Python机器学习应用之基于天气数据集的XGBoost分类篇解读

#%%导入基本库
import numpy as np 
import pandas as pd

## 绘图函数库
import matplotlib.pyplot as plt
import seaborn as sns
#读取数据
data=pd.read_csv('D:\Python\ML\data\XGBtrain.csv')

data=data.fillna(-1)
#利用value_counts()函数查看训练集标签的数量（Raintomorrow=no）
print(pd.Series(data['RainTomorrow']).value_counts())
data_des=data.describe()

#%%#可视化数据（特征值包括数字特征和非数字特征）
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']
#%% 选取三个特征与标签组合的散点可视化
sns.pairplot(data=data[['Rainfall','Evaporation','Sunshine'] + ['RainTomorrow']], diag_kind='hist', hue= 'RainTomorrow')
plt.show()

#%%每个特征的箱图
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()

#%%非数字特征
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()
#%%不同地区下雨情况
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()

#%%对离散变量进行编码
## 把所有的相同类别的特征编码为同一个值
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
#将非数字特征离散化
for i in category_features:
    data[i] = data[i].apply(get_mapfunction(data[i]))
#%%利用XGBoost进行训练与预测
## 为了正确评估模型性能，将数据划分为训练集和测试集，并在训练集上训练模型，在测试集上验证模型性能。
from sklearn.model_selection import train_test_split

## 选择其类别为0和1的样本 （不包括类别为2的样本）
data_target_part = data['RainTomorrow']
data_features_part = data[[x for x in data.columns if x != 'RainTomorrow']]

## 测试集大小为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)

#%%导入XGBoost模型
from xgboost.sklearn import XGBClassifier
## 定义 XGBoost模型 
clf = XGBClassifier()
# 在训练集上训练XGBoost模型
clf.fit(x_train, y_train)
#%% 在训练集和测试集上分布利用训练好的模型进行预测
train_predict = clf.predict(x_train)
test_predict = clf.predict(x_test)
from sklearn import metrics

## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
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))

## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用热力图对于结果进行可视化
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进行特征选择：
#XGboost中可以用属性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的其他重要参数评估特征的重要性
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))

#%%通过调参获得更好的效果
## 从sklearn库中导入网格调参函数
from sklearn.model_selection import GridSearchCV

## 定义参数取值范围
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)

## 进行网格搜索
clf = GridSearchCV(model, parameters, cv=3, scoring='accuracy',verbose=1,n_jobs=-1)
clf = clf.fit(x_train, y_train)
#%%网格搜索后的参数
print(clf.best_params_)

#%% 在训练集和测试集上分别利用最好的模型参数进行预测
## 定义带参数的 XGBoost模型 
clf = XGBClassifier(colsample_bytree = 0.6, learning_rate = 0.3, max_depth= 8, subsample = 0.9)
# 在训练集上训练XGBoost模型
clf.fit(x_train, y_train)

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

## 利用accuracy（准确度）【预测正确的样本数目占总预测样本数目的比例】评估模型效果
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))

## 查看混淆矩阵 (预测值和真实值的各类情况统计矩阵)
confusion_matrix_result = metrics.confusion_matrix(test_predict,y_test)
print('The confusion matrix result:\n',confusion_matrix_result)

# 利用热力图对于结果进行可视化
plt.figure(figsize=(8, 6))
sns.heatmap(confusion_matrix_result, annot=True, cmap='Blues')
plt.xlabel('Predicted labels')
plt.ylabel('True labels')
plt.show()