!pip install plotly==3.8.1
# Let us load in the relevant Python modules
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
import plotly.offline as py
py.init_notebook_mode(connected=True)
import plotly.graph_objs as go
import plotly.tools as tls
import warnings
from collections import Counter
from sklearn.feature_selection import mutual_info_classif
warnings.filterwarnings('ignore')
train = pd.read_csv("./train.csv")
train.head()
# Taking a look at how many rows and columns the train dataset contains
rows = train.shape[0]
columns = train.shape[1]
print("The train dataset contains {0} rows and {1} columns".format(rows, columns))
## 1. Data Quality checks
##### Null or missing values check
# any() applied twice to check run the isnull check across all columns.
train.isnull().any().any()