Visualize a decision tree regression using Python

1.0K    Asked by IraJoshi in Data Science , Asked on Nov 9, 2019
Answered by Ira Joshi

Let us import the model

# 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

y = dataset.iloc[:, 2].values

# Splitting the dataset into the Training set 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 = 0.2, random_state = 0)"""

# Feature Scaling

"""from sklearn.preprocessing import StandardScaler

sc_X = StandardScaler()

X_train = sc_X.fit_transform(X_train)

X_test = sc_X.transform(X_test)

sc_y = StandardScaler()

y_train = sc_y.fit_transform(y_train)"""

# Fitting Decision Tree Regression to the dataset

from sklearn.tree import DecisionTreeRegressor

regressor = DecisionTreeRegressor(random_state = 0)

regressor.fit(X, y)

# Predicting a new result

y_pred = regressor.predict(6.5)

Now let us visualize the data

# Visualising the Decision Tree Regression results (higher resolution)

X_grid = np.arange(min(X), max(X), 0.01)

X_grid = X_grid.reshape((len(X_grid), 1))

plt.scatter(X, y, color = 'red')

plt.plot(X_grid, regressor.predict(X_grid), color = 'blue')

plt.title('Truth or Bluff (Decision Tree Regression)')

plt.xlabel('Position level')

plt.ylabel('Salary')

plt.show()

We get the following diagram of the data




Your Answer

Interviews

Parent Categories