Random Forest and Ada Boost Algorithm Implementation Using Tic-tac-toe Dataset

Import Necessary Packages

import pandas as pd
import numpy as np

Load Dataset

df = pd.read_csv("Q1_training-tic-tac-toe.data/tic-tac-toe.data.txt")
df

Output:

Data Preprocessing

from sklearn.preprocessing import LabelEncoder

labelencoder = LabelEncoder()

df['x'] = labelencoder.fit_transform(df['x'])

df['x']

output:

df['x.1'] = labelencoder.fit_transform(df['x.1'])
df['x.3'] = labelencoder.fit_transform(df['x.3'])
df['x.4'] = labelencoder.fit_transform(df['x.4'])
df['o'] = labelencoder.fit_transform(df['o'])
df['o.1'] = labelencoder.fit_transform(df['o.1'])
df['o.2'] = labelencoder.fit_transform(df['o.2'])
df['o.3'] = labelencoder.fit_transform(df['o.3'])
df['positive'] = labelencoder.fit_transform(df['positive'])
df

X = df.iloc[:, 0:9].values

y = df.iloc[:, 9].values

from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

from sklearn.preprocessing import StandardScaler

feature_scaler = StandardScaler()

X_train = feature_scaler.fit_transform(X_train)

X_test = feature_scaler.transform(X_test)

2. Create a Random Forest Model (random_state = 0) using k- Cross-Validation Technique

from sklearn.ensemble import RandomForestClassifier

classifier = RandomForestClassifier(n_estimators=100, random_state=0)

from sklearn.model_selection import cross_val_score

all_accuracies = cross_val_score(estimator=classifier, X=X_train, y=y_train, cv=5)

all_accuracies

output:

array([0.91034483, 0.92307692, 0.9020979 , 0.93006993, 0.98601399])

Accuracy = all_accuracies[4]
Accuracy = round(Accuracy, 2)

3. Apply Ada Boost algorithm to improve the accuracy score (random_state = 0).

from sklearn.ensemble import AdaBoostClassifier
from sklearn import metrics
abc = AdaBoostClassifier(n_estimators=50,
                         learning_rate=1, random_state = 0)
# Train Adaboost Classifer
model = abc.fit(X_train, y_train)

y_pred = model.predict(X_test)

print("Accuracy:",metrics.accuracy_score(y_test, y_pred))

output:

Accuracy: 0.7708333333333334

Accuracy_Adaboost = metrics.accuracy_score(y_test, y_pred)
Accuracy_Adaboost = round(Accuracy_Adaboost, 2)

list_of_result_values = []
list_of_result_values.append(Accuracy)
list_of_result_values.append(Accuracy_Adaboost)

list_of_result_values

output:

[0.99, 0.77]

In [78]:

Save Result into csv file

file = open('./output/output.csv','a+')
file.write("Question1 Output" +"\n")
file.write(str(list_of_result_values) +"\n")
file.close()