Logistic Regression Manually

manual_logistic_regression.py

import numpy as np
from sklearn.model_selection import train_test_split
import pandas as pd

df = pd.read_csv(
    'https://raw.githubusercontent.com/johnmyleswhite/ML_for_Hackers/master/02-Exploration/data/01_heights_weights_genders.csv')
df.head()

BinaryGenders = np.zeros(len(df))

for i in range(len(df)):
    if df.iloc[i, 0] == "Male":
        BinaryGenders[i] = 1
    else:
        BinaryGenders[i] = 0

df['BinaryGenders'] = BinaryGenders

df = df.sample(frac=1).reset_index(drop=True)

Y = df['BinaryGenders'].values
X = df[['Height', 'Weight']].values

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.33)

n_samples, n_features = X.shape

def sigmoid(x):
    return 1 / (1 + np.exp(-x))
w = np.zeros(n_features)
b = 0

def cost_function(X, Y, w, b):
    m = len(Y)
    dz = np.dot(X, w) + b
    A = sigmoid(dz)
    cost = (-1 / m) * np.sum(Y * np.log(A) + (1 - Y) * np.log(1 - A))
    return cost

for _ in range(1000):
    y_pred = sigmoid(np.dot(X_train, w) + b)
    w -= 0.1 * np.dot(X_train.T, y_pred - Y_train) / n_samples
    b -= 0.1 * (y_pred - Y_train).sum() / n_samples

# Predictions
y_pred = sigmoid(np.dot(X_test, w) + b)
y_pred_class = np.where(y_pred > 0.5, 1, 0)

# Accuracy
print("Accuracy: ", (y_pred_class == Y_test).sum() / len(Y_test))