機械学習とGridDBを利用したフィッシングサイトの検出

import glob as gb # This builtin module would allow us to select only the file with .arff extension

files = [f for f in gb.glob("*.arff")] # We are using "files" because this selects all the files with that extension

# This function would convert the ARFF file to CSV file
def convert(lines):
    header = ""
    file_content = []
    data = not True
    
    for line in lines:
        if not data:
            if "@attribute" in line:
                attributes = line.split()
                columnName = attributes[attributes.index("@attribute")+1]
                header = header + columnName + ","
            elif "@data" in line:
                data = True
                header = header[:-1]
                header += "\n"
                file_content.append(header)
        else:
            file_content.append(line)
    return file_content
        

for file in files:
    with open(file, "r") as inp:
        lines = inp.readlines()
        output = convert(lines)
        with open("dataset" + ".csv", "w") as out:
            out.writelines(output)

import griddb_python as griddb
factory = griddb.StoreFactory.get_instance()
your_host = ""
your_port = ""
your_cluster_name = ""
your_username = ""
your_password = ""
try:
    gridstore = factory.get_store(host=your_host, port=your_port, 
            cluster_name=your_cluster_name, username=your_username, 
            password=your_password)
conInfo = griddb.ContainerInfo("Phishing Websites",
                    [              
                     ["having_IP_Address", griddb.Type.INTEGER],
                     ["URL_Length", griddb.Type.INTEGER],
                     ["Shortining_Service", griddb.Type.INTEGER],
                     ["having_At_Symbol", griddb.Type.INTEGER],
                     ["double_slash_redirecting", griddb.Type.INTEGER],
                     ["Prefix_Suffix", griddb.Type.INTEGER],
                     ["having_Sub_Domain", griddb.Type.INTEGER],
                     ["SSLfinal_State", griddb.Type.INTEGER],
                     ["Domain_registeration_length", griddb.Type.INTEGER],
                     ["Favicon", griddb.Type.INTEGER],
                     ["port", griddb.Type.INTEGER],
                     ["HTTPS_token", griddb.Type.INTEGER],
                     ["Request_URL", griddb.Type.INTEGER],
                     ["URL_of_Anchor", griddb.Type.INTEGER],
                     ["Links_in_tags", griddb.Type.INTEGER],
                     ["SFH", griddb.Type.INTEGER],
                     ["Submitting_to_email", griddb.Type.INTEGER],
                     ["Abnormal_URL", griddb.Type.INTEGER],
                     ["Redirect", griddb.Type.INTEGER],
                     ["on_mouseover", griddb.Type.INTEGER],
                     ["RightClick", griddb.Type.INTEGER],
                     ["popUpWidnow", griddb.Type.INTEGER],
                     ["Iframe", griddb.Type.INTEGER],
                     ["age_of_domain", griddb.Type.INTEGER],
                     ["DNSRecord", griddb.Type.INTEGER],
                     ["web_traffic", griddb.Type.INTEGER],
                     ["Page_Rank", griddb.Type.INTEGER],
                     ["Google_Index", griddb.Type.INTEGER],
                     ["Links_pointing_to_page", griddb.Type.INTEGER],
                     ["Statistical_report", griddb.Type.INTEGER],
                     ["Result", griddb.Type.INTEGER],                    
                    ],
                    griddb.ContainerType.COLLECTION, True)
    cont = gridstore.put_container(conInfo)   
    data = pd.read_csv("dataset.csv")
    
    #Add data
    for i in range(len(data)):
        ret = cont.put(data.iloc[i, :])
    print("Successfully added the data")
except griddb.GSException as e:
    for i in range(e.get_error_stack_size()):
        print("[", i, "]")
        print(e.get_error_code(i))
        print(e.get_location(i))
        print(e.get_message(i))

import pandas as pd
dataset = pd.read_csv("dataset.csv")

""" You can also decide to show the bottom five records of the data by 
typing dataset.tail()"""
dataset.head()

dataset.shape # Number of rows and columns

dataset.describe() # Describing the data to gain insights from it

X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values

print(X)

print(y)

from sklearn.model_selection import train_test_split as tts

X_train, X_test, y_train, y_test = tts(X, y, test_size=0.30, random_state=0)

import seaborn as sns
sns.pairplot(dataset)

from sklearn.tree import DecisionTreeClassifier

dtClassifier = DecisionTreeClassifier()

dtClassifier.fit(X_train, y_train)

dty_pred = dtClassifier.predict(X_test)

print(dty_pred)

from sklearn.metrics import confusion_matrix
cMatrix = confusion_matrix(y_test, dty_pred)
print(cMatrix)

# Accuracy of the model
dtacc = dtClassifier.score(X_test, y_test)
dtacc *= 100
dtaccu = round(dtacc, 2)
dtaccuracy = str(dtaccu)+"%"
print(
f"""
The Accuracy of our model, using the Decision Tree Classifier
{dtaccuracy}
"""
)