59doit

import pandas as pd import numpy as np df = pd.read_csv('pandas_dataset2/ex1.csv') df # # a b c d message # 0 1 2 3 4 hello # 1 5 6 7 8 world # 2 9 10 11 12 foo ▷ 구분자 => , pd.read_table('pandas_dataset2/ex1.csv', sep=',') # # a b c d message # 0 1 2 3 4 hello # 1 5 6 7 8 world # 2 9 10 11 12 foo ▷ type examples/ex2.csv pd.read_csv('pandas_dataset2/ex2.csv', header=None) # # 0 1 2 3 4 # 0 1 2 3 4..

df = pd.DataFrame([[1.4, np.nan], [7.1, -4.5], [np.nan, np.nan], [0.75, -1.3]], index=['a', 'b', 'c', 'd'], columns=['one', 'two']) df # # one two # a 1.40 NaN # b 7.10 -4.5 # c NaN NaN # d 0.75 -1.3 ▷ SUM df.sum() # # one 9.25 # two -5.80 # dtype: float64 df.sum(axis='columns') # # a 1.40 # b 2.60 # c 0.00 # d -0.55 # dtype: float64 ▷ MEAN df.mean(axis='columns',skipna=False) # # a NaN # b 1.30..

import pandas as pd import numpy as np ▷ 넘파이에 의한 랜덤난수 frame = pd.DataFrame(np.random.randn(4, 3), columns=list('bde'), index=['Utah', 'Ohio', 'Texas', 'Oregon']) frame # # b d e # Utah 0.274992 0.228913 1.352917 # Ohio 0.886429 -2.001637 -0.371843 # Texas 1.669025 -0.438570 -0.539741 # Oregon 0.476985 3.248944 -1.021228 np.abs(frame) ▷ lambda f = lambda x:x.max() - x.min() frame.apply(f) # # b 1..

numpy 는 정수여야만 했지만 판다스는 정수외에 실수도 사용가능 ▷ obj = pd.Series(np.arange(4.), index=['a', 'b', 'c', 'd']) obj # # a 0.0 # b 1.0 # c 2.0 # d 3.0 # dtype: float64 obj['b'] # 1.0 obj[1] # 1.0 obj[2:4] # # c 2.0 # d 3.0 # dtype: float64 obj[['b', 'a', 'd']] # # b 1.0 # a 0.0 # d 3.0 # dtype: float64 obj[[1, 3]] # # b 1.0 # d 3.0 # dtype: float64 obj[obj < 2] # # a 0.0 # b 1.0 # dtype: float64 obj['b':'c'] #..