lulutan98

from imblearn.over_sampling import SMOTE

smote = SMOTE()
X_os, y_os = smote.fit_sample(X, y)
plot_data(X_os,y_os, title="Balanced Dataset - 2 Component PCA")

# plot the balanced dataset

df1 = pd.DataFrame(X_os)
df1['target'] = y_os

lulutan98

def plot_data(X,y,title="Imbalanced Dataset - 2 Component PCA"):
    fig = plt.figure(figsize = (6,6))
    ax = fig.add_subplot(1,1,1) 
    ax.set_xlabel('PCA 1', fontsize = 12)
    ax.set_ylabel('PCA 2', fontsize = 12)
    ax.set_title(title, fontsize = 16)
    colors = ['g', 'm']
    classes = ['0','1']
    for i,c in zip(np.unique(y), colors):
        ax.scatter(

lulutan98

from sklearn.datasets import make_classification
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

X, y = make_classification(
    n_classes=2, weights=[0.9, 0.1], n_samples=100,
)
df = pd.DataFrame(X)
df['target'] = y