Random Forest is a bagging algorithm based on Ensemble Learning technique. The Random Forest algorithm can be used for both classification and regression problems.

In last article, we had solved a classification problem using Random Forest. In this article, we will solve a regression problem (predicting the petrol consumption in US) using Random Forest. We need to import

To measure the performance of a regression problem, we need to import

You can download

import pandas as pd

import numpy as np

from sklearn.preprocessing import StandardScaler

from sklearn.model_selection import train_test_split

from sklearn.metrics import mean_absolute_error, mean_squared_error

names = ['Index', 'One', 'Petrol tax (cents per gallon)', 'Average income (dollars)',

'Paved Highways (miles)', 'Proportion of population with driver licenses',

'Consumption of petrol (millions of gallons)']

dataset = pd.read_csv('petrol_consumption.csv', names=names)

dataset.shape

dataset.head()

dataset.describe()

X = dataset.iloc[:, 2:6].values

y = dataset.iloc[:, 6].values

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state=0)

X_train = standardScaler.fit_transform(X_train)

X_test = standardScaler.transform(X_test)

model.fit(X_train, y_train)

y_pred = model.predict(X_test)

df=pd.DataFrame({'Actual':y_test, 'Predicted':y_pred})

df

meanAbsoluteError =

meanSquaredError =

rootMeanSquaredError = np.sqrt(meanSquaredError)

print('Mean Absolute Error:', meanAbsoluteError)

print('Mean Squared Error:', meanSquaredError)

print('Root Mean Squared Error:', rootMeanSquaredError)

In last article, we had solved a classification problem using Random Forest. In this article, we will solve a regression problem (predicting the petrol consumption in US) using Random Forest. We need to import

**RandomForestRegressor**instead of**RandomForestClassifier**from sklearn library to implement Random Forest.To measure the performance of a regression problem, we need to import

**mean_absolute_error**and**mean_squared_error**metrics instead of**confusion_matrix, accuracy_score and classification_report**which we used in classification problem.You can download

**petrol_consumption.csv**from here. You can also download my Jupyter notebook containing below code of Random Forest implementation.

**Step 1: Import the required Python libraries like pandas, numpy and sklearn**import pandas as pd

import numpy as np

from sklearn.preprocessing import StandardScaler

from sklearn.model_selection import train_test_split

**from sklearn.ensemble import RandomForestRegressor**from sklearn.metrics import mean_absolute_error, mean_squared_error

**Step 2: Load and examine the dataset**names = ['Index', 'One', 'Petrol tax (cents per gallon)', 'Average income (dollars)',

'Paved Highways (miles)', 'Proportion of population with driver licenses',

'Consumption of petrol (millions of gallons)']

dataset = pd.read_csv('petrol_consumption.csv', names=names)

dataset.shape

dataset.head()

dataset.describe()

*Please note that "describe()" is used to display the statistical values of the data like mean and standard deviation.***Step 3: Mention X and Y axis**X = dataset.iloc[:, 2:6].values

y = dataset.iloc[:, 6].values

*Please note that first two columns "Index" and "One" are of no use for making any prediction. So excluded these two features. Also excluded the label which is the last column.*

*X contains the list of attributes**Y contains the list of labels***Step 4: Split the dataset into training and testing dataset**X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.20, random_state=0)

**Step 5: Scale the features****standardScaler = StandardScaler()**

X_train = standardScaler.fit_transform(X_train)

X_test = standardScaler.transform(X_test)

*This step is not must for Random Forest as it is being taken care by Random Forest internally.**Feature scaling is not required in tree based algorithms.***Step 6: Create and fit the model****model = RandomForestRegressor(n_estimators=120, random_state=0)**model.fit(X_train, y_train)

*"n_estimators" is the number of trees we want to create in a Random Forest. By default, it is 100.***Step 7: Predict from the model**y_pred = model.predict(X_test)

*The y_pred is a numpy array that contains all the predicted values for the input values in the X_test.**Lets see the difference between the actual and predicted values.*df=pd.DataFrame({'Actual':y_test, 'Predicted':y_pred})

df

**Step 8: Check the accuracy**meanAbsoluteError =

**mean_absolute_error**(y_test, y_pred)meanSquaredError =

**mean_squared_error**(y_test, y_pred)rootMeanSquaredError = np.sqrt(meanSquaredError)

print('Mean Absolute Error:', meanAbsoluteError)

print('Mean Squared Error:', meanSquaredError)

print('Root Mean Squared Error:', rootMeanSquaredError)

## No comments:

## Post a Comment