金融风控Task6学习笔记

一、学习知识点概要

这次是提交了比赛结果，完成了整个赛题，算是这段学习的一个结尾吧。

二、学习内容（部分代码）

xgb模型

导入需要的库

pip install bayesian-optimization
import pandas as pd
import numpy as np
import warnings
import os
import seaborn as sns
import matplotlib.pyplot as plt
import xgboost as xgb
from sklearn.model_selection import cross_val_score

读取文件

train1=pd.read_csv('d1_train.csv')
test_a1=pd.read_csv('d1_testa.csv')

压缩数据（预处理）

def reduce_mem_usage(df):
    start_mem = df.memory_usage().sum() 
    print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))
    
    for col in df.columns:
        col_type = df[col].dtype
        
        if col_type != object:
            c_min = df[col].min()
            c_max = df[col].max()
            if str(col_type)[:3] == 'int':
                if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:
                    df[col] = df[col].astype(np.int8)
                elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:
                    df[col] = df[col].astype(np.int16)
                elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:
                    df[col] = df[col].astype(np.int32)
                elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:
                    df[col] = df[col].astype(np.int64)  
            else:
                if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:
                    df[col] = df[col].astype(np.float16)
                elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:
                    df[col] = df[col].astype(np.float32)
                else:
                    df[col] = df[col].astype(np.float64)
        else:
            df[col] = df[col].astype('category')

    end_mem = df.memory_usage().sum() 
    print('Memory usage after optimization is: {:.2f} MB'.format(end_mem))
    print('Decreased by {:.1f}%'.format(100 * (start_mem - end_mem) / start_mem))
    
    return df

train1 = reduce_mem_usage(train1)
test_a1 = reduce_mem_usage(test_a1)

训练数据

X_train = train1.drop('isDefault', axis=1)
X_test = test_a1
y_train = train1['isDefault']

五折交叉验证

from sklearn.model_selection import KFold
folds = 5
seed = 2020
kf = KFold(n_splits=folds, shuffle=True, random_state=seed)

训练模型与保存

"""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

from sklearn.metrics import roc_auc_score


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]

    dtrain=xgb.DMatrix(X_train_split,label=y_train_split)
    dtest=xgb.DMatrix(X_val)


    params={'booster':'gbtree',
        'objective': 'binary:logistic',
        'eval_metric': 'auc',
        'max_depth':4,
        'lambda':10,
        'subsample':0.75,
        'colsample_bytree':0.75,
        'min_child_weight':2,
        'eta': 0.025,
        'seed':0,
        'nthread':8,
         'silent':1}

    watchlist = [(dtrain,'train')]
    model2=xgb.train(params,dtrain,num_boost_round=5,evals=watchlist)
    #输出概率
    val_pred=model2.predict(dtest)

    cv_scores.append(roc_auc_score(y_val, val_pred))
    print(cv_scores)

print("xgb_scotrainre_list:{}".format(cv_scores))
print("xgb_score_mean:{}".format(np.mean(cv_scores)))
print("xgb_score_std:{}".format(np.std(cv_scores)))

#保存模型
import pickle
# save model to file
pickle.dump(model2, open("pima.pickle.dat", "wb"))
# load model from file
loaded_model2 = pickle.load(open("pima.pickle.dat", "rb"))

三、问题与解决

Found arrays with inconsistent numbers of samples

链接: https://blog.csdn.net/weixin_37029453/article/details/78896425.

expected an indented block

Python语言是一款对缩进非常敏感的语言，Tab和空格的混用会导致错误，或者缩进不对，这是无法观测到的，在编译时会出现这样的错expected an indented block说明此处需要缩进，你只要在出现错误的那一行，按空格或Tab（但不能混用）键缩进就行。

四、思考与总结

其实像这样的学习还是实践最为重要，将代码自己敲打并运行一遍，根据需求去修改这些代码，当然可能会有一些错误出现，可以自行搜索解决办法，这样对代码的理解程度也会高一些。