import os
import sys
import operator
import numpy as np
import pandas as pd
import scipy
from scipy import sparse
from sklearn import model_selection, preprocessing, ensemble
from sklearn.metrics import log_loss
from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from nltk.stem import PorterStemmer
import re

train_file ="train.json"
train_df = pd.read_json(train_file)
train_df.head()

import matplotlib.pyplot as plt
import seaborn as sns
color = sns.color_palette()

%matplotlib inline

import xgboost as xgb

print("Train Rows : ", train_df.shape[0])