Revisiting Machine Learning Datasets - Banknote Authentication

import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import sklearn
from sklearn.naive_bayes import GaussianNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import GradientBoostingClassifier, RandomForestClassifier, AdaBoostClassifier
from sklearn.preprocessing import OneHotEncoder
import catboost 
import xgboost
import keras
from keras.backend.tensorflow_backend import set_session
import tensorflow as tf 
config = tf.ConfigProto()
#config.gpu_options.per_process_gpu_memory_fraction = 0.90
config.gpu_options.allow_growth = True
set_session(tf.Session(config=config))

from keras.utils import to_categorical
from keras.models import Sequential
from keras.layers import (Input, Dense, BatchNormalization,Dropout)
from keras import optimizers
from keras import callbacks


from keras import backend as K
K.tensorflow_backend._get_available_gpus()

from sklearn.model_selection import  train_test_split
from sklearn.model_selection import GridSearchCV, train_test_split, KFold
from sklearn.metrics import accuracy_score, classification_report,confusion_matrix



filepath_input_data = "./data/data_banknote_authentication.txt"
input_data_df = pd.read_csv(filepath_input_data,
                           names=['Variance of Wavelet Transformed Image',
                                  'Skewness of Wavelet Transformed Image',
                                  'Curtosis of Wavelet Transformed Image',
                                  'Entropy of Image', 
                                  'Class'])

display(input_data_df.head(3))
display(input_data_df.tail(3))
input_data_df.describe()

y = input_data_df['Class'].values.reshape(-1,1)
X_df = input_data_df.copy()
X_df.drop(['Class'], axis=1, inplace=True)
X = X_df.values

plt.close('all')
plt.figure(figsize=(8,(X_df.shape[-1] // 2) * 4))
idx = 1
for Feature in X_df:
    plt.subplot((X_df.shape[-1] // 2),2, idx)
    idx += 1
    plt.boxplot(X_df[Feature], meanline=False, notch=True, labels=[''])
    plt.title(Feature)
plt.tight_layout()
plt.show()

plt.figure(figsize=(11,9))
for Class in input_data_df['Class'].unique():
    plt.plot(X_df[input_data_df['Class'] == Class].values[0], label=Class)
plt.title("Examples of both classes (unscaled)")
plt.legend()
plt.show()