Question

Python , I need to Implement a Random Forest Classification Model in Python from any open dataset available online

Answer 1

#Text code

# importing the libraries

import pandas as pd

from sklearn.metrics import accuracy_score

# reading csv file "heart.csv"

# file source: https://www.kaggle.com/ronitf/heart-disease-uci#heart.csv

dataset = pd.read_csv("heart.csv")

# extracting features

# “iloc” in pandas is used to select rows and columns by number

X = dataset.iloc[:, :-1]

y = dataset.iloc[:, -1]

# Splitting the dataset into the Training set and Test set

from sklearn.model_selection 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

# Scale X object

sc_X = StandardScaler()

X_train = sc_X.fit_transform(X_train)

X_test = sc_X.fit_transform(X_test)

# Fitting Random Forest Classification to the Training set

from sklearn.ensemble import RandomForestClassifier

random_forest_classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)

random_forest_classifier.fit(X_train, y_train)

# Predicting the Test set results

y_pred_random_forest = random_forest_classifier.predict(X_test)

# finding percentage accuracy

print(accuracy_score(y_test, y_pred_random_forest))

# Output: 0.8688524590163934

#CODE SCREENSHOT