Python数据挖掘——银行分控模型的建立

数据初始化

import pandas as pd from keras.models import Sequential from keras.layers.core import Dense, Activation import numpy as np # 参数初始化 inputfile = 'F:\Python\data(1)\data\bankloan.xls' data = pd.read_excel(inputfile) x_test = data.iloc[:,:8].values y_test = data.iloc[:,8].values

神经网络

inputfile = 'F:\Python\data(1)\data\bankloan.xls'
data = pd.read_excel(inputfile)
x_test = data.iloc[:,:8].values
y_test = data.iloc[:,8].values

model = Sequential() # 建立模型
model.add(Dense(input_dim = 8, units = 8))
model.add(Activation('relu')) # 用relu函数作为激活函数，能够大幅提供准确度
model.add(Dense(input_dim = 8, units = 1))
model.add(Activation('sigmoid')) # 由于是0-1输出，用sigmoid函数作为激活函数
model.compile(loss = 'mean_squared_error', optimizer = 'adam')
# 编译模型。由于我们做的是二元分类，所以我们指定损失函数为binary_crossentropy，以及模式为binary
# 另外常见的损失函数还有mean_squared_error、categorical_crossentropy等，请阅读帮助文件。
# 求解方法我们指定用adam，还有sgd、rmsprop等可选
model.fit(x_test, y_test, epochs = 1000, batch_size = 10)
predict_x=model.predict(x_test)
classes_x=np.argmax(predict_x,axis=1)
yp = classes_x.reshape(len(y_test))

def cm_plot(y, yp):
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y, yp)
import matplotlib.pyplot as plt
plt.matshow(cm, cmap=plt.cm.Greens)
plt.colorbar()
for x in range(len(cm)):
for y in range(len(cm)):
plt.annotate(cm[x,y], xy=(x, y), horizontalalignment='center', verticalalignment='center')
plt.ylabel('True label')
plt.xlabel('Predicted label')
return plt
cm_plot(y_test,yp).show()# 显示混淆矩阵可视化结果
score = model.evaluate(x_test,y_test,batch_size=128) # 模型评估
print(score)

SVM支持向量机

from sklearn import svm
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from matplotlib import pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
data_load = "F:\Python\data(1)\data\bankloan.xls"
data = pd.read_excel(data_load)
data.describe()
data.columns
data.index
## 转为np 数据切割
X = np.array(data.iloc[:,0:-1])
y = np.array(data.iloc[:,-1])
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=1, train_size=0.8, test_size=0.2, shuffle=True)
svm = svm.SVC()
svm.fit(X_test,y_test)
y_pred = svm.predict(X_test)
accuracy_score(y_test, y_pred)
print(accuracy_score(y_test, y_pred))
cm = confusion_matrix(y_test, y_pred)
heatmap = sns.heatmap(cm, annot=True, fmt='d')
heatmap.yaxis.set_ticklabels(heatmap.yaxis.get_ticklabels(), rotation=0, ha='right')
heatmap.xaxis.set_ticklabels(heatmap.xaxis.get_ticklabels(), rotation=45, ha='right')
plt.ylabel("true label")
plt.xlabel("predict label")
plt.show()

决策树

import pandas as pd
from sklearn.tree import DecisionTreeClassifier as DTC
from sklearn.tree import export_graphviz
from IPython.display import Image
from sklearn import tree
import pydotplus
# 参数初始化
filename = 'F:\Python\data(1)\data\bankloan.xls'
data = pd.read_excel(filename) # 导入数据

# 数据是类别标签，要将它转换为数据
x = data.iloc[:,:8].astype(int)
y = data.iloc[:,8].astype(int)

dtc = DTC(criterion='entropy') # 建立决策树模型，基于信息熵
dtc.fit(x, y) # 训练模型

# 导入相关函数，可视化决策树。
x = pd.DataFrame(x)
with open("C:/Users/GPC2019/Desktop/大数据挖掘/data/tree.dot", 'w') as f:
export_graphviz(dtc, feature_names = x.columns, out_file = f)
f.close()
dot_data = tree.export_graphviz(dtc, out_file=None, #regr_1 是对应分类器
feature_names=data.columns[:8], #对应特征的名字
class_names=data.columns[8], #对应类别的名字
filled=True, rounded=True,
special_characters=True)

graph = pydotplus.graph_from_dot_data(dot_data)
graph.write_png('F:\Python\data(1)\data\bankloan.xls') #保存图像
Image(graph.create_png())