Random Forest Regression Added

machine_learning/Random Forest Regression/Position_Salaries.csv

@@ -0,0 +1,11 @@
+Position,Level,Salary
+Business Analyst,1,45000
+Junior Consultant,2,50000
+Senior Consultant,3,60000
+Manager,4,80000
+Country Manager,5,110000
+Region Manager,6,150000
+Partner,7,200000
+Senior Partner,8,300000
+C-level,9,500000
+CEO,10,1000000

machine_learning/Random Forest Regression/random_forest_regression.py

@@ -0,0 +1,41 @@
+# 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()