

In [3]:

    
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

Data Preparation

Importing a dataset



In [4]:

    
dataset = pd.read_csv('Social_Network_Ads.csv')



In [5]:

    
X = dataset.iloc[:, [2, 3]].values
y = dataset.iloc[:, 4].values

Splitting the dataset into a Training set a Test set



In [6]:

    
from sklearn.model_selection import train_test_split



In [7]:

    
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)

Feature Scaling



In [8]:

    
from sklearn.preprocessing import StandardScaler



In [9]:

    
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)









    



/usr/local/opt/pyenv/versions/3.6.0/Python.framework/Versions/3.6/lib/python3.6/site-packages/sklearn/utils/validation.py:429: DataConversionWarning: Data with input dtype int64 was converted to float64 by StandardScaler.
  warnings.warn(msg, _DataConversionWarning)

Modeling

Fitting Logistic Regression to the Training set



In [10]:

    
from sklearn.linear_model import LogisticRegression



In [11]:

    
classifier = LogisticRegression(random_state=0)
classifier.fit(X_train, y_train)









    Out[11]:





LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,
          intercept_scaling=1, max_iter=100, multi_class='ovr', n_jobs=1,
          penalty='l2', random_state=0, solver='liblinear', tol=0.0001,
          verbose=0, warm_start=False)

Predicting the Test set results



In [12]:

    
y_pred = classifier.predict(X_test)

Making the Confusion Matrix



In [13]:

    
from sklearn.metrics import confusion_matrix



In [14]:

    
confusion_matrix(y_test, y_pred)









    Out[14]:





array([[65,  3],
       [ 8, 24]])

Visualising results



In [15]:

    
from matplotlib.colors import ListedColormap



In [16]:

    
def draw(X_set, y_set, title):
    X1, X2 = np.meshgrid(np.arange(start=X_set[:, 0].min() - 1, stop=X_set[:, 0].max() + 1, step=0.01),
                         np.arange(start=X_set[:, 1].min() - 1, stop=X_set[:, 1].max() + 1, step=0.01))
    plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
                 alpha=0.5, cmap=ListedColormap(('red', 'green')))
    plt.xlim(X1.min(), X1.max())
    plt.ylim(X2.min(), X2.max())
    for i, j in enumerate(np.unique(y_set)):
        plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                    c=ListedColormap(('red', 'green'))(i), label=j)
    plt.title(title)
    plt.xlabel('Age')
    plt.ylabel('Estimated Salary')
    plt.legend()
    plt.show()



In [17]:

    
draw(X_train, y_train, 'Logistic Regression (Training set)')



In [18]:

    
draw(X_test, y_test, 'Logistic Regression (Test set)')