protected async Task <TrainSet> ScheduleProcessNotImplemented(TrainSet data)
{
data.SetFailed("Not implimented yet");
return(data);
}
protected async Task <TrainSet> ScheduleProcessTwitter(TrainSet data)
{
var collection = await _twitterCollectionsStore.Get(data.SourceId);
if (collection == null)
{
data.SetFailed("Can not find source data");
return(data);
}
var sources = await _twitterSourcesStore.GetBy(x => x.CollectionId == collection.Id);
if (sources == null || !sources.Any())
{
data.SetFailed("Can not find any twitter sources");
return(data);
}
var user = await _userStore.FindByIdAsync(collection.UserId);
if (user == null)
{
data.SetFailed("Can not find user data");
return(data);
}
var userTwitter = await _userSocialsStore.GetTwitter(user.Id);
if (userTwitter == null)
{
data.SetFailed("No twitter access token");
return(data);
}
try
{
OAuthTwitter(userTwitter);
}
catch
{
data.SetFailed("Error with twitter connections");
return(data);
}
// upload twitter data
int min = data.MinCount;
min = Math.Max(1, min);
int max = data.MaxCount;
max = Math.Max(100, max);
max = Math.Min(10000, max);
if (min > max)
{
var t = min;
max = min;
min = t;
}
int perSource = (int)Math.Ceiling((double)max / sources.Count);
var entity = new TrainSetModel {
};
var rawData = new StringBuilder();
int total = 0;
var regex = new Regex("http[s]?://[A-Za-z0-9._-]*");
foreach (var screen in sources)
{
long?lastId = null;
int count = 0;
var twetterUser = await UserAsync.GetUserFromId(screen.TwitterId);
while (perSource > count)
{
var @params = new UserTimelineParameters
{
MaximumNumberOfTweetsToRetrieve = 50,
};
if (lastId.HasValue)
{
@params.SinceId = lastId.Value;
}
var tweets = await TimelineAsync.GetUserTimeline(twetterUser, @params);
if (tweets == null || !tweets.Any())
{
break;
}
count += tweets.Count();
foreach (var t in tweets)
{
rawData.Append(regex.Replace(t.FullText, string.Empty));
}
}
total += count;
}
if (total < min)
{
data.SetFailed($"Not enough data avaliable. Avaliable : {total}. Minimum: {min}");
return(data);
}
WordBag wb = WordBag.CreateToWords(rawData.ToString(), data.InputWordsCount + 1);
_vReader.UploadBinary();
List <Tuple <string[], string[]> > stringList = new List <Tuple <string[], string[]> >();
List <Tuple <double[], double[]> > doubleList = new List <Tuple <double[], double[]> >();
foreach (var s in wb.Read())
{
var vectorList = new List <double[]>();
var wordList = new List <string>();
foreach (var ss in s)
{
var word = _vReader.Vocab.GetRepresentationOrNullFor(ss);
if (word == null)
{
break;
}
vectorList.Add(ss.Select(x => (double)x).ToArray());
wordList.Add(ss);
}
if (vectorList.Count < s.Length)
{
continue;
}
var tmpVector = new List <double>();
foreach (var i in vectorList.Take(data.InputWordsCount))
{
tmpVector.AddRange(i);
}
doubleList.Add(new Tuple <double[], double[]>(tmpVector.ToArray(), vectorList.Last().ToArray()));
stringList.Add(new Tuple <string[], string[]>(wordList.Take(wordList.Count - 1).ToArray(), new string[1] {
wordList.Last()
}));
}
entity.Data = doubleList.ToArray();
entity.StringSource = stringList.ToArray();
string dataString = JsonConvert.SerializeObject(entity);
await _storageBlobClient.SetContainer(CONTAINER_NAME, true);
var storageKey = await _storageBlobClient.WriteText(dataString);
if (string.IsNullOrWhiteSpace(storageKey))
{
data.SetFailed("Can not upload train set to storage");
return(data);
}
data.StorageKey = storageKey;
data.SetReady();
data.ExamplesCount = entity.Data.Count();
return(data);
}