#!/usr/bin/env python
# coding: utf-8

# In[10]:


# Import libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.ensemble import RandomForestClassifier
import lightgbm as lgb
import scipy.stats

datapath='Data/'


# In[11]:


# Import data
train_df=pd.read_csv(datapath+'train_u6lujuX_CVtuZ9i.csv')
test_df=pd.read_csv(datapath+'test_Y3wMUE5_7gLdaTN.csv')


# In[12]:


train_df.head()


# In[13]:


# % of target composition
train_df.Loan_Status.value_counts()/len(train_df)


# In[14]:


# Null values in columns
train_df.isnull().sum() * 100/len(train_df)


# In[15]:


train_df['Credit_History'].nunique()


# In[16]:


# Add a feature EMI. Formula here https://javatutoring.com/wp-content/uploads/2016/12/emi-calculation-formula.jpg
# On account of time paucity, rate of interest was avaergaed for gender. Definitely a better way worth investigating later.

dataset = [train_df,test_df]
for i in dataset:
    l = []
    for j in i.Gender.index:
        if i.Gender[j] == "Male":
            r = 8.65/(12*100)
        else:
            r = 8.6/(12*100)
        P = i.LoanAmount[j]*1000
        n = i.Loan_Amount_Term[j]
        E = P*r*(1 + r)**n/((1 + r)**n - 1)
        l.append(E)
    i["EMI"] = l


# In[17]:


# Add a ratio feature EMI. This we be capacitating loan amount with compined income per record

for i in dataset:
    i["income"] = i["ApplicantIncome"] + i["CoapplicantIncome"]
#     i["app_income/loan"] = [x[0]/x[1] for x in zip(i["ApplicantIncome"],i["LoanAmount"])]
    i["income_loan_ratio"] = [x[0]/x[1] for x in zip(i["income"],i["LoanAmount"])]
    i.drop(["CoapplicantIncome"],axis = 1,inplace = True)


# In[18]:


train_df.shape,test_df.shape


# In[19]:


train_df.info()


# In[20]:


# Nothing fancy. Simply treat missing values based on data type

for i in train_df.columns[train_df.dtypes == "object"]:
    train_df[i].fillna(train_df[i].mode()[0],inplace = True)
for i in train_df.columns[train_df.dtypes != "object"]:
    train_df[i].fillna(train_df[i].mean(),inplace = True)
for i in test_df.columns[test_df.dtypes == "object"]:
    test_df[i].fillna(train_df[i].mode()[0],inplace = True)
for i in train_df.columns[train_df.dtypes != "object"]:
    test_df[i].fillna(test_df[i].mean(),inplace = True)


# In[21]:


# Label encode categoricals

for i in list(set(train_df.columns[train_df.dtypes == "object"]) -set(["Loan_ID",'Loan_Status'])):
    le = LabelEncoder()
    train_df[i] = le.fit_transform(train_df[i].astype("str"))
    test_df[i] = le.transform(test_df[i].astype("str"))


# In[22]:


# Create and apply model

tra_col = sorted(list(set (train_df.columns)- set(["Loan_ID","Loan_Status"])))
test_df_col = sorted(list(set (test_df.columns)- set(["Loan_ID"])))
print(tra_col,test_df_col)


import xgboost as xgb
from xgboost import XGBClassifier
model = XGBClassifier()

model.fit(train_df[tra_col],train_df["Loan_Status"])
# from scipy import sparse
#model.predict(test_df[test_df_col])


# In[23]:


#Predict and create submission

result = pd.DataFrame({"Loan_ID":(test_df.Loan_ID),"Loan_Status":model.predict(test_df[test_df_col])}).reset_index(drop = True)

result[["Loan_ID","Loan_Status"]].to_csv("loan_prediction_analyticsvidhya.csv",index = False)


# In[ ]: