'''
#Python 機器學習-鳶尾花分類
'''

#匯入類庫
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
from sklearn.model_selection import cross_val_score
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

#匯入資料
filename = 'iris.data.csv'
names = ['separ-length','separ-width','petal-length','petal-width','class']
dataset = read_csv(filename,names=names)

#檢視資料緯度
print('資料緯度:行%s,列%s'%dataset.shape)

#檢視資料前十行
print(dataset.head(10))

#統計描述資料
print(dataset.describe())

#資料分類分佈
print(dataset.groupby('class').size())

#箱線圖
dataset.plot(kind='box',subplots=True,layout=(2,2),sharex=False,sharey=False)
pyplot.show()

#直方圖
dataset.hist()
pyplot.show()

#散點矩陣圖
scatter_matrix(dataset)
pyplot.show()

#分離評估資料集
array=dataset.values
X=array[:,0:4]
Y=array[:,4]
validation_size=0.2
seed=7
X_train,X_validation,Y_train,Y_validation=\
    train_test_split(X,Y,test_size=validation_size,
    random_state=seed)

#演算法審查
models={}
models['LR']=LogisticRegression()
models['LDA']=LinearDiscriminantAnalysis()
models['KNN']=KNeighborsClassifier()
models['CART']=DecisionTreeClassifier()
models['NB']=GaussianNB()
models['SVM']=SVC()
results=[]
for key in models:
    kfold=KFold(n_splits=10,random_state=seed)
    cv_results=cross_val_score(models[key],X_train,
        Y_train,cv=kfold,scoring='accuracy')
    results.append(cv_results)
    print('%s:%f(%f)'%(key,cv_results.mean(),cv_results.std()))

#箱線圖比較演算法    
fig = pyplot.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
pyplot.boxplot(results)
ax.set_xticklabels(models.keys())
pyplot.show()

#使用評估資料集評估演算法
svm = SVC()
svm.fit(X=X_train,y=Y_train)
predictions = svm.predict(X_validation)
print(accuracy_score(Y_validation,predictions))
print(confusion_matrix(Y_validation,predictions))
print(classification_report(Y_validation,predictions))