mirror of
https://github.com/TheAlgorithms/Python.git
synced 2024-10-06 21:59:30 +00:00
41 lines
1.3 KiB
Python
41 lines
1.3 KiB
Python
# Random Forest Regression
|
|
|
|
# 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 Random Forest Regression to the dataset
|
|
from sklearn.ensemble import RandomForestRegressor
|
|
regressor = RandomForestRegressor(n_estimators = 10, random_state = 0)
|
|
regressor.fit(X, y)
|
|
|
|
# Predicting a new result
|
|
y_pred = regressor.predict(6.5)
|
|
|
|
# Visualising the Random Forest 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 (Random Forest Regression)')
|
|
plt.xlabel('Position level')
|
|
plt.ylabel('Salary')
|
|
plt.show() |