Targeting Social Media using Machine Learning

Warren HansenMachine LearningLeave a Comment

I’m working on a test project for a luxury SUV client to help analyze a large data set. Here is a small sample of what I started with.

I’m using some common libraries in Python to process the data set.
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv(social_media_date.csv)

After that I slice, split and scale the data.
# import the dataset, get index 2 + 3
X = dataset.iloc[:, [2,3]].values
y = dataset.iloc[:, 4].values
# split training and test set
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state= 0)
# feature scaling
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
# only need to transform not fit
X_test = sc_X.transform(X_test)

Next, I fit the data to a logistic regression model.
# fitting Logistic regression to the training set
from sklearn.linear_model import LogisticRegression
classifier = LogisticRegression()
classifier.fit(X_train,y_train)
# predicting the test result set
y_pred = classifier.predict(X_test,)
# making the confusion matrix - -correct and incorrect predictions
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)

When I observe my confusion matrix by print cm, here is what I see…
[[65 3] = 65 correct predictions, 3 incorrect predictions
[ 8 24]] = 8 incorrect predictions 42 correct predictions
logistic regression is doing a nice job here!

Final step is to visualise the data.
# visualise the training set results
from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
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 = 0.75, cmap = ListedColormap(('gray', 'white')))
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, s=10)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

Here is a scatter plot of the training set and test set that has been scaled. We can see that making a Confusion Matrix on Logistic Regression was able to accurately predict a purchase given age and salary of a potential customer. In just 72 lines of code, Python has helped bring great insight into a large data set.

I learned this from a comprehensive course on machine learning at Udemy.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.