25.機器學習評估模型-參數對準確率的影響

前置準備機器學習應用-決策樹二元分類算法 

import matplotlib.pyplot as plt
def showchart(df,evalparm ,barData,lineData,yMin,yMax):
    ax = df[barData].plot(kind='bar', title =evalparm,
                                         figsize=(10,6),legend=True, fontsize=12)
    ax.set_xlabel(evalparm,fontsize=12)
    ax.set_ylim([yMin,yMax])
    ax.set_ylabel(barData,fontsize=12)
    ax2 = ax.twinx()
    ax2.plot(df[lineData ].values, linestyle='-', marker='o',
                    linewidth=2.0,color='r')
    plt.show()
    
#定義evalParameter函數
def evalParameter(trainData, validationData, evalparm,
                  impurityList, maxDepthList, maxBinsList):
    #訓練評估參數
    metrics = [trainEvaluateModel(trainData, validationData,  
                                impurity,maxDepth,  maxBins  ) 
                       for impurity in impurityList
                       for maxDepth in maxDepthList  
                       for maxBins in maxBinsList ]
    #設置當前評估的參數
    if evalparm=="impurity":
        IndexList=impurityList[:]
    elif evalparm=="maxDepth":
        IndexList=maxDepthList[:]
    elif evalparm=="maxBins":
        IndexList=maxBinsList[:]
    #轉換爲Pandas DataFrame
    df = pd.DataFrame(metrics,index=IndexList,
            columns=['AUC', 'duration','impurity', 'maxDepth', 'maxBins','model'])
    #顯示圖形
    showchart(df,evalparm,'AUC','duration',0.5,0.7 )
    
evalParameter(trainData, validationData,"impurity", 
                              impurityList=["gini", "entropy"],   
                              maxDepthList=[10],  
                              maxBinsList=[10 ])  
evalParameter(trainData, validationData,"maxDepth", 
                          impurityList=["gini"],                    
                          maxDepthList=[3, 5, 10, 15, 20, 25],    
                          maxBinsList=[10])