用我儿子的话说，有一天啊,小乌龟遇见小兔子………
有一天，我在网上看到这样一片文章，决策书做贷款决策分析。
贷还是不贷：如何用Python和机器学习帮你决策？
import pandas as pddf = pd.read_csv('loans.csv')#print(df.head())X = df.drop('safe_loans', axis=1)y = df.safe_loans#change categoricalfrom sklearn.preprocessing import LabelEncoderfrom collections import defaultdictd = defaultdict(LabelEncoder)X_trans = X.apply(lambda x: d[x.name].fit_transform(x))X_trans.head()#X_trans.to_excel('X_trans.xls') #random take train and testfrom sklearn.cross_validation import train_test_splitX_train, X_test, y_train, y_test = train_test_split(X_trans, y, random_state=1)#call decision treefrom sklearn import treeclf = tree.DecisionTreeClassifier(max_depth=8)clf = clf.fit(X_train, y_train)test_rec = X_test.iloc[1,:]clf.predict([test_rec])y_test.iloc[1]from sklearn.metrics import accuracy_scoreprint(accuracy_score(y_test, clf.predict(X_test)))这篇文章写的非常好，从中学到好多，但是计算的正确率不太高，8层的决策树正确率才能达到0.645
0.645480347467我用神经网络重新做了计算
#!/usr/bldds/env python3# -*- coding: utf-8 -*-"""Created on Thu Aug 17 21:14:08 2017@author: luogan"""#read dataimport pandas as pddf = pd.read_csv('loans.csv')#print(df.head())#X = df.drop('safe_loans', axis=1)X = df.drop(['safe_loans' ],axis=1)y = df.safe_loans#change categoricalfrom sklearn.preprocessing import LabelEncoderfrom collections import defaultdictd = defaultdict(LabelEncoder)X_trans = X.apply(lambda x: d[x.name].fit_transform(x))X_trans.head()#X_trans.to_excel('X_trans.xls') ##############data_train=X_transdata_max = data_train.max()data_min = data_train.min()data_mean = data_train.mean()## data_std = data_train.std()X_train1 = (data_train-data_max)/(data_max-data_min)y=0.5*(y+1)#random take train and testfrom sklearn.cross_validation import train_test_splitx_train, x_test, y_train, y_test = train_test_split(X_train1, y, random_state=1)#x_train.to_excel('xx_trans.xls') #y_train.to_excel('y_trans.xls') #call decision tree#from sklearn import tree#clf = tree.DecisionTreeClassifier(max_depth=10)#clf = clf.fit(X_train, y_train)from keras.models import Sequentialfrom keras.layers.core import Dense, Dropout, Activationmodel = Sequential() #建立模型model.add(Dense(input_dim = 12, output_dim = 48)) #添加输入层、隐藏层的连接model.add(Activation('tanh')) #以Relu函数为激活函数model.add(Dense(input_dim = 48, output_dim = 48)) #添加隐藏层、隐藏层的连接model.add(Activation('relu')) #以Relu函数为激活函数model.add(Dropout(0.2))model.add(Dense(input_dim = 48, output_dim = 36)) #添加隐藏层、隐藏层的连接model.add(Activation('relu')) #以Relu函数为激活函数model.add(Dropout(0.2))model.add(Dense(input_dim = 36, output_dim = 36)) #添加隐藏层、隐藏层的连接model.add(Activation('relu')) #以Relu函数为激活函数model.add(Dense(input_dim = 36, output_dim = 12)) #添加隐藏层、隐藏层的连接model.add(Activation('relu')) #以Relu函数为激活函数model.add(Dense(input_dim = 12, output_dim = 12)) #添加隐藏层、隐藏层的连接model.add(Activation('relu')) #以Relu函数为激活函数model.add(Dense(input_dim = 12, output_dim = 1)) #添加隐藏层、输出层的连接model.add(Activation('sigmoid')) #以sigmoid函数为激活函数#编译模型，损失函数为blddsary_crossentropy，用adam法求解model.compile(loss='mean_squared_error', optimizer='adam')model.fit(x_train.values, y_train.values, nb_epoch = 70, batch_size = 2000) #训练模型r = pd.DataFrame(model.predict_classes(x_test.values))'''r = pd.DataFrame(model.predict(x_test.values))rr=r.valuestr=rr.flatten()for i in range(tr.shape[0]): if tr[i]>0.5: tr[i]=1 else: tr[i]=0''' from sklearn.metrics import accuracy_scoreprint(accuracy_score(y_test, r)) 0.650640749978我对神经网络进行了各种优化，正确率一直上不去，计算结果还不如我的神经网络股票预测代码
我不高兴，非常不高兴，65%的正确率是我无法容忍的，让我郁闷的是，我一直深爱的神经网络居然也这么无力
不能这样下去，下回我们将采用传说中的xgboost试一下
百度云代码下载
提取码 jc5x