##  基礎(chǔ)函數(shù)庫
import numpy as np 
import pandas as pd

## 繪圖函數(shù)庫
import matplotlib.pyplot as plt
import seaborn as sns
#%%讀入數(shù)據(jù)
#利用Pandas自帶的read_csv函數(shù)讀取并轉(zhuǎn)化為DataFrame格式
data = pd.read_csv('D:\Python\ML\data\penguins_raw.csv')
#我選取了四個簡單的特征進行研究
data = data[['Species','Culmen Length (mm)','Culmen Depth (mm)',
            'Flipper Length (mm)','Body Mass (g)']]
data.info()
#查看數(shù)據(jù)
print(data.head())
#發(fā)現(xiàn)數(shù)據(jù)中存在的NAN，缺失值此處使用-1將缺失值進行填充
data=data.fillna(-1)
print(data.tail())
#查看對應(yīng)標簽
print(data['Species'].unique())
#統(tǒng)計每個類別的數(shù)量
print(pd.Series(data['Species']).value_counts())
#對特征進行統(tǒng)一描述
print(data.describe())
#可視化描述
sns.pairplot(data=data,diag_kind='hist',hue='Species')
plt.show()
#%%為了方便處理，將標簽數(shù)字化
# 'Adelie Penguin (Pygoscelis adeliae)'        ------0
#  'Gentoo penguin (Pygoscelis papua)'          ------1
#  'Chinstrap penguin (Pygoscelis antarctica)   ------2 

def trans(x):
    if x == data['Species'].unique()[0]:
        return 0
    if x == data['Species'].unique()[1]:
        return 1
    if x == data['Species'].unique()[2]:
        return 2
data['Species'] = data['Species'].apply(trans)

#利用箱圖得到不同類別在不同特征上的分布差異
for col in data.columns:
    if col != 'Species':
        sns.boxplot(x='Species', y=col, saturation=0.5, palette='pastel', data=data)
        plt.title(col)
        plt.show()
        plt.figure()

#%%選取species，culmen_length和culmen_depth三個特征繪制三維散點圖
from mpl_toolkits.mplot3d import Axes3D
fig = plt.figure(figsize=(10,8))
ax = fig.add_subplot(111, projection='3d')

data_class0 = data[data['Species']==0].values
data_class1 = data[data['Species']==1].values
data_class2 = data[data['Species']==2].values
# 'setosa'(0), 'versicolor'(1), 'virginica'(2)
ax.scatter(data_class0[:,0], data_class0[:,1], data_class0[:,2],label=data['Species'].unique()[0])
ax.scatter(data_class1[:,0], data_class1[:,1], data_class1[:,2],label=data['Species'].unique()[1])
ax.scatter(data_class2[:,0], data_class2[:,1], data_class2[:,2],label=data['Species'].unique()[2])
plt.legend()
plt.show()

#%%利用決策樹模型在二分類上進行訓(xùn)練和預(yù)測——選取0和1兩類樣本，樣本選取其中的四個特征
## 為了正確評估模型性能，將數(shù)據(jù)劃分為訓(xùn)練集和測試集，并在訓(xùn)練集上訓(xùn)練模型，在測試集上驗證模型性能。
from sklearn.model_selection import train_test_split

data_target_part = data[data['Species'].isin([0,1])][['Species']]
data_features_part = data[data['Species'].isin([0,1])][['Culmen Length (mm)','Culmen Depth (mm)',
            'Flipper Length (mm)','Body Mass (g)']]

## 測試集大小為20%， 80%/20%分
x_train, x_test, y_train, y_test = train_test_split(
    data_features_part, data_target_part, test_size = 0.2, random_state = 2020)
## 從sklearn中導(dǎo)入決策樹模型
from sklearn.tree import DecisionTreeClassifier
from sklearn import tree
## 定義 決策樹模型 
clf = DecisionTreeClassifier(criterion='entropy')
# 在訓(xùn)練集上訓(xùn)練決策樹模型
clf.fit(x_train, y_train)
#%% 可視化決策樹
import pydotplus
dot_data = tree.export_graphviz(clf, out_file=None)
graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_png("D:\Python\ML\DTpraTree.png") 
#%% 在訓(xùn)練集和測試集上利用訓(xùn)練好的模型進行預(yù)測
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
from sklearn import metrics

## 利用accuracy（準確度）【預(yù)測正確的樣本數(shù)目占總預(yù)測樣本數(shù)目的比例】評估模型效果
print('The accuracy of the train_DecisionTree is:',metrics.accuracy_score(y_train,train_predict))
print('The accuracy of the test_DecisionTree is:',metrics.accuracy_score(y_test,test_predict))

## 查看混淆矩陣 (預(yù)測值和真實值的各類情況統(tǒng)計矩陣)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用熱力圖對于結(jié)果進行可視化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
plt.xlabel('Predicted labels')
plt.ylabel('True labels')
plt.show()

#%%利用決策樹在多分類（三分類）上進行訓(xùn)練和預(yù)測
## 測試集大小為20%， 80%/20%分
x_train, x_test, y_train, y_test = train_test_split(data[['Culmen Length (mm)','Culmen Depth (mm)',
            'Flipper Length (mm)','Body Mass (g)']], data[['Species']], test_size = 0.2, random_state = 2020)
## 定義 決策樹模型 
clf = DecisionTreeClassifier()
# 在訓(xùn)練集上訓(xùn)練決策樹模型
clf.fit(x_train, y_train)
## 在訓(xùn)練集和測試集上分布利用訓(xùn)練好的模型進行預(yù)測
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
train_predict_proba = clf.predict_proba(x_train)
test_predict_proba = clf.predict_proba(x_test)

print('The test predict Probability of each class:\n',test_predict_proba)
## 其中第一列代表預(yù)測為0類的概率，第二列代表預(yù)測為1類的概率，第三列代表預(yù)測為2類的概率。

## 利用accuracy（準確度）【預(yù)測正確的樣本數(shù)目占總預(yù)測樣本數(shù)目的比例】評估模型效果
print('The accuracy of the train_DecisionTree is:',metrics.accuracy_score(y_train,train_predict))
print('The accuracy of the test_DecisionTree is:',metrics.accuracy_score(y_test,test_predict))


## 查看混淆矩陣 (預(yù)測值和真實值的各類情況統(tǒng)計矩陣)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用熱力圖對于結(jié)果進行可視化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
plt.xlabel('Predicted labels')
plt.ylabel('True labels')
plt.show()