一、邏輯回歸
import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.preprocessing import MinMaxScaler from sklearn.preprocessing import StandardScaler from sklearn.linear_model import LogisticRegression import matplotlib.pyplot as plt #導入數據 df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',header=None) df_wine.columns=['Class label','Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline'] print ('class labels:',np.unique(df_wine['Class label'])) #print (df_wine.head(5)) #分割訓練集合測試集 X,y=df_wine.iloc[:,1:].values,df_wine.iloc[:,0].values X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0) #特征值縮放 #歸一化 mms=MinMaxScaler() X_train_norm=mms.fit_transform(X_train) X_test_norm=mms.fit_transform(X_test) #標准化 stdsc=StandardScaler() X_train_std=stdsc.fit_transform(X_train) X_test_std=stdsc.fit_transform(X_test) #L1正則化的邏輯斯蒂模型 lr=LogisticRegression(penalty='l2',C=0.1)#penalty='l2' lr.fit(X_train_std,y_train) print ('Training accuracy:',lr.score(X_train_std, y_train)) print ('Test accuracy:',lr.score(X_test_std, y_test))#比較訓練集和測試集，觀察是否出現過擬合 print (lr.intercept_)#查看截距，三個類別 print (lr.coef_)#查看權重系數，L1有稀疏化效果做特征選擇 #正則化效果，減少約束參數值C，增加懲罰力度，各特征權重系數趨近於0 fig=plt.figure() ax=plt.subplot(111) colors=['blue','green','red','cyan','magenta','yellow','black','pink','lightgreen','lightblue','gray','indigo','orange'] weights,params=[],[] for c in np.arange(-4,6,dtype=float): lr=LogisticRegression(penalty='l2',C=10**c,random_state=0) lr.fit(X_train_std,y_train) weights.append(lr.coef_[0])#三個類別，選擇第一個類別來觀察 params.append(10**c) weights=np.array(weights) for column,color in zip(range(weights.shape[1]),colors): plt.plot(params,weights[:,column],label=df_wine.columns[column+1],color=color) plt.axhline(0,color='black',linestyle='--',linewidth=3) plt.xlim([10**(-5),10**5]) plt.ylabel('weight coefficient') plt.xlabel('C') plt.xscale('log') plt.legend(loc='upper left') ax.legend(loc='upper center',bbox_to_anchor=(1.38,1.03),ncol=1,fancybox=True) plt.show()
二、隨機森林
##隨機森林特征重要性排序--wine數據 import pandas as pd import numpy as np from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler import matplotlib.pyplot as plt from sklearn.ensemble import RandomForestClassifier #導入數據 df_wine = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/wine/wine.data',header=None) df_wine.columns=['Class label','Alcohol','Malic acid','Ash','Alcalinity of ash','Magnesium','Total phenols','Flavanoids','Nonflavanoid phenols','Proanthocyanins','Color intensity','Hue','OD280/OD315 of diluted wines','Proline'] df_wine.shape #df_wine.head() print ('class labels:',np.unique(df_wine['Class label'])) #分割訓練集合測試集 X,y=df_wine.iloc[:,1:].values,df_wine.iloc[:,0].values X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=0) #特征值縮放-標准化，決策樹模型不依賴特征縮放 #stdsc=StandardScaler() #X_train_std=stdsc.fit_transform(X_train) #X_test_std=stdsc.fit_transform(X_test) #隨機森林評估特征重要性 feat_labels=df_wine.columns[1:] forest=RandomForestClassifier(n_estimators=10000,n_jobs=-1,random_state=0) forest.fit(X_train,y_train) importances=forest.feature_importances_ indices=np.argsort(importances)[::-1] for f in range(X_train.shape[1]): #給予10000顆決策樹平均不純度衰減的計算來評估特征重要性 print ("%2d) %-*s %f" % (f+1,30,feat_labels[f],importances[indices[f]]) ) #可視化特征重要性-依據平均不純度衰減 plt.title('Feature Importance-RandomForest') plt.bar(range(X_train.shape[1]),importances[indices],color='lightblue',align='center') plt.xticks(range(X_train.shape[1]),feat_labels,rotation=90) plt.xlim([-1,X_train.shape[1]]) plt.tight_layout() plt.show()