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

# In[1]:


import pandas as pd
import numpy as np
from pandas.io.parsers import read_csv
get_ipython().run_line_magic('matplotlib', 'inline')

from matplotlib import pyplot as plt
import matplotlib as mpl

import scipy

import xgboost as xgb


# In[2]:


dtrain = xgb.DMatrix("train.buffer")
dvalidation = xgb.DMatrix("validation.buffer")


# In[3]:


param = {'bst:max_depth':7, 'bst:eta':1, 'silent':1, 'objective':'binary:logistic' }
param['nthread'] = 4
plst = param.items()
plst += [('eval_metric', 'logloss')]
plst += [('eval_metric', 'auc')]


# In[4]:


evallist  = [(dvalidation,'eval'), (dtrain,'train')]


# In[5]:


num_round = 40
bst = xgb.train( plst, dtrain, num_round, evallist )


# In[6]:


bst.save_model("0001.model")


# In[7]:


tr_leafindex = bst.predict(dtrain, pred_leaf=True)


# In[8]:


va_leafindex = bst.predict(dvalidation, pred_leaf=True)


# In[9]:


tr_y = dtrain.get_label()
va_y = dvalidation.get_label()


# In[10]:


np.save("tr.xgb", tr_leafindex)


# In[11]:


np.save("va.xgb", va_leafindex)


# In[12]:


np.save("tr.label", tr_y)
np.save("va.label", va_y)


# In[ ]: