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(r'./train.csv')
data_test_a = pd.read_csv(r'./testA.csv')
读取数据,导入包,可以导入一些无监督学习相关的包.做prediction之前也可以做一些无监督学习先处理数据,
numerical_fea = list(data_train.select_dtypes(exclude=['object']).columns)
category_fea = list(filter(lambda x: x not in numerical_fea,list(data_train.columns)))
label = 'isDefault'
numerical_fea.remove(label)
先查询对象特征和数值特征
#查看缺失值情况
data_train.isnull().sum()
id 0
loanAmnt 0
term 0
interestRate 0
installment 0
grade 0
subGrade 0
employmentTitle 1
employmentLength 46799
homeOwnership 0
annualIncome 0
verificationStatus 0
issueDate 0
isDefault 0
purpose 0
postCode 1
regionCode 0
dti 239
delinquency_2years 0
ficoRangeLow 0
ficoRangeHigh 0
openAcc 0
pubRec 0
pubRecBankruptcies 405
revolBal 0
revolUtil 531
totalAcc 0
initialListStatus 0
applicationType 0
earliesCreditLine 0
title 1
policyCode 0
n0 40270
n1 40270
n2 40270
n3 40270
n4 33239
n5 40270
n6 40270
n7 40270
n8 40271
n9 40270
n10 33239
n11 69752
n12 40270
n13 40270
n14 40270
dtype: int64
#按照平均数填充数值型特征
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())
一般來说可以多尝试几次,平均数,中位数,众数填充都可以试一下.也可以根据数据集具体分析.
data_train.isnull().sum()
id 0
loanAmnt 0
term 0
interestRate 0
installment 0
grade 0
subGrade 0
employmentTitle 0
employmentLength 46799
homeOwnership 0
annualIncome 0
verificationStatus 0
issueDate 0
isDefault 0
purpose 0
postCode 0
regionCode 0
dti 0
delinquency_2years 0
ficoRangeLow 0
ficoRangeHigh 0
openAcc 0
pubRec 0
pubRecBankruptcies 0
revolBal 0
revolUtil 0
totalAcc 0
initialListStatus 0
applicationType 0
earliesCreditLine 0
title 0
policyCode 0
n0 0
n1 0
n2 0
n3 0
n4 0
n5 0
n6 0
n7 0
n8 0
n9 0
n10 0
n11 0
n12 0
n13 0
n14 0
dtype: int64
#查看类别特征
category_fea
['grade', 'subGrade', 'employmentLength', 'issueDate', 'earliesCreditLine']
这几个特征需要预处理
#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()
1 year 52489
10+ years 262753
2 years 72358
3 years 64152
4 years 47985
5 years 50102
6 years 37254
7 years 35407
8 years 36192
9 years 30272
< 1 year 64237
NaN 46799
Name: employmentLength, dtype: int64
#对象类特征转化为数值举例
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)
data['employmentLength'].value_counts(dropna=False).sort_index()
0.0 15989
1.0 13182
2.0 18207
3.0 16011
4.0 11833
5.0 12543
6.0 9328
7.0 8823
8.0 8976
9.0 7594
10.0 65772
NaN 11742
Name: employmentLength, dtype: int64
这样我们将对象类型但是实际含义可量化的量时间转化为了数值
data_train['earliesCreditLine'].sample(5)
639106 Dec-1992
398594 Nov-1999
340977 Mar-2004
57563 Feb-2007
94343 Aug-1998
Name: earliesCreditLine, dtype: object
for data in [data_train, data_test_a]:
data['earliesCreditLine'] = data['earliesCreditLine'].apply(lambda s: int(s[-4:]))
data_train['earliesCreditLine'].sample(5)
423205 2005
355992 2003
619994 2000
668429 2000
395884 1996
Name: earliesCreditLine, dtype: int64
舍弃次要信息,直接转成年份.如果数据够干净也是可以转成月份的.
# 部分类别特征
cate_features = ['grade', 'subGrade', 'employmentTitle', 'homeOwnership', 'verificationStatus', 'purpose', 'postCode', 'regionCode', \
'applicationType', 'initialListStatus', 'title', 'policyCode']
for f in cate_features:
print(f, '类型数：', data[f].nunique())
grade 类型数： 7
subGrade 类型数： 35
employmentTitle 类型数： 79282
homeOwnership 类型数： 6
verificationStatus 类型数： 3
purpose 类型数： 14
postCode 类型数： 889
regionCode 类型数： 51
applicationType 类型数： 2
initialListStatus 类型数： 2
title 类型数： 12058
policyCode 类型数： 1
for data in [data_train, data_test_a]:
data['grade'] = data['grade'].map({'A':1,'B':2,'C':3,'D':4,'E':5,'F':6,'G':7})
# 类型数在2之上，又不是高维稀疏的,且纯分类特征
for data in [data_train, data_test_a]:
data = pd.get_dummies(data, columns=['subGrade', 'homeOwnership', 'verificationStatus', 'purpose', 'regionCode'], drop_first=True)
注意序数类的特征也可以考虑直接映射.
#异常值处理
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
data_train = data_train.copy()
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)
正常值 800000
Name: id_outliers, dtype: int64
id_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 800000
Name: loanAmnt_outliers, dtype: int64
loanAmnt_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 800000
Name: term_outliers, dtype: int64
term_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 794259
异常值 5741
Name: interestRate_outliers, dtype: int64
interestRate_outliers
异常值 2916
正常值 156694
Name: isDefault, dtype: int64
**********
正常值 792046
异常值 7954
Name: installment_outliers, dtype: int64
installment_outliers
异常值 2152
正常值 157458
Name: isDefault, dtype: int64
**********
正常值 800000
Name: employmentTitle_outliers, dtype: int64
employmentTitle_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 799701
异常值 299
Name: homeOwnership_outliers, dtype: int64
homeOwnership_outliers
异常值 62
正常值 159548
Name: isDefault, dtype: int64
**********
正常值 793973
异常值 6027
Name: annualIncome_outliers, dtype: int64
annualIncome_outliers
异常值 756
正常值 158854
Name: isDefault, dtype: int64
**********
正常值 800000
Name: verificationStatus_outliers, dtype: int64
verificationStatus_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 783003
异常值 16997
Name: purpose_outliers, dtype: int64
purpose_outliers
异常值 3635
正常值 155975
Name: isDefault, dtype: int64
**********
正常值 798931
异常值 1069
Name: postCode_outliers, dtype: int64
postCode_outliers
异常值 221
正常值 159389
Name: isDefault, dtype: int64
**********
正常值 799994
异常值 6
Name: regionCode_outliers, dtype: int64
regionCode_outliers
异常值 1
正常值 159609
Name: isDefault, dtype: int64
**********
正常值 798440
异常值 1560
Name: dti_outliers, dtype: int64
dti_outliers
异常值 466
正常值 159144
Name: isDefault, dtype: int64
**********
正常值 778245
异常值 21755
Name: delinquency_2years_outliers, dtype: int64
delinquency_2years_outliers
异常值 5089
正常值 154521
Name: isDefault, dtype: int64
**********
正常值 788261
异常值 11739
Name: ficoRangeLow_outliers, dtype: int64
ficoRangeLow_outliers
异常值 778
正常值 158832
Name: isDefault, dtype: int64
**********
正常值 788261
异常值 11739
Name: ficoRangeHigh_outliers, dtype: int64
ficoRangeHigh_outliers
异常值 778
正常值 158832
Name: isDefault, dtype: int64
**********
正常值 790889
异常值 9111
Name: openAcc_outliers, dtype: int64
openAcc_outliers
异常值 2195
正常值 157415
Name: isDefault, dtype: int64
**********
正常值 792471
异常值 7529
Name: pubRec_outliers, dtype: int64
pubRec_outliers
异常值 1701
正常值 157909
Name: isDefault, dtype: int64
**********
正常值 794120
异常值 5880
Name: pubRecBankruptcies_outliers, dtype: int64
pubRecBankruptcies_outliers
异常值 1423
正常值 158187
Name: isDefault, dtype: int64
**********
正常值 790001
异常值 9999
Name: revolBal_outliers, dtype: int64
revolBal_outliers
异常值 1359
正常值 158251
Name: isDefault, dtype: int64
**********
正常值 799948
异常值 52
Name: revolUtil_outliers, dtype: int64
revolUtil_outliers
异常值 23
正常值 159587
Name: isDefault, dtype: int64
**********
正常值 791663
异常值 8337
Name: totalAcc_outliers, dtype: int64
totalAcc_outliers
异常值 1668
正常值 157942
Name: isDefault, dtype: int64
**********
正常值 800000
Name: initialListStatus_outliers, dtype: int64
initialListStatus_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 784586
异常值 15414
Name: applicationType_outliers, dtype: int64
applicationType_outliers
异常值 3875
正常值 155735
Name: isDefault, dtype: int64
**********
正常值 775134
异常值 24866
Name: title_outliers, dtype: int64
title_outliers
异常值 3900
正常值 155710
Name: isDefault, dtype: int64
**********
正常值 800000
Name: policyCode_outliers, dtype: int64
policyCode_outliers
正常值 159610
Name: isDefault, dtype: int64
**********
正常值 782773
异常值 17227
Name: n0_outliers, dtype: int64
n0_outliers
异常值 3485
正常值 156125
Name: isDefault, dtype: int64
**********
正常值 790500
异常值 9500
Name: n1_outliers, dtype: int64
n1_outliers
异常值 2491
正常值 157119
Name: isDefault, dtype: int64
**********
正常值 789067
异常值 10933
Name: n2_outliers, dtype: int64
n2_outliers
异常值 3205
正常值 156405
Name: isDefault, dtype: int64
**********
正常值 789067
异常值 10933
Name: n3_outliers, dtype: int64
n3_outliers
异常值 3205
正常值 156405
Name: isDefault, dtype: int64
**********
正常值 788660
异常值 11340
Name: n4_outliers, dtype: int64
n4_outliers
异常值 2476
正常值 157134
Name: isDefault, dtype: int64
**********
正常值 790355
异常值 9645
Name: n5_outliers, dtype: int64
n5_outliers
异常值 1858
正常值 157752
Name: isDefault, dtype: int64
**********
正常值 786006
异常值 13994
Name: n6_outliers, dtype: int64
n6_outliers
异常值 3182
正常值 156428
Name: isDefault, dtype: int64
**********
正常值 788430
异常值 11570
Name: n7_outliers, dtype: int64
n7_outliers
异常值 2746
正常值 156864
Name: isDefault, dtype: int64
**********
正常值 789625
异常值 10375
Name: n8_outliers, dtype: int64
n8_outliers
异常值 2131
正常值 157479
Name: isDefault, dtype: int64
**********
正常值 786384
异常值 13616
Name: n9_outliers, dtype: int64
n9_outliers
异常值 3953
正常值 155657
Name: isDefault, dtype: int64
**********
正常值 788979
异常值 11021
Name: n10_outliers, dtype: int64
n10_outliers
异常值 2639
正常值 156971
Name: isDefault, dtype: int64
**********
正常值 799434
异常值 566
Name: n11_outliers, dtype: int64
n11_outliers
异常值 112
正常值 159498
Name: isDefault, dtype: int64
**********
正常值 797585
异常值 2415
Name: n12_outliers, dtype: int64
n12_outliers
异常值 545
正常值 159065
Name: isDefault, dtype: int64
**********
正常值 788907
异常值 11093
Name: n13_outliers, dtype: int64
n13_outliers
异常值 2482
正常值 157128
Name: isDefault, dtype: int64
**********
正常值 788884
异常值 11116
Name: n14_outliers, dtype: int64
n14_outliers
异常值 3364
正常值 156246
Name: isDefault, dtype: int64
**********
我们同样可以用箱型图进行分类,留坑日后补
数据分箱:可以对数据进行分箱操作.可以对数据进行线性变换后更新,如果横跨多个数量级而且分布还不错,可以考虑取对数之后分箱
# 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']))
data['loanAmnt_bin3'] = pd.qcut(data['loanAmnt'], 10, labels=False)
可以尝试中位数分箱或者卡方分箱
特征交互:可以用matplotlib绘制一下两个特征彼此的分布图,显然这个是特征平方起跳的算法,特征太多的话要筛选一下.
for col in ['grade', 'subGrade']:
temp_dict = data_train.groupby([col])['isDefault'].agg(['mean']).reset_index().rename(columns={'mean': col + '_target_mean'})
temp_dict.index = temp_dict[col].values
temp_dict = temp_dict[col + '_target_mean'].to_dict()
data_train[col + '_target_mean'] = data_train[col].map(temp_dict)
data_test_a[col + '_target_mean'] = data_test_a[col].map(temp_dict)
# 其他衍生变量 mean 和 std
for df in [data_train, data_test_a]:
for item in ['n0','n1','n2','n4','n5','n6','n7','n8','n9','n10','n11','n12','n13','n14']:
df['grade_to_mean_' + item] = df['grade'] / df.groupby([item])['grade'].transform('mean')
df['grade_to_std_' + item] = df['grade'] / df.groupby([item])['grade'].transform('std')
Feature Encoding
#label-encode:subGrade,postCode,title
# 高维类别特征需要进行转换
for col in tqdm(['employmentTitle', 'postCode', 'title','subGrade']):
le = LabelEncoder()
le.fit(list(data_train[col].astype(str).values) + list(data_test_a[col].astype(str).values))
data_train[col] = le.transform(list(data_train[col].astype(str).values))
data_test_a[col] = le.transform(list(data_test_a[col].astype(str).values))
print('Label Encoding 完成')
100%|████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:06<00:00, 1.68s/it]
Label Encoding 完成
可以直接丢进树模型
#logistic regression记得要standardlization 或者 normalization
# 举例归一化过程
#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])))
特征选择的方法：
1 Filter
方差选择法
相关系数法（pearson 相关系数）
卡方检验
互信息法
2 Wrapper （RFE）
递归特征消除法
3 Embedded
基于惩罚项的特征选择法
基于树模型的特征选择
重点记录一下Embedded
from sklearn.feature_selection import SelectFromModel
from sklearn.linear_model import LogisticRegression
#带L1惩罚项的逻辑回归作为基模型的特征选择
#SelectFromModel(LogisticRegression(penalty="l1", C=0.1)).fit_transform(train,target_train)
基于惩罚项的特征选择法 使用带惩罚项的基模型，除了筛选出特征外，同时也进行了降维。 在feature_selection库的SelectFromModel类结合逻辑回归模型可以用于选择特征
from sklearn.feature_selection import SelectFromModel
from sklearn.ensemble import GradientBoostingClassifier
#GBDT作为基模型的特征选择
#SelectFromModel(GradientBoostingClassifier()).fit_transform(train,target_train)
基于树模型的特征选择 树模型中GBDT也可用来作为基模型进行特征选择。 在feature_selection库的SelectFromModel类结合GBDT模型可以用于选择特征
data_train =pd.read_csv(r'./train.csv')
data_test_a = pd.read_csv(r'./testA.csv')
# 删除不需要的数据
for data in [data_train, data_test_a]:
data.drop(['issueDate','id'], axis=1,inplace=True)
"纵向用缺失值上面的值替换缺失值"
data_train = data_train.fillna(axis=0,method='ffill')
x_train = data_train.drop(['isDefault'], axis=1)
#计算协方差
data_corr = x_train.corrwith(data_train.isDefault) #计算相关性
result = pd.DataFrame(columns=['features', 'corr'])
result['features'] = data_corr.index
result['corr'] = data_corr.values
numerical_fea.remove('id')
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)
output_42_1.png
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
def xgb_model(x_train, y_train, x_test):
xgb_train, xgb_test = cv_model(xgb, x_train, y_train, x_test, "xgb")
return xgb_train, xgb_test
def cat_model(x_train, y_train, x_test):
cat_train, cat_test = cv_model(CatBoostRegressor, x_train, y_train, x_test, "cat")
lgb_train, lgb_test = lgb_model(x_nuneric, y_train, x_test)
###此处应当去除非numeric的量.
reference:
Task3 特征工程