnMainThread(async() =>
{
if (data == null)
{
await Application.Current.MainPage.DisplayAlert("Error", "No data returned. Please record your command again or contact support", "Cancel", "ok");
}
if (data.ClassId.Trim() == "Add to cart" && data.Probability > 70.0)
{
AddToCartCommand.Execute(this);
}
else if (data.ClassId.Trim() == "Open Cart" && data.Probability > 70.0)
{
CardItemCommand.Execute(null);
}
else
{
await Application.Current.MainPage.DisplayAlert("Error", "Please record your command again. Recording is not clear enough", "Cancel", "ok");
}
});
}
private async void MessageCenterSubmitAsync(RecorderViewModel arg1, PredictionData data)
{
Device.BeginInvokeOnMainThread(async() =>
{
if (data == null)
{
await Application.Current.MainPage.DisplayAlert("Error", "No data returned. Please record your command again or contact support", "Cancel", "ok");
}
if (data.ClassId.Trim() == "Men's shoes" && data.Probability > 70.0)
{
var cat = Categories.FirstOrDefault(x => x.EngName.Trim() == "Men's Shoes");
CategorySelectedCommand.Execute(cat);
}
else if (data.ClassId.Trim() == "Men's watches" && data.Probability > 70.0)
{
var cat = Categories.FirstOrDefault(x => x.EngName.Trim() == "Men's Watches");
CategorySelectedCommand.Execute(cat);
}
else if (data.ClassId.Trim() == "Women's bags" && data.Probability > 70.0)
{
var cat = Categories.FirstOrDefault(x => x.EngName.Trim() == "Women's Bags");
CategorySelectedCommand.Execute(cat);
}
else if (data.ClassId.Trim() == "Women's shoes" && data.Probability > 70.0)
{
var cat = Categories.FirstOrDefault(x => x.EngName.Trim() == "Women's Shoes");
CategorySelectedCommand.Execute(cat);
}
else
{
await Application.Current.MainPage.DisplayAlert("Error", "Please record your command again. Recording is not clear enough", "Cancel", "ok");
}
});
}
private void giveTop3ToSceneManager(PredictionData prediction)
{
List <int> temp = new List <int>();
for (int i = 0; i < 5; i++)
{
if (ItemEventManager.Instance.ItemData[prediction.numbers[i]].Tag2 != "Filtered")
{
temp.Add(prediction.numbers[i]);
Debug.Log(prediction.numbers[i] + " : " + prediction.names[i]);
}
}
if (temp.Count >= 3)
{
for (int k = 0; k < 3; k++)
{
scene1Manager.top3PredictionIds[k] = temp[k];
}
UIManager.Instance.ActiveChoiceBtns(true);
scene1Manager.SetBtnsName();
}
}
private async void MessageCenterSubmitAsync(RecorderViewModel source, PredictionData data)
{
Device.BeginInvokeOnMainThread(async() =>
{
if (data == null)
{
await Application.Current.MainPage.DisplayAlert("Error", "No data returned. Please record your command again or contact support", "Cancel", "ok");
}
//if english
if (data.ClassId.Trim() == "Place order" && data.Probability > 70.0)
{
PlaceOrderCommand.Execute(null);
}
else if (data.ClassId == "Back or Go back" && data.Probability > 70.0)
{
await Application.Current.MainPage.Navigation.PopAsync();
}
else
{
await Application.Current.MainPage.DisplayAlert("Error", "Please record your command again. Recording is not clear enough", "Cancel", "ok");
}
});
}
public IList <double> Execute(ISecurity source)
{
var count = source.Bars.Count;
if (count == 0)
{
return(new double[0]);
}
var context = Context;
Contract.Assert(context != null);
/* var usedVars = 1;
* if (UseHigh)
* usedVars++;
* if (UseLow)
* usedVars++;
* if (UseVolume)
* usedVars++;
*
* var size = HistoryBarsBack * usedVars;*/
var key = $"PredictionData.{source.CacheName}.{HighOrLow}.{Period}.{HistoryBarsBack}";
var data = context.LoadObject <PredictionData[]>(key, () => null);
if (data?.Length != count)
{
data = null;
}
int size = 6;
if (data == null)
{
var preview = MakeHighLowCache(context, source, Period);
var closes = source.ClosePrices;
var rsi = Make(Series.RSI, closes, HistoryBarsBack);
var cci = Make(Series.CCI, source.Bars, HistoryBarsBack);
var stDev = Make(Series.StDev, closes, HistoryBarsBack);
var highs = Make(Series.Highest, source.HighPrices, HistoryBarsBack);
var lows = Make(Series.Lowest, source.LowPrices, HistoryBarsBack);
var ema = Make(Series.EMA, closes, HistoryBarsBack);
var ema2 = Make(Series.EMA, closes, HistoryBarsBack / 2);
var ema3 = Make(Series.EMA, closes, HistoryBarsBack * 2);
data = context.GetArray <PredictionData>(count) ?? new PredictionData[count];
for (var i = 0; i < data.Length; i++)
{
var label = (float)(HighOrLow ? preview[i].V1 : -preview[i].V2);
var values = new[]
{
(float)(ema[i] - closes[i]), (float)(ema3[i] - closes[i]),
(float)(ema3[i] - closes[i]), (float)rsi[i], (float)(ema[i] - ema2[i]),
(float)cci[i], (float)stDev[i], (float)(highs[i] - closes[i]),
(float)(lows[i] - closes[i])
};
size = values.Length;
data[i] = new PredictionData
{
Features = new VBuffer <float>(values.Length, values), Preview = label
};
}
context.StoreObject(key, data);
}
else
{
size = data[0].Features.Length;
}
var splitInterval = new Interval(ChangeMinutes, DataIntervals.MINUTE);
var helper = new SeparatedModelHelper <PredictionData, PredictionResult>(context, TrainDays,
splitInterval, CalcLastNumModels);
return(helper.Build(key, source.Bars, data, size, Period,
res => res.PredictedPreview * (HighOrLow ? 1 : -1)));
}