python按行拆分表格_Python将单元格中的多个值拆分为多行

使用：#create dataframe

df = pd.read_csv(filename, sep=';')

#split all values

df = df.applymap(lambda x: x.split('|'))

print (df)

fruit_type fruit_color fruit_weight

0 [Apple, Banana] [Red, Yellow] [2, 1]

1 [Orange] [Orange] [4]

2 [Pineapple, Grape, Watermelon] [Brown, Purple, Green] [12, 1, 15]

#get position of max weight

a = pd.DataFrame(df['fruit_weight'].values.tolist()).astype(float).idxmax(1).tolist()

print (a)

[0, 0, 2]

#convert df to dictionary

b = df.to_dict('list')

print (b)

{'fruit_weight': [['2', '1'], ['4'], ['12', '1', '15']],

'fruit_color': [['Red', 'Yellow'], ['Orange'], ['Brown', 'Purple', 'Green']],

'fruit_type': [['Apple', 'Banana'], ['Orange'], ['Pineapple', 'Grape', 'Watermelon']]}

^{pr2}$

计时：df = pd.concat([df]*1000).reset_index(drop=True)

def col(df):

df = df.applymap(lambda x: x.split('|'))

idx = df.index.repeat(df.fruit_weight.str.len())

df = df.apply(lambda x: pd.Series(np.concatenate(x.tolist())), 0)

return df.assign(idx=idx).groupby('idx', group_keys=False).apply(lambda x: x.sort_values('fruit_weight', ascending=False).head(1))

def jez(df):

df = df.applymap(lambda x: x.split('|'))

a = pd.DataFrame(df['fruit_weight'].values.tolist()).astype(float).idxmax(1).tolist()

b = df.to_dict('list')

a = {k: [k1[v1] for k1,v1 in zip(v, a)] for k, v in b.items()}

return pd.DataFrame(a)

print (col(df))

print (jez(df))

In [229]: %timeit (col(df))

1 loop, best of 3: 1.58 s per loop

In [230]: %timeit (jez(df))

100 loops, best of 3: 19.3 ms per loop