#%%導入基本庫
import numpy as np 
import pandas as pd

## 繪圖函數庫
import matplotlib.pyplot as plt
import seaborn as sns
#讀取數據
data=pd.read_csv('D:\Python\ML\data\XGBtrain.csv')

data=data.fillna(-1)
#利用value_counts()函數查看訓練集標簽的數量（Raintomorrow=no）
print(pd.Series(data['RainTomorrow']).value_counts())
data_des=data.describe()

#%%#可視化數據（特征值包括數字特征和非數字特征）
numerical_features = [x for x in data.columns if data[x].dtype == np.float]
category_features = [x for x in data.columns if data[x].dtype != np.float and x != 'RainTomorrow']
#%% 選取三個特征與標簽組合的散點可視化
sns.pairplot(data=data[['Rainfall','Evaporation','Sunshine'] + ['RainTomorrow']], diag_kind='hist', hue= 'RainTomorrow')
plt.show()

#%%每個特征的箱圖
i=0
for col in data[numerical_features].columns:
    if col != 'RainTomorrow':
        plt.subplot(2,8,i+1)
        sns.boxplot(x='RainTomorrow', y=col, saturation=0.5, palette='pastel', data=data)
        plt.title(col)
        i=i+1
plt.show()

#%%非數字特征
tlog = {}
for i in category_features:
    tlog[i] = data[data['RainTomorrow'] == 'Yes'][i].value_counts()
flog = {}
for i in category_features:
    flog[i] = data[data['RainTomorrow'] == 'No'][i].value_counts()
#%%不同地區(qū)下雨情況
plt.figure(figsize=(20,10))
plt.subplot(1,2,1)
plt.title('RainTomorrow')
sns.barplot(x = pd.DataFrame(tlog['Location']).sort_index()['Location'], y = pd.DataFrame(tlog['Location']).sort_index().index, color = "red")
plt.subplot(1,2,2)
plt.title('Not RainTomorrow')
sns.barplot(x = pd.DataFrame(flog['Location']).sort_index()['Location'], y = pd.DataFrame(flog['Location']).sort_index().index, color = "blue")
plt.show()

#%%
plt.figure(figsize=(20,5))
plt.subplot(1,2,1)
plt.title('RainTomorrow')
sns.barplot(x = pd.DataFrame(tlog['RainToday'][:2]).sort_index()['RainToday'], y = pd.DataFrame(tlog['RainToday'][:2]).sort_index().index, color = "red")
plt.subplot(1,2,2)
plt.title('Not RainTomorrow')
sns.barplot(x = pd.DataFrame(flog['RainToday'][:2]).sort_index()['RainToday'], y = pd.DataFrame(flog['RainToday'][:2]).sort_index().index, color = "blue")
plt.show()

#%%對離散變量進行編碼
## 把所有的相同類別的特征編碼為同一個值
def get_mapfunction(x):
    mapp = dict(zip(x.unique().tolist(),
         range(len(x.unique().tolist()))))
    def mapfunction(y):
        if y in mapp:
            return mapp[y]
        else:
            return -1
    return mapfunction
#將非數字特征離散化
for i in category_features:
    data[i] = data[i].apply(get_mapfunction(data[i]))
#%%利用XGBoost進行訓練與預測
## 為了正確評估模型性能，將數據劃分為訓練集和測試集，并在訓練集上訓練模型，在測試集上驗證模型性能。
from sklearn.model_selection import train_test_split

## 選擇其類別為0和1的樣本 （不包括類別為2的樣本）
data_target_part = data['RainTomorrow']
data_features_part = data[[x for x in data.columns if x != 'RainTomorrow']]

## 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)

#%%導入XGBoost模型
from xgboost.sklearn import XGBClassifier
## 定義 XGBoost模型 
clf = XGBClassifier()
# 在訓練集上訓練XGBoost模型
clf.fit(x_train, y_train)
#%% 在訓練集和測試集上分布利用訓練好的模型進行預測
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
from sklearn import metrics

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

## 查看混淆矩陣 (預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XGBoost進行特征選擇：
#XGboost中可以用屬性feature_importances_去查看特征的重要度。
sns.barplot(y=data_features_part.columns,x=clf.feature_importances_)

#利用XGBoost的其他重要參數評估特征的重要性
from sklearn.metrics import accuracy_score
from xgboost import plot_importance

def estimate(model,data):
    #sns.barplot(data.columns,model.feature_importances_)
    ax1=plot_importance(model,importance_type="gain")
    ax1.set_title('gain')
    ax2=plot_importance(model, importance_type="weight")
    ax2.set_title('weight')
    ax3 = plot_importance(model, importance_type="cover")
    ax3.set_title('cover')
    plt.show()
def classes(data,label,test):
    model=XGBClassifier()
    model.fit(data,label)
    ans=model.predict(test)
    estimate(model, data)
    return ans
 
ans=classes(x_train,y_train,x_test)
pre=accuracy_score(y_test, ans)
print('acc=',accuracy_score(y_test,ans))

#%%通過調參獲得更好的效果
## 從sklearn庫中導入網格調參函數
from sklearn.model_selection import GridSearchCV

## 定義參數取值范圍
learning_rate = [0.1, 0.3, 0.6]
subsample = [0.8, 0.9]
colsample_bytree = [0.6, 0.8]
max_depth = [3,5,8]

parameters = { 'learning_rate': learning_rate,
              'subsample': subsample,
              'colsample_bytree':colsample_bytree,
              'max_depth': max_depth}
model = XGBClassifier(n_estimators = 50)

## 進行網格搜索
clf = GridSearchCV(model, parameters, cv=3, scoring='accuracy',verbose=1,n_jobs=-1)
clf = clf.fit(x_train, y_train)
#%%網格搜索后的參數
print(clf.best_params_)

#%% 在訓練集和測試集上分別利用最好的模型參數進行預測
## 定義帶參數的 XGBoost模型 
clf = XGBClassifier(colsample_bytree = 0.6, learning_rate = 0.3, max_depth= 8, subsample = 0.9)
# 在訓練集上訓練XGBoost模型
clf.fit(x_train, y_train)

train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)

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

## 查看混淆矩陣 (預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()