logistic_regression.py

# Importar librerías
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Importar el dataset de training
dataset = pd.read_csv('Social_Network_Ads.csv')
dataset['Age'] = dataset['Age'].fillna(dataset['Age'].mean())
dataset['EstimatedSalary'] = dataset['EstimatedSalary'].fillna(dataset['EstimatedSalary'].mean())
X = dataset.iloc[:len(dataset),[2,3]].values
y = dataset.iloc[:len(dataset), -1]

# Dividir dataset en conjunto de entrenamiento y conjunto de testing
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

# Escalado de variables
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)

# Aplicación del modelo con gradient descent
regression = LogisticRegressionGD(l_rate = 0.0000001, n_iter = 20000)
coef = regression.fit(X_train, y_train)
y_predict = regression.predict(X_test)

# Aplicación del modelo con librería de sklearn
from sklearn.linear_model import LogisticRegression
logistic = LogisticRegression(random_state = 0)
logistic.fit(X_train, y_train)
y_predict_py = logistic.predict(X_test)

# Matriz de confusión para ver resultados finales
from sklearn.metrics import confusion_matrix
cm_sklearn = confusion_matrix(y_test, y_predict_py)
cm_GD = confusion_matrix(y_test, y_predict)