import numpy as np
import pandas as pd

from matplotlib import pyplot as plt
import matplotlib
%matplotlib inline
import seaborn as sns
import pandas_profiling
matplotlib.rc('xtick', labelsize=20) 
matplotlib.rc('ytick', labelsize=20)
from sklearn.model_selection import train_test_split
from sklearn.linear_model import SGDClassifier
from sklearn.metrics import f1_score, log_loss
from sklearn.neural_network import MLPClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.gaussian_process.kernels import RBF
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from xgboost.sklearn import XGBClassifier
from sklearn.ensemble import ExtraTreesClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.ensemble import BaggingClassifier
from sklearn.model_selection import KFold
from sklearn import metrics
from sklearn.feature_selection import SelectKBest 
from sklearn.feature_selection import chi2
import collections
import warnings
warnings.filterwarnings('ignore')
%matplotlib inline
from collections import Counter

from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_mode_interactivity = "all"

x1=pd.ExcelFile(r'Data_Train.xlsx')
x2=pd.ExcelFile(r'Data_Test.xlsx')

x1.sheet_names