Requirement Details
Implement Adaboost using two different week classifier ( Decision Tree and Perceptron) and compare the results.
Describe the algorithm
Submit the code for the implementation.
Provide a table showing the performance of each classifier, as well as the combined performance of both classifiers.
Will need the algorithm of each classifier :
decision tree + adaboost
pla +adaboost
Implementation
AdaBoost
AdaBoost, short for “Adaptive Boosting,” is a boosting ensemble machine learning algorithm, and was one of the first successful boosting approaches. In this, I implement Adaboost with Decision Tree and Perceptron. This is a Ensemble Algorithm which used for classification and regression problems.
Real the columns
col_names=["Class Name",
"handicapped-infants",
"water-project-cost-sharing",
"adoption-of-the-budget-resolution",
"physician-fee-freeze",
"el-salvador-aid",
"religious-groups-in-schools",
"anti-satellite-test-ban",
"aid-to-nicaraguan-contras",
"mx-missile",
"immigration",
"synfuels-corporation-cutback",
"education-spending",
"superfund-right-to-sue",
"crime",
"duty-free-exports",
"export-administration-act-south-africa"]Read Data
import pandas as pd
# reading csv files
data = pd.read_csv('/content/house-votes-84(1) (1).data',names=col_names)
print(data)Output:
Change it to the pandas DataFrame
df = pd.DataFrame(data)
dfOutput:
Describe the dataset
df.describe()Output:
Show the information of dataset
df.info()output:
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 435 entries, 0 to 434
Data columns (total 17 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 Class Name 435 non-null object
1 handicapped-infants 435 non-null object
2 water-project-cost-sharing 435 non-null object
3 adoption-of-the-budget-resolution 435 non-null object
4 physician-fee-freeze 435 non-null object
5 el-salvador-aid 435 non-null object
6 religious-groups-in-schools 435 non-null object
7 anti-satellite-test-ban 435 non-null object
8 aid-to-nicaraguan-contras 435 non-null object
9 mx-missile 435 non-null object
10 immigration 435 non-null object
11 synfuels-corporation-cutback 435 non-null object
12 education-spending 435 non-null object
13 superfund-right-to-sue 435 non-null object
14 crime 435 non-null object
15 duty-free-exports 435 non-null object
16 export-administration-act-south-africa 435 non-null object
dtypes: object(17)
memory usage: 57.9+ KB#replace '?' using np.nan
df[df.loc[:,:]=="?" ]= np.nan
#replace 'n' with 0
df[df.loc[:,:]=="n" ]= 0
#replace 'y' with 1
df[df.loc[:,:]=="y" ]= 1Finding sum of missing value
#missing values
df.isna().sum()Output:
Class Name 0
handicapped-infants 12
water-project-cost-sharing 48
adoption-of-the-budget-resolution 11
physician-fee-freeze 11
el-salvador-aid 15
religious-groups-in-schools 11
anti-satellite-test-ban 14
aid-to-nicaraguan-contras 15
mx-missile 22
immigration 7
synfuels-corporation-cutback 21
education-spending 31
superfund-right-to-sue 25
crime 17
duty-free-exports 28
export-administration-act-south-africa 104
dtype: int64Encoding the dataset columns
from sklearn.preprocessing import OrdinalEncoder
ord_enc = OrdinalEncoder()
from sklearn.preprocessing import OrdinalEncoder
ord_enc = OrdinalEncoder()
for column in col_names:
df[column] = ord_enc.fit_transform(df[[column]])Import Libraries
from sklearn.ensemble import AdaBoostClassifier
from sklearn import datasets
# Import train_test_split function
from sklearn.model_selection import train_test_split
#Import scikit-learn metrics module for accuracy calculation
from sklearn import metrics
Split Dataset
X=df.iloc[:,1:]
y=df.iloc[:,1]Split Dataset
# 70% training and 30% test
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.35) ADB + DT
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import Perceptron
dt= DecisionTreeClassifier()
pla = Perceptron()# Create adaboost classifer object
Adb_dt = AdaBoostClassifier(n_estimators=50,
learning_rate=1,
base_estimator = dt
)
# Train Adaboost Classifer
model = Adb_dt.fit(X_train, y_train)
#Predict the response for test dataset
y_pred = model.predict(X_test)Find the accuracy
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))Confusion Matrics & Classification Report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
# confusion matrix
matrix = confusion_matrix(y_test, y_pred)
print('Confusion matrix : \n',matrix)Confusion matrix : [[88 0] [ 0 65]]
Classification Report
matrix = classification_report(y_test, y_pred)
print('Classification report : \n',matrix)Output:
lassification report :
precision recall f1-score support
0.0 1.00 1.00 1.00 88
1.0 1.00 1.00 1.00 65
accuracy 1.00 153
macro avg 1.00 1.00 1.00 153
weighted avg 1.00 1.00 1.00 153pla +adaboost
# Create adaboost classifer object
Adb_pla = AdaBoostClassifier(base_estimator=Perceptron(), n_estimators=15, algorithm='SAMME')
# Train Adaboost Classifer
model = Adb_pla.fit(X_train, y_train)
#Predict the response for test dataset
y_pred = model.predict(X_test)Print the accuracy
print("Accuracy:",metrics.accuracy_score(y_test, y_pred))Confusion Matrix
# confusion matrix
matrix = confusion_matrix(y_test, y_pred)
print('Confusion matrix : \n',matrix)Output: [[88 0] [ 0 65]]
Classification Report
matrix = classification_report(y_test, y_pred)
print('Classification report : \n',matrix)Output:
Classification report :
precision recall f1-score support
0.0 1.00 1.00 1.00 88
1.0 1.00 1.00 1.00 65
accuracy 1.00 153
macro avg 1.00 1.00 1.00 153
weighted avg 1.00 1.00 1.00 153If you need any programming assignment help in Machine Learning Assignment, Machine Learning Homework or Machine Learning Projet.
Send your request at realcode4you@gmail.com and get instant help with an affordable price.
We are always focus to delivered unique or without plagiarism code which is written by our highly educated professional which provide well structured code within your given time frame.
If you are looking other programming language help like C, C++, Java, Python, PHP, Asp.Net, NodeJs, ReactJs, etc. with the different types of databases like MySQL, MongoDB, SQL Server, Oracle, etc. then also contact us.
Commentaires