To find best fit n_estimators in random forest algorithm to improve performance of the model
Iris data set
Improved classification results.
Import the library.
Load the sample data set.
Split the data train and test.
Define the number of n_estimators.
Fit the train data into Gridsearch model.
Find the optimal number of n_estimators.
Improve the model performance.
Calculate precision, recall and accuracy.
#import libraries
import warnings
warnings.filterwarnings(“ignore”)
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import classification_report, confusion_matrix, accuracy_score
#load the sample data from iris.csv file
data = pd.read_csv(‘/home/soft50/soft50/Sathish/practice/iris.csv’)
#Make it as a data frame
df = pd.DataFrame(data)
#feature variables
X = df.iloc[:,0:4]
y = df.iloc[:,4]
#Split the data into train and testing
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
#Random forest
rf = RandomForestClassifier()
#create a dictionary of all values we want to test for n_estimators
params_rf = {‘n_estimators’: [50, 100, 200]}
#use gridsearch to test all values for n_estimators
rf_gs = GridSearchCV(rf, params_rf, cv=5)
#fit model to training data
rf_gs.fit(X_train, y_train)
rf_best = rf_gs.best_estimator_
print(“Optimal number of n_estimators for the model\n\n”,rf_best)
y_pred = rf_best.predict(X_test)
#Evaluate the model
print(“\n”)
print(“Classification report for Random Forest\n”)
print(classification_report(y_test, y_pred))
print(“Confusion matrix\n”)
print(confusion_matrix(y_test, y_pred))
print(“\n”)
print(“Accuracy score”)
print(accuracy_score(y_test, y_pred))