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

# In[1]:


import os, math, subprocess
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import pandas_profiling

# some settings for displaying Pandas results
pd.set_option('display.width', 2000)
pd.set_option('display.max_rows', 500)
pd.set_option('display.max_columns', 500)
pd.set_option('display.precision', 4)
pd.set_option('display.max_colwidth', -1)


# In[2]:


# load data
pdf_data = pd.read_csv("data/application_train.csv")
print(pdf_data.shape)
pdf_data.head()


# In[3]:


get_ipython().run_cell_magic('time', '', 'profile = pandas_profiling.ProfileReport(pdf_data)\nprofile\n')


# In[4]:


get_ipython().run_cell_magic('time', '', 'profile.to_file(outputfile="{}_profiling.html".format("application_train"))\n')


# In[ ]: