def RecommendByNativeBayes(train_data, train_data_y, test_data, test_data_y, recommendNum=5, bayesType=1):
"""使用NB
recommendNum : 推荐数量
bayesType : 1 Bernoulli
2 Gaussian
3 Multionmial
"""
from sklearn.naive_bayes import GaussianNB, MultinomialNB, BernoulliNB
clf = None
if bayesType == 2:
clf = GaussianNB()
elif bayesType == 3:
clf = MultinomialNB()
param = {"alpha": [0.2 * x for x in range(0, 10)], "fit_prior": [False, True]}
clf = GridSearchCV(clf, param_grid=param)
elif bayesType == 1:
clf = BernoulliNB()
clf.fit(X=train_data, y=train_data_y)
if bayesType == 3:
print(clf.best_params_, clf.best_score_)
"""查看算法的学习曲线"""
MLGraphHelper.plot_learning_curve(clf, 'Bayes', train_data, train_data_y).show()
pre = clf.predict_proba(test_data)
# print(clf.classes_)
pre_class = clf.classes_
recommendList = DataProcessUtils.getListFromProbable(pre, pre_class, recommendNum)
# print(recommendList)
answer = [[x] for x in test_data_y]
# print(answer)
return [recommendList, answer]
def RecommendByRF(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""多标签分类 随机森林"""
clf = RandomForestClassifier(n_estimators=50, max_depth=5, n_jobs=-1)
"""对弱分类器数量做调参数量"""
# param_test1 = {'n_estimators': range(200, 250, 10)}
# clf = GridSearchCV(estimator=clf, param_grid=param_test1)
# print(clf.best_params_)
# print(clf.best_params_, clf.best_score_)
"""对决策树的参数做调参"""
# param_test2 = {'max_depth': range(6, 8, 1), 'min_samples_split': range(18, 22, 1)}
# clf = GridSearchCV(estimator=clf, param_grid=param_test1, cv=5, n_jobs=5)
clf.fit(train_data, train_data_y)
predictions = clf.predict_proba(test_data)
# print(clf.best_params_)
# print(clf.best_score_)
# print(clf.cv_results_)
"""预测结果转化为data array"""
predictions = DataProcessUtils.convertMultilabelProbaToDataArray(predictions)
print(predictions)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]
def RecommendByDT(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
grid_parameters = [
{'min_samples_leaf': [2, 4, 8, 16, 32, 64], 'max_depth': [2, 4, 6, 8]}] # 调节参数
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
clf = DecisionTreeClassifier()
clf = GridSearchCV(clf, param_grid=grid_parameters, n_jobs=-1)
clf.fit(train_data, train_data_y)
predictions = clf.predict_proba(test_data)
print(clf.best_params_)
"""预测结果转化为data array"""
predictions = DataProcessUtils.convertMultilabelProbaToDataArray(predictions)
print(predictions)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]
def RecommendBySVM(train_data, train_data_y, test_data, test_data_y, recommendNum=5, CoreType='rbf', C=1,
gamma='auto',
decisionShip='ovo'):
"""使用SVM
recommendNum : 推荐数量
CoreType : 'linear' 线性
'rbf' 高斯
C： 惩罚系数
gamma： 核参数lambda
decisionShip: 分类策略
"""
"""设定判断参数"""
"""训练集按照3 7开分成训练集和交叉验证集"""
"""自定义验证集 而不是使用交叉验证"""
"""这里使用交叉验证还是自定义验证需要再研究一下 3.31"""
test_fold = numpy.zeros(train_data.shape[0])
test_fold[:ceil(train_data.shape[0] * 0.7)] = -1
ps = PredefinedSplit(test_fold=test_fold)
grid_parameters = [
{'kernel': ['rbf'], 'gamma': [0.0005, 0.00075, 0.0001],
'C': [100, 105, 108, 110], 'decision_function_shape': ['ovr']}]
# {'kernel': ['linear'], 'C': [90, 95, 100],
# 'decision_function_shape': ['ovr', 'ovo'],
# 'class_weight': ['balanced', None]}] # 调节参数
from sklearn import svm
from sklearn.model_selection import GridSearchCV
clf = svm.SVC(C=C, kernel=CoreType, probability=True, gamma=gamma, decision_function_shape=decisionShip)
"""
因为REVIEW中有特征是时间相关的 所以讲道理nfold不能使用
需要自定义验证集 如果使用自定义验证集 GridSearchCVA(CV=ps)
"""
# clf = GridSearchCV(clf, param_grid=grid_parameters, cv=ps) # 网格搜索参数
clf.fit(X=train_data, y=train_data_y)
# clf.fit(X=train_features, y=train_label)
# print(clf.best_params_)
# clf = svm.SVC(C=100, kernel='linear', probability=True)
# clf.fit(train_data, train_data_y)
pre = clf.predict_proba(test_data)
pre_class = clf.classes_
# print(pre)
# print(pre_class)
"""查看算法的学习曲线"""
MLGraphHelper.plot_learning_curve(clf, 'SVM', train_data, train_data_y).show()
recommendList = DataProcessUtils.getListFromProbable(pre, pre_class, recommendNum)
# print(recommendList.__len__())
answer = [[x] for x in test_data_y]
# print(answer.__len__())
return [recommendList, answer]
def RecommendByRandomForest(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""使用随机森林
n_estimators : 最大弱学习器个数
recommendNum : 推荐数量
max_depth 决策树最大深度
min_samples_split 内部节点划分所需最小样本数
min_samples_leaf 叶子节点最小样本数
class_weight 分类权重
"""
"""设定判断参数"""
"""自定义验证集 而不是使用交叉验证"""
test_fold = numpy.zeros(train_data.shape[0])
test_fold[:ceil(train_data.shape[0] * 0.7)] = -1
ps = PredefinedSplit(test_fold=test_fold)
"""导入模型"""
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
clf = RandomForestClassifier(min_samples_split=100,
min_samples_leaf=20, max_depth=8, max_features='sqrt', random_state=10)
# clf = GridSearchCV(clf, param_grid=grid_parameters, cv=ps, n_jobs=-1)
# clf.fit(train_data, train_data_y)
#
# print("OOB SCORE:", clf.oob_score_)
"""对弱分类器数量做调参数量"""
# param_test1 = {'n_estimators': range(10, 200, 10)}
# clf = GridSearchCV(estimator=clf, param_grid=param_test1)
# clf.fit(train_data, train_data_y)
# print(clf.best_params_, clf.best_score_)
"""对决策树的参数做调参"""
param_test2 = {'max_depth': range(3, 14, 2), 'min_samples_split': range(50, 201, 20)}
clf = GridSearchCV(estimator=clf, param_grid=param_test2, iid=False, cv=5)
clf.fit(train_data, train_data_y)
# gsearch2.grid_scores_, gsearch2.best_params_, gsearch2.best_score_
"""查看算法的学习曲线"""
MLGraphHelper.plot_learning_curve(clf, 'RF', train_data, train_data_y).show()
pre = clf.predict_proba(test_data)
pre_class = clf.classes_
# print(pre)
# print(pre_class)
recommendList = DataProcessUtils.getListFromProbable(pre, pre_class, recommendNum)
# print(recommendList)
answer = [[x] for x in test_data_y]
# print(answer)
return [recommendList, answer]
def RecommendBySVM(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""svm 一对多"""
classifier = SVC(kernel='linear', probability=True, class_weight='balanced', C=70)
clf = OneVsRestClassifier(classifier)
clf.fit(train_data, train_data_y)
predictions = clf.predict_proba(test_data)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
# print(predictions)
# print(test_data_y)
# print(recommendList)
# print(answerList)
return [recommendList, answerList]
def RecommendByClassifierChain(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""分类器链"""
classifier = ClassifierChain(RandomForestClassifier(oob_score=True, max_depth=10, min_samples_split=20))
classifier.fit(train_data, train_data_y)
predictions = classifier.predict_proba(test_data)
predictions = predictions.todense().getA()
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]
def RecommendByMLKNN(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""ML KNN算法"""
classifier = MLkNN(k=train_data_y.shape[1])
classifier.fit(train_data, train_data_y)
predictions = classifier.predict_proba(test_data).todense()
"""预测结果转化为data array"""
predictions = numpy.asarray(predictions)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]
def RecommendByKN(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""ML KNeighbors"""
clf = KNeighborsClassifier()
clf.fit(train_data, train_data_y)
predictions = clf.predict_proba(test_data)
"""预测结果转化为data array"""
predictions = DataProcessUtils.convertMultilabelProbaToDataArray(predictions)
print(predictions)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]
def RecommendByDecisionTree(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""使用决策树
recommendNum : 推荐数量
max_depth 决策树最大深度
min_samples_split 内部节点划分所需最小样本数
min_samples_leaf 叶子节点最小样本数
class_weight 分类权重
"""
"""设定判断参数"""
"""训练集按照3 7开分成训练集和交叉验证集"""
"""自定义验证集 而不是使用交叉验证"""
test_fold = numpy.zeros(train_data.shape[0])
test_fold[:ceil(train_data.shape[0] * 0.7)] = -1
ps = PredefinedSplit(test_fold=test_fold)
grid_parameters = [
{'min_samples_leaf': [2, 4, 8, 16, 32, 64], 'max_depth': [2, 4, 6, 8],
'class_weight': [None]}] # 调节参数
# # scores = ['precision', 'recall'] # 判断依据
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import GridSearchCV
clf = DecisionTreeClassifier()
clf = GridSearchCV(clf, param_grid=grid_parameters, cv=ps, n_jobs=-1)
clf.fit(train_data, train_data_y)
print(clf.best_params_)
# dot_data = export_graphviz(clf, out_file=None)
# graph = graphviz.Source(dot_data)
# graph.render("DTree")
pre = clf.predict_proba(test_data)
pre_class = clf.classes_
# print(pre)
# print(pre_class)
recommendList = DataProcessUtils.getListFromProbable(pre, pre_class, recommendNum)
# print(recommendList)
answer = [[x] for x in test_data_y]
# print(answer)
return [recommendList, answer]
def RecommendByETS(train_data, train_data_y, test_data, test_data_y, recommendNum=5):
"""多标签分类 """
clf = ExtraTreesClassifier(n_jobs=3, n_estimators=250)
param_test2 = {'max_depth': range(10, 40, 10), 'min_samples_split': range(15, 30, 5)}
clf = GridSearchCV(estimator=clf, param_grid=param_test2, iid=False, cv=10, n_jobs=2)
clf.fit(train_data, train_data_y)
predictions = clf.predict_proba(test_data)
"""预测结果转化为data array"""
predictions = DataProcessUtils.convertMultilabelProbaToDataArray(predictions)
print(predictions)
recommendList = DataProcessUtils.getListFromProbable(predictions, range(1, train_data_y.shape[1] + 1),
recommendNum)
answerList = test_data_y
print(predictions)
print(test_data_y)
print(recommendList)
print(answerList)
return [recommendList, answerList]