【数据集下载】

这是我们本次算法实践进阶数据的下载地址 https://pan.baidu.com/s/1wO9qJRjnrm8uhaSP67K0lw
说明：这份数据集是金融数据（非原始数据，已经处理过了），我们要做的是预测贷款用户是否会逾期。表格中 “status” 是结果标签：0表示未逾期，1表示逾期。

【任务1·数据预处理】

数据类型转换和缺失值处理（尝试不同的填充看效果）以及及其他你能借鉴的数据探索。

导入相关库

import pandas as pd

读取数据

data_all = pd.read_csv('data.csv')

数据清洗

# 删除无关数据
data_all = data_all.drop(['custid', 'trade_no', 'bank_card_no', 'id_name'], axis=1)
#删除重复数据
X = data_all.drop(labels='status',axis=1)
L = []
for col in X:
if len(X[col].unique()) == 1:
L.append(col)
for col in L:
X.drop(col, axis=1, inplace=True)

缺失值处理

# 查看缺失数据
print(data_all.isnull().sum())

结果

Unnamed: 0                                  0
low_volume_percent                          2
middle_volume_percent                       2
take_amount_in_later_12_month_highest       0
trans_amount_increase_rate_lately           3
trans_activity_month                        2
trans_activity_day                          2
transd_mcc                                  2
trans_days_interval_filter                  8
trans_days_interval                         2
regional_mobility                           2
student_feature                          2998
repayment_capability                        0
is_high_user                                0
number_of_trans_from_2011                   2
first_transaction_time                      2
historical_trans_amount                     0
historical_trans_day                        2
rank_trad_1_month                           2
trans_amount_3_month                        0
avg_consume_less_12_valid_month             2
abs                                         0
top_trans_count_last_1_month                2
avg_price_last_12_month                     0
avg_price_top_last_12_valid_month         104
reg_preference_for_trad                     2
trans_top_time_last_1_month                 8
trans_top_time_last_6_month                 8
consume_top_time_last_1_month               8
consume_top_time_last_6_month               8
...
loans_credibility_behavior                297
loans_count                               297
loans_settle_count                        297
loans_overdue_count                       297
loans_org_count_behavior                  297
consfin_org_count_behavior                297
loans_cash_count                          297
latest_one_month_loan                     297
latest_three_month_loan                   297
latest_six_month_loan                     297
history_suc_fee                           297
history_fail_fee                          297
latest_one_month_suc                      297
latest_one_month_fail                     297
loans_long_time                           297
loans_latest_time                         297
loans_credit_limit                        297
loans_credibility_limit                   297
loans_org_count_current                   297
loans_product_count                       297
loans_max_limit                           297
loans_avg_limit                           297
consfin_credit_limit                      297
consfin_credibility                       297
consfin_org_count_current                 297
consfin_product_count                     297
consfin_max_limit                         297
consfin_avg_limit                         297
latest_query_day                          304
loans_latest_day                          297
Length: 86, dtype: int64

填充缺失值

#用0填充
data_all.fillna(0)
#用均值填充
data_all.fillna(data_all.mean())

删除缺失值

data_all.dropna()

数据类型转换

# 将汉字转为数字
data_all['reg_preference_for_trad'] = data_all['reg_preference_for_trad'].map({'境外':0,'一线城市':1, '二线城市':2, '三线城市':3})

日期型特征处理

# 细分为年、月、日
data_all['latest_query_time'] = pd.to_datetime(data_all['latest_query_time'])
data_all['latest_query_time_year'] = data_all['latest_query_time'].dt.year
data_all['latest_query_time_month'] = data_all['latest_query_time'].dt.month
data_all['latest_query_time_day'] = data_all['latest_query_time'].dt.day

data_all['loans_latest_time'] = pd.to_datetime(data_all['loans_latest_time'])
data_all['loans_latest_time_year'] = data_all['loans_latest_time'].dt.year
data_all['loans_latest_time_month'] = data_all['loans_latest_time'].dt.month
data_all['loans_latest_time_day'] = data_all['loans_latest_time'].dt.day

data_all.drop(labels=['latest_query_time', 'loans_latest_time'], axis=1, inplace=True)

# 对日期缺失值进行众数填充
# 常用方法有三种：删除，补全和忽略
data_all['latest_query_time_year'].fillna(data_all['latest_query_time_year'].mode(), inplace=True)
data_all['latest_query_time_month'].fillna(data_all['latest_query_time_month'].mode(), inplace=True)
data_all['latest_query_time_day'].fillna(data_all['latest_query_time_day'].mode(), inplace=True)

data_all['loans_latest_time_year'].fillna(data_all['loans_latest_time_year'].mode(), inplace=True)
data_all['loans_latest_time_month'].fillna(data_all['loans_latest_time_month'].mode(), inplace=True)
data_all['loans_latest_time_day'].fillna(data_all['loans_latest_time_day'].mode(), inplace=True)

划分数据集

from sklearn.model_selection import train_test_split
x = data_all.drop(columns=["status"]).as_matrix()
y = data_all[["status"]].as_matrix()
y = y.ravel()
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.3, random_state=2018)