Machine [supervised{Classification(K-Nearest Neighbor)}]

In [1]:

import pandas as pd

In [3]:

df = pd.read_csv("../data/Social_Network_Ads.csv")

In [4]:

df

Out[4]:

	User ID	Gender	Age	EstimatedSalary	Purchased
0	15624510	Male	19	19000	0
1	15810944	Male	35	20000	0
2	15668575	Female	26	43000	0
3	15603246	Female	27	57000	0
4	15804002	Male	19	76000	0
...	...	...	...	...	...
395	15691863	Female	46	41000	1
396	15706071	Male	51	23000	1
397	15654296	Female	50	20000	1
398	15755018	Male	36	33000	0
399	15594041	Female	49	36000	1

400 rows × 5 columns

In [5]:

df.isna().sum()

Out[5]:

User ID            0
Gender             0
Age                0
EstimatedSalary    0
Purchased          0
dtype: int64

In [6]:

df.describe()

Out[6]:

	User ID	Age	EstimatedSalary	Purchased
count	4.000000e+02	400.000000	400.000000	400.000000
mean	1.569154e+07	37.655000	69742.500000	0.357500
std	7.165832e+04	10.482877	34096.960282	0.479864
min	1.556669e+07	18.000000	15000.000000	0.000000
25%	1.562676e+07	29.750000	43000.000000	0.000000
50%	1.569434e+07	37.000000	70000.000000	0.000000
75%	1.575036e+07	46.000000	88000.000000	1.000000
max	1.581524e+07	60.000000	150000.000000	1.000000

In [7]:

y = df["Purchased"]

In [12]:

X = df.loc[ : ,["Age", "EstimatedSalary"] ]

In [13]:

from sklearn.preprocessing import MinMaxScaler

In [14]:

scaler_X = MinMaxScaler()

In [15]:

X = scaler_X.fit_transform(X)

In [18]:

y.value_counts()

Out[18]:

0    257
1    143
Name: Purchased, dtype: int64

In [19]:

from sklearn.model_selection import train_test_split

In [20]:

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=1)

In [ ]:

In [21]:

from sklearn.neighbors import KNeighborsClassifier

In [22]:

# 가장 가까운 5개 데이터로 분류
classifier = KNeighborsClassifier()

In [23]:

classifier.fit(X_train,y_train)

Out[23]:

KNeighborsClassifier()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

In [24]:

y_pred = classifier.predict(X_test)

In [25]:

y_pred

Out[25]:

array([0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1,
       1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0,
       1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 1, 1,
       0, 0, 1, 0, 1, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0,
       1, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0], dtype=int64)

In [27]:

y_test.values

Out[27]:

array([0, 0, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 1, 0, 1,
       1, 0, 1, 0, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 1, 0, 0,
       1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 1,
       0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0,
       1, 0, 1, 1, 1, 0, 0, 1, 1, 1, 0, 0], dtype=int64)

In [ ]:

In [29]:

from sklearn.metrics import confusion_matrix, accuracy_score

In [30]:

cm = confusion_matrix(y_test, y_pred)

In [31]:

cm

Out[31]:

array([[50,  8],
       [ 4, 38]], dtype=int64)

In [32]:

accuracy_score(y_test,y_pred)

Out[32]:

0.88

In [ ]:

In [36]:

import numpy as np
import matplotlib.pyplot as plt

In [37]:

# Visualising the Test set results
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.legend()
plt.show()

*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*.  Please use the *color* keyword-argument or provide a 2D array with a single row if you intend to specify the same RGB or RGBA value for all points.
*c* argument looks like a single numeric RGB or RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches with *x* & *y*.  Please use the *color* keyword-argument or provide a 2D array with a single row if you intend to specify the same RGB or RGBA value for all points.