In [1]:

    

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


    

In [2]:

    

%matplotlib inline


    

In [3]:

    

#importing the dataset
dataset=pd.read_csv('Position_Salaries.csv')
X=dataset.iloc[:,1:2].values
y=dataset.iloc[:,2].values


    

In [4]:

    

X


    

    
Out[4]:





array([[ 1],
       [ 2],
       [ 3],
       [ 4],
       [ 5],
       [ 6],
       [ 7],
       [ 8],
       [ 9],
       [10]], dtype=int64)

In [5]:

    

y


    

    
Out[5]:





array([  45000,   50000,   60000,   80000,  110000,  150000,  200000,
        300000,  500000, 1000000], dtype=int64)

In [15]:

    

#fitting the random forest regression to the dataset
from sklearn.ensemble import RandomForestRegressor
regressor=RandomForestRegressor(n_estimators=300,random_state=0)
regressor.fit(X,y)


    

    
Out[15]:





RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,
           max_features='auto', max_leaf_nodes=None,
           min_impurity_decrease=0.0, min_impurity_split=None,
           min_samples_leaf=1, min_samples_split=2,
           min_weight_fraction_leaf=0.0, n_estimators=300, n_jobs=None,
           oob_score=False, random_state=0, verbose=0, warm_start=False)

In [16]:

    

#predicting the results
from numpy import array
y_pred=regressor.predict(array([[6.5]]))


    

In [17]:

    

y_pred


    

    
Out[17]:





array([160333.33333333])

In [18]:

    

#visualising the Regression results
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 vs Bluff(Random Forest Regression)')
plt.xlabel('Position level')
plt.ylabel('Salary')
plt.show()


    

In [ ]: