import numpy as np
from sklearn import linear_model
# 读取数据
sports = pd.read_csv(r'C:\Users\Administrator\Desktop\Run or Walk.csv')
# 提取出所有自变量名称
predictors = sports.columns[4:]
# 构建自变量矩阵
X = sports.ix[:,predictors]
# 提取y变量值
y = sports.activity
# 将数据集拆分为训练集和测试集
X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size = 0.25, random_state = 1234)
# 利用训练集建模
sklearn_logistic = linear_model.LogisticRegression()
sklearn_logistic.fit(X_train, y_train)
# 返回模型的各个参数
print(sklearn_logistic.intercept_, sklearn_logistic.coef_)
# 模型预测
sklearn_predict = sklearn_logistic.predict(X_test)
# 预测结果统计
pd.Series(sklearn_predict).value_counts()
-------------------------------------------------------------------------------------------------------------------------------------------
# 导入第三方模块
from sklearn import metrics
# 混淆矩阵
cm = metrics.confusion_matrix(y_test, sklearn_predict, labels = [0,1])
cm
Accuracy = metrics.scorer.accuracy_score(y_test, sklearn_predict)
Sensitivity = metrics.scorer.recall_score(y_test, sklearn_predict)
Specificity = metrics.scorer.recall_score(y_test, sklearn_predict, pos_label=0)
print('模型准确率为%.2f%%:' %(Accuracy*100))
print('正例覆盖率为%.2f%%' %(Sensitivity*100))
print('负例覆盖率为%.2f%%' %(Specificity*100))
-------------------------------------------------------------------------------------------------------------------------------------------
# 混淆矩阵的可视化
# 导入第三方模块
import seaborn as sns
import matplotlib.pyplot as plt
# 绘制热力图
sns.heatmap(cm, annot = True, fmt = '.2e',cmap = 'GnBu')
plt.show()
------------------------------------------------------------------------------------------------------------------------------------------
# 绘制ROC曲线
# 计算真正率和假正率
fpr,tpr,threshold = metrics.roc_curve(y_test, sm_y_probability)
# 计算auc的值
roc_auc = metrics.auc(fpr,tpr)
# 绘制面积图
plt.stackplot(fpr, tpr, color='steelblue', alpha = 0.5, edgecolor = 'black')
# 添加边际线
plt.plot(fpr, tpr, color='black', lw = 1)
# 添加对角线
plt.plot([0,1],[0,1], color = 'red', linestyle = '--')
# 添加文本信息
plt.text(0.5,0.3,'ROC curve (area = %0.2f)' % roc_auc)
# 添加x轴与y轴标签
plt.xlabel('1-Specificity')
plt.ylabel('Sensitivity')
plt.show()
-------------------------------------------------------------------------------------------------------------------------------------------
#ks曲线 链接：https://www.jianshu.com/p/b1b1344bd99f 风控数据分析学习笔记（二）Python建立信用评分卡 -
fig, ax = plt.subplots()
ax.plot(1 - threshold, tpr, label='tpr')# ks曲线要按照预测概率降序排列，所以需要1-threshold镜像
ax.plot(1 - threshold, fpr, label='fpr')
ax.plot(1 - threshold, tpr-fpr,label='KS')
plt.xlabel('score')
plt.title('KS Curve')
plt.ylim([0.0, 1.0])
plt.figure(figsize=(20,20))
legend = ax.legend(loc='upper left')
plt.show()
用keras框架较为方便
首先安装anaconda，然后通过pip安装keras
以下转自wphh的博客。
#coding:utf-8'''
GPU run command:
THEANO_FLAGS=mode=FAST_RUN,device=gpu,floatX=float32 python cnn.py
CPU run command:
python cnn.py
2016.06.06更新：
这份代码是keras开发初期写的，当时keras还没有现在这么流行，文档也还没那么丰富，所以我当时写了一些简单的教程。
现在keras的API也发生了一些的变化，建议及推荐直接上keras.io看更加详细的教程。
'''
#导入各种用到的模块组件
from __future__ import absolute_import
from __future__ import print_function
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.layers.advanced_activations import PReLU
from keras.layers.convolutional import Convolution2D, MaxPooling2D
from keras.optimizers import SGD, Adadelta, Adagrad
from keras.utils import np_utils, generic_utils
from six.moves import range
from data import load_data
import random
import numpy as np
np.random.seed(1024) # for reproducibility
#加载数据
data, label = load_data()
#打乱数据
index = [i for i in range(len(data))]
random.shuffle(index)
data = data[index]
label = label[index]
print(data.shape[0], ' samples')
#label为0~9共10个类别，keras要求格式为binary class matrices,转化一下，直接调用keras提供的这个函数
label = np_utils.to_categorical(label, 10)
###############
#开始建立CNN模型
###############
#生成一个model
model = Sequential()
#第一个卷积层，4个卷积核，每个卷积核大小5*5。1表示输入的图片的通道,灰度图为1通道。
#border_mode可以是valid或者full，具体看这里说明：http://deeplearning.net/software/theano/library/tensor/nnet/conv.html#theano.tensor.nnet.conv.conv2d
#激活函数用tanh
#你还可以在model.add(Activation('tanh'))后加上dropout的技巧: model.add(Dropout(0.5))
model.add(Convolution2D(4, 5, 5, border_mode='valid',input_shape=(1,28,28)))
model.add(Activation('tanh'))
#第二个卷积层，8个卷积核，每个卷积核大小3*3。4表示输入的特征图个数，等于上一层的卷积核个数
#激活函数用tanh
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(8, 3, 3, border_mode='valid'))
model.add(Activation('tanh'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#第三个卷积层，16个卷积核，每个卷积核大小3*3
#激活函数用tanh
#采用maxpooling，poolsize为(2,2)
model.add(Convolution2D(16, 3, 3, border_mode='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
#全连接层，先将前一层输出的二维特征图flatten为一维的。
#Dense就是隐藏层。16就是上一层输出的特征图个数。4是根据每个卷积层计算出来的：(28-5+1)得到24,(24-3+1)/2得到11，(11-3+1)/2得到4
#全连接有128个神经元节点,初始化方式为normal
model.add(Flatten())
model.add(Dense(128, init='normal'))
model.add(Activation('tanh'))
#Softmax分类，输出是10类别
model.add(Dense(10, init='normal'))
model.add(Activation('softmax'))
#############
#开始训练模型
##############
#使用SGD + momentum
#model.compile里的参数loss就是损失函数(目标函数)
sgd = SGD(lr=0.05, decay=1e-6, momentum=0.9, nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer=sgd,metrics=["accuracy"])
#调用fit方法，就是一个训练过程. 训练的epoch数设为10，batch_size为100．
#数据经过随机打乱shuffle=True。verbose=1，训练过程中输出的信息，0、1、2三种方式都可以，无关紧要。show_accuracy=True，训练时每一个epoch都输出accuracy。
#validation_split=0.2，将20%的数据作为验证集。
model.fit(data, label, batch_size=100, nb_epoch=10,shuffle=True,verbose=1,validation_split=0.2)
"""
#使用data augmentation的方法
#一些参数和调用的方法，请看文档
datagen = ImageDataGenerator(
featurewise_center=True, # set input mean to 0 over the dataset
samplewise_center=False, # set each sample mean to 0
featurewise_std_normalization=True, # divide inputs by std of the dataset
samplewise_std_normalization=False, # divide each input by its std
zca_whitening=False, # apply ZCA whitening
rotation_range=20, # randomly rotate images in the range (degrees, 0 to 180)
width_shift_range=0.2, # randomly shift images horizontally (fraction of total width)
height_shift_range=0.2, # randomly shift images vertically (fraction of total height)
horizontal_flip=True, # randomly flip images
vertical_flip=False) # randomly flip images
# compute quantities required for featurewise normalization
# (std, mean, and principal components if ZCA whitening is applied)
datagen.fit(data)
for e in range(nb_epoch):
print('-'*40)
print('Epoch', e)
print('-'*40)
print("Training...")
# batch train with realtime data augmentation
progbar = generic_utils.Progbar(data.shape[0])
for X_batch, Y_batch in datagen.flow(data, label):
loss,accuracy = model.train(X_batch, Y_batch,accuracy=True)
progbar.add(X_batch.shape[0], values=[("train loss", loss),("accuracy:", accuracy)] )
"""
