Support Vector Regression (SVR)

Code: SVR

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('Position_Salaries.csv')
X = dataset.iloc[:, 1:2].values  # Only one column taken
y = dataset.iloc[:, 2].values

# Splitting the dataset into the Training set and Test set is skipped due the dataset size is just 10 rows
"""from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"""

# Feature Scaling (Unlike Polynomial, scaling is required here as SVR library do not have in-build scaling. Without this plot will look like as in Fig 1, flat line)
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
sc_y = StandardScaler()
X = sc_X.fit_transform(X)
y = sc_y.fit_transform(y)

# Fitting SVR to the dataset
# kernel : Specifies the kernel type to be used in the algorithm. 
# It must be one of ‘linear’, ‘poly’, ‘rbf’, ‘sigmoid’, ‘precomputed’ or a callable.
from sklearn.svm import SVR
regressor = SVR(kernel = 'rbf') # 'rbf' is non-linear
regressor.fit(X, y)

# Visualising the SVR results
plt.scatter(X, y, color = 'red')
plt.plot(X, regressor.predict(X), color = 'blue')
plt.title('Truth or Bluff (SVR)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()

# Visualising the SVR results (for higher resolution and smoother curve)
X_grid = np.arange(min(X), max(X), 0.01) # choice of 0.01 instead of 0.1 step because the data is feature scaled
X_grid = X_grid.reshape((len(X_grid), 1))

# Re-Visualising the SVR results
plt.scatter(X, y, color = 'red')
plt.plot(X_grid, regressor.predict(X_grid), color = 'blue')
plt.title('Truth or Bluff (SVR)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()

Fig 1.

Hope this helps!!

Regards,
Arun Manglick