/// <summary>
/// 第一种方案。
/// </summary>
/// <param name="a">大楼。</param>
/// <returns></returns>
static testResult PlanA(int[] a)
{
var lo = 0;
var hi = a.Length - 1;
var mid = 0;
var eggs = 0;
var result = new testResult();
while (lo <= hi)
{
mid = lo + (hi - lo) / 2;
if (ThrowEgg(mid))
{
lo = mid + 1;
}
else
{
eggs++;
hi = mid - 1;
}
}
result.BrokenEggs = eggs;
result.F = hi;
return(result);
}
static List<testResult> parseXML(XElement mainFile)
{
List<testResult> ret = new List<testResult>();
List<XElement> assembly = getElements("assembly", mainFile);
List<XElement> collection = getElements("collection", assembly);
List<XElement> test = getElements("test", collection);
foreach (var testRun in test)
{
testResult testResult = new testResult();
testResult.testName = testRun.Attribute("name").Value;
testResult.timeElapsed = testRun.Attribute("time").Value;
testResult.result = testRun.Attribute("result").Value;
XElement performance = testRun.Element("performance");
testResult.runID = performance.Attribute("runid").Value;
testResult.etlPath = performance.Attribute("etl").Value;
XElement metrics = performance.Element("metrics");
XElement iterations = performance.Element("iterations");
if(iterations == null)
{
continue;
}
foreach(var iteration in iterations.Elements())
{
string it = iteration.Attribute("index").Value;
if (it == "0")
continue;
foreach (var metric in getMetrics(metrics))
{
if (metric.unit != "list")
{
metric.value = iteration.Attribute(metric.name).Value;
metric.iteration = it;
testResult.metrics.Add(metric);
}
else
{
foreach (var ListResult in iteration.Elements("ListResult"))
{
if(ListResult.Attribute("Name").Value == metric.name)
{
testResult.ListResults.Add(ListResult);
}
}
}
}
}
ret.Add(testResult);
}
return ret;
}
static void Main(string[] args)
{
int[] building = new int[100000];
for (int i = 0; i < 100000; i++)
{
building[i] = i;
}
// 第一问：二分查找即可
testResult A = PlanA(building);
Console.WriteLine($"Plan A: F={A.F}, Broken Eggs={A.BrokenEggs}");
// 第二问：按照第 1, 2, 4, 8,..., 2^k 层顺序查找，一直到 2^k > F，
// 随后在 [2^(k - 1), 2^k] 范围中二分查找。
testResult B = PlanB(building);
Console.WriteLine($"Plan B: F={B.F}, Broken Eggs={B.BrokenEggs}");
}
static void Main(string[] args)
{
int[] building = new int[100000];
for (int i = 0; i < 100000; i++)
{
building[i] = i;
}
// 第一问：第一个蛋按照 √(N), 2√(N), 3√(N), 4√(N),..., √(N) * √(N) 顺序查找直至碎掉。这里扔了 k 次，k <= √(N)
// k-1√(N) ~ k√(N) 顺序查找直至碎掉，F 值就找到了。这里最多扔 √(N) 次。
testResult A = PlanA(building);
Console.WriteLine($"Plan A: F={A.F}, Broken Eggs={A.BrokenEggs}, Throw Times={A.ThrowTimes}");
// 第二问：按照第 1, 3, 6, 10,..., 1/2k^2 层顺序查找，一直到 1/2k^2 > F，
// 随后在 [1/2k^2 - k, 1/2k^2] 范围中顺序查找。
testResult B = PlanB(building);
Console.WriteLine($"Plan B: F={B.F}, Broken Eggs={B.BrokenEggs}, Throw Times={B.ThrowTimes}");
}
/// <summary>
/// 第二种方案。
/// </summary>
/// <param name="a">大楼。</param>
/// <returns></returns>
static testResult PlanB(int[] a)
{
int lo = 0;
int hi = 1;
int mid = 0;
int eggs = 0;
testResult result = new testResult();
while (ThrowEgg(hi))
{
lo = hi;
hi *= 2;
}
eggs++;
if (hi > a.Length - 1)
{
hi = a.Length - 1;
}
while (lo <= hi)
{
mid = lo + (hi - lo) / 2;
if (ThrowEgg(mid))
{
lo = mid + 1;
}
else
{
eggs++;
hi = mid - 1;
}
}
result.BrokenEggs = eggs;
result.F = hi;
return(result);
}
/// <summary>
/// 第二种方案。
/// </summary>
/// <param name="a">大楼。</param>
/// <returns></returns>
static testResult PlanB(int[] a)
{
var lo = 0;
var hi = 0;
var eggs = 0;
var throwTimes = 0;
var result = new testResult();
for (var i = 0; ThrowEgg(hi); i++)
{
throwTimes++;
lo = hi;
hi += i;
}
eggs++;
if (hi > a.Length - 1)
{
hi = a.Length - 1;
}
while (lo <= hi)
{
if (!ThrowEgg(lo))
{
eggs++;
break;
}
lo++;
throwTimes++;
}
result.BrokenEggs = eggs;
result.F = lo - 1;
result.ThrowTimes = throwTimes;
return(result);
}
/// <summary>
/// 第一种方案。
/// </summary>
/// <param name="a">大楼。</param>
/// <returns></returns>
static testResult PlanA(int[] a)
{
var lo = 0;
var hi = 0;
var eggs = 0;
var throwTimes = 0;
var result = new testResult();
while (ThrowEgg(hi))
{
throwTimes++;
lo = hi;
hi += (int)Math.Sqrt(a.Length);
}
eggs++;
if (hi > a.Length - 1)
{
hi = a.Length - 1;
}
while (lo <= hi)
{
if (!ThrowEgg(lo))
{
eggs++;
break;
}
throwTimes++;
lo++;
}
result.BrokenEggs = eggs;
result.F = lo - 1;
result.ThrowTimes = throwTimes;
return(result);
}
public static List<testResult> RunTest(string path,Hashtable dictionary ,int dicSize, Hashtable idfTable, KNearestNeighbors knn)
{
List<testResult> result = new List<testResult>();
//int[] trainingAnswer = new int[17998];
int count = 0;
string[] categories = Directory.GetDirectories(path);
for (int i = 0; i < categories.Count(); i++) //traverse Categories
{
Console.WriteLine(Path.GetFileName(categories[i]));
string[] file_names = Directory.GetFiles(categories[i]);
for (int j = 0; j < file_names.Count(); j++) //file in Cagetory
{
Console.WriteLine(Path.GetFileName(file_names[j]));
System.IO.StreamReader file = new System.IO.StreamReader(file_names[j]);
double[] featureV = new double[dicSize];
for(int k = 0;k<dicSize;k++) //initial
featureV[k] = 0;
String line;
int counter = 0;
Hashtable docWord = new Hashtable();
Stemmer stemmer = new Stemmer();
int sumWordCount = 0;
stemmer.stem();
//Console.WriteLine(stemmer.stem("running"));
//String word;
/******Structured Column*****/
while ((line = file.ReadLine()) != null)
{
//Console.WriteLine(line);
if (line.Contains(": "))
{
string[] splitPart = line.Split(new string[] { ": " }, StringSplitOptions.None);
string columnName = splitPart[0].Trim();
string content = splitPart[splitPart.Length - 1];
if (columnName.ToLower() == "subject")
{
foreach (string iter_word in Regex.Split(content, @"[^A-Za-z0-9_-]"))
{
String word = iter_word.ToLower().Trim(new Char[] { '_', '-' });
double Num;
bool isNum = double.TryParse(word, out Num);
if (isNum)
{
continue;
}
stemmer.add(word.ToCharArray(), word.Length);
stemmer.stem();
word = stemmer.ToString();
if (word.Length == 0)
{
continue;
}
if (stopWordTable.ContainsKey(word))
{
continue;
}
sumWordCount += 1 * subjectWeight;
// word preprocess done
if (docWord.ContainsKey(word))
{
int temp = (int)docWord[word];
temp += 1 * subjectWeight;
docWord[word] = temp;
}
else
{
docWord[word] = 1 * subjectWeight;
}
}
}
/*else if (columnName.ToLower() == "keywords")
{
foreach (string iter_word in Regex.Split(content, @"[^A-Za-z0-9_-]"))
{
String word = iter_word.ToLower().Trim(new Char[] { '_', '-' });
double Num;
bool isNum = double.TryParse(word, out Num);
if (isNum)
{
continue;
}
stemmer.add(word.ToCharArray(), word.Length);
stemmer.stem();
word = stemmer.ToString();
if (word.Length == 0)
{
continue;
}
if (stopWordTable.ContainsKey(word))
{
continue;
}
sumWordCount += 1 * keywordsWeight;
// word preprocess done
if (docWord.ContainsKey(word))
{
int temp = (int)docWord[word];
temp += 1 * keywordsWeight;
docWord[word] = temp;
}
else
{
docWord[word] = 1 * keywordsWeight;
}
}
}
if (columnName.ToLower() == "newsgroups")
{
foreach (string iter_word in content.Split(new char[] { ',' }))
{
String word = iter_word.ToLower().Trim();
sumWordCount += 1 * newsgroupsWeight;
// word preprocess done
if (docWord.ContainsKey(word))
{
int temp = (int)docWord[word];
temp += 1 * newsgroupsWeight;
docWord[word] = temp;
}
else
{
docWord[word] = 1 * newsgroupsWeight;
}
}
}*/
/*else if (columnName.ToLower() == "from")
{
Regex emailRegex = new Regex(@"\w+([-+.]\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*", RegexOptions.IgnoreCase);
//find items that matches with our pattern
MatchCollection emailMatches = emailRegex.Matches(content);
foreach (Match emailMatch in emailMatches)
{
String word = emailMatch.Value;
// word preprocess done
if (docWord.ContainsKey(word))
{
int temp = (int)docWord[word];
temp += 1 * fromWeight;
docWord[word] = temp;
}
else
{
docWord[word] = 1 * fromWeight;
}
}
}*/
}
else
{
break;
}
}
/******Text******/
while ((line = file.ReadLine()) != null)
{
if (line.StartsWith(">") || line.StartsWith("|>"))
{
continue;
}
//foreach(string iter_word in line.Split(new Char [] {' ', ',', '.', ':', '\t', '\n' }))
foreach (string iter_word in Regex.Split(line, @"[^A-Za-z0-9_-]"))
{
String word = iter_word.ToLower().Trim(new Char[] { '_', '-' });
double Num;
bool isNum = double.TryParse(word, out Num);
if (isNum)
{
continue;
}
stemmer.add(word.ToCharArray(), word.Length);
stemmer.stem();
word = stemmer.ToString();
if (word.Length == 0)
{
continue;
}
if (stopWordTable.ContainsKey(word))
{
continue;
}
sumWordCount++;
// word preprocess done
if (docWord.ContainsKey(word))
{
int temp = (int)docWord[word];
temp++;
docWord[word] = temp;
}
else
{
docWord[word] = 1;
}
}
}// line end
foreach (string word in docWord.Keys)
{
if (dictionary.ContainsKey(word))
{
int indexOfDic = (int)dictionary[word];
double TF = System.Convert.ToDouble((int)docWord[word])/System.Convert.ToDouble(sumWordCount);
double IDF = (double)idfTable[word];
featureV[indexOfDic] = TF * IDF;
}
}
testResult resultTemp = new testResult();
resultTemp.docName = Path.GetFileName(file_names[j]);
resultTemp.oriClass = i;
resultTemp.resultClass = knn.Compute(featureV);
result.Add(resultTemp);
Console.WriteLine(resultTemp.resultClass);
}//file end
//Console.ReadLine();
}//category end
return result;
}
