import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
import statsmodels.api as sm
from sklearn.feature_selection import RFE
from sklearn.feature_selection import RFECV
from sklearn.linear_model import LogisticRegression
plt.style.use('ggplot')

# Altering output display
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

# Understanding the data dictionary
columns_description = pd.read_excel('Leads Data Dictionary.xlsx')
pd.set_option('display.max_columns', None)
columns_description=columns_description.iloc[2:,1:3]
columns_description.columns=['Variables', 'Description']
columns_description.reset_index(inplace=True,drop=True)
columns_description

df=pd.read_csv('Leads.csv')