로지스틱 회귀¶
구글 코랩에서 실행하기럭키백의 확률¶
데이터 준비하기¶
In [1]:
import pandas as pd
fish = pd.read_csv('https://bit.ly/fish_csv_data')
fish.head()
Out[1]:
In [2]:
print(pd.unique(fish['Species']))
In [3]:
fish_input = fish[['Weight','Length','Diagonal','Height','Width']].to_numpy()
In [4]:
print(fish_input[:5])
In [5]:
fish_target = fish['Species'].to_numpy()
In [6]:
from sklearn.model_selection import train_test_split
train_input, test_input, train_target, test_target = train_test_split(
fish_input, fish_target, random_state=42)
In [7]:
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
ss.fit(train_input)
train_scaled = ss.transform(train_input)
test_scaled = ss.transform(test_input)
k-최근접 이웃 분류기의 확률 예측¶
In [8]:
from sklearn.neighbors import KNeighborsClassifier
kn = KNeighborsClassifier(n_neighbors=3)
kn.fit(train_scaled, train_target)
print(kn.score(train_scaled, train_target))
print(kn.score(test_scaled, test_target))
In [9]:
print(kn.classes_)
In [10]:
print(kn.predict(test_scaled[:5]))
In [11]:
import numpy as np
proba = kn.predict_proba(test_scaled[:5])
print(np.round(proba, decimals=4))
In [12]:
distances, indexes = kn.kneighbors(test_scaled[3:4])
print(train_target[indexes])
로지스틱 회귀¶
In [13]:
import numpy as np
import matplotlib.pyplot as plt
z = np.arange(-5, 5, 0.1)
phi = 1 / (1 + np.exp(-z))
plt.plot(z, phi)
plt.xlabel('z')
plt.ylabel('phi')
plt.show()
로지스틱 회귀로 이진 분류 수행하기¶
In [14]:
char_arr = np.array(['A', 'B', 'C', 'D', 'E'])
print(char_arr[[True, False, True, False, False]])
In [15]:
bream_smelt_indexes = (train_target == 'Bream') | (train_target == 'Smelt')
train_bream_smelt = train_scaled[bream_smelt_indexes]
target_bream_smelt = train_target[bream_smelt_indexes]
In [16]:
from sklearn.linear_model import LogisticRegression
lr = LogisticRegression()
lr.fit(train_bream_smelt, target_bream_smelt)
Out[16]:
In [17]:
print(lr.predict(train_bream_smelt[:5]))
In [18]:
print(lr.predict_proba(train_bream_smelt[:5]))
In [19]:
print(lr.classes_)
In [20]:
print(lr.coef_, lr.intercept_)
In [21]:
decisions = lr.decision_function(train_bream_smelt[:5])
print(decisions)
In [22]:
from scipy.special import expit
print(expit(decisions))
로지스틱 회귀로 다중 분류 수행하기¶
In [23]:
lr = LogisticRegression(C=20, max_iter=1000)
lr.fit(train_scaled, train_target)
print(lr.score(train_scaled, train_target))
print(lr.score(test_scaled, test_target))
In [24]:
print(lr.predict(test_scaled[:5]))
In [25]:
proba = lr.predict_proba(test_scaled[:5])
print(np.round(proba, decimals=3))
In [26]:
print(lr.classes_)
In [27]:
print(lr.coef_.shape, lr.intercept_.shape)
In [28]:
decision = lr.decision_function(test_scaled[:5])
print(np.round(decision, decimals=2))
In [29]:
from scipy.special import softmax
proba = softmax(decision, axis=1)
print(np.round(proba, decimals=3))