import pandasas pd
import matplotlib.pyplotas plt
import numpyas np
data= pd.read_csv("creditcard.csv")
a=pd.value_counts(data["Class"])
count_classes= pd.value_counts(data['Class'], sort = True).sort_index()
from sklearn.preprocessingimport StandardScaler
# 1、StandardScaler就是z-score方法
# 将原始数据归一化为均值为0,方差为1的数据集 并将之存储到Amount列
data['normAmount'] = StandardScaler().fit_transform(data['Amount'].values.reshape(-1, 1))
# 删除数据中Time Amount 列
# 删除没用的两列数据,得到一个新的数据集
data= data.drop(['Time','Amount'],axis=1)
# 先对数据进行切分
X= data.ix[:, data.columns!= 'Class']
y= data.ix[:, data.columns== 'Class']
# 随机下采样
# 筛选出class为1的数据总数,并取得其索引值
# Number of data points in the minority class
# 统计异常值得个数
number_records_fraud= len(data[data.Class== 1])
# 统计欺诈样本的下标,并变成矩阵的格式:
fraud_indices= np.array(data[data.Class== 1].index)
# Picking the indices of the normal classes
# 记录正常值的下标:
# 把class为0的数据索引拿到手
normal_indices= data[data.Class== 0].index
# Out of the indices we picked, randomly select "x" number (number_records_fraud)
# 从normal_indices中抽取number_records_fraud
# 从正常值的索引中,选择和异常值相等个数的样本,保证样本的均衡:
# np.random.choice(a,size, replace, p):在a中以概率p随机选择size个数据,replace是指是否有放回;
random_normal_indices= np.random.choice(normal_indices, number_records_fraud, replace = False)
# 将数据转换成数组:
# 转换成numpy的array格式
random_normal_indices= np.array(random_normal_indices)
# Appending the 2 indices
# fraud_indices:欺诈样本的下标;random_normal_indices:正常值数组;
# concatenate:数据库的拼接;axis=1:按照对应行的数据进行拼接;
# 将两组索引数据连接成性的数据索引
under_sample_indices= np.concatenate([fraud_indices,random_normal_indices])
# Under sample dataset
# loc["a","b"]:表示第a行,第b列;
# iloc[1,1]:按照行列来索引,左式为第二行第二列;
# 获取下标所在行的所有列,即得到训练所需要的数据集:
# 下采样数据集
# 定位到真正的数据
under_sample_data= data.iloc[under_sample_indices,:]
# 将数据集按照class列进行分类
# 切分出下采样数据的特征和标签
X_undersample= under_sample_data.ix[:, under_sample_data.columns!= 'Class']
y_undersample= under_sample_data.ix[:, under_sample_data.columns== 'Class']
# Showing ratio
# 展示下比例
# 计算正负比例为0.5
print("Percentage of normal transactions: ", len(under_sample_data[under_sample_data.Class== 0])/len(under_sample_data))
print("Percentage of fraud transactions: ", len(under_sample_data[under_sample_data.Class== 1])/len(under_sample_data))
print("Total number of transactions in resampled data: ", len(under_sample_data))
# 导入交叉验证模块的数据切分
from sklearn.model_selectionimport train_test_split
# Whole dataset
# 交叉验证
# 随机划分训练集和测试集:x为除了class之外的其他的值,y为最终的结果列;
# test_size:样本占比;
# 从原始集中获取到训练集与测试集:
# train_test_split:x,y按照test_size的尺寸随机提取数据,然后划分到四个数据集中
# 对全部数据集进行切分,注意使用相同的随机策略
X_train, X_test, y_train, y_test= train_test_split(X,y,test_size = 0.3, random_state = 0)
print("Number transactions train dataset: ", len(X_train))
print("Number transactions test dataset: ", len(X_test))
print("Total number of transactions: ", len(X_train)+len(X_test))
# Undersampled dataset
# 数据平衡之后的数据中获取到训练集与测试集:
# 对下采样数据集进行切分
X_train_undersample, X_test_undersample, y_train_undersample, y_test_undersample= train_test_split(X_undersample
,y_undersample
,test_size = 0.3
,random_state = 0)
print("")
print("Number transactions train dataset: ", len(X_train_undersample))
print("Number transactions test dataset: ", len(X_test_undersample))
print("Total number of transactions: ", len(X_train_undersample)+len(X_test_undersample))
网友评论