import pandas as pd import numpy as np import matplotlib.pyplot as plt import seaborn as sns;sns.set() import warnings warnings.filterwarnings(action = 'ignore')

train=pd.read_csv('train_loan.csv') test=pd.read_csv('test_loan.csv')

train.head(5)

train.dtypes

train.isnull().sum()

test.isnull().sum()

train.columns

test.columns

train.shape,test.shape

train['Loan_Status'].value_counts()

train['Loan_Status'].value_counts(normalize=True)

train['Loan_Status'].value_counts(normalize=True).plot(kind='bar')

cat_var=['Gender','Married','Self_Employed','Credit_History']

def plot_categorical(cat_var): size=len(cat_var) plt.figure(figsize=(20,10)) for j,i in enumerate(cat_var): plt.subplot(2,2,j+1) train[i].value_counts(normalize=True).plot.bar(title=i)

plot_categorical(cat_var)

ordinal_var=['Education','Dependents','Property_Area']

def plot_ordinal(ordinal_var): plt.figure(figsize=(20,10)) for j,i in enumerate(ordinal_var): plt.subplot(2,2,j+1) train[i].value_counts(normalize=True).plot.bar(title=i)

plot_ordinal(ordinal_var)

Following inferences can be made from the above bar plots: Most of the applicants don’t have any dependents. Around 80% of the applicants are Graduate. Most of the applicants are from Semiurban area.

plt.figure(figsize=(20,10)) plt.subplot(1,2,1) sns.distplot(train['ApplicantIncome']) plt.subplot(1,2,2) plt.boxplot(train['ApplicantIncome']) plt.show()

train.boxplot(column='ApplicantIncome' ,by='Education') plt.suptitle("")

plt.figure(1) plt.subplot(121) sns.distplot(train['CoapplicantIncome']) plt.subplot(122) train['CoapplicantIncome'].plot.box(figsize=(16,5))

plt.figure(1) df=train.dropna() plt.subplot(121) sns.distplot(df['LoanAmount']) plt.subplot(122) df['LoanAmount'].plot.box(figsize=(10,7))

Gender= pd.crosstab(train['Gender'],train['Loan_Status']) Gender.div(Gender.sum(1).astype(float),axis=0).plot(kind='bar',stacked=True,figsize=(4,4))

Married=pd.crosstab(train['Married'],train['Loan_Status']) Dependents=pd.crosstab(train['Dependents'],train['Loan_Status']) Education=pd.crosstab(train['Education'],train['Loan_Status']) Self_Employed=pd.crosstab(train['Self_Employed'],train['Loan_Status']) Married.div(Married.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True, figsize=(4,4)) plt.show() Dependents.div(Dependents.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True) plt.show() Education.div(Education.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True, figsize=(4,4)) plt.show() Self_Employed.div(Self_Employed.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True, figsize=(4,4)) plt.show()

Credit_History=pd.crosstab(train['Credit_History'],train['Loan_Status']) Property_Area=pd.crosstab(train['Property_Area'],train['Loan_Status']) Credit_History.div(Credit_History.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True, figsize=(4,4)) plt.show() Property_Area.div(Property_Area.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True) plt.show()

train.groupby('Loan_Status')['ApplicantIncome'].mean().plot(kind='bar',title='loan status and applicant income')

bins=[0,1000,3000,42000] group=['low','average','high'] train['CoapplicantIncome_bin']=pd.cut(train['CoapplicantIncome'],bins,labels=group) CoapplicantIncome_bin = pd.crosstab(train['CoapplicantIncome_bin'],train['Loan_Status']) CoapplicantIncome_bin.div(CoapplicantIncome_bin.sum(1).astype(float),axis=0).plot(kind='bar',stacked=True,figsize=(4,4))

#new variable in which we will combine the applicant’s and coapplicant’s income t train['Total_Income']=train['ApplicantIncome']+train['CoapplicantIncome'] bins=[0,2500,4000,6000,81000] group=['Low','Average','High', 'Very high'] train['Total_Income_bin']=pd.cut(train['Total_Income'],bins,labels=group) Total_Income_bin=pd.crosstab(train['Total_Income_bin'],train['Loan_Status']) Total_Income_bin.div(Total_Income_bin.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True) plt.xlabel('Total_Income') P = plt.ylabel('Percentage')

bins=[0,100,200,700] group=['Low','Average','High'] train['LoanAmount_bin']=pd.cut(train['LoanAmount'],bins,labels=group) LoanAmount_bin=pd.crosstab(train['LoanAmount_bin'],train['Loan_Status']) LoanAmount_bin.div(LoanAmount_bin.sum(1).astype(float), axis=0).plot(kind="bar", stacked=True) plt.xlabel('LoanAmount') P = plt.ylabel('Percentage')

train.head(5)

train=train.drop(['Total_Income_bin','LoanAmount_bin','CoapplicantIncome_bin'],axis=1)

train.head(5)

train['Dependents'].replace('3+',3,inplace=True) train['Loan_Status'].replace('Y',1,inplace=True) train['Loan_Status'].replace('N',0,inplace=True)

train['Loan_Status']=train['Loan_Status'].astype('int64')

matrix=train.corr() f,ax=plt.subplots(figsize=(9,6)) sns.heatmap(matrix,vmax=.8,square=True,cmap='BuPu')

train.isnull().sum()

train['Gender'].fillna(train['Gender'].mode()[0],inplace=True) train['Married'].fillna(train['Married'].mode()[0],inplace=True) train['Dependents'].fillna(train['Dependents'].mode()[0],inplace=True) train['Self_Employed'].fillna(train['Self_Employed'].mode()[0],inplace=True) train['Credit_History'].fillna(train['Credit_History'].mode()[0],inplace=True) train['Loan_Amount_Term'].fillna(train['Loan_Amount_Term'].mode()[0],inplace=True)

train['LoanAmount'].fillna(train['LoanAmount'].median(),inplace=True)

train.info()

test['Gender'].fillna(train['Gender'].mode()[0], inplace=True) test['Dependents'].fillna(train['Dependents'].mode()[0], inplace=True) test['Self_Employed'].fillna(train['Self_Employed'].mode()[0], inplace=True) test['Credit_History'].fillna(train['Credit_History'].mode()[0], inplace=True) test['Loan_Amount_Term'].fillna(train['Loan_Amount_Term'].mode()[0], inplace=True) test['LoanAmount'].fillna(train['LoanAmount'].median(), inplace=True)

train['LoanAmountLog']=np.log(train['LoanAmount']) test['LoanAmountLog']=np.log(test['LoanAmount']) train['LoanAmountLog'].hist(bins=20)

train.head(5) test['Total_Income'] =test['ApplicantIncome']+test['CoapplicantIncome']

test.head(5)

sns.distplot(train['Total_Income'])

train['Total_Income_log']=np.log(train['Total_Income']) sns.distplot(train['Total_Income_log']) test['Total_Income_log']= np.log(train['Total_Income'])

train['EMI']=train['LoanAmount']/train['Loan_Amount_Term'] test['EMI']=test['LoanAmount']/test['Loan_Amount_Term']

sns.distplot(train['EMI'])

train['Balance_Income']=train['Total_Income']-(train['EMI']*1000) test['Balance_Income']=test['Total_Income']-(test['EMI']*1000)

sns.distplot(train['Balance_Income'])

train=train.drop(['ApplicantIncome','CoapplicantIncome','LoanAmount','Loan_Amount_Term'],axis=1) test=test.drop(['ApplicantIncome','CoapplicantIncome','LoanAmount','Loan_Amount_Term'],axis=1)

train.head(5)

test.head(5)

train=train.drop('Loan_ID',axis=1) test_loan_id=test['Loan_ID'] test=test.drop('Loan_ID',axis=1)

train.head(5)

test.head(5)

y=train.Loan_Status X=train.drop(['Loan_Status'],axis=1)

X.head(2)

y.head(2)

X=pd.get_dummies(X) train=pd.get_dummies(train) test=pd.get_dummies(test) train.shape,test.shape

X.head(5)

from sklearn import tree from sklearn.model_selection import StratifiedKFold from sklearn.metrics import accuracy_score

from sklearn.metrics import confusion_matrix as cm

train['Loan_Status'].value_counts()

from sklearn.ensemble import RandomForestClassifier as rfc

i=1 kf=StratifiedKFold(n_splits=10,random_state=6,shuffle=True) accuracy_list=[] for train_index , test_index in kf.split(X,y): print('\n{} of kfold {}'.format(i,kf.n_splits)) xtr,xvl=X.loc[train_index],X.loc[test_index] ytr,yvl=y.loc[train_index],y.loc[test_index] model=rfc(n_estimators=100,criterion='gini', max_depth=4) model.fit(X,y) pred_train=model.predict(X) score=accuracy_score(y,pred_train) accuracy_list.append(score) print('accuracy_score',score)

mean_accuracy_rfc=sum(accuracy_list)/len(accuracy_list)

mean_accuracy_rfc

original_test_predictions=model.predict(test)

submissions=pd.read_csv('sample_submission.csv')

submissions['Loan_Status']=original_test_predictions

submissions['Loan_Status'].value_counts()

submissions['Loan_Status'].replace(0, 'N',inplace=True) submissions['Loan_Status'].replace(1, 'Y',inplace=True)

pd.DataFrame(submissions, columns=['Loan_ID','Loan_Status']).to_csv('randomforest.csv',index=False)

import xgboost as xgb from sklearn.model_selection import StratifiedKFold, GridSearchCV xgb_model = xgb.XGBClassifier(objective = "binary:logistic") params = { 'eta': np.arange(0.1, 0.26, 0.05), 'gamma': [5], } skf = StratifiedKFold(n_splits=20, shuffle = True) grid = GridSearchCV(xgb_model, param_grid = params, n_jobs = -1, cv = skf.split(X, y), refit = "accuracy_score") grid.fit(X,y)

xgboost_test_predictions=grid.predict(test)

xgboost_test_predictions

submissions['Loan_Status']=xgboost_test_predictions

submissions['Loan_Status'].value_counts()

submissions['Loan_Status'].replace(0, 'N',inplace=True) submissions['Loan_Status'].replace(1, 'Y',inplace=True)

pd.DataFrame(submissions, columns=['Loan_ID','Loan_Status']).to_csv('xgboostmodel.csv',index=False)

from sklearn.model_selection import train_test_split x_train,x_test,y_train,y_test=train_test_split(X,y,test_size=0.3,random_state=102)

from sklearn.ensemble import GradientBoostingClassifier gbk=GradientBoostingClassifier() gbk.fit(x_train,y_train) pred_gbc=gbk.predict(x_test) acc_gbc=accuracy_score(y_test,pred_gbc)*100 acc_gbc

xgb_test2=gbk.predict(test)

submissions['Loan_Status']=xgboost_test_predictions

submissions['Loan_Status'].value_counts()

submissions['Loan_Status'].replace(0, 'N',inplace=True) submissions['Loan_Status'].replace(1, 'Y',inplace=True)

pd.DataFrame(submissions, columns=['Loan_ID','Loan_Status']).to_csv('xgboostmodel2.csv',index=False)