# %load /home/felipe/firstcell.py
%reload_ext autoreload
%autoreload 2
import numpy as np
import pandas as pd
pd.set_option('display.max_columns',1000)
import os
import matplotlib.pyplot as plt
from sklearn.pipeline import FeatureUnion
from sklearn.datasets import make_classification
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
%matplotlib inline
X, y = make_classification(n_samples=10000, n_features=4)