Machine [supervised{Classification(Logisticregression)}]

In [1]:

# Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

In [2]:

# 나이와 연봉으로 분석해서, 물건을 구매할지 안할지를 분류하자!!

In [3]:

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

In [4]:

df.head()

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

In [5]:

df["Purchased"].unique()

Out[5]:

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

In [6]:

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

In [7]:

X

Out[7]:

	Age	EstimatedSalary
0	19	19000
1	35	20000
2	26	43000
3	27	57000
4	19	76000
...	...	...
395	46	41000
396	51	23000
397	50	20000
398	36	33000
399	49	36000

400 rows × 2 columns

In [8]:

y = df["Purchased"]

In [9]:

y

Out[9]:

0      0
1      0
2      0
3      0
4      0
      ..
395    1
396    1
397    1
398    0
399    1
Name: Purchased, Length: 400, dtype: int64

In [10]:

# 로지스틱 리그레션은, 피처 스케일링을 하자

In [11]:

from sklearn.preprocessing import MinMaxScaler

In [12]:

scaler_X = MinMaxScaler()

In [13]:

scaler_X.fit_transform(X)

Out[13]:

array([[0.02380952, 0.02962963],
       [0.4047619 , 0.03703704],
       [0.19047619, 0.20740741],
       [0.21428571, 0.31111111],
       [0.02380952, 0.45185185],
       [0.21428571, 0.31851852],
       [0.21428571, 0.51111111],
       [0.33333333, 1.        ],
       [0.16666667, 0.13333333],
       [0.4047619 , 0.37037037],
       [0.19047619, 0.48148148],
       [0.19047619, 0.27407407],
       [0.04761905, 0.52592593],
       [0.33333333, 0.02222222],
       [0.        , 0.4962963 ],
       [0.26190476, 0.48148148],
       [0.69047619, 0.07407407],
       [0.64285714, 0.08148148],
       [0.66666667, 0.0962963 ],
       [0.71428571, 0.1037037 ],
       [0.64285714, 0.05185185],
       [0.69047619, 0.25185185],
       [0.71428571, 0.19259259],
       [0.64285714, 0.05185185],
       [0.66666667, 0.05925926],
       [0.69047619, 0.03703704],
       [0.73809524, 0.0962963 ],
       [0.69047619, 0.11111111],
       [0.26190476, 0.20740741],
       [0.30952381, 0.02222222],
       [0.30952381, 0.43703704],
       [0.21428571, 0.9037037 ],
       [0.07142857, 0.00740741],
       [0.23809524, 0.21481481],
       [0.21428571, 0.55555556],
       [0.4047619 , 0.08888889],
       [0.35714286, 0.0962963 ],
       [0.28571429, 0.25185185],
       [0.19047619, 0.42222222],
       [0.21428571, 0.11851852],
       [0.21428571, 0.01481481],
       [0.35714286, 0.26666667],
       [0.4047619 , 0.68888889],
       [0.28571429, 0.        ],
       [0.23809524, 0.51111111],
       [0.11904762, 0.03703704],
       [0.16666667, 0.47407407],
       [0.21428571, 0.28888889],
       [0.28571429, 0.88888889],
       [0.30952381, 0.54814815],
       [0.14285714, 0.12592593],
       [0.        , 0.21481481],
       [0.26190476, 0.5037037 ],
       [0.4047619 , 0.05925926],
       [0.21428571, 0.31851852],
       [0.14285714, 0.2962963 ],
       [0.11904762, 0.24444444],
       [0.23809524, 0.47407407],
       [0.0952381 , 0.02222222],
       [0.33333333, 0.75555556],
       [0.21428571, 0.03703704],
       [0.16666667, 0.53333333],
       [0.11904762, 0.37777778],
       [0.33333333, 0.77777778],
       [0.97619048, 0.5037037 ],
       [0.14285714, 0.31851852],
       [0.14285714, 0.02962963],
       [0.11904762, 0.4962963 ],
       [0.0952381 , 0.35555556],
       [0.30952381, 0.39259259],
       [0.16666667, 0.48148148],
       [0.14285714, 0.08888889],
       [0.04761905, 0.05925926],
       [0.35714286, 0.72592593],
       [0.33333333, 0.02222222],
       [0.38095238, 0.71851852],
       [0.        , 0.27407407],
       [0.0952381 , 0.08888889],
       [0.23809524, 0.53333333],
       [0.19047619, 0.01481481],
       [0.28571429, 0.48148148],
       [0.5       , 0.2       ],
       [0.04761905, 0.25185185],
       [0.4047619 , 0.54074074],
       [0.28571429, 0.34814815],
       [0.30952381, 0.76296296],
       [0.14285714, 0.2962963 ],
       [0.23809524, 0.51851852],
       [0.19047619, 0.48888889],
       [0.4047619 , 0.25925926],
       [0.0952381 , 0.48888889],
       [0.28571429, 0.74814815],
       [0.19047619, 0.        ],
       [0.26190476, 0.0962963 ],
       [0.26190476, 0.5037037 ],
       [0.4047619 , 0.21481481],
       [0.4047619 , 0.07407407],
       [0.23809524, 0.8       ],
       [0.4047619 , 0.42962963],
       [0.23809524, 0.16296296],
       [0.21428571, 0.54074074],
       [0.23809524, 0.32592593],
       [0.33333333, 0.52592593],
       [0.35714286, 0.99259259],
       [0.02380952, 0.04444444],
       [0.07142857, 0.42222222],
       [0.19047619, 0.14814815],
       [0.21428571, 0.54814815],
       [0.19047619, 0.52592593],
       [0.47619048, 0.48148148],
       [0.5       , 0.41481481],
       [0.45238095, 0.41481481],
       [0.47619048, 0.34074074],
       [0.45238095, 0.2962963 ],
       [0.57142857, 0.48148148],
       [0.52380952, 0.31111111],
       [0.4047619 , 0.44444444],
       [0.42857143, 0.27407407],
       [0.52380952, 0.32592593],
       [0.54761905, 0.32592593],
       [0.42857143, 0.44444444],
       [0.45238095, 0.42222222],
       [0.52380952, 0.44444444],
       [0.4047619 , 0.28148148],
       [0.54761905, 0.26666667],
       [0.5       , 0.34074074],
       [0.57142857, 0.37037037],
       [0.19047619, 0.12592593],
       [0.28571429, 0.01481481],
       [0.19047619, 0.51111111],
       [0.30952381, 0.31851852],
       [0.35714286, 0.11851852],
       [0.28571429, 0.53333333],
       [0.07142857, 0.39259259],
       [0.23809524, 0.2962963 ],
       [0.11904762, 0.35555556],
       [0.04761905, 0.4962963 ],
       [0.28571429, 0.68148148],
       [0.23809524, 0.32592593],
       [0.02380952, 0.07407407],
       [0.02380952, 0.51851852],
       [0.        , 0.39259259],
       [0.4047619 , 0.32592593],
       [0.28571429, 0.54814815],
       [0.38095238, 0.07407407],
       [0.14285714, 0.54814815],
       [0.21428571, 0.6       ],
       [0.54761905, 0.11111111],
       [0.26190476, 0.34074074],
       [0.04761905, 0.43703704],
       [0.19047619, 0.        ],
       [0.54761905, 0.22222222],
       [0.30952381, 0.45185185],
       [0.42857143, 0.25925926],
       [0.52380952, 0.23703704],
       [0.30952381, 0.        ],
       [0.66666667, 0.32592593],
       [0.26190476, 0.44444444],
       [0.19047619, 0.11111111],
       [0.33333333, 0.88888889],
       [0.33333333, 0.62962963],
       [0.16666667, 0.55555556],
       [0.45238095, 0.13333333],
       [0.4047619 , 0.17037037],
       [0.35714286, 0.4       ],
       [0.        , 0.52592593],
       [0.0952381 , 0.2962963 ],
       [0.4047619 , 0.41481481],
       [0.26190476, 0.98518519],
       [0.26190476, 0.23703704],
       [0.07142857, 0.54074074],
       [0.38095238, 0.74074074],
       [0.19047619, 0.76296296],
       [0.38095238, 0.20740741],
       [0.38095238, 0.42222222],
       [0.11904762, 0.0962963 ],
       [0.4047619 , 0.23703704],
       [0.16666667, 0.05185185],
       [0.14285714, 0.05925926],
       [0.30952381, 0.14074074],
       [0.19047619, 0.00740741],
       [0.30952381, 0.41481481],
       [0.33333333, 0.75555556],
       [0.35714286, 0.20740741],
       [0.35714286, 0.33333333],
       [0.30952381, 0.37777778],
       [0.04761905, 0.4962963 ],
       [0.35714286, 0.19259259],
       [0.4047619 , 0.42222222],
       [0.23809524, 0.12592593],
       [0.14285714, 0.51111111],
       [0.02380952, 0.08148148],
       [0.26190476, 0.20740741],
       [0.02380952, 0.40740741],
       [0.23809524, 0.54814815],
       [0.38095238, 0.20740741],
       [0.28571429, 0.47407407],
       [0.04761905, 0.15555556],
       [0.19047619, 0.48148148],
       [0.4047619 , 0.05185185],
       [0.4047619 , 0.17777778],
       [0.73809524, 0.43703704],
       [0.5       , 0.88148148],
       [0.54761905, 0.41481481],
       [0.95238095, 0.63703704],
       [0.69047619, 0.23703704],
       [0.88095238, 0.85185185],
       [0.80952381, 0.73333333],
       [0.52380952, 0.94074074],
       [0.66666667, 0.05185185],
       [0.71428571, 0.6       ],
       [0.80952381, 1.        ],
       [0.97619048, 0.2       ],
       [0.4047619 , 0.31851852],
       [0.69047619, 0.20740741],
       [1.        , 0.68888889],
       [0.73809524, 0.37037037],
       [0.52380952, 0.46666667],
       [0.66666667, 0.6       ],
       [0.97619048, 0.94814815],
       [0.54761905, 0.48148148],
       [0.4047619 , 0.56296296],
       [0.45238095, 0.95555556],
       [1.        , 0.64444444],
       [0.4047619 , 0.33333333],
       [0.45238095, 0.28148148],
       [0.42857143, 0.82222222],
       [0.9047619 , 0.87407407],
       [0.52380952, 0.42222222],
       [0.57142857, 0.48148148],
       [0.4047619 , 0.97777778],
       [0.5       , 0.2       ],
       [0.52380952, 0.68148148],
       [0.73809524, 0.52592593],
       [0.47619048, 0.71851852],
       [0.66666667, 0.47407407],
       [0.52380952, 0.31111111],
       [0.45238095, 0.48148148],
       [0.66666667, 0.4962963 ],
       [0.83333333, 0.94814815],
       [0.57142857, 0.99259259],
       [0.47619048, 0.32592593],
       [0.76190476, 0.54074074],
       [0.9047619 , 0.65925926],
       [0.54761905, 0.42222222],
       [0.78571429, 0.97037037],
       [0.4047619 , 0.25925926],
       [0.92857143, 0.79259259],
       [0.54761905, 0.27407407],
       [0.4047619 , 0.60740741],
       [0.61904762, 0.17777778],
       [0.45238095, 0.27407407],
       [0.71428571, 0.88148148],
       [0.45238095, 0.97037037],
       [0.76190476, 0.21481481],
       [0.80952381, 0.55555556],
       [0.54761905, 0.42222222],
       [0.52380952, 0.31111111],
       [0.95238095, 0.59259259],
       [0.64285714, 0.85925926],
       [0.4047619 , 0.45925926],
       [0.42857143, 0.95555556],
       [0.88095238, 0.81481481],
       [0.4047619 , 0.42222222],
       [0.71428571, 0.55555556],
       [0.57142857, 0.68888889],
       [0.52380952, 0.44444444],
       [0.45238095, 0.43703704],
       [0.69047619, 0.95555556],
       [0.52380952, 0.34074074],
       [0.5952381 , 0.87407407],
       [0.97619048, 0.45185185],
       [1.        , 0.2       ],
       [0.5       , 0.67407407],
       [0.92857143, 0.08148148],
       [0.92857143, 0.43703704],
       [0.47619048, 0.41481481],
       [0.73809524, 0.54074074],
       [0.80952381, 0.17037037],
       [0.76190476, 0.15555556],
       [0.97619048, 0.54074074],
       [0.4047619 , 0.34074074],
       [0.45238095, 0.40740741],
       [0.80952381, 0.04444444],
       [0.71428571, 0.93333333],
       [0.45238095, 0.57777778],
       [0.45238095, 0.34814815],
       [0.71428571, 0.91111111],
       [0.54761905, 0.47407407],
       [0.45238095, 0.46666667],
       [0.5       , 0.88148148],
       [0.73809524, 0.54814815],
       [0.88095238, 0.17777778],
       [0.45238095, 0.45925926],
       [0.4047619 , 0.31111111],
       [0.42857143, 0.35555556],
       [0.57142857, 0.42962963],
       [0.5952381 , 0.71851852],
       [0.64285714, 0.47407407],
       [0.66666667, 0.75555556],
       [0.95238095, 0.17037037],
       [0.71428571, 0.43703704],
       [0.45238095, 0.9037037 ],
       [0.45238095, 0.47407407],
       [0.52380952, 0.33333333],
       [0.57142857, 0.28888889],
       [0.78571429, 0.88148148],
       [0.69047619, 0.72592593],
       [0.42857143, 0.81481481],
       [0.47619048, 0.25925926],
       [0.57142857, 0.40740741],
       [0.5       , 0.6       ],
       [0.47619048, 0.25925926],
       [0.73809524, 0.93333333],
       [0.5       , 0.47407407],
       [0.5       , 0.44444444],
       [0.85714286, 0.65925926],
       [0.4047619 , 0.2962963 ],
       [0.64285714, 0.12592593],
       [0.42857143, 0.33333333],
       [0.80952381, 0.91111111],
       [0.83333333, 0.4962963 ],
       [0.54761905, 0.27407407],
       [0.71428571, 0.11111111],
       [0.71428571, 0.85925926],
       [0.54761905, 0.33333333],
       [0.54761905, 0.42222222],
       [0.57142857, 0.44444444],
       [0.42857143, 0.76296296],
       [0.69047619, 0.68148148],
       [0.47619048, 0.26666667],
       [0.71428571, 0.77037037],
       [0.57142857, 0.37037037],
       [0.52380952, 0.37037037],
       [0.92857143, 0.33333333],
       [0.42857143, 0.28888889],
       [0.95238095, 0.95555556],
       [0.4047619 , 0.47407407],
       [0.47619048, 0.2962963 ],
       [0.5       , 0.79259259],
       [0.83333333, 0.65925926],
       [0.4047619 , 0.44444444],
       [0.47619048, 0.37037037],
       [0.69047619, 0.26666667],
       [0.69047619, 0.66666667],
       [0.54761905, 0.35555556],
       [0.83333333, 0.42222222],
       [0.85714286, 0.68888889],
       [0.5       , 0.45925926],
       [0.47619048, 0.34074074],
       [0.47619048, 0.72592593],
       [0.45238095, 0.44444444],
       [0.57142857, 0.55555556],
       [0.45238095, 0.31111111],
       [0.42857143, 0.62222222],
       [1.        , 0.14074074],
       [0.85714286, 0.40740741],
       [0.54761905, 0.42222222],
       [0.52380952, 0.41481481],
       [0.57142857, 0.28888889],
       [0.5952381 , 0.84444444],
       [0.83333333, 0.14074074],
       [0.69047619, 0.25925926],
       [0.57142857, 0.47407407],
       [0.57142857, 0.65925926],
       [0.97619048, 0.1037037 ],
       [0.95238095, 0.23703704],
       [0.66666667, 0.54074074],
       [0.47619048, 0.41481481],
       [0.85714286, 0.08148148],
       [1.        , 0.22962963],
       [1.        , 0.5037037 ],
       [0.5       , 0.42962963],
       [0.97619048, 0.85185185],
       [0.45238095, 0.48148148],
       [0.66666667, 0.12592593],
       [0.66666667, 0.43703704],
       [0.57142857, 0.28148148],
       [0.54761905, 0.53333333],
       [0.95238095, 0.05925926],
       [0.57142857, 0.36296296],
       [0.71428571, 0.13333333],
       [0.61904762, 0.91851852],
       [0.73809524, 0.0962963 ],
       [0.92857143, 0.13333333],
       [0.9047619 , 0.33333333],
       [0.73809524, 0.17777778],
       [0.5       , 0.41481481],
       [0.69047619, 0.14074074],
       [0.71428571, 0.14814815],
       [0.71428571, 0.13333333],
       [0.69047619, 0.05925926],
       [0.64285714, 0.22222222],
       [1.        , 0.2       ],
       [0.5       , 0.32592593],
       [0.66666667, 0.19259259],
       [0.78571429, 0.05925926],
       [0.76190476, 0.03703704],
       [0.42857143, 0.13333333],
       [0.73809524, 0.15555556]])

In [14]:

X = scaler_X.fit_transform(X)

In [15]:

y

Out[15]:

0      0
1      0
2      0
3      0
4      0
      ..
395    1
396    1
397    1
398    0
399    1
Name: Purchased, Length: 400, dtype: int64

In [16]:

from sklearn.model_selection import train_test_split

In [17]:

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

In [ ]:

In [19]:

# 구매를 할지 말지 여부에 대한, 인공지능 개발
# 할지 말지 => 분류의 문제!!

In [18]:

from sklearn.linear_model import LogisticRegression

In [19]:

classifier = LogisticRegression(random_state=1) # 변수명만 보아도 무엇인지 알수있다.

In [20]:

classifier.fit(X_train,y_train)

Out[20]:

LogisticRegression(random_state=1)

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 [21]:

y_pred = classifier.predict(X_test)

In [22]:

y_pred

Out[22]:

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

In [23]:

classifier.predict_proba(X_test)  # 좌측열이 0일확률 , 우측열이 1일확률

Out[23]:

array([[0.86288917, 0.13711083],
       [0.70574277, 0.29425723],
       [0.49025346, 0.50974654],
       [0.38383672, 0.61616328],
       [0.75287835, 0.24712165],
       [0.71129842, 0.28870158],
       [0.97386557, 0.02613443],
       [0.28966461, 0.71033539],
       [0.93977209, 0.06022791],
       [0.12665048, 0.87334952],
       [0.76998121, 0.23001879],
       [0.64784915, 0.35215085],
       [0.74892811, 0.25107189],
       [0.1531759 , 0.8468241 ],
       [0.2308496 , 0.7691504 ],
       [0.06437334, 0.93562666],
       [0.1158091 , 0.8841909 ],
       [0.91090318, 0.08909682],
       [0.8275719 , 0.1724281 ],
       [0.07924665, 0.92075335],
       [0.61066233, 0.38933767],
       [0.2708696 , 0.7291304 ],
       [0.19380091, 0.80619909],
       [0.58666188, 0.41333812],
       [0.72241711, 0.27758289],
       [0.96740026, 0.03259974],
       [0.26765906, 0.73234094],
       [0.36227221, 0.63772779],
       [0.4643787 , 0.5356213 ],
       [0.14241022, 0.85758978],
       [0.7849406 , 0.2150594 ],
       [0.94528387, 0.05471613],
       [0.93955256, 0.06044744],
       [0.1842331 , 0.8157669 ],
       [0.85196752, 0.14803248],
       [0.81646998, 0.18353002],
       [0.97780003, 0.02219997],
       [0.75572999, 0.24427001],
       [0.62540997, 0.37459003],
       [0.98159252, 0.01840748],
       [0.13217047, 0.86782953],
       [0.09975728, 0.90024272],
       [0.56412277, 0.43587723],
       [0.93144621, 0.06855379],
       [0.25669316, 0.74330684],
       [0.63123437, 0.36876563],
       [0.60149068, 0.39850932],
       [0.23204368, 0.76795632],
       [0.61703901, 0.38296099],
       [0.47107607, 0.52892393],
       [0.9352704 , 0.0647296 ],
       [0.78282372, 0.21717628],
       [0.52722181, 0.47277819],
       [0.68932852, 0.31067148],
       [0.56554415, 0.43445585],
       [0.74711787, 0.25288213],
       [0.24478251, 0.75521749],
       [0.80527561, 0.19472439],
       [0.11231343, 0.88768657],
       [0.25176908, 0.74823092],
       [0.83748287, 0.16251713],
       [0.90512579, 0.09487421],
       [0.46580477, 0.53419523],
       [0.8290771 , 0.1709229 ],
       [0.59409164, 0.40590836],
       [0.32543863, 0.67456137],
       [0.9501836 , 0.0498164 ],
       [0.58175782, 0.41824218],
       [0.23548422, 0.76451578],
       [0.77437752, 0.22562248],
       [0.33052572, 0.66947428],
       [0.84705661, 0.15294339],
       [0.46031003, 0.53968997],
       [0.65786581, 0.34213419],
       [0.9290781 , 0.0709219 ],
       [0.13085527, 0.86914473],
       [0.85663321, 0.14336679],
       [0.96669606, 0.03330394],
       [0.79214651, 0.20785349],
       [0.79545105, 0.20454895],
       [0.94031341, 0.05968659],
       [0.73979099, 0.26020901],
       [0.23687211, 0.76312789],
       [0.9329054 , 0.0670946 ],
       [0.91628607, 0.08371393],
       [0.87151489, 0.12848511],
       [0.61203631, 0.38796369],
       [0.80254888, 0.19745112],
       [0.68829919, 0.31170081],
       [0.95322984, 0.04677016],
       [0.51162714, 0.48837286],
       [0.27891764, 0.72108236],
       [0.56460496, 0.43539504],
       [0.75448865, 0.24551135],
       [0.86390626, 0.13609374],
       [0.30839502, 0.69160498],
       [0.2942329 , 0.7057671 ],
       [0.67473982, 0.32526018],
       [0.72758505, 0.27241495],
       [0.86402151, 0.13597849]])

In [25]:

y_pred

Out[25]:

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

In [26]:

y_test.values

Out[26]:

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 [27]:

X_test.shape

Out[27]:

(100, 2)

In [ ]:

Confusion Matrix¶

두 개의 클래스로 분류하는 경우는 아래와 같다.¶

In [28]:

from sklearn.metrics import confusion_matrix

In [30]:

# 0과 1로 분류하는 문제 
# 따라서, y_test 값도 0과 1, y_pred 값도 0과 1

# y_test의 0과 1은 행으로 셋팅하고, y_pred 의 0과 1은 열로 셋팅합니다.
cm = confusion_matrix(y_test, y_pred)  # 외워야한다.

In [31]:

cm

Out[31]:

array([[52,  6],
       [14, 28]], dtype=int64)

In [34]:

(52+28) / cm.sum()   # 정확도 수동계산

Out[34]:

0.8

In [35]:

from sklearn.metrics import accuracy_score    # 정확도 함수

In [36]:

accuracy_score(y_test, y_pred)

Out[36]:

0.8

In [37]:

from sklearn.metrics import classification_report

In [39]:

print(classification_report(y_test, y_pred))   # print를 생략하면 메모리 상태가 보임

              precision    recall  f1-score   support

           0       0.79      0.90      0.84        58
           1       0.82      0.67      0.74        42

    accuracy                           0.80       100
   macro avg       0.81      0.78      0.79       100
weighted avg       0.80      0.80      0.80       100

In [ ]:

아래 코드는, 그대로 활용하면 됩니다.¶

In [ ]:

# 아래는, 테스트 데이터로 나온 예측 결과를 나타낸 것이다. Confusion Matrix 와 같다.

In [40]:

# 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.xlabel('Age')
plt.ylabel('Estimated Salary')
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.

In [ ]:

In [ ]:

# 아래는 학습에 사용된 데이터를 그래프로 나타낸 것입니다.

In [ ]:

# Visualising the Training set results
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()

In [ ]: