def get_factors(startDate: str = start_date):
dataset_names = famafrench.get_available_datasets()
print("Getting Fama French 3 factors")
factors = famafrench.FamaFrenchReader("F-F_Research_Data_Factors",
start=startDate)
ff3factors: DataFrame = factors.read()[0]
print("Getting Fama French momentum factor")
momentum = famafrench.FamaFrenchReader("F-F_Momentum_Factor",
start=startDate)
momfactors: DataFrame = momentum.read()[0]
together = concat([ff3factors, momfactors], axis=1)
return together
def printThreeFactorDataList(self):
"""
Obtains the list of datasets from Kenneth French data library related
to the 3 factor model.
http://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html
(Kenneth French data library)
"""
ffData = get_available_datasets()
self.ff3DataList = [
dataset for dataset in ffData if '3_Factors' in dataset
]
for i in range(0, len(self.ff3DataList)):
print(i, '.', self.ff3DataList[i])
def Data_FF_search(term,all_info=False):
'''
Search specific Summary of sets available to download using DataReader_FF function
'''
from pandas_datareader.famafrench import get_available_datasets
import pandas_datareader.data as web
import numpy as np
import pandas as pd
sets = np.array(get_available_datasets())
if all_info!=False:
data = sets
else:
b_idx = np.array([x.find(term)!=-1 for x in sets])
data = sets[b_idx]
return data
def update(self, evt=None):
"""Update data widget(s)"""
datasets = []
self.applyOptions()
source = self.kwds['source']
x = ['F']
if source == 'Yahoo Finance':
x = ['F']
elif source == 'FAMA/French':
from pandas_datareader.famafrench import get_available_datasets
x = get_available_datasets()
w = self.widgets['dataset']
w['values'] = x
w.set(x[0])
return
#create a performance chart and save for later
portfolio_index = (1 + Combined_Portfolio_returns).cumprod()
ax = portfolio_index.plot(title='In Sample ' + str(test_sector) +
' performance')
fig = ax.get_figure()
Sector_Performance_Chart = 'In Sample Performance Chart ' + test_sector
path_to_file = (
r'/Users/downey/coding/Python/Scripts/EPAT Project RF Models, Code,'
' and Results/Sector Performance/')
output_name = path_to_file + Sector_Performance_Chart + '.pdf'
fig.savefig(output_name)
####################get risk free rate from kenneth french#####################
len(get_available_datasets())
ds = web.DataReader(
'F-F_Research_Data_Factors_daily',
'famafrench',
start='1990-08-30',
)
print(ds['DESCR'])
ds[0].head()
data = ds[0]
data = data.dropna()
data = data / 100 #convert to percent returns
RF_data = (1 + data['RF']).cumprod()
def test_get_available_datasets(self):
# _skip_if_no_lxml()
l = get_available_datasets()
assert len(l) > 100
#pip install pandas-datareader (in case you haven't install this package)
from pandas_datareader.famafrench import get_available_datasets
import pickleshare
import pandas as pd
from pandas.core.frame import DataFrame
import numpy as np
import datetime as dt
import psycopg2
import matplotlib.pyplot as plt
from dateutil.relativedelta import *
from pandas.tseries.offsets import *
from scipy import stats
from matplotlib.backends.backend_pdf import PdfPages
#You can extract all the available datasets from Ken French's website and find that there are 295 of them. We can opt to see all the datasets available.
datasets = get_available_datasets()
print('No. of datasets:{}'.format(len(datasets)))
#datasets # comment out if you want to see all the datasets
##############
#Customize your data selection
##############
#Note:If this is what you are intended to find: '6_Portfolios_ME_OP_2x3', but don't know exactly what it is named, do the following line
#df_me_op_factor = [dataset for dataset in datasets if 'ME' in dataset and 'OP' in dataset and '2x3' in dataset]
#print(df_me_op_factor)
#It is important to check the description of the dataset we access by using the following codes
Datatoread='F-F_Research_Data_5_Factors_2x3_daily'
sdate='1992-07-01'
edate='2018-06-30'
def test_get_available_datasets(self):
pytest.importorskip("lxml")
l = get_available_datasets()
assert len(l) > 100
def test_get_available_datasets(self):
_skip_if_no_lxml()
l = get_available_datasets()
assert len(l) > 100
def fama_french():
from pandas_datareader.famafrench import get_available_datasets
get_available_datasets()
ds = web.DataReader('5_Industry_Portfolios', 'famafrench')
print(ds['DESCR'])
# pprint(os.environ)
# FRED
start = datetime(2010, 1, 1)
end = datetime(2013, 1, 27)
gdp = web.DataReader('GDP', 'fred', start, end)
print(gdp.info())
inflation = web.DataReader(['CPIAUCSL', 'CPILFESL'], 'fred', start, end)
print(inflation.info())
# Fama/French
from pandas_datareader.famafrench import get_available_datasets
print(get_available_datasets())
ds = web.DataReader('5_Industry_Portfolios', 'famafrench')
print(ds['DESCR'])
# World Bank
from pandas_datareader import wb
gdp_variables = wb.search('gdp.*capita.*const')
gdp_variables.head()
wb_data = wb.download(indicator='NY.GDP.PCAP.KD',
country=['US', 'CA', 'MX'],
start=1990,
end=2019)
