To predict loan defaulters

Lending club case study

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib import style
style.use("ggplot")
from sklearn import svm
import ggplot as ggp
from sklearn.model_selection import train_test_split
Data_main=pd.read_csv(filepath_or_buffer='D:\loan_data.csv')
np.sum(Data_main.isnull())
ggp.ggplot(Data_main,ggp.aes(x='fico'))+ggp.geom_density(color='red')+ggp.geom_histogram(fill='blue')+ggp.facet_grid('not.fully.paid','credit.policy')
Data_main.describe()
y=Data_main['not.fully.paid']
X=Data_main.drop('not.fully.paid',axis=1)
y.shape,X.shape
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=123)
X_train.shape,X_test.shape,y_test.shape,y_train.shape
from sklearn import preprocessing
X_scaledTest=preprocessing.scale(X_test[['int.rate','installment','log.annual.inc','dti','fico','days.with.cr.line','revol.bal','revol.util','inq.last.6mths','delinq.2yrs','pub.rec']])
X_scaledTrain=preprocessing.scale(X_train[['int.rate','installment','log.annual.inc','dti','fico','days.with.cr.line','revol.bal','revol.util','inq.last.6mths','delinq.2yrs','pub.rec']])
model=svm.SVC(kernel='linear',C=1,gamma=1)
model.fit(X_scaledTrain,y_train)
from sklearn.metrics import accuracy_score
accuracy_score(y_test,model.predict(X_scaledTest))
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report
parameters = [{'kernel': ['rbf'],
               'gamma': [1e-4, 1e-3, 0.01, 0.1, 0.2, 0.5],
                'C': [1, 10, 100, 1000]},
              {'kernel': ['linear'], 'C': [1, 10, 100, 1000]}]
model_T=svm.SVC(kernel='rbf',C=1,gamma=1)
model_T.fit(X_scaledTrain,y_train)
accuracy_score(y_test,model_T.predict(X_scaledTest))
tune=GridSearchCV(cv=None, error_score='raise',
       estimator=SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,
  decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',
  max_iter=-1, probability=False, random_state=None, shrinking=True,
  tol=0.001, verbose=False),
       fit_params={}, iid=True, n_jobs=-1,
       param_grid=parameters
       pre_dispatch='2*n_jobs', refit=True, scoring=None, verbose=0)
tune.fit(X_scaledTrain,y_train)

accuracy_score(y_test,tune.predict(X_scaledTest))