数据特征工程的一些trick!以风控逾期为案例
数据分析（下面内容都是风控逾期预测的案例）
链接：https://tianchi.aliyun.com/notebook-ai/detail?spm=5176.12586969.1002.6.3b3022faB2aZ2J&postId=129320
1.导入数据分析及可视化过程需要的库
下面展示一些 内联代码片。
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import datetime
import warnings
warnings.filterwarnings('ignore')
#导入数据
data_train = pd.read_csv('./train.csv')
data_test_a = pd.read_csv('./testA.csv')
data_test_a.shape
data_train.shape
data_train.columns
特征工程
1.学习特征预处理、缺失值、异常值处理、数据分桶等特征处理方法
2.学习特征交互、编码、选择的相应方法
（1）导入数据和包
#导入需要的包
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import datetime
from tqdm import tqdm
from sklearn.preprocessing import LabelEncoder
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.preprocessing import MinMaxScaler
import xgboost as xgb
import lightgbm as lgb
from catboost import CatBoostRegressor
import warnings
from sklearn.model_selection import StratifiedKFold, KFold
from sklearn.metrics import accuracy_score, f1_score, roc_auc_score, log_loss
warnings.filterwarnings('ignore')
data_train =pd.read_csv('../train.csv')
data_test_a = pd.read_csv('../testA.csv')
（2）找出缺失值并且填充：
#查看缺失值情况
data_train.isnull().sum()
#按照中位数填充数值型特征
data_train[numerical_fea] = data_train[numerical_fea].fillna(data_train[numerical_fea].median())
data_test_a[numerical_fea] = data_test_a[numerical_fea].fillna(data_train[numerical_fea].median())
#按照众数填充类别型特征
data_train[category_fea] = data_train[category_fea].fillna(data_train[category_fea].mode())
data_test_a[category_fea] = data_test_a[category_fea].fillna(data_train[category_fea].mode())
#再次查看缺失值情况（用于jupyter lab 一步一步看）
data_train.isnull().sum()
（3）时间格式处理：
#转化成时间格式
for data in [data_train, data_test_a]:
data['issueDate'] = pd.to_datetime(data['issueDate'],format='%Y-%m-%d')
startdate = datetime.datetime.strptime('2007-06-01', '%Y-%m-%d')
#构造时间特征
data['issueDateDT'] = data['issueDate'].apply(lambda x: x-startdate).dt.days
data_train['employmentLength'].value_counts(dropna=False).sort_index()
对象类型特征转换到数值：
def employmentLength_to_int(s):
if pd.isnull(s):
return s
else:
return np.int8(s.split()[0])
for data in [data_train, data_test_a]:
data['employmentLength'].replace(to_replace='10+ years', value='10 years', inplace=True)
data['employmentLength'].replace('< 1 year', '0 years', inplace=True)
data['employmentLength'] = data['employmentLength'].apply(employmentLength_to_int)
#查看情况
data['employmentLength'].value_counts(dropna=False).sort_index()
（4）异常值处理（重点！！！）
4.1 均方差（3segma原则）
在统计学中，如果一个数据分布近似正态，那么大约 68% 的数据值会在均值的一个标准差范围内，大约 95% 会在两个标准差范围内，大约 99.7% 会在三个标准差范围内。
def find_outliers_by_3segama(data,fea):
data_std = np.std(data[fea])
data_mean = np.mean(data[fea])
outliers_cut_off = data_std * 3
lower_rule = data_mean - outliers_cut_off
upper_rule = data_mean + outliers_cut_off
data[fea+'_outliers'] = data[fea].apply(lambda x:str('异常值') if x > upper_rule or x < lower_rule else '正常值')
return data
for fea in numerical_fea:
data_train = find_outliers_by_3segama(data_train,fea)
print(data_train[fea+'_outliers'].value_counts())
print(data_train.groupby(fea+'_outliers')['isDefault'].sum())
print('*'*10)
4.2 数据分桶
（1）特征分箱的目的：
从模型效果上来看，特征分箱主要是为了降低变量的复杂性，减少变量噪音对模型的影响，提高自变量和因变量的相关度。从而使模型更加稳定。
特别要注意一下分箱的基本原则：
i.最小分箱占比不低于5%
ii.箱内不能全部是好客户
iii.连续箱单调
#通过除法映射到间隔均匀的分箱中，每个分箱的取值范围都是loanAmnt/1000
data['loanAmnt_bin1'] = np.floor_divide(data['loanAmnt'], 1000)
#通过对数函数映射到指数宽度分箱
data['loanAmnt_bin2'] = np.floor(np.log10(data['loanAmnt']))
(5)逻辑回归等模型要单独增加的特征工程
对特征做归一化，去除相关性高的特征,避免特征大吃小的问题
#伪代码
for fea in [要归一化的特征列表]：
data[fea] = ((data[fea] - np.min(data[fea])) / (np.max(data[fea]) - np.min(data[fea])))
(6)特征选择
介绍三种方式：方差选择法、相关系数法（pearson 相关系数）、卡方检验
i.方差选择法
先要计算各个特征的方差，然后根据设定的阈值，选择方差大于阈值的特征
from sklearn.feature_selection import VarianceThreshold
#其中参数threshold为方差的阈值
VarianceThreshold(threshold=3).fit_transform(train,target_train)
ii.相关系数法（pearson相关系数）
皮尔森相关系数是一种最简单的，可以帮助理解特征和响应变量之间关系的方法，该方法衡量的是变量之间的线性相关性。 结果的取值区间为 [-1，1] ， -1 表示完全的负相关， +1表示完全的正相关，0 表示没有线性相关。
from sklearn.feature_selection import SelectKBest
from scipy.stats import pearsonr
#选择K个最好的特征，返回选择特征后的数据
#第一个参数为计算评估特征是否好的函数，该函数输入特征矩阵和目标向量，
#输出二元组（评分，P值）的数组，数组第i项为第i个特征的评分和P值。在此定义为计算相关系数
#参数k为选择的特征个数
SelectKBest(k=5).fit_transform(train,target_train)
iii.卡方检验
经典的卡方检验是用于检验自变量对因变量的相关性。 假设自变量有N种取值，因变量有M种取值，考虑自变量等于i且因变量等于j的样本频数的观察值与期望的差距。 其统计量如下： χ2=∑(A−T)2T，其中A为实际值，T为理论值
(注：卡方只能运用在正定矩阵上，否则会报错Input X must be non-negative)
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
#参数k为选择的特征个数
SelectKBest(chi2, k=5).fit_transform(train,target_train)
！！！！当然也可以直接用图片表示各个特征之间的关系
# 当然也可以直接看图
data_numeric = data_train[numerical_fea]
correlation = data_numeric.corr()
f , ax = plt.subplots(figsize = (7, 7))
plt.title('Correlation of Numeric Features with Price',y=1,size=16)
sns.heatmap(correlation,square = True, vmax=0.8)
(7)模型训练
features = [f for f in data_train.columns if f not in ['id','issueDate','isDefault'] and '_outliers' not in f]
x_train = data_train[features]
x_test = data_test_a[features]
y_train = data_train['isDefault']
def cv_model(clf, train_x, train_y, test_x, clf_name):
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
train = np.zeros(train_x.shape[0])
test = np.zeros(test_x.shape[0])
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(train_x, train_y)):
print('************************************ {} ************************************'.format(str(i+1)))
trn_x, trn_y, val_x, val_y = train_x.iloc[train_index], train_y[train_index], train_x.iloc[valid_index], train_y[valid_index]
if clf_name == "lgb":
train_matrix = clf.Dataset(trn_x, label=trn_y)
valid_matrix = clf.Dataset(val_x, label=val_y)
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': 'auc',
'min_child_weight': 5,
'num_leaves': 2 ** 5,
'lambda_l2': 10,
'feature_fraction': 0.8,
'bagging_fraction': 0.8,
'bagging_freq': 4,
'learning_rate': 0.1,
'seed': 2020,
'nthread': 28,
'n_jobs':24,
'silent': True,
'verbose': -1,
}
model = clf.train(params, train_matrix, 50000, valid_sets=[train_matrix, valid_matrix], verbose_eval=200,early_stopping_rounds=200)
val_pred = model.predict(val_x, num_iteration=model.best_iteration)
test_pred = model.predict(test_x, num_iteration=model.best_iteration)
# print(list(sorted(zip(features, model.feature_importance("gain")), key=lambda x: x[1], reverse=True))[:20])
if clf_name == "xgb":
train_matrix = clf.DMatrix(trn_x , label=trn_y)
valid_matrix = clf.DMatrix(val_x , label=val_y)
params = {'booster': 'gbtree',
'objective': 'binary:logistic',
'eval_metric': 'auc',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.04,
'tree_method': 'exact',
'seed': 2020,
'nthread': 36,
"silent": True,
}
watchlist = [(train_matrix, 'train'),(valid_matrix, 'eval')]
model = clf.train(params, train_matrix, num_boost_round=50000, evals=watchlist, verbose_eval=200, early_stopping_rounds=200)
val_pred = model.predict(valid_matrix, ntree_limit=model.best_ntree_limit)
test_pred = model.predict(test_x , ntree_limit=model.best_ntree_limit)
if clf_name == "cat":
params = {'learning_rate': 0.05, 'depth': 5, 'l2_leaf_reg': 10, 'bootstrap_type': 'Bernoulli',
'od_type': 'Iter', 'od_wait': 50, 'random_seed': 11, 'allow_writing_files': False}
model = clf(iterations=20000, **params)
model.fit(trn_x, trn_y, eval_set=(val_x, val_y),
cat_features=[], use_best_model=True, verbose=500)
val_pred = model.predict(val_x)
test_pred = model.predict(test_x)
train[valid_index] = val_pred
test = test_pred / kf.n_splits
cv_scores.append(roc_auc_score(val_y, val_pred))
print(cv_scores)
print("%s_scotrainre_list:" % clf_name, cv_scores)
print("%s_score_mean:" % clf_name, np.mean(cv_scores))
print("%s_score_std:" % clf_name, np.std(cv_scores))
return train, test
def lgb_model(x_train, y_train, x_test):
lgb_train, lgb_test = cv_model(lgb, x_train, y_train, x_test, "lgb")
return lgb_train, lgb_test
lgb_train, lgb_test = lgb_model(x_train, y_train, x_test)
（8）简单建模
Tips1：金融风控的实际项目多涉及到信用评分，因此需要模型特征具有较好的可解释性，所以目前在实际项目中多还是以逻辑回归作为基础模型。但是在比赛中以得分高低为准，不需要严谨的可解释性，所以大多基于集成算法进行建模。
Tips2：因为逻辑回归的算法特性，需要提前对异常值、缺失值数据进行处理【参考task3部分】
Tips3：基于树模型的算法特性，异常值、缺失值处理可以跳过，但是对于业务较为了解的同学也可以自己对缺失异常值进行处理，效果可能会更优于模型处理的结果。
from sklearn.model_selection import KFold
# 分离数据集，方便进行交叉验证
X_train = data.loc[data['sample']=='train', :].drop(['id','issueDate','isDefault', 'sample'], axis=1)
X_test = data.loc[data['sample']=='test', :].drop(['id','issueDate','isDefault', 'sample'], axis=1)
y_train = data.loc[data['sample']=='train', 'isDefault']
# 5折交叉验证
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)
"""对训练集数据进行划分，分成训练集和验证集，并进行相应的操作"""
from sklearn.model_selection import train_test_split
import lightgbm as lgb
# 数据集划分
X_train_split, X_val, y_train_split, y_val = train_test_split(X_train, y_train, test_size=0.2)
train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
valid_matrix = lgb.Dataset(X_val, label=y_val)
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'learning_rate': 0.1,
'metric': 'auc',
'min_child_weight': 1e-3,
'num_leaves': 31,
'max_depth': -1,
'reg_lambda': 0,
'reg_alpha': 0,
'feature_fraction': 1,
'bagging_fraction': 1,
'bagging_freq': 0,
'seed': 2020,
'nthread': 8,
'silent': True,
'verbose': -1,
}
"""使用训练集数据进行模型训练"""
model = lgb.train(params, train_set=train_matrix, valid_sets=valid_matrix, num_boost_round=20000, verbose_eval=1000, early_stopping_rounds=200)
对验证集进行预测
from sklearn import metrics
from sklearn.metrics import roc_auc_score
"""预测并计算roc的相关指标"""
val_pre_lgb = model.predict(X_val, num_iteration=model.best_iteration)
fpr, tpr, threshold = metrics.roc_curve(y_val, val_pre_lgb)
roc_auc = metrics.auc(fpr, tpr)
print('未调参前lightgbm单模型在验证集上的AUC：{}'.format(roc_auc))
"""画出roc曲线图"""
plt.figure(figsize=(8, 8))
plt.title('Validation ROC')
plt.plot(fpr, tpr, 'b', label = 'Val AUC = %0.4f' % roc_auc)
plt.ylim(0,1)
plt.xlim(0,1)
plt.legend(loc='best')
plt.title('ROC')
plt.ylabel('True Positive Rate')
plt.xlabel('False Positive Rate')
# 画出对角线
plt.plot([0,1],[0,1],'r--')
plt.show()
更进一步的，使用5折交叉验证进行模型性能评估
import lightgbm as lgb
"""使用lightgbm 5折交叉验证进行建模预测"""
cv_scores = []
for i, (train_index, valid_index) in enumerate(kf.split(X_train, y_train)):
print('************************************ {} ************************************'.format(str(i+1)))
X_train_split, y_train_split, X_val, y_val = X_train.iloc[train_index], y_train[train_index], X_train.iloc[valid_index], y_train[valid_index]
train_matrix = lgb.Dataset(X_train_split, label=y_train_split)
valid_matrix = lgb.Dataset(X_val, label=y_val)
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'learning_rate': 0.1,
'metric': 'auc',
'min_child_weight': 1e-3,
'num_leaves': 31,
'max_depth': -1,
'reg_lambda': 0,
'reg_alpha': 0,
'feature_fraction': 1,
'bagging_fraction': 1,
'bagging_freq': 0,
'seed': 2020,
'nthread': 8,
'silent': True,
'verbose': -1,
}
model = lgb.train(params, train_set=train_matrix, num_boost_round=20000, valid_sets=valid_matrix, verbose_eval=1000, early_stopping_rounds=200)
val_pred = model.predict(X_val, num_iteration=model.best_iteration)
cv_scores.append(roc_auc_score(y_val, val_pred))
print(cv_scores)
print("lgb_scotrainre_list:{}".format(cv_scores))
print("lgb_score_mean:{}".format(np.mean(cv_scores)))
print("lgb_score_std:{}".format(np.std(cv_scores)))
总结
我们主要完成了建模与调参的工作，首先在建模的过程中通过划分数据集、交叉验证等方式对模型的性能进行评估验证，并通过可视化方式绘制模型ROC曲线