# %load_ext autoreload
# %autoreload 2
import datetime as dt
import pandas as pd
from dateutil.relativedelta import relativedelta
from euraculus.data import DataMap
from euraculus.factor import decompose_variance
# ## Set up
# ### Data
data = DataMap("../data")
df_spy = data.load_spy_data(series="var")
# ### Dates
# define timeframe
first_sampling_date = dt.datetime(year=1994, month=1, day=31)
last_sampling_date = dt.datetime(year=2021, month=12, day=31)
# ## Construct CAPM idiosyncratic variances
# ### Backward part
# %%time
sampling_date = first_sampling_date
while sampling_date <= last_sampling_date:
# load betas
sampling_date = dt.datetime(year=2021, month=12, day=31)
# %% [markdown]
# ### Data
# %%
option = "logvar_capm_resid" # "spy_capm_decomp"
# %%
data = DataMap("../data")
df_idio_var = data.load_historic(sampling_date=sampling_date,
column="var_idio")
df_logvar_resid = data.load_historic(sampling_date=sampling_date,
column="logvar_capm_resid")
df_var = data.load_historic(sampling_date=sampling_date, column="var")
df_spy_var = data.load_spy_data(series="var").loc[df_idio_var.index]
df_info = data.load_asset_estimates(
sampling_date=sampling_date,
columns=["ticker", "comnam", "last_size", "mean_size"])
# %% [markdown]
# ### Tickers
# %%
ticker_list = (data.load_historic(
sampling_date=sampling_date,
column="ticker").tail(1).values.ravel().tolist())
column_to_ticker = make_ticker_dict(ticker_list)
# %% [markdown]
# Make and export table:
def load_estimation_data(data: DataMap, sampling_date: dt.datetime) -> dict:
"""Load the data necessary for estimation from disk.
Args:
data: DataMap to load data from.
sampling_date: Last day in the sample.
Returns:
df_info: Summarizing information.
df_log_mcap_vola: Logarithm of value variance variable.
df_factors: Factor data.
"""
# asset data
df_var = data.load_historic(sampling_date=sampling_date, column="var")
df_noisevar = data.load_historic(sampling_date=sampling_date,
column="noisevar")
df_ret = data.load_historic(sampling_date=sampling_date, column="retadj")
df_mcap = data.load_historic(sampling_date=sampling_date, column="mcap")
df_info = data.load_asset_estimates(
sampling_date=sampling_date,
columns=["ticker", "comnam", "last_size", "mean_size"],
)
df_info["ticker"] = make_tickers_unique(df_info["ticker"])
# prepare asset data
df_vola = np.sqrt(df_var)
df_noisevola = np.sqrt(df_noisevar)
df_lagged_mcap = df_mcap / (df_ret + 1)
df_log_vola = prepare_log_data(df_data=df_vola, df_fill=df_noisevola)
df_log_mcap = log_replace(df=df_lagged_mcap, method="ffill")
df_log_mcap_vola = df_log_vola + df_log_mcap
df_log_mcap_vola = map_columns(df_log_mcap_vola,
mapping=df_info["ticker"],
mapping_name="ticker")
# factor data
df_factors = pd.DataFrame(index=df_var.index)
def prepare_spy_factor(df_spy):
open_prc = df_spy["prc"] / (1 + df_spy["ret"])
std = df_spy["var"]**0.5
factor = log_replace(open_prc * std, method="min").rename("spy")
return factor
def prepare_yahoo_factor(df_yahoo):
open_prc = df_yahoo["Open"]
std = np.sqrt(0.3607) * (np.log(df_yahoo["High"]) -
np.log(df_yahoo["Low"]))
factor = log_replace(open_prc * std, method="min").rename("yahoo")
return factor
def prepare_ew_factor(df_obs):
factor = df_obs.sub(df_obs.mean()).div(
df_obs.std()).mean(axis=1).rename("ew")
return factor
df_spy = data.load_spy_data().reindex(df_var.index)
spy_factor = prepare_spy_factor(df_spy)
df_factors = df_factors.join(spy_factor)
ew_factor = prepare_ew_factor(df_log_mcap_vola)
df_factors = df_factors.join(ew_factor)
crsp_factor = construct_crsp_index(sampling_date=sampling_date, data=data)
df_factors = df_factors.join(crsp_factor)
for ticker in ["^VIX", "DX-Y.NYB", "^TNX"]:
df_yahoo = data.load_yahoo(ticker).reindex(df_var.index)
factor = prepare_yahoo_factor(df_yahoo).rename(ticker)
df_factors = df_factors.join(factor)
return (df_info, df_log_mcap_vola, df_factors)