from pandas import read_csv
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.svm import SVC
filename = 'pima_data.csv'
names = ['preg','plas','pres','skin','test','mass','pedi','age','class']
data = read_csv(filename,names = names)
array = data.values
X = array[:,0:8]
Y = array[:,8]
num_folds = 10
seed = 7
kfold = KFold(n_splits=num_folds,random_state=seed)

#邏輯迴歸(線性演算法)
# model = LogisticRegression()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())

#線性判別分析（線性演算法）
'''將高維的模式樣本投影到最佳鑑別向量空間，可以抽取分類資訊和壓縮特徵空間維數'''
# model = LinearDiscriminantAnalysis()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())

#非線性演算法
#K近鄰演算法
'''如果一個樣本在特徵空間的K個最相似的樣本中的大多數屬於一個類別，該樣本也屬於這個類別'''
# model = KNeighborsClassifier()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())

#貝葉斯分類器
'''先計算先驗概率，用貝葉斯公式計算出後驗概率，最小錯誤率上的優化'''
# model = GaussianNB()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())

#分類與迴歸樹
# model = DecisionTreeClassifier()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())

#支援向量機SVM
# model = SVC()
# result = cross_val_score(model,X,Y,cv=kfold)
# print(result.mean())