Credit price tool
Project description
#Introduction This package is used to create a suitable plan of credit price for different borrowers.As historical borrowers' credit score and loan interests are given, you can train a credit price model through this package, and this model will allow you to calculate a different, recommended loan interest for any borrower only based on his or her credit score.
#Example:
import creditprice as cp
#生成数据
import numpy as np
import pandas as pd
np.random.seed(123)
score = 650 + 100 * np.random.randn(1000)
price = 0.2 + 0.1 * np.random.randn(1000)
flag = np.random.randint(2, size=1000)
flagy = np.random.binomial(1, 0.2, size=flag[flag == 1].shape[0])
data = pd.DataFrame(columns=['score', 'r', 'accept', 'flagy'])
data['score'] = score
data['r'] = price
data['accept'] = flag
data.loc[data.accept == 1, 'flagy'] = flagy
#生成模型
cl = cp.calc(ld=0.5, d = 1, rl = 0.05, rf = 0.04, score='score', interest='r', flag='accept', y = 'flagy')
#计算利率表
r_table = cl.calc_r_table(data = data)
#根据data计算单利率
r = cl.calc_r(p=0.2, data=data)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
creditprice-0.0.8.tar.gz
(4.3 kB
view details)
Built Distribution
File details
Details for the file creditprice-0.0.8.tar.gz
.
File metadata
- Download URL: creditprice-0.0.8.tar.gz
- Upload date:
- Size: 4.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.21.0 requests-toolbelt/0.9.1 tqdm/4.37.0 CPython/3.7.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 3ad81f65c798b4d5f912e8d0933bbec891a3bccb301180e47e1b3b5f8d5c1b8b |
|
MD5 | 90a74f1e80117c2196e7474694dab23c |
|
BLAKE2b-256 | 6ef81db753aa2c42a164a15737ff47aa5fae0a6969cf68b7cbad63ad664dfdfb |
File details
Details for the file creditprice-0.0.8-py3-none-any.whl
.
File metadata
- Download URL: creditprice-0.0.8-py3-none-any.whl
- Upload date:
- Size: 5.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.21.0 requests-toolbelt/0.9.1 tqdm/4.37.0 CPython/3.7.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | bf9181651c8f3b9ac985540e9127061201c637fc038fec7a590bb97e60037c12 |
|
MD5 | 3a570256400be588a8478decad8eef9e |
|
BLAKE2b-256 | 8427c03e3e3338d4a3a7c551072f77e55a6e72b62917a36599d67d4b0e41c8ec |