├── Position_Salaries.csv
├── README.md
└── random_forest_regression.py


/Position_Salaries.csv:
--------------------------------------------------------------------------------
 1 | Position,Level,Salary
 2 | Business Analyst,1,45000
 3 | Junior Consultant,2,50000
 4 | Senior Consultant,3,60000
 5 | Manager,4,80000
 6 | Country Manager,5,110000
 7 | Region Manager,6,150000
 8 | Partner,7,200000
 9 | Senior Partner,8,300000
10 | C-level,9,500000
11 | CEO,10,1000000


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | # Random-Forest-Regression
2 | Random Forest Regression
3 | 


--------------------------------------------------------------------------------
/random_forest_regression.py:
--------------------------------------------------------------------------------
 1 | # Random Forest Regression
 2 | 
 3 | # Importing the libraries
 4 | import numpy as np
 5 | import matplotlib.pyplot as plt
 6 | import pandas as pd
 7 | 
 8 | # Importing the dataset
 9 | dataset = pd.read_csv('Position_Salaries.csv')
10 | X = dataset.iloc[:, 1:2].values
11 | y = dataset.iloc[:, 2].values
12 | 
13 | # Splitting the dataset into the Training set and Test set
14 | """from sklearn.cross_validation import train_test_split
15 | X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)"""
16 | 
17 | # Feature Scaling
18 | """from sklearn.preprocessing import StandardScaler
19 | sc_X = StandardScaler()
20 | X_train = sc_X.fit_transform(X_train)
21 | X_test = sc_X.transform(X_test)
22 | sc_y = StandardScaler()
23 | y_train = sc_y.fit_transform(y_train)"""
24 | 
25 | # Fitting Random Forest Regression to the dataset
26 | from sklearn.ensemble import RandomForestRegressor
27 | regressor = RandomForestRegressor(n_estimators = 10, random_state = 0)
28 | regressor.fit(X, y)
29 | 
30 | # Predicting a new result
31 | y_pred = regressor.predict(6.5)
32 | 
33 | # Visualising the Random Forest Regression results (higher resolution)
34 | X_grid = np.arange(min(X), max(X), 0.01)
35 | X_grid = X_grid.reshape((len(X_grid), 1))
36 | plt.scatter(X, y, color = 'red')
37 | plt.plot(X_grid, regressor.predict(X_grid), color = 'blue')
38 | plt.title('Truth or Bluff (Random Forest Regression)')
39 | plt.xlabel('Position level')
40 | plt.ylabel('Salary')
41 | plt.show()


--------------------------------------------------------------------------------