Random Forest2.txt

Reference


Random Forest
===================================


import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score


df=pd.read_csv('https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data', header=None)


##Preprocess the data to prepare it for the model. In this example, we will be encoding the categorical variable (species) using one-hot encoding.
X = df.iloc[:, :-1]
y = df.iloc[:, -1]
y = pd.get_dummies(y)


X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

rfc = RandomForestClassifier(n_estimators=100, max_depth=10, random_state=42)

rfc.fit(X_train, y_train)

y_pred = rfc.predict(X_test)

acc = accuracy_score(y_test, y_pred)
print('Accuracy:', acc)
=========================================================================

Gradient Descending
-------------------


import pandas as pd

import numpy as np

from sklearn.metrics import classification_report

from sklearn.datasets import load_breast_cancer

from sklearn.ensemble import GradientBoostingClassifier

from sklearn.model_selection import train_test_split



df = pd.DataFrame(load_breast_cancer()['data'],

columns=load_breast_cancer()['feature_names'])

df['y'] = load_breast_cancer()['target']

df.head(5)



X,y = df.drop('y',axis=1),df.y

test_size = 0.30 # taking 70:30 training and test set

seed = 7  # Random number seeding for reapeatability of the code

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


 

gradient_booster = GradientBoostingClassifier(learning_rate=0.1)

gradient_booster.fit(X_train,y_train)

===========================================================================================================