在pandas中遍历DataFrame行的实现方法

import pandas as pd
inp = [{'c1':10, 'c2':100}, {'c1':11,'c2':110}, {'c1':12,'c2':120}]
df = pd.DataFrame(inp)
print df

for row in df.rows:
 print row['c1'], row['c2']

for index, row in df.iterrows():
 print row["c1"], row["c2"]

for row in df.itertuples(index=True, name='Pandas'):
 print getattr(row, "c1"), getattr(row, "c2")

def valuation_formula(x, y):
 return x * y * 0.5
 
df['price'] = df.apply(lambda row: valuation_formula(row['x'], row['y']), axis=1)

for i in range(0, len(df)):
 print df.iloc[i]['c1'], df.iloc[i]['c2']

from collections import namedtuple
 
def myiter(d, cols=None):
 if cols is None:
  v = d.values.tolist()
  cols = d.columns.values.tolist()
 else:
  j = [d.columns.get_loc(c) for c in cols]
  v = d.values[:, j].tolist()
 
 n = namedtuple('MyTuple', cols)
 
 for line in iter(v):
  yield n(*line)

list(myiter(df))
 
[MyTuple(c1=10, c2=100), MyTuple(c1=11, c2=110), MyTuple(c1=12, c2=120)]

list(df.itertuples(index=False))
 
[Pandas(c1=10, c2=100), Pandas(c1=11, c2=110), Pandas(c1=12, c2=120)]

def iterfullA(d):
 return list(myiter(d))
 
def iterfullB(d):
 return list(d.itertuples(index=False))
 
def itersubA(d):
 return list(myiter(d, ['col3', 'col4', 'col5', 'col6', 'col7']))
 
def itersubB(d):
 return list(d[['col3', 'col4', 'col5', 'col6', 'col7']].itertuples(index=False))
 
res = pd.DataFrame(
 index=[10, 30, 100, 300, 1000, 3000, 10000, 30000],
 columns='iterfullA iterfullB itersubA itersubB'.split(),
 dtype=float
)
 
for i in res.index:
 d = pd.DataFrame(np.random.randint(10, size=(i, 10))).add_prefix('col')
 for j in res.columns:
  stmt = '{}(d)'.format(j)
  setp = 'from __main__ import d, {}'.format(j)
  res.at[i, j] = timeit(stmt, setp, number=100)
 
res.groupby(res.columns.str[4:-1], axis=1).plot(loglog=True);