sagarhowal

from sklearn.ensemble import BaggingClassifier
from sklearn.tree import DecisionTreeClassifier

bag_clf = BaggingClassifier(
    DecisionTreeClassifier(random_state=42), n_estimators=500,
    max_samples=100, bootstrap=True, n_jobs=-1, random_state=42)
bag_clf.fit(X_train, y_train)

y_pred = bag_clf.predict(X_test)
 

sagarhowal

bag_clf = BaggingClassifier(
DecisionTreeClassifier(random_state=42), n_estimators=500,
max_samples=100, bootstrap=True, n_jobs=-1, random_state=42,
oob_score = True) 

sagarhowal

bootstrap_features = True, max_samples = 0.6
#max_samples to be less than 1.0 or discard variable

sagarhowal

Bootstrap = True, bootstrap_features = True, max_features = 0.6
#max_samples less than 1.0 or discarded

sagarhowal

from sklearn.ensemble import RandomForestClassifier

rnd_clf = RandomForestClassifier(n_estimators=500, max_leaf_nodes=16, n_jobs=-1, random_state=42)
rnd_clf.fit(X_train, y_train)

y_pred_rf = rnd_clf.predict(X_test)

sagarhowal

from sklearn.ensemble import AdaBoostClassifier

ada_clf = AdaBoostClassifier(
    DecisionTreeClassifier(max_depth=1), n_estimators=200,
    algorithm="SAMME.R", learning_rate=0.5, random_state=42)
ada_clf.fit(X_train, y_train)

sagarhowal

from sklearn.ensemble import GradientBoostingRegressor

gbrt = GradientBoostingRegressor(max_depth=2, n_estimators=3, learning_rate=1.0, random_state=42)
gbrt.fit(X, y)

sagarhowal

from xgboost import XGBoostClassifier
xgb_clf = XGBClassifier()
xgb_clf.fit(X, y)

sagarhowal

import numpy as np
import pandas as pd

#Importing dataset
dataset = pd.read_csv('breast_cancer.csv')

#Check the first 5 rows of the dataset. 
	dataset.head(5)

sagarhowal

#Seperating dependent and independent variables. 

X = dataset.iloc[:, 2:32].values  #Note: Exclude Last column with all NaN values.
y = dataset.iloc[:, 1].values