from simple_ml.base.base_model import BaseClassifier
from simple_ml.base.base_enum import ClassifierType


class AdaBoost(BaseClassifier):

    __doc__ = "AdaBoost Classifier"

    def __init__(self, classifier=ClassifierType.LR, nums=10):
        pass

def fit(self, x, y)

def predict(self, x)

def score(self, x, y)

def classify_plot(self, x, y, title="")

from simple_ml.base.base_model import BaseClassifier, BaseFeatureSelect

class GBDT(BaseClassifier, BaseFeatureSelect):

    __doc__ = "GBDT Regression"

    def __init__(self, nums=10, learning_rate=1):
        pass

def fit(self, x, y)

def predict(self, x)

def score(self, x, y)

def classify_plot(self, x, y, title="")

def feature_select(self, top_n)

from simple_ml.base.base_model import BaseClassifier


class RandomForest(BaseClassifier):

    __doc__ = "Random Forest"

    def __init__(self, m, tree_num=200):
        pass

def fit(self, x, y)

def predict(self, x)

def score(self, x, y)

def classify_plot(self, x, y, title="")

from simple_ml.base.base_model import BaseClassifier
from simple_ml.logistic import LogisticRegression

class Stacking(BaseClassifier):

    __doc__ = "Ensemble Model of Stacking"

    def __init__(self, models, meta_model=LogisticRegression(), k_folder=5):
        """
        模型融合Stacking方法，支持分类问题
        :param models:      子模型列表，必须包含fit和predict方法，或者继承BaseClassifier
        :param meta_model:  元分类器，用于stacking第二层分类
        :param k_folder:    折叠次数
        """
        pass

def fit(self, x, y)

def predict(self, x)

def score(self, x, y)

def classify_plot(self, x, y, title="")

from simple_ml.ensemble import AdaBoost
from simple_ml.classify_data import get_wine
from simple_ml.data_handle import train_test_split
from simple_ml.base.base_enum import *


x, y = get_wine()
x = x[(y == 0) | (y == 1)]
y = y[(y == 0) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)

# 采用Logistic回归作为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.LR)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", LR")

# 采用KNN作为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.KNN)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", KNN")

# 采用CART树为子分类器的AdaBoost
ada = AdaBoost(classifier=ClassifierType.CART)
ada.fit(x_train, y_train)
print(ada.score(x_test, y_test))
ada.classify_plot(x_test, y_test, ", CART")

from simple_ml.ensemble import *
from simple_ml.classify_data import *
from simple_ml.data_handle import train_test_split


x, y = get_watermelon()
y = x[:, -1]     # y为连续标签
x = x[:, :-1]    # x为离散标签
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)

gbdt = GBDT(learning_rate=1)
gbdt.fit(x_train, y_train)
print(gbdt.predict(x_test), y_test)
print("R square: %.4f" % gbdt.score(x_test, y_test))

x, y = get_wine()
y = x[:, -1]  # y为连续标签
x = x[:, :-1]  # x为离散标签
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)

gbdt = GBDT(learning_rate=1)
gbdt.fit(x_train, y_train)
print(gbdt.predict(x_test), y_test)
print("R square: %.4f" % gbdt.score(x_test, y_test))

from simple_ml.classify_data import *
from simple_ml.data_handle import *
from simple_ml.ensemble import RandomForest


x, y = get_wine()
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 918)

rf = RandomForest(4, 50)
rf.fit(x_train, y_train)
print(rf.score(x_test, y_test))
rf.classify_plot(x_test, y_test)

from simple_ml import *
from simple_ml.classify_data import *
from simple_ml.data_handle import train_test_split

x, y = get_wine()
x = x[(y == 2) | (y == 1)]
y = y[(y == 2) | (y == 1)]
x_train, y_train, x_test, y_test = train_test_split(x, y, 0.3, 91)

model_list = [LogisticRegression(), NaiveBayes()]     # , SVM(kernel_type=KernelTbbype.gaussian, sigma=1)]

stack = Stacking(model_list, k_folder=5)
stack.fit(x_train, y_train)
print(stack.score(x_test, y_test))
print(stack.score_mat)
stack.classify_plot(x_test, y_test)