Data Analysis From Scratch With Python: Step By Step Guide

random_state = 0)
# Fitting Simple Linear Regression to the Training set
from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, y_train)
# Predicting the Test set results
y_pred = regressor.predict(X_test)

---

# Visualising the Training set results
plt.scatter(X_train, y_train, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Training set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
# Visualising the Test set results
plt.scatter(X_test, y_test, color = 'red')
plt.plot(X_train, regressor.predict(X_train), color = 'blue')
plt.title('Salary vs Experience (Test set)')
plt.xlabel('Years of Experience')
plt.ylabel('Salary')
plt.show()
The overall goal here is to create a model that will predict Salary
based on Years of Experience. First, we create a model using the Training Set
(70% of the dataset). It will then fit a line that is close as possible with most of
the data points.
After the line is created, we then apply that same line to the Test Set (the
remaining 30% or 1/3 of the dataset).

---

Notice that the line performed well both on the Training Set and the Test Set. As
a result, there’s a good chance that the line or our model will also perform well
on new data.
Let’s have a recap of what happened. First, we imported the necessary libraries
(pandas for processing data, matplotlib for data visualization). Next, we
imported the dataset and assigned X (the independent variable) to Years of
Experience and y (the target) to Salary. We then split the dataset into Training
Set (⅔) and Test Set (⅓).
Then, we apply the Linear Regression model and fitted a line (with the help of
scikit-learn, which is a free software machine learning library for the Python
programming language). This is accomplished through the following lines of
code: