[ Python - Pandas&Numpy ] ex

import numpy as np
import pandas as pd

 

 

ex1 

s = pd.Series(np.random.randn(6))
s[::2] = np.nan
s

s.fillna(s.mean())
states = ['Ohio', 'New York', 'Vermont', 'Florida', 'Oregon', 'Nevada', 'California', 'Idaho']
group_key=['East']*4+['West']*4
data=pd.Series(np.random.randn(8),index=states)
data

data[['Vermont','Nevada','Idaho']] = np.nan
data

data.groupby(group_key).mean()

fill_mean = lambda g: g.fillna(g.mean())
data.groupby(group_key).apply(fill_mean)

fill_values = {'East': 0.5, 'West': -1}
fill_func = lambda g: g.fillna(fill_values[g.name])
data.groupby(group_key).apply(fill_func)

# <출력>
# Ohio         -1.759884
# New York      0.143524
# Vermont       0.500000
# Florida       0.775893
# Oregon        0.570685
# Nevada       -1.000000
# California    0.333238
# Idaho        -1.000000
# dtype: float64

 

 

---

 

 

 ex2 

suits = ['H', 'S', 'C', 'D']
card_val = (list(range(1, 11)) + [10] * 3) * 4
base_names = ['A'] + list(range(2, 11)) + ['J', 'K', 'Q']
cards = []
for suit in ['H', 'S', 'C', 'D']:
 cards.extend(str(num) + suit for num in base_names)
deck = pd.Series(card_val, index=cards)
deck[:13]

def draw(deck, n=5):
 return deck.sample(n)
draw(deck)

get_suit = lambda card: card[-1] # last letter is suit
deck.groupby(get_suit).apply(draw, n=2)

deck.groupby(get_suit, group_keys=False).apply(draw, n=2)

# <출력> 
# 5C     5
# 6C     6
# 2D     2
# 9D     9
# 7H     7
# QH    10
# 6S     6
# 8S     8
# dtype: int64

 

 

---

 

 

stock_px.csv

0.38MB

 

 

 ex3 

df = pd.DataFrame({'category': ['a', 'a', 'a', 'a', 'b', 'b', 'b', 'b'],
                   'data': np.random.randn(8), 'weights': np.random.rand(8)})
df

grouped = df.groupby('category')
get_wavg = lambda g: np.average(g['data'], weights=g['weights'])
grouped.apply(get_wavg)

close_px = pd.read_csv('C:/stock_px.csv', parse_dates=True, index_col=0)
close_px.info()

close_px[-4:]

spx_corr = lambda x: x.corrwith(x['SPX'])
rets = close_px.pct_change().dropna()
get_year = lambda x: x.year
by_year = rets.groupby(get_year)
by_year.apply(spx_corr)

by_year.apply(lambda g: g['AAPL'].corr(g['MSFT']))

# <출력> 
# 1990    0.408271
# 1991    0.266807
# 1992    0.450592
# 1993    0.236917
# 1994    0.361638
#           ...   
# 2007    0.417738
# 2008    0.611901
# 2009    0.432738
# 2010    0.571946
# 2011    0.581987
# Length: 22, dtype: float64

 

 

 

---

 

 

 

 ex4 

import statsmodels.api as sm

def regress(data,yvar,xvars):
    Y = data[yvar]
    X = data[xvars]
    X['intercept']=1.
    result = sm.OLS(Y,X).fit()
    return result.params
by_year.apply(regress,'AAPL',['SPX'])

# <출력>
#            SPX  intercept
# 1990  1.512772   0.001395
# 1991  1.187351   0.000396
# 1992  1.832427   0.000164
# 1993  1.390470  -0.002657
# 1994  1.190277   0.001617
#         ...        ...
# 2007  1.198761   0.003438
# 2008  0.968016  -0.001110
# 2009  0.879103   0.002954
# 2010  1.052608   0.001261