bro's coding

교차검증 - shuffle을 적용하지 않고, 분류의 경우 원본 비율을 유지(stratified)(옵션으로 바꿀 수 있음) import numpy as np import pandas as pd import matplotlib.pyplot as plt from sklearn.datasets import load_iris iris=load_iris() from sklearn.linear_model import LogisticRegression from sklearn.tree import DecisionTreeClassifier from sklearn.model_selection import cross_val_score model=DecisionTreeClassifier(max_features=2) scores..

import pandas as pd 'data=pd.read_csv('CARD_SUBWAY_MONTH_201905.csv') # 역명 별 승차총승객수의 합을 오름차순으로 정렬 ser=data.groupby('역명').승차총승객수.sum().sort_values() ser.head()

#data_time을 이용해 요일 알아내기 data2.일자.dt.dayofweek data2['년']=data2.일자.dt.year data2['월']=data2.일자.dt.month data2['일']=data2.일자.dt.day data2['wday']=data2.일자.dt.weekday data2['wname']=data2.일자.dt.weekday_name # 0 : 월요일 data2.head() data2['요일']=data2.일자.dt.weekday.map({0:'월',1:'화',2:'수',3:'목',4:'금',5:'토',6:'일'}) data2.head()

import pandas as pd data=pd.read_csv('CARD_SUBWAY_MONTH_201905.csv') data data.pivot_table(values='승차총승객수',index='사용일자',columns='노선명',aggfunc='sum') # [사용일자:노선명] 에 따른 승차총승객수(sum)

data=pd.read_csv('CARD_SUBWAY_MONTH_201905.csv') data

# 꽃 이름에 따른 dictionary를 생성 label={i:iris.target_names[i] for i in range(3)} label # {0: 'setosa', 1: 'versicolor', 2: 'virginica'} # target number에 따라 꽃 이름을 mapping pd.Series(iris.target).map(label) 0 setosa 1 setosa 2 setosa 3 setosa 4 setosa 5 setosa 6 setosa 7 setosa 8 setosa 9 setosa 10 setosa 11 setosa 12 setosa 13 setosa 14 setosa 15 setosa 16 setosa 17 setosa 18 setosa 19 setosa 20 setosa ..

# target을 one-hot-incoding한다 import numpy as np import pandas as pd from sklearn.datasets import load_iris iris=load_iris() data=np.c_[iris.data,pd.get_dummies(iris.target).values] data array([[5.1, 3.5, 1.4, ..., 1. , 0. , 0. ], [4.9, 3. , 1.4, ..., 1. , 0. , 0. ], [4.7, 3.2, 1.3, ..., 1. , 0. , 0. ], ..., [6.5, 3. , 5.2, ..., 0. , 0. , 1. ], [6.2, 3.4, 5.4, ..., 0. , 0. , 1. ], [5.9, 3. , 5.1,..

from sklearn.manifold import TSNE import numpy as np import matplotlib.pyplot as plt from sklearn.datasets import load_digits mnist=load_digits() tsne =TSNE() mnist_tsne=tsne.fit_transform(mnist.data) # 상대적인 거리를 이용해 가까운 것들은 더 가깝게, 먼 것들은 더 멀게 만든다. xmax, ymax = mnist_tsne.max(axis=0) xmin, ymin = mnist_tsne.min(axis=0) colors = ["#476A2A", "#7851B8", "#BD3430", "#4A2D4E", "#875525", "#A83683", "#4..

y=mnist.target.copy() y=np.where(y==9,1,0) ''' if(y==9): y=1 else: y=0 '''

from sklearn.neighbors import KNeighborsClassifier knn=KNeighborsClassifier(5) knn.fit(mnist.data,mnist.target) knn.score(mnist.data,mnist.target) # 0.9905397885364496