data_prep_hyperparameter_blog.py

# Dataprep
from sklearn.model_selection import train_test_split
from sklearn.datasets import load_wine
import numpy as np
import pandas as pd

import warnings
# silence warnings for parameter options we have already tried, useful when iterating
warnings.filterwarnings("ignore")

d = load_wine()
X, y = d.data, d.target

# X = X[:, np.newaxis, 2]
# X = np.array(X.iloc[:, 0]).reshape(-1, 1)

X_train, X_test, y_train, y_test = train_test_split(
    X, y, test_size=0.20, random_state=0
)

print(X_train[:1])
print(y_train[:1])

import matplotlib.pyplot as plt
def plot(x,y, title="Scores over n iterations"):
    plt.plot(x,y)
    plt.ylabel('Mean Test Score')
    plt.title(title)
    plt.grid(True)
    plt.show()