import numpy as np
import pandas as pd
import seaborn as sns
import time
import re
import os
import matplotlib.pyplot as plt
sns.set(style="ticks")

# import libraries required for preprocessing
import sklearn as sk
from scipy import stats
from sklearn import preprocessing

# set the working directory to the following
os.chdir("/Users/svk/Desktop/packt_exercises")

# read the downloaded input data (marketing data)
df = pd.read_csv('bank.csv', sep=';')

numeric_df = df._get_numeric_data()
numeric_df.head()

numeric_df_array = np.array(numeric_df) # converting to numpy arrays for more efficient computation

loop_c = -1
col_for_normalization = list()

for column in numeric_df_array.T:
    loop_c+=1
    x = column
    k2, p = stats.normaltest(x) 
    alpha = 0.001
    print("p = {:g}".format(p))
        
    # rules for printing the normality output
    if p < alpha:
        test_result = "non_normal_distr"
        col_for_normalization.append((loop_c)) # applicable if yeo-johnson is used
        
        #if min(x) > 0: # applicable if box-cox is used
            #col_for_normalization.append((loop_c)) # applicable if box-cox is used
        print("The null hypothesis can be rejected: non-normal distribution")
        
    else:
        test_result = "normal_distr"
        print("The null hypothesis cannot be rejected: normal distribution")

columns_to_normalize = numeric_df[numeric_df.columns[col_for_normalization]]
names_col = list(columns_to_normalize)

# density plots of the features to check the normality
columns_to_normalize.plot.kde(bw_method=3)

pt = preprocessing.PowerTransformer(method='yeo-johnson', standardize=True, copy=True)
normalized_columns = pt.fit_transform(columns_to_normalize)
normalized_columns = pd.DataFrame(normalized_columns, columns=names_col)

normalized_columns.plot.kde(bw_method=3)