import numpy as np
import pandas as pd
import seaborn as sns
from scipy import stats
import matplotlib.pyplot as plt

import statsmodels.api as sm
from statsmodels.stats import diagnostic as diag
from statsmodels.stats.outliers_influence import variance_inflation_factor

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error

%matplotlib inline

bank_df = pd.read_csv('C:/Users/msafar/Desktop/Datasets/Bank/bank-full.csv')

bank_df2 = pd.read_csv('C:/Users/msafar/Desktop/Datasets/Bank/bank.csv')

def strip_quotes(x):
    if x[0] == '"':
        return x[1:-1]
    else:
        return x

output = pd.DataFrame(list(map(strip_quotes, bank_df.loc[0][0].split(';')))).T
output.columns = list(map(strip_quotes, bank_df.columns.values[0].split(';')))

for i in range(1,len(bank_df)):
    temp = pd.DataFrame(list(map(strip_quotes, bank_df.loc[i][0].split(';')))).T
    temp.columns = list(map(strip_quotes, bank_df.columns.values[0].split(';')))
    output = output.append(temp)
    
output