File size: 4,151 Bytes
a824eab |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import RandomizedSearchCV
df = pd.read_csv("credit_risk_dataset.csv")
df = df.dropna()
df.columns
X =df.drop("loan_status", axis = 1)
y = df['loan_status']
categorical_features = ["person_home_ownership", "loan_intent", "loan_grade", "cb_person_default_on_file"]
X = pd.get_dummies(X, categorical_features)
X.columns
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2)
X_train.head()
from sklearn.preprocessing import StandardScaler
scaler_normal = StandardScaler()
def scaler(data, runtime = False):
normal_col = ['person_income','person_age','person_emp_length', 'loan_amnt','loan_int_rate','cb_person_cred_hist_length','loan_percent_income']
if(runtime == False):
data.loc[:,normal_col] = scaler_normal.fit_transform(data.loc[:,normal_col])
else:
data.loc[:,normal_col] = scaler_normal.transform(data.loc[:,normal_col])
return data
X_train = scaler(X_train)
X_test = scaler(X_test, True)
model = RandomForestClassifier(max_depth = 5)
model.fit(X_train, y_train)
y_predict = model.predict(X_test)
features = {
"person_home_ownership": ['MORTGAGE', 'OTHER','OWN', 'RENT',],
"loan_intent": ['DEBTCONSOLIDATION', 'EDUCATION', 'HOMEIMPROVEMENT', 'MEDICAL', 'PERSONAL', 'VENTURE'],
"loan_grade": ['A','B', 'C', 'D', 'E','F', 'G'],
"cb_person_default_on_file": ['N', 'Y']
}
def preprocess(model_input):
for feature in features:
for option in features[feature]:
selection = model_input[feature]
if option is selection:
model_input[f'{feature}_{option}'] = 1
else:
model_input[f'{feature}_{option}'] = 0
model_input.drop([_ for _ in features], inplace = True, axis = 1)
return model_input
def credit_run(person_age, person_income, person_home_ownership,
person_emp_length, loan_intent, loan_grade, loan_amnt,
loan_int_rate, cb_person_default_on_file, cb_person_cred_hist_length):
model_input = preprocess(
pd.DataFrame( { 'person_age': person_age,
'person_income': person_income,
'person_home_ownership': person_home_ownership,
'person_emp_length': person_emp_length,
'loan_intent': loan_intent,
'loan_grade': loan_grade,
'loan_amnt': loan_amnt,
'loan_int_rate': loan_int_rate,
'loan_percent_income': loan_amnt / person_income,
'cb_person_default_on_file': cb_person_default_on_file,
'cb_person_cred_hist_length': cb_person_cred_hist_length
}, index = [0]
))
out = model.predict(model_input)
return "High risk of defaulting" if out[0] == 1 else "Low risk of defaulting"
import gradio as gr
demo = gr.Interface(
fn = credit_run,
inputs = [
gr.Slider(label="Person_Age(In Years)", minimum=18, maximum=90, step=1),
gr.Number(label="person_income(per month)"),
gr.Radio(['MORTGAGE', 'OTHER','OWN', 'RENT']),
gr.Slider(label="person_emp_length(In Years)", minimum=0, maximum=60, step=1),
gr.Radio(['DEBTCONSOLIDATION', 'EDUCATION', 'HOMEIMPROVEMENT', 'MEDICAL', 'PERSONAL', 'VENTURE']),
gr.Radio(['A','B', 'C', 'D', 'E','F', 'G']),
gr.Number(label="loan_amnt"),
gr.Number(label="loan_int_rate"),
gr.Radio(['0', '1']),
gr.Number(label="cb_person_cred_hist_length"),
],
outputs = "text",
title = "Credit Risk Predictor",
examples = [[23,15000,'RENT',2,'EDUCATION','A',300000,8.9,'0',6],
[34,50000,'OWN',1,'MEDICAL','B',1000000,10.65,'0',3],
[42,30000,"MORTGAGE",12,'HOMEIMPROVEMENT','C',800000,7.9,'1',8],
[42,20000,"MORTGAGE",10,'PERSONAL','F',100000,15.25,'1',5]]
)
demo.launch(share = True,debug=True)
|