Decision Tree

계속하여 이것인지 저것인지 결정합니다.

구글드라이브 import

from google.colab import drive
drive.mount('/content/drive')

필요한 라이브러리 한글 가능 import

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sb

%matplotlib inline

import platform

from matplotlib import font_manager, rc
plt.rcParams['axes.unicode_minus'] = False

if platform.system() == 'Darwin':
    rc('font', family='AppleGothic')
elif platform.system() == 'Windows':
    path = "c:/Windows/Fonts/malgun.ttf"
    font_name = font_manager.FontProperties(fname=path).get_name()
    rc('font', family=font_name)
else:
    print('Unknown system... sorry~~~~')

 

Social_Network_Ads.csv

0.01MB

df=pd.read_csv('/content/drive/MyDrive/위치/Social_Network_Ads.csv')

X=df.iloc[:,[2,3]]
y = df['Purchased']

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X=scaler.fit_transform(X)

from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.25,random_state=3)

X와 y를 정해주고 스캐일링 해줍니다

 

모델링

from sklearn.tree import DecisionTreeClassifier
classifier = DecisionTreeClassifier(random_state=3)
classifier.fit(X_train,y_train)

 

검증

y_pred=classifier.predict(X_test)
from sklearn.metrics import confusion_matrix,accuracy_score
confusion_matrix(y_test,y_pred)

accuracy_score(y_test,y_pred)

저는 81프로 나왔습니다.

 

from matplotlib.colors import ListedColormap
X_set, y_set = X_test, y_test
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.figure(figsize=[10,7])
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Classifier (Test set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()

from matplotlib.colors import ListedColormap
X_set, y_set = X_train, y_train
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
                     np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
plt.figure(figsize=[10,7])
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
             alpha = 0.75, cmap = ListedColormap(('red', 'green')))
plt.xlim(X1.min(), X1.max())
plt.ylim(X2.min(), X2.max())
for i, j in enumerate(np.unique(y_set)):
    plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
                c = ListedColormap(('red', 'green'))(i), label = j)
plt.title('Logistic Regression (Training set)')
plt.xlabel('Age')
plt.ylabel('Estimated Salary')
plt.legend()
plt.show()