59doit

Numpy 는 ndarray 를 이어붙이는 concatenate()함수 제공 arr = np.arange(12).reshape((3, 4)) arr # # array([[ 0, 1, 2, 3], # [ 4, 5, 6, 7], # [ 8, 9, 10, 11]]) ▷ column 기준으로 병합 np.concatenate([arr, arr], axis=1) # # array([[ 0, 1, 2, 3, 0, 1, 2, 3], # [ 4, 5, 6, 7, 4, 5, 6, 7], # [ 8, 9, 10, 11, 8, 9, 10, 11]]) ▷ s1 = pd.Series([0, 1], index=['a', 'b']) s1 # # a 0 # b 1 # dtype: int64 s2 = pd.Series([2, 3, 4]..

combining df1 = pd.DataFrame({'key': ['b', 'b', 'a', 'c', 'a', 'a', 'b'], 'data1': range(7)}) df1 # # key data1 # 0 b 0 # 1 b 1 # 2 a 2 # 3 c 3 # 4 a 4 # 5 a 5 # 6 b 6 df2 = pd.DataFrame({'key': ['a', 'b', 'd'], 'data2': range(3)}) df2 # # key data2 # 0 a 0 # 1 b 1 # 2 d 2 ▷ merg() 함수 pd.merge(df1, df2) # # key data1 data2 # 0 b 0 1 # 1 b 1 1 # 2 b 6 1 # 3 a 2 0 # 4 a 4 0 # 5 a 5 0 ▷ merge()함수는 ..

import numpy as np import pandas as pd pd.options.display.max_rows = 20 np.random.seed(12345) import matplotlib.pyplot as plt plt.rc('figure', figsize=(10, 6)) np.set_printoptions(precision=4, suppress=True) data = pd.Series(np.random.randn(9), index=[['a', 'a', 'a', 'b', 'b', 'c', 'c', 'd', 'd'], [1, 2, 3, 1, 3, 1, 2, 2, 3]]) data # # a 1 -0.204708 # 2 0.478943 # 3 -0.519439 # b 1 -0.555730 # 3..

import pandas as pd import numpy as np data = pd.Series([1., -999., 2., -999., -1000., 3.]) data # # 0 1.0 # 1 -999.0 # 2 2.0 # 3 -999.0 # 4 -1000.0 # 5 3.0 # dtype: float64 ▷ 여러개를 한번에 치환 data.replace(-999, np.nan) # # 0 1.0 # 1 NaN # 2 2.0 # 3 NaN # 4 -1000.0 # 5 3.0 # dtype: float64 data.replace([-999, -1000], np.nan) # # 0 1.0 # 1 NaN # 2 2.0 # 3 NaN # 4 NaN # 5 3.0 # dtype: float64 ▷ 대응관계 di..