def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") # X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") minmax_scale(X, copy=False) res = compactness(X, y, types=types, metric=1) print(res[0], res[1], res[2])
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") X, types, y = ToFormNumpy( r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") metric = 1 minmax_scale(X, copy=False) w = Lagranj_nd(X, y) value = w.min() X_Test = np.array(X[:, w == value]) types_Test = np.array(types[w == value]) i = 0 while X_Test.shape[1] < 2000: value = np.min(w[w > value]) X_Test = X[:, w <= value] types_Test = types[w <= value] noisy = find_noisy(X_Test, y, types=types_Test, metric=metric) cond = np.logical_not(noisy) print("\nnoisy = ", len(noisy[noisy == True])) compactness(X_Test[cond], y[cond], types=types_Test, metric=metric) i += 1
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") X, types, y = ToFormNumpy("D:\\tanlanmalar\\Asian Religion.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\arcene_train.txt") minmax_scale(X, copy=False) #Normalizing_Estmation(X, y, types=types) k = 10 k_fold = KFold(n_splits=k, shuffle=True, random_state=None) # Neighbors nnc = NearestNeighborClassifier() knc = TemplateClassifier() begin = time.time() max_mean1 = CVS(nnc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() end = time.time() print("Time: ", (end - begin) * 1000) print(max_mean1) begin = time.time() max_mean2 = CVS(knc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() end = time.time() print("Time: ", (end - begin) * 1000) print(max_mean1, max_mean2)
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") X, types, y = ToFormNumpy(r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") metric = 1 minmax_scale(X, copy=False) #w = Lagranj_nd(X, y) w = Lagranj(X) value = w.max() value = w.max() cond = w == value while len(cond[cond == True]) < 661: value = np.max(w[w < value]) cond = w >= value X_Test = X[:, w >= value] k = 10 k_fold = KFold(n_splits=k, shuffle=True, random_state=None) svm = SVC(kernel="linear") #svm.fit(X_Test, y) nn = MLPClassifier() nn.fit(X_Test, y) max_mean = CVS(nn, X_Test, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() print(max_mean)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") reg = KnnOptimalRegression() reg.fit(X, y) print(reg.predict(X))
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy(r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") X, types, y = ToFormNumpy( r"D:\Nuu\AI\Selections\LSVT_voice_rehabilitation\data.txt") minmax_scale(X, copy=False) metric = 1 w = Lagranj1(X, y) minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) while X.shape[1] > 103: cond = w != w.min() X = X[:, cond] w = w[cond] nnc1 = NearestNeighborClassifier_(noisy=True) nnc2 = NearestNeighborClassifier() nnc3 = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 mean4 = 0 mean5 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.45, random_state=None, shuffle=True) nnc1.fit(X_train, y_train) nnc2.fit(X_train, y_train) nnc3.fit(X_train, y_train) svm.fit(X_train, y_train) nn.fit(X_train, y_train) mean1 += nnc1.score(X_test, y_test) mean2 += nnc2.score(X_test, y_test) mean3 += nnc3.score(X_test, y_test) mean4 += svm.score(X_test, y_test) mean5 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k mean4 /= k mean5 /= k print(mean1, mean2, mean3, mean4, mean5)
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") X, types, y = ToFormNumpy(r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") #y[y == 2] = 1 minmax_scale(X, copy=False) #minmax_scale(X, copy=False) w = Lagranj_nd(X, y) #return 0 value = w.max() cond = w == value while len(cond[cond == True]) < 5000: value = np.max(w[w < value]) cond = w >= value if len(cond[cond == True]) > 154: compactness(X[:, cond], y, types) return 0 print(len(cond[cond == True])) X = X[:, cond] types = types[cond] metric = 1 #nnc = NearestNeighborClassifier_(noisy=True) nnc = NearestNeighborClassifier() # nnc = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.5, random_state=None, shuffle=True) nnc.fit(X_train, y_train) svm.fit(X_train, y_train) nn.fit(X_train, y_train) mean1 += nnc.score(X_test, y_test) mean2 += svm.score(X_test, y_test) mean3 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k print(mean1, mean2, mean3)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") y -= 1 minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) compactness(X, y, types=types, metric=1)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") y -= 1 file = open("test.txt", "w") print(Fris(X, y, types=types, file=file)) file.close()
def main(): path = r"D:\tanlanmalar\GIPER_MY.txt" X, types, y = ToFormNumpy(path) y -= 1 minmax_scale(X, copy=False) # Normalizing_Estmation(X, y) print(compactness(X, y, types)) res = find_standard(X, y, types) res = find_noisy(X, y, types) s = 0 for i in range(res.shape[0]): if res[i] == True and y[i] == 1: print(i + 1) s += 1 print(s) return 0 #nnc = NearestNeighborClassifier_(noisy=True) #nnc = NearestNeighborClassifier() #nnc = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=None, shuffle=True) nnc.fit(X_train, y_train) svm.fit(X_train, y_train) nn.fit(X_train, y_train) mean1 += nnc.score(X_test, y_test) mean2 += svm.score(X_test, y_test) mean3 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k print(mean1, mean2, mean3)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") y -= 1 minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) group, comp1 = Fris(X, y, types=types, file=None)
def main(): #path = r"D:\Nuu\AI\Selections\leukemia\leukemia_small.csv" #X, types, y = ReadFromCSVWithHeaderClass(path) X, types, y = ToFormNumpy(r"D:\tanlanmalar\spame.txt") minmax_scale(X, copy=False) #res = find_shell(X, y, types) #res = find_standard(X, y, types) #res = find_noisy(X, y, types) #count(res, y) #X = X[res == False] #y = y[res == False] #print(X.shape) #print(compactness(X, y, types)) #return 0 nnc = NearestNeighborClassifier_(noisy=False) #nnc = NearestNeighborClassifier() #nnc = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=None, shuffle=True) nnc.fit(X_train, y_train) #svm.fit(X_train, y_train) #nn.fit(X_train, y_train) mean1 += nnc.score(X_test, y_test) #mean2 += svm.score(X_test, y_test) #mean3 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k print(mean1, mean2, mean3)
def main(): path = r"D:\Tanlanmalar\MATBIO_MY.txt" X, types, y = ToFormNumpy(path) y -= 1 print(X.shape) #minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) count(find_shell(X, y), y)
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") #y -= 1 #y[y == 2] = 1 for i in range(X.shape[1]): for j in range(i + 1, X.shape[1]): ReductionOptimal(X[:, i], X[:, j], y)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasteralogy.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") y = y - 1 #minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) drawobjects(X[:, [3, 5]], classes=y, isVisibleLabel=True)
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") #X, types, y = ToFormNumpy("D:\\german.txt") #71.2 #X, types, y = ToFormNumpy("D:\\german1.txt") #91.7 #X, types, y = ToFormNumpy("D:\\german2.txt") #91.7 #X, types, y = ToFormNumpy("D:\\german3.txt") #94.4 #X, types, y = ToFormNumpy("D:\\german4.txt") #95.4 #X, types, y = ToFormNumpy("D:\\german5.txt") #97.7 X, types, y = ToFormNumpy("D:\\german6.txt") #98.1 #X, types, y = ToFormNumpy("D:\\german7.txt") #97.3 #X, types, y = ToFormNumpy("D:\\german8.txt") #94.5 #X, types, y = ToFormNumpy("D:\\tanlanmalar\\german.txt") #y[y == 2] = 1 _, ln = np.unique(y, return_counts=True) #minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) # Cross Validation k = 10 k_fold = KFold(n_splits=k, shuffle=True, random_state=None) #Nerual network mlp = MLPClassifier(hidden_layer_sizes=(100, 200)) # Knn n_neighbors = 2 * min(ln) - 3 # mertic Euclidean #knc = KNeighborsClassifier(n_neighbors=n_neighbors) knc = KNeighborsClassifier(n_neighbors=1) #SVM svc = SVC() #print("MLP") max_mean1 = CVS(mlp, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() #print("KNN") max_mean2 = CVS(knc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() #print("SVM") max_mean3 = CVS(svc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() print(max_mean1, max_mean2, max_mean3)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") # X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") metric = 1 minmax_scale(X, copy=False) noisy = find_noisy(X, y, types=types, metric=metric) #for item in noisy: # print(item) print(len(noisy))
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") #X, types, y = ToFormNumpy(r"D:\Nuu\Data mining\Articles\PCA operator\Computing\Gastown1.txt") X, types, y = ToFormNumpy(r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") #minmax_scale(X, copy=False) w = Lagranj_nd(X, y) cond = w > 0 print(len(cond[cond == True]))
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") X, types, y = ToFormNumpy("D:\\tanlanmalar\\arcene_train.txt") minmax_scale(X, copy=False) w = Lagranj_nd(X, y) print(w.shape) X_Test = np.array(X[:, w == w.min()]) types_Test = np.array(types[w == w.min()]) print(X_Test) res = compactness(X_Test, y, types=types_Test, metric=1)
def main(): path = r"D:\Tanlanmalar\german.txt" X, types, y = ToFormNumpy(path) minmax_scale(X, copy=False) #Normalizing_Estmation(X, y) nnc1 = NearestNeighborClassifier_(noisy=True) nnc2 = NearestNeighborClassifier() nnc3 = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 mean4 = 0 mean5 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.45, random_state=None, shuffle=True) nnc1.fit(X_train, y_train) nnc2.fit(X_train, y_train) nnc3.fit(X_train, y_train) svm.fit(X_train, y_train) nn.fit(X_train, y_train) mean1 += nnc1.score(X_test, y_test) mean2 += nnc2.score(X_test, y_test) mean3 += nnc3.score(X_test, y_test) mean4 += svm.score(X_test, y_test) mean5 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k mean4 /= k mean5 /= k print(mean1, mean2, mean3, mean4, mean5)
def main(): path = r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt" X, types, y = ToFormNumpy(path) minmax_scale(X, copy=False) _, ln = np.unique(y, return_counts=True) w = Lagranj1(X, y) compactness(X, y, types=types, metric=1) while X.shape[1] > 2: cond = w != w.min() X = X[:, cond] w = w[cond] compactness(X, y, types=types, metric=1)
def main(): path = r"D:\Nuu\AI\Selections\LSVT_voice_rehabilitation\data.txt" X, types, y = ToFormNumpy(path) #minmax_scale(X, copy=False) Normalizing_Estmation(X, y) _, ln = np.unique(y, return_counts=True) w = Lagranj1(X, y) compactness(X, y, types=types, metric=1) while X.shape[1] > 2: cond = w != w.min() X = X[:, cond] w = w[cond] compactness(X, y, types=types, metric=1)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\arcene_train.txt") X_Test = np.loadtxt( r"D:\Nuu\AI\Selections\Arcena Data Set\arcene_test.data") minmax_scale(X, copy=False) minmax_scale(X_Test, copy=False) #Normalizing_Estmation(X, y, types=types) nnc = NearestNeighborClassifier() begin = time.time() nnc.fit(X, y) print(nnc.predict(X_Test)) end = time.time() print("Time: ", (end - begin) * 1000)
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") X, types, y = ToFormNumpy(r"D:\Nuu\AI\Selections\Amazon_initial_50_30_10000\data.txt") minmax_scale(X, copy=False) #minmax_scale(X, copy=False) X = SelectKBest(chi2, k=2000).fit_transform(X, y) metric = 1 # nnc = NearestNeighborClassifier_(noisy=True) nnc = NearestNeighborClassifier() # nnc = TemplateClassifier(noisy=True) nn = MLPClassifier() svm = SVC() k = 10 mean1 = 0 mean2 = 0 mean3 = 0 for i in range(k): X_train, X_test, y_train, y_test = train_test_split( X, y, test_size=0.5, random_state=None, shuffle=True) #nnc.fit(X_train, y_train) svm.fit(X_train, y_train) nn.fit(X_train, y_train) #mean1 += nnc.score(X_test, y_test) mean2 += svm.score(X_test, y_test) mean3 += nn.score(X_test, y_test) mean1 /= k mean2 /= k mean3 /= k print(mean1, mean2, mean3)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") minmax_scale(X, copy=False) #X, types, y = ToFormNumpy(r"D:\Nuu\Data mining\Articles\PCA operator\Computing\Lagranj\Spame\data\own\(4595, 57).txt") k = 5 k_fold = KFold(n_splits=k, shuffle=True, random_state=42) mlp = MLPClassifier(hidden_layer_sizes=(50, 200), activation='relu', max_iter=1000, alpha=1e-5, solver='adam', verbose=False, tol=1e-4, random_state=1, learning_rate_init=.1) max_mean = sum(CVS(mlp, X, y, cv=k_fold, n_jobs=4, scoring='accuracy')) / k print('Score = ', max_mean)
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\german.txt") _, ln = np.unique(y, return_counts=True) for j in range(X.shape[1]): if types[j] == 0: gradation = {} for i in range(X.shape[0]): if not (X[i, j] in gradation): nyu1 = np.count_nonzero(X[y == 0, j] == X[i, j]) / ln[0] nyu2 = np.count_nonzero(X[y == 1, j] == X[i, j]) / ln[1] gradation[X[i, j]] = nyu1 / (nyu1 + nyu2) if y[i] == 0: X[i, j] = gradation[X[i, j]] else: X[i, j] = 1 - gradation[X[i, j]] for i in range(X.shape[0]): for j in range(X.shape[1]): print(X[i, j], end=' ') print(y[i] + 1)
import numpy as np from Test.read_data import ToFormNumpy from uz.nuu.datamining.graphic.drawing import mscatter from ai.own.fris import Fris X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X = np.array([[4, 4], [3, 6], [5, 2]], dtype=float) #X = np.array([[4, 3, 5], [4, 6, 2]]) y -= 1 X -= X.mean(axis=0) covmat = np.dot(X.T, X) covmat = np.array([[0.6066353658781276, 0.6301733805074563, 0.6214466136515134, 0.8592131106607721, 0.8736921033877233, 0.600853414661878, 0.6094070313817901, 0.5867057852210043, 0.5786615866051649, 0.7006998089403434, 0.6163119318278932, 0.6522341941050182, 0.600853414661878, 0.8736921033877233, 0.8096234318951467, 0.5791038997423555, 0.635994346239335, 0.6229420214572404, 0.5867057852210043, 0.600853414661878, 0.6214466136515134, 0.6453908994369276, 0.6522341941050182, 0.6066353658781276, 0.6013082124440698, 0.6203214350207669, 0.6340651713331743, 0.7392127093686114, 0.7446575751698247, ], [0.6301733805074563, 0.2526354862657758, 0.5541910135822533, 0.903192279138827, 0.7186195103789759, 0.2818595878729509, 0.2742637217767136, 0.31516312154767984, 0.27900015828746344, 0.6846108915151231, 0.5030495974816688, 0.5251028311161942, 0.28179954267556345, 0.8668488087196328, 0.7817367478837411, 0.2877247700558762, 0.27703932588862057, 0.2869910742219577, 0.31516312154767984, 0.28445312424525493, 0.5219978701790134, 0.5378191108703357, 0.34730253638939607, 0.3516703786191537, 0.30316574926819917, 0.27619445726349956, 0.35664261143103015, 0.48890977094392085, 0.4597624350408315, ], [0.6214466136515134, 0.5541910135822533, 0.5071687871984828, 0.8809462023270487, 0.8379863159373181, 0.4566814030065701, 0.41643789297835326, 0.48890977094392085, 0.5215768849770335, 0.6148852638830367, 0.5481133694942159, 0.5215768849770335, 0.44322496215591983, 0.8592131106607721, 0.8241024246220979, 0.4391580890467305, 0.5053005492500667, 0.4566814030065701, 0.48890977094392085, 0.4391580890467305, 0.5381905290591259, 0.5215768849770335, 0.5738029789254734, 0.45777269474374155, 0.4785228435562512, 0.4784405786632958, 0.5644675856257149, 0.600853414661878, 0.6301733805074563, ], [0.8592131106607721, 0.903192279138827, 0.8809462023270487, 0.903192279138827, 0.9193229606741115, 0.9193229606741115, 0.845217674987534, 0.9349088509444856, 0.903192279138827, 0.8962343189514681, 0.903192279138827, 0.8719953806813495, 0.9429656085186894, 0.9349088509444856, 0.903192279138827, 0.9193229606741115, 0.9349088509444856, 0.9349088509444856, 0.9349088509444856, 0.9193229606741115, 0.903192279138827, 0.8719953806813495, 0.9349088509444856, 0.9116872626152508, 0.8668488087196328, 0.9116872626152508, 0.9349088509444856, 0.8574610244988864, 0.9193229606741115, ], [0.8736921033877233, 0.7186195103789759, 0.8379863159373181, 0.9193229606741115, 0.7515372833858358, 0.7628688079319111, 0.6846108915151231, 0.7627978386701475, 0.7897935054579449, 0.8507181271843484, 0.8299295583631144, 0.8110616184112844, 0.7344496686738706, 0.8412934092221398, 0.9349088509444856, 0.7446575751698247, 0.7543028551937238, 0.770433536729008, 0.7627978386701475, 0.733098503105927, 0.8241024246220979, 0.8110616184112844, 0.772785926238042, 0.772785926238042, 0.7344496686738706, 0.7628688079319111, 0.772785926238042, 0.7543028551937238, 0.733098503105927, ], [0.600853414661878, 0.2818595878729509, 0.4566814030065701, 0.9193229606741115, 0.7628688079319111, 0.2529438867226544, 0.2838028823181013, 0.3026134523536157, 0.2994060876020787, 0.6453908994369276, 0.4843688528914958, 0.45528877058201483, 0.26080178173719376, 0.8890029599012524, 0.8096234318951467, 0.2902945261519872, 0.27851214243196426, 0.3108877251416227, 0.3026134523536157, 0.28179954267556345, 0.505249644596341, 0.48512989604303636, 0.3287914492071879, 0.3088273128362215, 0.31642332755918506, 0.27897117607585314, 0.3488175629229823, 0.5943920163667752, 0.733098503105927, ], [0.6094070313817901, 0.2742637217767136, 0.41643789297835326, 0.845217674987534, 0.6846108915151231, 0.2838028823181013, 0.26748329621380845, 0.26854783514026276, 0.28363552862439273, 0.6229420214572404, 0.4893443554913488, 0.5219978701790134, 0.2838028823181013, 0.8209787367174153, 0.8096234318951467, 0.29513492705771843, 0.28796613985923564, 0.284858355014257, 0.26854783514026276, 0.29183370452858204, 0.4736911373140029, 0.5335978145926178, 0.31272921027932166, 0.3649482444582667, 0.310192820883244, 0.2882702301410542, 0.3255433607326703, 0.4659357947405461, 0.4477305813608709, ], [0.5867057852210043, 0.31516312154767984, 0.48890977094392085, 0.9349088509444856, 0.7627978386701475, 0.3026134523536157, 0.26854783514026276, 0.2756011393724831, 0.27851214243196426, 0.6439822896393053, 0.4784405786632958, 0.4937398422921809, 0.28727205304785114, 0.8890029599012524, 0.8096234318951467, 0.30932892803716855, 0.2778019296207863, 0.3009744711303732, 0.2815887156644395, 0.304426475473246, 0.4631916251812317, 0.509335021732943, 0.3907907164774277, 0.3461766889383816, 0.3653727967016757, 0.3211642971850841, 0.3711599498533426, 0.5266203099907628, 0.5378191108703357, ], [0.5786615866051649, 0.27900015828746344, 0.5215768849770335, 0.903192279138827, 0.7897935054579449, 0.2994060876020787, 0.28363552862439273, 0.27851214243196426, 0.2502966961021898, 0.6292602179016433, 0.5365374282968938, 0.5095717097944269, 0.2940188889706336, 0.8719953806813495, 0.7970248645081608, 0.3168840704104253, 0.2778019296207863, 0.2934039458909541, 0.27851214243196426, 0.2988699166872887, 0.5365374282968938, 0.5095717097944269, 0.3402344437979182, 0.33814267125328745, 0.3034149962880475, 0.274536005939124, 0.35820631321744906, 0.48512989604303636, 0.4902953435989813, ], [0.7006998089403434, 0.6846108915151231, 0.6148852638830367, 0.8962343189514681, 0.8507181271843484, 0.6453908994369276, 0.6229420214572404, 0.6439822896393053, 0.6292602179016433, 0.6268914794527267, 0.6301733805074563, 0.6229420214572404, 0.59789722907763, 0.8962343189514681, 0.8379863159373181, 0.6214466136515134, 0.6377552013780671, 0.6453908994369276, 0.6439822896393053, 0.6453908994369276, 0.6301733805074563, 0.6008630753990813, 0.6684802099798388, 0.6214466136515134, 0.6148852638830367, 0.6084891127207386, 0.6684802099798388, 0.7817367478837411, 0.727298345115717, ], [0.6163119318278932, 0.5030495974816688, 0.5481133694942159, 0.903192279138827, 0.8299295583631144, 0.4843688528914958, 0.4893443554913488, 0.4784405786632958, 0.5365374282968938, 0.6301733805074563, 0.5239109933987439, 0.5365374282968938, 0.5136370223229911, 0.8890029599012524, 0.8096234318951467, 0.4841139580560516, 0.48512989604303636, 0.4736911373140029, 0.4784405786632958, 0.4784405786632958, 0.5239109933987439, 0.5492767451935974, 0.5365374282968938, 0.5483231561182563, 0.5263093085661757, 0.5596923575394251, 0.48512989604303636, 0.7627978386701475, 0.65905549201763, ], [0.6522341941050182, 0.5251028311161942, 0.5215768849770335, 0.8719953806813495, 0.8110616184112844, 0.45528877058201483, 0.5219978701790134, 0.4937398422921809, 0.5095717097944269, 0.6229420214572404, 0.5365374282968938, 0.5139411126048097, 0.4621320652501053, 0.8809462023270487, 0.7917037304565143, 0.44322496215591983, 0.509335021732943, 0.4631916251812317, 0.4937398422921809, 0.4754180312457966, 0.5492767451935974, 0.5251028311161942, 0.5156610953938348, 0.4843688528914958, 0.4671480686328496, 0.505249644596341, 0.5263093085661757, 0.7173812268095862, 0.6439822896393053, ], [0.600853414661878, 0.28179954267556345, 0.44322496215591983, 0.9429656085186894, 0.7344496686738706, 0.26080178173719376, 0.2838028823181013, 0.28727205304785114, 0.2940188889706336, 0.59789722907763, 0.5136370223229911, 0.4621320652501053, 0.2529438867226544, 0.8809462023270487, 0.7448781372315151, 0.27619445726349956, 0.29513492705771843, 0.2941543622315709, 0.28727205304785114, 0.2848552338530067, 0.5156610953938348, 0.4719695196309896, 0.3399748672205984, 0.311812703572169, 0.310192820883244, 0.262221761479371, 0.3461766889383816, 0.5738029789254734, 0.733098503105927, ], [0.8736921033877233, 0.8668488087196328, 0.8592131106607721, 0.9349088509444856, 0.8412934092221398, 0.8890029599012524, 0.8209787367174153, 0.8890029599012524, 0.8719953806813495, 0.8962343189514681, 0.8890029599012524, 0.8809462023270487, 0.8809462023270487, 0.8890029599012524, 0.903192279138827, 0.8574610244988864, 0.9349088509444856, 0.8736921033877233, 0.8890029599012524, 0.8736921033877233, 0.8962343189514681, 0.8809462023270487, 0.9116872626152508, 0.8890029599012524, 0.8668488087196328, 0.8668488087196328, 0.8890029599012524, 0.8011284484187231, 0.8302166308847824, ],
def main(): X, types, y = ToFormNumpy(r"D:/test.txt") mscatter1(X, y, marker=['v', 's'], size=6, colors=['black', 'black'])
def main(): X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\german.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") #X, types, y = ToFormNumpy(r"D:\Nuu\Data mining\Articles\PCA operator\Computing\Gastown1.txt") y -= 1 #y[y == 2] = 1 _, ln = np.unique(y, return_counts=True) #minmax_scale(X, copy=False) Normalizing_Estmation(X, y, types=types) #return None root = r"D:\Nuu\Data mining\Articles\PCA operator\Computing\Lagranj" selection_Name = r'\It_bori' preproccesing_name = r'own' img_path = root + selection_Name + \ "\images " + preproccesing_name save_name = img_path + r"\img" save_name += str(X.shape) + ".png" path = root + selection_Name + \ "/res " + preproccesing_name + ".txt" path1 = root + selection_Name + \ "/res1 " + preproccesing_name + ".txt" p_res = root + selection_Name + \ "/data/" + preproccesing_name + "/" p_res_PCA = root + selection_Name + \ "/data/" + preproccesing_name + "/" file = open(path, 'w') file1 = open(path1, 'w') shape = X.shape #Computing for X print("Computing for shape " + str(X.shape)) file.write("Computing for shape " + str(X.shape) + "\n") group, comp1, noisy1 = Fris(X, y, types=types, file=file) similarity0 = DecomposionEstimation(group, group, X.shape[0]) print("Similarity between shape " + str(shape) + " and " + str(X.shape) + " are " + str(similarity0)) file.write("Similarity between shape " + str(shape) + " and " + str(X.shape) + " are " + str(similarity0) + "\n") writeNP(p_res + str(X.shape) + ".txt", X, y, types=types) #PCA print("Computing for PCA") file.write("Computing for PCA\n") #pca = PCA(n_components=2) pca = KernelPCA(n_components=2, kernel='poly') pca.fit(X, y=y) transform = pca.transform(X) writeNP(p_res_PCA + str(transform.shape) + str(X.shape) + ".txt", transform, y, types=[1, 1]) mscatter(transform, y=y, save_name=save_name) group_b, comp2, noisy2 = Fris(transform, y, types, file=file) similarity = DecomposionEstimation(group, group_b, X.shape[0]) print("Similarity between shape " + str(shape) + " and " + str(transform.shape) + " are " + str(similarity)) file.write("Similarity between shape " + str(shape) + " and " + str(transform.shape) + " are " + str(similarity) + "\n") file1.write( str(X.shape[1]) + "\t" + str(comp1) + "\t" + str(similarity0) + "\t" + str(comp2) + "\t" + str(similarity) + "\t" + str(similarity) + "\t" + str(noisy1) + "\t" + str(noisy2) + "\n") # 25 w = Lagranj(X, y, types, ln=ln) while X.shape[1] > 2: cond = w != w.min() X = X[:, cond] types = types[cond] w = w[cond] print("\n" + "*" * 50) file.write("\n" + "*" * 50 + "\n") print("Computing for shape " + str(X.shape)) file.write("Computing for shape " + str(X.shape) + "\n") # For X group_b, comp1, noisy2 = Fris(X, y, types=types, file=file) similarity0 = DecomposionEstimation(group, group_b, obj_count=X.shape[0]) print("Similarity between shape " + str(shape) + " and " + str(X.shape) + " are " + str(similarity0)) file.write("Similarity between shape " + str(shape) + " and " + str(X.shape) + " are " + str(similarity0) + "\n") #PCA print("Computing for PCA") file.write("Computing for PCA\n") pca = PCA(n_components=2) pca.fit(X, y=y) transform = pca.transform(X) #Save images save_name = img_path + r"\img" save_name += str(X.shape) + ".png" mscatter(transform, y=y, save_name=save_name) group_c, comp2, noisy2 = Fris(transform, y, types, file=file) similarity = DecomposionEstimation(group, group_c, X.shape[0]) similarity1 = DecomposionEstimation(group_b, group_c, X.shape[0]) print("Similarity between shape " + str(shape) + " and " + str(transform.shape) + " are " + str(similarity)) file.write("Similarity between shape " + str(shape) + " and " + str(transform.shape) + " are " + str(similarity) + "\n") file1.write( str(X.shape[1]) + "\t" + str(comp1) + "\t" + str(similarity0) + "\t" + str(comp2) + "\t" + str(similarity) + "\t" + str(similarity1) + "\t" + str(noisy1) + "\t" + str(noisy2) + "\n") writeNP(p_res + str(X.shape) + ".txt", X, y, types=types) writeNP(p_res_PCA + str(transform.shape) + str(X.shape) + ".txt", transform, y, types=[1, 1]) file.close() file1.close()
def main(): #X, types, y = ToFormNumpy("D:\\tanlanmalar\\IT_BORI_42_6.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\giper_my.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\spame.txt") X, types, y = ToFormNumpy("D:\\tanlanmalar\\gasterlogy1394.txt") #X, types, y = ToFormNumpy("D:\\tanlanmalar\\MATBIO_MY.txt") y[y == 2] = 1 _, ln = np.unique(y, return_counts=True) #print(ln) #minmax_scale(X, copy=False) Normalizing_Estmation(X, y) indx = clearNoisy(X, y) X = X[indx] y = y[indx] #print(X.shape) #print(y.shape) #return None selection_Name = r'\Gasterology2' preproccesing_name = r'own' path = r"D:\Nuu\Data mining\Articles\Cross Validation\Computing" + selection_Name + \ r"\res " + preproccesing_name + ".txt" file = open(path, 'w') # Cross Validation k = 10 k_fold = KFold(n_splits=k, shuffle=True, random_state=None) #Nerual network mlp = MLPClassifier(hidden_layer_sizes=(100, 200), activation='logistic') # Knn n_neighbors = 2 * min(ln) - 3 # mertic Euclidean knc = KNeighborsClassifier(n_neighbors=n_neighbors, p=2) #SVM svc = SVC(kernel="linear", degree=5) # RDF rdf = RandomForestClassifier(max_depth=1000) #print("MLP") max_mean1 = CVS(mlp, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() #print("KNN") max_mean2 = CVS(knc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() #print("SVM") max_mean3 = CVS(svc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy').mean() print(X.shape[1], max_mean1, max_mean2, max_mean3) # 25 w = Lagranj(X, y, types) while X.shape[1] > 2: # Cross Validation k = 5 k_fold = KFold(n_splits=k, shuffle=True, random_state=42) # Nerual network mlp = MLPClassifier(hidden_layer_sizes=(50, 200), activation='relu', max_iter=1000, alpha=1e-5, solver='adam', verbose=False, tol=1e-8, random_state=1, learning_rate_init=.1) # Knn n_neighbors = 2 * min(ln) - 3 # mertic Euclidean knc = KNeighborsClassifier(n_neighbors=n_neighbors, p=2) # SVM svc = SVC(gamma='scale') max_mean1 = sum(CVS(mlp, X, y, cv=k_fold, n_jobs=4, scoring='accuracy')) / k max_mean2 = sum(CVS(knc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy')) / k max_mean3 = sum(CVS(svc, X, y, cv=k_fold, n_jobs=4, scoring='accuracy')) / k print(X.shape[1], max_mean1, max_mean2, max_mean3) file.write( str(X.shape[1]) + "\t" + str(max_mean1) + "\t" + str(max_mean2) + "\t" + str(max_mean3) + "\n") cond = w != w.min() X = X[:, cond] w = w[cond] file.close()