Predicting Salaries with Linear Regression

1. Exploring the data

# Import all usefull modules import pandas as pd import matplotlib.pyplot as plt from sklearn.model_selection import train_test_split from sklearn.linear_model import LinearRegression %matplotlib inline

# Exploring the dataset data = pd.read_csv('Salary.csv') data.head()

# Describe the dataset data.describe()

2. Extracting independent and dependent variables

# our independent variable is the years of experience # x = data.iloc[:, 0].values.reshape(1,-1).T x = data.iloc[:, :1].values # our dependent variable is the salary y = data.iloc[:, 1].values

# Now, let's separate some values for train and some others for test # Let's use 80% or training # Note: We can use random_state = 0 for always getting the same random values (static seed) x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2, random_state=0)

3. Constructing our ML model

# These next two lines are enough to create our model regressor = LinearRegression() regressor.fit(x_train, y_train)

4. Plotting results

# y Prediction from the train model y_predicted = regressor.predict(x_train)

# Plotting train data plt.scatter(x_train, y_train) plt.plot(x_train, y_predicted, color = 'black') # Description axis plt.title('Salary vs Experience') plt.xlabel('Experience') plt.ylabel('Salary') # Show plot plt.show()

# Plotting test data plt.scatter(x_test, y_test, color = 'green') plt.plot(x_train, y_predicted, color = 'black') # Description axis plt.title('Salary vs Experience') plt.xlabel('Experience') plt.ylabel('Salary') # Show plot plt.show()

# Verify the accuracy of our model regressor.score(x_test, y_test)

5. Testing with more data

Execute the following lines of code for generating larger synthetic data. Then, execute again from steps 2 to 4 to see the new results.

import numpy as np def get_dataset(m, b, size): ''' Read the pendient, the constant, and the number of elements that will be genearted for a linear function ''' x = np.linspace(1, size, size) # start, end, number of elements # x = np.arange(-size/2, size/2, 1) # start, end, increment y = m*x + b # adding noise to y noise = np.random.normal(size/10, size, y.shape) y = y + noise return x, y

# getting the linear function with <size> elements and plot it x, y = get_dataset(m=10, b=1000, size=1000) plt.scatter(x, y)