|
1.赛题介绍
保险风控为背景，保险是重要的金融体系，对社会发展，民生保障起到重要作用。保险欺诈近些年层出不穷，在某些险种上保险欺诈的金额已经占到了理赔金额的20%甚至更多。对保险欺诈的识别成为保险行业中的关键应用场景。
2.数据描述性统计
1.导入数据
import pandas as pd
# 数据加载
train = pd.read_csv('./train.csv')
train
test = pd.read_csv('./test.csv')
test
# 合并train, test
data = pd.concat([train, test], axis=0)
data
data.index = range(len(data))
data
## 数据探索
data.isnull().sum()
# 唯一值个数
for col in data.columns:
print(col, data[col].nunique())
cat_columns = data.select_dtypes(include='O').columns
cat_columns
column_name = []
unique_value = []
for col in cat_columns:
#print(col, data[col].nunique())
column_name.append(col)
unique_value.append(data[col].nunique())
df = pd.DataFrame()
df['col_name'] = column_name
df['value'] = unique_value
df = df.sort_values('value', ascending=False)
df
data[cat_columns]
# 单独看某个字段
data['property_damage'].value_counts()
data['property_damage'] = data['property_damage'].map({'NO': 0, 'YES': 1, '?': 2})
data['property_damage'].value_counts()
data['police_report_available'].value_counts()
data['police_report_available'] = data['police_report_available'].map({'NO': 0, 'YES': 1, '?': 2})
data['police_report_available'].value_counts()
# policy_bind_date, incident_date
data['policy_bind_date'] = pd.to_datetime(data['policy_bind_date'])
data['incident_date'] = pd.to_datetime(data['incident_date'])
# 查看最大日期，最小日期
data['policy_bind_date'].min() # 1990-01-08
data['policy_bind_date'].max() # 2015-02-22
data['incident_date'].min() # 2015-01-01
data['incident_date'].max() # 2015-03-01
base_date = data['policy_bind_date'].min()
# 转换为date_diff
data['policy_bind_date_diff'] = (data['policy_bind_date'] - base_date).dt.days
data['incident_date_diff'] = (data['incident_date'] - base_date).dt.days
data['incident_date_policy_bind_date_diff'] = data['incident_date_diff'] - data['policy_bind_date_diff']
data[['policy_bind_date', 'incident_date', 'policy_bind_date_diff', 'incident_date_diff', 'incident_date_policy_bind_date_diff']]
# 去掉原始日期字段 policy_bind_date incident_date
data.drop(['policy_bind_date', 'incident_date'], axis=1, inplace=True)
data
#data['policy_id'].value_counts()
data.drop(['policy_id'], axis=1, inplace=True)
data.columns
## 标签编码
from sklearn.preprocessing import LabelEncoder
cat_columns = data.select_dtypes(include='O').columns
for col in cat_columns:
le = LabelEncoder()
data[col] = le.fit_transform(data[col])
data[cat_columns]
# 数据集切分
train = data[data['fraud'].notnull()]
test = data[data['fraud'].isnull()]
import lightgbm as lgb
model_lgb = lgb.LGBMClassifier(
num_leaves=2**5-1, reg_alpha=0.25, reg_lambda=0.25, objective='binary',
max_depth=-1, learning_rate=0.005, min_child_samples=3, random_state=2022,
n_estimators=2000, subsample=1, colsample_bytree=1,
)
# 模型训练
model_lgb.fit(train.drop(['fraud'], axis=1), train['fraud'])
# AUC评测： 以proba进行提交，结果会更好
y_pred = model_lgb.predict_proba(test.drop(['fraud'], axis=1))
y_pred
# 25.8%
train['fraud'].mean()
y_pred[:, 1]
result = pd.read_csv('./submission.csv')
result['fraud'] = y_pred[:, 1]
result.to_csv('./zzz.csv', index=False)
|