In [ ]:
from __future__ import division
from pandas import Series, DataFrame
import pandas as pd
from numpy.random import randn
import numpy as np
pd.options.display.max_rows = 12
np.set_printoptions(precision=4, suppress=True)
import matplotlib.pyplot as plt
plt.rc('figure', figsize=(12, 4))
In [ ]:
%cd ../book_scripts
In [ ]:
%matplotlib inline
In [ ]:
from datetime import datetime
now = datetime.now()
now
In [ ]:
now.year, now.month, now.day
In [ ]:
delta = datetime(2011, 1, 7) - datetime(2008, 6, 24, 8, 15)
delta
In [ ]:
delta.days
In [ ]:
delta.seconds
In [ ]:
from datetime import timedelta
start = datetime(2011, 1, 7)
start + timedelta(12)
In [ ]:
start - 2 * timedelta(12)
In [ ]:
stamp = datetime(2011, 1, 3)
In [ ]:
str(stamp)
In [ ]:
stamp.strftime('%Y-%m-%d')
In [ ]:
value = '2011-01-03'
datetime.strptime(value, '%Y-%m-%d')
In [ ]:
datestrs = ['7/6/2011', '8/6/2011']
[datetime.strptime(x, '%m/%d/%Y') for x in datestrs]
In [ ]:
from dateutil.parser import parse
parse('2011-01-03')
In [ ]:
parse('Jan 31, 1997 10:45 PM')
In [ ]:
parse('6/12/2011', dayfirst=True)
In [ ]:
datestrs
In [ ]:
pd.to_datetime(datestrs)
# note: output changed (no '00:00:00' anymore)
In [ ]:
idx = pd.to_datetime(datestrs + [None])
idx
In [ ]:
idx[2]
In [ ]:
pd.isnull(idx)
In [ ]:
from datetime import datetime
dates = [datetime(2011, 1, 2), datetime(2011, 1, 5), datetime(2011, 1, 7),
datetime(2011, 1, 8), datetime(2011, 1, 10), datetime(2011, 1, 12)]
ts = Series(np.random.randn(6), index=dates)
ts
In [ ]:
type(ts)
# note: output changed to "pandas.core.series.Series"
In [ ]:
ts.index
In [ ]:
ts + ts[::2]
In [ ]:
ts.index.dtype
# note: output changed from dtype('datetime64[ns]') to dtype('<M8[ns]')
In [ ]:
stamp = ts.index[0]
stamp
# note: output changed from <Timestamp: 2011-01-02 00:00:00> to Timestamp('2011-01-02 00:00:00')
In [ ]:
stamp = ts.index[2]
ts[stamp]
In [ ]:
ts['1/10/2011']
In [ ]:
ts['20110110']
In [ ]:
longer_ts = Series(np.random.randn(1000),
index=pd.date_range('1/1/2000', periods=1000))
longer_ts
In [ ]:
longer_ts['2001']
In [ ]:
longer_ts['2001-05']
In [ ]:
ts[datetime(2011, 1, 7):]
In [ ]:
ts
In [ ]:
ts['1/6/2011':'1/11/2011']
In [ ]:
ts.truncate(after='1/9/2011')
In [ ]:
dates = pd.date_range('1/1/2000', periods=100, freq='W-WED')
long_df = DataFrame(np.random.randn(100, 4),
index=dates,
columns=['Colorado', 'Texas', 'New York', 'Ohio'])
long_df.ix['5-2001']
In [ ]:
dates = pd.DatetimeIndex(['1/1/2000', '1/2/2000', '1/2/2000', '1/2/2000',
'1/3/2000'])
dup_ts = Series(np.arange(5), index=dates)
dup_ts
In [ ]:
dup_ts.index.is_unique
In [ ]:
dup_ts['1/3/2000'] # not duplicated
In [ ]:
dup_ts['1/2/2000'] # duplicated
In [ ]:
grouped = dup_ts.groupby(level=0)
grouped.mean()
In [ ]:
grouped.count()
In [ ]:
ts
In [ ]:
ts.resample('D')
In [ ]:
index = pd.date_range('4/1/2012', '6/1/2012')
index
In [ ]:
pd.date_range(start='4/1/2012', periods=20)
In [ ]:
pd.date_range(end='6/1/2012', periods=20)
In [ ]:
pd.date_range('1/1/2000', '12/1/2000', freq='BM')
In [ ]:
pd.date_range('5/2/2012 12:56:31', periods=5)
In [ ]:
pd.date_range('5/2/2012 12:56:31', periods=5, normalize=True)
In [ ]:
from pandas.tseries.offsets import Hour, Minute
hour = Hour()
hour
In [ ]:
four_hours = Hour(4)
four_hours
In [ ]:
pd.date_range('1/1/2000', '1/3/2000 23:59', freq='4h')
In [ ]:
Hour(2) + Minute(30)
In [ ]:
pd.date_range('1/1/2000', periods=10, freq='1h30min')
In [ ]:
rng = pd.date_range('1/1/2012', '9/1/2012', freq='WOM-3FRI')
list(rng)
In [ ]:
ts = Series(np.random.randn(4),
index=pd.date_range('1/1/2000', periods=4, freq='M'))
ts
In [ ]:
ts.shift(2)
In [ ]:
ts.shift(-2)
In [ ]:
ts.shift(2, freq='M')
In [ ]:
ts.shift(3, freq='D')
In [ ]:
ts.shift(1, freq='3D')
In [ ]:
ts.shift(1, freq='90T')
In [ ]:
from pandas.tseries.offsets import Day, MonthEnd
now = datetime(2011, 11, 17)
now + 3 * Day()
In [ ]:
now + MonthEnd()
In [ ]:
now + MonthEnd(2)
In [ ]:
offset = MonthEnd()
offset.rollforward(now)
In [ ]:
offset.rollback(now)
In [ ]:
ts = Series(np.random.randn(20),
index=pd.date_range('1/15/2000', periods=20, freq='4d'))
ts.groupby(offset.rollforward).mean()
In [ ]:
ts.resample('M', how='mean')
In [ ]:
import pytz
pytz.common_timezones[-5:]
In [ ]:
tz = pytz.timezone('US/Eastern')
tz
In [ ]:
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = Series(np.random.randn(len(rng)), index=rng)
In [ ]:
print(ts.index.tz)
In [ ]:
pd.date_range('3/9/2012 9:30', periods=10, freq='D', tz='UTC')
In [ ]:
ts_utc = ts.tz_localize('UTC')
ts_utc
In [ ]:
ts_utc.index
In [ ]:
ts_utc.tz_convert('US/Eastern')
In [ ]:
ts_eastern = ts.tz_localize('US/Eastern')
ts_eastern.tz_convert('UTC')
In [ ]:
ts_eastern.tz_convert('Europe/Berlin')
In [ ]:
ts.index.tz_localize('Asia/Shanghai')
In [ ]:
stamp = pd.Timestamp('2011-03-12 04:00')
stamp_utc = stamp.tz_localize('utc')
stamp_utc.tz_convert('US/Eastern')
In [ ]:
stamp_moscow = pd.Timestamp('2011-03-12 04:00', tz='Europe/Moscow')
stamp_moscow
In [ ]:
stamp_utc.value
In [ ]:
stamp_utc.tz_convert('US/Eastern').value
In [ ]:
# 30 minutes before DST transition
from pandas.tseries.offsets import Hour
stamp = pd.Timestamp('2012-03-12 01:30', tz='US/Eastern')
stamp
In [ ]:
stamp + Hour()
In [ ]:
# 90 minutes before DST transition
stamp = pd.Timestamp('2012-11-04 00:30', tz='US/Eastern')
stamp
In [ ]:
stamp + 2 * Hour()
In [ ]:
rng = pd.date_range('3/7/2012 9:30', periods=10, freq='B')
ts = Series(np.random.randn(len(rng)), index=rng)
ts
In [ ]:
ts1 = ts[:7].tz_localize('Europe/London')
ts2 = ts1[2:].tz_convert('Europe/Moscow')
result = ts1 + ts2
result.index
In [ ]:
p = pd.Period(2007, freq='A-DEC')
p
In [ ]:
p + 5
In [ ]:
p - 2
In [ ]:
pd.Period('2014', freq='A-DEC') - p
In [ ]:
rng = pd.period_range('1/1/2000', '6/30/2000', freq='M')
rng
In [ ]:
Series(np.random.randn(6), index=rng)
In [ ]:
values = ['2001Q3', '2002Q2', '2003Q1']
index = pd.PeriodIndex(values, freq='Q-DEC')
index
In [ ]:
p = pd.Period('2007', freq='A-DEC')
p.asfreq('M', how='start')
In [ ]:
p.asfreq('M', how='end')
In [ ]:
p = pd.Period('2007', freq='A-JUN')
p.asfreq('M', 'start')
In [ ]:
p.asfreq('M', 'end')
In [ ]:
p = pd.Period('Aug-2007', 'M')
p.asfreq('A-JUN')
In [ ]:
rng = pd.period_range('2006', '2009', freq='A-DEC')
ts = Series(np.random.randn(len(rng)), index=rng)
ts
In [ ]:
ts.asfreq('M', how='start')
In [ ]:
ts.asfreq('B', how='end')
In [ ]:
p = pd.Period('2012Q4', freq='Q-JAN')
p
In [ ]:
p.asfreq('D', 'start')
In [ ]:
p.asfreq('D', 'end')
In [ ]:
p4pm = (p.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
p4pm
In [ ]:
p4pm.to_timestamp()
In [ ]:
rng = pd.period_range('2011Q3', '2012Q4', freq='Q-JAN')
ts = Series(np.arange(len(rng)), index=rng)
ts
In [ ]:
new_rng = (rng.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
ts.index = new_rng.to_timestamp()
ts
In [ ]:
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(randn(3), index=rng)
pts = ts.to_period()
ts
In [ ]:
pts
In [ ]:
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(randn(6), index=rng)
ts2.to_period('M')
In [ ]:
pts = ts.to_period()
pts
In [ ]:
pts.to_timestamp(how='end')
In [ ]:
data = pd.read_csv('ch08/macrodata.csv')
data.year
In [ ]:
data.quarter
In [ ]:
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
index
In [ ]:
data.index = index
data.infl
In [ ]:
rng = pd.date_range('1/1/2000', periods=100, freq='D')
ts = Series(randn(len(rng)), index=rng)
ts.resample('M', how='mean')
In [ ]:
ts.resample('M', how='mean', kind='period')
In [ ]:
rng = pd.date_range('1/1/2000', periods=12, freq='T')
ts = Series(np.arange(12), index=rng)
ts
In [ ]:
ts.resample('5min', how='sum')
# note: output changed (as the default changed from closed='right', label='right' to closed='left', label='left'
In [ ]:
ts.resample('5min', how='sum', closed='left')
In [ ]:
ts.resample('5min', how='sum', closed='left', label='left')
In [ ]:
ts.resample('5min', how='sum', loffset='-1s')
In [ ]:
ts.resample('5min', how='ohlc')
# note: output changed because of changed defaults
In [ ]:
rng = pd.date_range('1/1/2000', periods=100, freq='D')
ts = Series(np.arange(100), index=rng)
ts.groupby(lambda x: x.month).mean()
In [ ]:
ts.groupby(lambda x: x.weekday).mean()
In [ ]:
frame = DataFrame(np.random.randn(2, 4),
index=pd.date_range('1/1/2000', periods=2, freq='W-WED'),
columns=['Colorado', 'Texas', 'New York', 'Ohio'])
frame
In [ ]:
df_daily = frame.resample('D')
df_daily
In [ ]:
frame.resample('D', fill_method='ffill')
In [ ]:
frame.resample('D', fill_method='ffill', limit=2)
In [ ]:
frame.resample('W-THU', fill_method='ffill')
In [ ]:
frame = DataFrame(np.random.randn(24, 4),
index=pd.period_range('1-2000', '12-2001', freq='M'),
columns=['Colorado', 'Texas', 'New York', 'Ohio'])
frame[:5]
In [ ]:
annual_frame = frame.resample('A-DEC', how='mean')
annual_frame
In [ ]:
# Q-DEC: Quarterly, year ending in December
annual_frame.resample('Q-DEC', fill_method='ffill')
# note: output changed, default value changed from convention='end' to convention='start' + 'start' changed to span-like
# also the following cells
In [ ]:
annual_frame.resample('Q-DEC', fill_method='ffill', convention='start')
In [ ]:
annual_frame.resample('Q-MAR', fill_method='ffill')
In [ ]:
close_px_all = pd.read_csv('ch09/stock_px.csv', parse_dates=True, index_col=0)
close_px = close_px_all[['AAPL', 'MSFT', 'XOM']]
close_px = close_px.resample('B', fill_method='ffill')
close_px.info()
In [ ]:
close_px['AAPL'].plot()
In [ ]:
close_px.ix['2009'].plot()
In [ ]:
close_px['AAPL'].ix['01-2011':'03-2011'].plot()
In [ ]:
appl_q = close_px['AAPL'].resample('Q-DEC', fill_method='ffill')
appl_q.ix['2009':].plot()
In [ ]:
close_px = close_px.asfreq('B').fillna(method='ffill')
In [ ]:
close_px.AAPL.plot()
pd.rolling_mean(close_px.AAPL, 250).plot()
In [ ]:
plt.figure()
In [ ]:
appl_std250 = pd.rolling_std(close_px.AAPL, 250, min_periods=10)
appl_std250[5:12]
In [ ]:
appl_std250.plot()
In [ ]:
# Define expanding mean in terms of rolling_mean
expanding_mean = lambda x: rolling_mean(x, len(x), min_periods=1)
In [ ]:
pd.rolling_mean(close_px, 60).plot(logy=True)
In [ ]:
plt.close('all')
In [ ]:
fig, axes = plt.subplots(nrows=2, ncols=1, sharex=True, sharey=True,
figsize=(12, 7))
aapl_px = close_px.AAPL['2005':'2009']
ma60 = pd.rolling_mean(aapl_px, 60, min_periods=50)
ewma60 = pd.ewma(aapl_px, span=60)
aapl_px.plot(style='k-', ax=axes[0])
ma60.plot(style='k--', ax=axes[0])
aapl_px.plot(style='k-', ax=axes[1])
ewma60.plot(style='k--', ax=axes[1])
axes[0].set_title('Simple MA')
axes[1].set_title('Exponentially-weighted MA')
In [ ]:
close_px
spx_px = close_px_all['SPX']
In [ ]:
spx_rets = spx_px / spx_px.shift(1) - 1
returns = close_px.pct_change()
corr = pd.rolling_corr(returns.AAPL, spx_rets, 125, min_periods=100)
corr.plot()
In [ ]:
corr = pd.rolling_corr(returns, spx_rets, 125, min_periods=100)
corr.plot()
In [ ]:
from scipy.stats import percentileofscore
score_at_2percent = lambda x: percentileofscore(x, 0.02)
result = pd.rolling_apply(returns.AAPL, 250, score_at_2percent)
result.plot()
In [ ]:
rng = pd.date_range('1/1/2000', periods=10000000, freq='10ms')
ts = Series(np.random.randn(len(rng)), index=rng)
ts
In [ ]:
ts.resample('15min', how='ohlc').info()
In [ ]:
%timeit ts.resample('15min', how='ohlc')
In [ ]:
rng = pd.date_range('1/1/2000', periods=10000000, freq='1s')
ts = Series(np.random.randn(len(rng)), index=rng)
%timeit ts.resample('15s', how='ohlc')