def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) #from sklearn.linear_model import SGDClassifier #clf=SGDClassifier(loss='log',penalty='l2',class_weight='balanced')#modified_huber #print('TrainModel Start!') #clf.partial_fit(x_train,y_train,classes=np.unique(y_train)) #clf.fit(x_train,y_train) from sklearn.neighbors import KNeighborsClassifier clf = KNeighborsClassifier(n_neighbors=7) #clf.fit(x_train,y_train) #pickle.dump(clf, open('./SGD_zhuyuan.pickle', 'wb'), -1) #print('TrainModel Finish!') print('交叉验证开始') from sklearn.model_selection import ShuffleSplit from sklearn.model_selection import cross_val_score cv = ShuffleSplit(n_splits=5, test_size=0.01, random_state=0) accs = cross_val_score(clf, x_train, y_train, cv=cv, n_jobs=5) print('交叉验证结果:', accs) print('交叉验证结束') return clf
def getPredictTopN(): import TT_ML.ModelStatis.topN as topN modelFile = './SklearnDNN_zhuyuan.pickle' import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( '/home/jq/jeeker/zy_322/train.libsvm', '/home/jq/jeeker/zy_322/test.libsvm') topN.predictTop(modelFile, x_test, y_test, len(y_test))
def trainModel_MLP(trainFile, testFile): import TT_ML.deepLearning.sklearn_DNN as sklearnDNN import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) clf = sklearnDNN.MLP_normal(x_train, y_train, x_test, y_test) pickle.dump(clf, open('./SklearnDNN_zhuyuan.pickle', 'wb'), -1) return clf
def trainModel(trainFile, testFile): import TT_ML.deepLearning.keras_nn as KerasNN import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() #加载模型 x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) clf = KerasNN.Kmodel_1(x_train, y_train, x_test, y_test) return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) from sklearn.neighbors import KNeighborsClassifier clf = KNeighborsClassifier(n_neighbors=7) clf.fit(x_train, y_train) print('TrainModel Start!') pickle.dump(clf, open(MODELPATH + '/KNN_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) from sklearn.naive_bayes import MultinomialNB clf = MultinomialNB() clf.partial_fit(x_train, y_train, classes=np.unique(y_train)) print('TrainModel Start!') pickle.dump(clf, open(MODELPATH + '/NB_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile,testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper=dataProcess.DataPrepare() x_train,y_train,x_test,y_test=data_helper.loadLibSVMFile(trainFile,testFile) from sklearn.linear_model import SGDClassifier clf=SGDClassifier(loss='log',penalty='l2')#modified_huber clf.partial_fit(x_train,y_train,classes=np.unique(y_train)) #from sklearn.neighbors import KNeighborsClassifier #clf=KNeighborsClassifier(n_neighbors=10) clf.fit(x_train,y_train) print('TrainModel Start!') pickle.dump(clf, open('./SGD_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def loadModel_Kears(): from keras.models import load_model model = load_model('my_model.h5') import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( '/home/jq/jeeker/zy_data2/train.libsvm', '/home/jq/jeeker/zy_data2/test.libsvm') y_pred = model.predict(x_train[:60000], batch_size=256) import numpy as np note_prediction = np.argmax(y_pred, axis=1) print('*' * 20, note_prediction, '*' * 20) from sklearn.metrics import classification_report, confusion_matrix #print(confusion_matrix(y_test, note_prediction)) print(classification_report(y_train[:60000], note_prediction))
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() #加载训练集和测试集 x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) #设置模型的参数,调参 import TT_ML.singleLearning.KNN as KNN clf = KNN.KNN_normal(x_train, y_train, x_test, y_test) #训练模型 print('TrainModel Start!') #保存模型,线上部署需要 pickle.dump(clf, open(MODELPATH + '/KNN_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile,testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess import TT_ML.singleLearning.NB as NB data_helper=dataProcess.DataPrepare() #加载训练集和测试集 x_train,y_train,x_test,y_test=data_helper.loadLibSVMFile(trainFile,testFile) #设置模型的参数,调参 clf = NB.NB_normal(x_train,y_train,x_test,y_test,modelName='BernoulliNB') #训练模型 #clf.fit(x_train,y_train) print('TrainModel Start!') #保存模型,线上部署需要 pickle.dump(clf, open(MODELPATH+'/NB_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() #加载训练集和测试集 x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) from sklearn.linear_model import SGDClassifier #设置模型的参数,调参 import TT_ML.ensembleLearning.RandomForest as ensemble_RF clf = ensemble_RF.RF_normal(x_train, y_train, x_test, y_test) #训练模型 print('TrainModel Start!') #保存模型,线上部署需要 pickle.dump(clf, open(MODELPATH + '/RF_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile,testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper=dataProcess.DataPrepare() x_train,y_train,x_test,y_test=data_helper.loadLibSVMFile(trainFile,testFile) from sklearn.naive_bayes import MultinomialNB clf = MultinomialNB() print('交叉验证开始') from sklearn.model_selection import ShuffleSplit from sklearn.model_selection import cross_val_score cv = ShuffleSplit(n_splits=5, test_size=0.2, random_state=0) accs=cross_val_score(clf,x_train,y_train,cv=cv,n_jobs=5) print('交叉验证结果:',accs) print('交叉验证结束') return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(n_estimators=70, class_weight='balanced') print('TrainModel Finish!') print('交叉验证开始') from sklearn.model_selection import ShuffleSplit from sklearn.model_selection import cross_val_score cv = ShuffleSplit(n_splits=5, test_size=0.01, random_state=0) accs = cross_val_score(clf, x_train, y_train, cv=cv, n_jobs=5) print('交叉验证结果:', accs) print('交叉验证结束') return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() #加载训练集和测试集 x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) from sklearn.linear_model import SGDClassifier #设置模型的参数,调参 clf = SGDClassifier(loss='log', penalty='l2', class_weight='balanced') #modified_huber #clf.partial_fit(x_train,y_train,classes=np.unique(y_train)) #训练模型 clf.fit(x_train, y_train) print('TrainModel Start!') #保存模型,线上部署需要 pickle.dump(clf, open(MODELPATH + '/SGD_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf
def trainModel(trainFile, testFile): import numpy as np import TT_ML.data_helper.data_prepare as dataProcess data_helper = dataProcess.DataPrepare() x_train, y_train, x_test, y_test = data_helper.loadLibSVMFile( trainFile, testFile) #from sklearn.linear_model import SGDClassifier #clf=SGDClassifier(loss='log',penalty='l2',class_weight='balanced')#modified_huber #clf.partial_fit(x_train,y_train,classes=np.unique(y_train)) #clf.fit(x_train,y_train) #from sklearn.neighbors import KNeighborsClassifier #clf=KNeighborsClassifier(n_neighbors=10) #clf.fit(x_train,y_train) from sklearn.ensemble import RandomForestClassifier clf = RandomForestClassifier(n_estimators=70, class_weight='balanced') clf = clf.fit(x_train, y_train) print('TrainModel Start!') pickle.dump(clf, open(MODELPATH + '/RF_zhuyuan.pickle', 'wb'), -1) print('TrainModel Finish!') return clf